itdominator/SolarFM
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Merge pull request 'Externalized items to new glade files and classes' (#10) from develop into master

Browse Source 
Reviewed-on: #10
This commit is contained in:
itdominator 2022-12-04 08:49:44 +00:00
commit da70244a54
1017 changed files with 193605 additions and 1726 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
plugins/disk_usage/plugin.py
View File

@ -76,9 +76,10 @@ class Plugin(PluginBase):
path = self._fm_state.tab.get_current_directory()
# NOTE: -h = human readable, -d = depth asigned to 1
command = ["du", "-h", "-d", "1", path]
proc = subprocess.Popen(command, stdout=subprocess.PIPE)
proc = subprocess.Popen(command, stdout=subprocess.PIPE, encoding="utf-8")
raw_data = proc.communicate()[0]
data = raw_data.decode("utf-8").strip() # NOTE: Will return data AFTER completion (if any)
# NOTE: Will return data AFTER completion (if any)
data = raw_data.strip()
parts = data.split("\n")
# NOTE: Last entry is curret dir. Move to top of list and pop off...

7
plugins/searcher/mixins/file_search_mixin.py
View File

@ -4,6 +4,7 @@ import subprocess
import signal
import json
import shlex
from datetime import datetime
# Lib imports
import gi
@ -38,8 +39,10 @@ class FileSearchMixin:
@daemon_threaded
def _handle_find_file_query(self, widget=None, eve=None, query=None):
# NOTE: Freeze IPC consumption
self.pause_fifo_update = True
self.search_query = ""
self.pause_fifo_update = True
self.search_query = ""
dt = datetime.now()
self.fsearch_time_stamp = datetime.timestamp(dt) # NOTE: Get timestamp
# NOTE: Kill the former process
if self._list_proc:

3
plugins/searcher/mixins/grep_search_mixin.py
View File

@ -5,6 +5,7 @@ import subprocess
import signal
import json
import shlex
from datetime import datetime
libgcc_s = ctypes.CDLL('libgcc_s.so.1')
# Lib imports
@ -42,6 +43,8 @@ class GrepSearchMixin:
# NOTE: Freeze IPC consumption
self.pause_fifo_update = True
self.grep_query = ""
dt = datetime.now()
self.grep_time_stamp = datetime.timestamp(dt) # NOTE: Get timestamp
# NOTE: Kill the former process
if self._grep_proc:

32
plugins/searcher/plugin.py
View File

@ -37,23 +37,25 @@ class Plugin(IPCServer, FileSearchMixin, GrepSearchMixin, PluginBase):
def __init__(self):
super().__init__()
self.path = os.path.dirname(os.path.realpath(__file__))
self.name = "Search" # NOTE: Need to remove after establishing private bidirectional 1-1 message bus
# where self.name should not be needed for message comms
self._GLADE_FILE = f"{self.path}/search_dialog.glade"
self.path = os.path.dirname(os.path.realpath(__file__))
self.name = "Search" # NOTE: Need to remove after establishing private bidirectional 1-1 message bus
# where self.name should not be needed for message comms
self._GLADE_FILE = f"{self.path}/search_dialog.glade"
self._search_dialog = None
self._active_path = None
self.file_list_parent = None
self.grep_list_parent = None
self._file_list = None
self._grep_list = None
self._grep_proc = None
self._list_proc = None
self.pause_fifo_update = False
self.update_list_ui_buffer = ()
self.grep_query = ""
self.search_query = ""
self._search_dialog = None
self._active_path = None
self.file_list_parent = None
self.grep_list_parent = None
self._file_list = None
self._grep_list = None
self._grep_proc = None
self._list_proc = None
self.pause_fifo_update = False
self.grep_time_stamp = None
self.fsearch_time_stamp = None
self.grep_query = ""
self.search_query = ""
def run(self):

20
plugins/searcher/utils/ipc_server.py
View File

@ -60,14 +60,22 @@ class IPCServer:
msg = conn.recv()
if "SEARCH|" in msg:
file = msg.split("SEARCH|")[1].strip()
if file:
GLib.idle_add(self._load_file_ui, file, priority=GLib.PRIORITY_LOW)
ts, file = msg.split("SEARCH|")[1].strip().split("|", 1)
try:
timestamp = float(ts)
if timestamp > self.fsearch_time_stamp and file:
GLib.idle_add(self._load_file_ui, file, priority=GLib.PRIORITY_LOW)
except Exception as e:
...
if "GREP|" in msg:
data = msg.split("GREP|")[1].strip()
if data:
GLib.idle_add(self._load_grep_ui, data, priority=GLib.PRIORITY_LOW)
ts, data = msg.split("GREP|")[1].strip().split("|", 1)
try:
timestamp = float(ts)
if timestamp > self.grep_time_stamp and data:
GLib.idle_add(self._load_grep_ui, data, priority=GLib.PRIORITY_LOW)
except Exception as e:
...
conn.close()

107
plugins/searcher/utils/search.py
View File

@ -5,11 +5,11 @@
import os
import traceback
import argparse
import threading
import subprocess
import json
import base64
import time
import pickle
from datetime import datetime
from setproctitle import setproctitle
from multiprocessing.connection import Client
@ -26,18 +26,10 @@ _ipc_authkey = b'' + bytes(f'solarfm-search_grep-ipc', 'utf-8')
filter = (".cpp", ".css", ".c", ".go", ".html", ".htm", ".java", ".js", ".json", ".lua", ".md", ".py", ".rs", ".toml", ".xml", ".pom") + \
(".txt", ".text", ".sh", ".cfg", ".conf", ".log")
# NOTE: Threads WILL NOT die with parent's destruction.
def threaded(fn):
def wrapper(*args, **kwargs):
threading.Thread(target=fn, args=args, kwargs=kwargs, daemon=False).start()
return wrapper
# NOTE: Threads WILL die with parent's destruction.
def daemon_threaded(fn):
def wrapper(*args, **kwargs):
threading.Thread(target=fn, args=args, kwargs=kwargs, daemon=True).start()
return wrapper
# NOTE: Create timestamp of when this launched. Is used in IPC to see if
# we are stale and that new call didn't fully kill this or older processes.
dt = datetime.now()
ts = datetime.timestamp(dt)
def send_ipc_message(message) -> None:
@ -55,84 +47,51 @@ def file_search(path, query):
for file in _files:
if query in file.lower():
target = os.path.join(_path, file)
data = f"SEARCH|{json.dumps([target, file])}"
data = f"SEARCH|{ts}|{json.dumps([target, file])}"
send_ipc_message(data)
except Exception as e:
print("Couldn't traverse to path. Might be permissions related...")
traceback.print_exc()
def _search_for_string(file, query):
b64_file = base64.urlsafe_b64encode(file.encode('utf-8')).decode('utf-8')
grep_result_set = {}
padding = 15
with open(file, 'rb') as fp:
# NOTE: I know there's an issue if there's a very large file with content
# all on one line will lower and dupe it. And, yes, it will only
# return one instance from the file.
try:
for i, raw in enumerate(fp):
line = None
llower = raw.lower()
if not query in llower:
continue
def grep_search(target=None, query=None):
if not query or not target:
return
if len(raw) > 72:
start = 0
end = len(raw) - 1
index = llower.index(query)
sindex = llower.index(query) - 15 if index >= 15 else abs(start - index) - index
eindex = sindex + 15 if end > (index + 15) else abs(index - end) + index
line = raw[sindex:eindex]
else:
line = raw
# NOTE: -n = provide line numbers, -R = Search recursive in given target
# -i = insensitive, -F = don't do regex parsing. (Treat as raw string)
command = ["grep", "-n", "-R", "-i", "-F", query, target]
proc = subprocess.Popen(command, stdout=subprocess.PIPE, encoding="utf-8")
raw_data = proc.communicate()[0].strip()
proc_data = raw_data.split("\n") # NOTE: Will return data AFTER completion (if any)
collection = {}
b64_line = base64.urlsafe_b64encode(line).decode('utf-8')
if f"{b64_file}" in grep_result_set.keys():
grep_result_set[f"{b64_file}"][f"{i+1}"] = b64_line
else:
grep_result_set[f"{b64_file}"] = {}
grep_result_set[f"{b64_file}"] = {f"{i+1}": b64_line}
for line in proc_data:
file, line_no, data = line.split(":", 2)
b64_file = base64.urlsafe_b64encode(file.encode('utf-8')).decode('utf-8')
b64_data = base64.urlsafe_b64encode(data.encode('utf-8')).decode('utf-8')
except Exception as e:
...
if b64_file in collection.keys():
collection[f"{b64_file}"][f"{line_no}"] = b64_data
else:
collection[f"{b64_file}"] = {}
collection[f"{b64_file}"] = { f"{line_no}": b64_data}
try:
data = f"GREP|{json.dumps(grep_result_set)}"
send_ipc_message(data)
except Exception as e:
...
@daemon_threaded
def _search_for_string_threaded(file, query):
_search_for_string(file, query)
def grep_search(path, query):
try:
for file in os.listdir(path):
target = os.path.join(path, file)
if os.path.isdir(target):
grep_search(target, query)
else:
if target.lower().endswith(filter):
size = os.path.getsize(target)
if not size > 5000:
_search_for_string(target, query)
else:
_search_for_string_threaded(target, query)
data = f"GREP|{ts}|{json.dumps(collection, separators=(',', ':'), indent=4)}"
send_ipc_message(data)
except Exception as e:
print("Couldn't traverse to path. Might be permissions related...")
traceback.print_exc()
...
collection = {}
def search(args):
if args.type == "file_search":
file_search(args.dir, args.query.lower())
if args.type == "grep_search":
grep_search(args.dir, args.query.lower().encode("utf-8"))
grep_search(args.dir, args.query.encode("utf-8"))
if __name__ == "__main__":

5
plugins/trasher/plugin.py
View File

@ -97,7 +97,6 @@ class Plugin(PluginBase):
self.empty.hide()
def delete_files(self, widget = None, eve = None):
self._event_system.emit("do_hide_context_menu")
self._event_system.emit("get_current_state")
state = self._fm_state
uris = state.selected_files
@ -121,23 +120,19 @@ class Plugin(PluginBase):
break
def trash_files(self, widget = None, eve = None, verbocity = False):
self._event_system.emit("do_hide_context_menu")
self._event_system.emit("get_current_state")
state = self._fm_state
for uri in state.selected_files:
self.trashman.trash(uri, verbocity)
def restore_trash_files(self, widget = None, eve = None, verbocity = False):
self._event_system.emit("do_hide_context_menu")
self._event_system.emit("get_current_state")
state = self._fm_state
for uri in state.selected_files:
self.trashman.restore(filename=uri.split("/")[-1], verbose = verbocity)
def empty_trash(self, widget = None, eve = None, verbocity = False):
self._event_system.emit("do_hide_context_menu")
self.trashman.empty(verbose = verbocity)
def go_to_trash(self, widget = None, eve = None, verbocity = False):
self._event_system.emit("do_hide_context_menu")
self._event_system.emit("go_to_path", self.trash_files_path)

6
plugins/youtube_download/download.sh
View File

@ -10,8 +10,10 @@
function main() {
cd "$(dirname "")"
echo "Working Dir: " $(pwd)
LINK=`xclip -selection clipboard -o`
yt-dlp --write-sub --embed-sub --sub-langs en -o "${1}/%(title)s.%(ext)s" "${LINK}"
python "${HOME}/.config/solarfm/plugins/youtube_download/yt_dlp/__main__.py" \
--cookies-from-browser firefox --write-sub --embed-sub --sub-langs en \
-o "${1}/%(title)s.%(ext)s" "${LINK}"
}
main "$@";

0
plugins/youtube_download/yt_dlp-2022.2.4.dist-info/AUTHORS Normal file
View File

1
plugins/youtube_download/yt_dlp-2022.2.4.dist-info/INSTALLER Normal file
View File

@ -0,0 +1 @@
pip

24
plugins/youtube_download/yt_dlp-2022.2.4.dist-info/LICENSE Normal file
View File

@ -0,0 +1,24 @@
This is free and unencumbered software released into the public domain.
Anyone is free to copy, modify, publish, use, compile, sell, or
distribute this software, either in source code form or as a compiled
binary, for any purpose, commercial or non-commercial, and by any
means.
In jurisdictions that recognize copyright laws, the author or authors
of this software dedicate any and all copyright interest in the
software to the public domain. We make this dedication for the benefit
of the public at large and to the detriment of our heirs and
successors. We intend this dedication to be an overt act of
relinquishment in perpetuity of all present and future rights to this
software under copyright law.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
IN NO EVENT SHALL THE AUTHORS BE LIABLE FOR ANY CLAIM, DAMAGES OR
OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
OTHER DEALINGS IN THE SOFTWARE.
For more information, please refer to <http://unlicense.org/>

1992
plugins/youtube_download/yt_dlp-2022.2.4.dist-info/METADATA Normal file
View File

File diff suppressed because it is too large Load Diff

1939
plugins/youtube_download/yt_dlp-2022.2.4.dist-info/RECORD Normal file
View File

File diff suppressed because it is too large Load Diff

0
plugins/youtube_download/yt_dlp-2022.2.4.dist-info/REQUESTED Normal file
View File

6
plugins/youtube_download/yt_dlp-2022.2.4.dist-info/WHEEL Normal file
View File

@ -0,0 +1,6 @@
Wheel-Version: 1.0
Generator: bdist_wheel (0.37.1)
Root-Is-Purelib: true
Tag: py2-none-any
Tag: py3-none-any

3
plugins/youtube_download/yt_dlp-2022.2.4.dist-info/entry_points.txt Normal file
View File

@ -0,0 +1,3 @@
[console_scripts]
yt-dlp = yt_dlp:main

1
plugins/youtube_download/yt_dlp-2022.2.4.dist-info/top_level.txt Normal file
View File

@ -0,0 +1 @@
yt_dlp

3874
plugins/youtube_download/yt_dlp/YoutubeDL.py Normal file
View File

File diff suppressed because it is too large Load Diff

871
plugins/youtube_download/yt_dlp/__init__.py Normal file
View File

@ -0,0 +1,871 @@
#!/usr/bin/env python3
# coding: utf-8
f'You are using an unsupported version of Python. Only Python versions 3.6 and above are supported by yt-dlp' # noqa: F541
__license__ = 'Public Domain'
import codecs
import io
import itertools
import os
import random
import re
import sys
from .options import (
parseOpts,
)
from .compat import (
compat_getpass,
compat_os_name,
compat_shlex_quote,
workaround_optparse_bug9161,
)
from .cookies import SUPPORTED_BROWSERS, SUPPORTED_KEYRINGS
from .utils import (
DateRange,
decodeOption,
DownloadCancelled,
DownloadError,
error_to_compat_str,
expand_path,
GeoUtils,
float_or_none,
int_or_none,
match_filter_func,
parse_duration,
preferredencoding,
read_batch_urls,
render_table,
SameFileError,
setproctitle,
std_headers,
write_string,
)
from .update import run_update
from .downloader import (
FileDownloader,
)
from .extractor import gen_extractors, list_extractors
from .extractor.common import InfoExtractor
from .extractor.adobepass import MSO_INFO
from .postprocessor import (
FFmpegExtractAudioPP,
FFmpegSubtitlesConvertorPP,
FFmpegThumbnailsConvertorPP,
FFmpegVideoConvertorPP,
FFmpegVideoRemuxerPP,
MetadataFromFieldPP,
MetadataParserPP,
)
from .YoutubeDL import YoutubeDL
def _real_main(argv=None):
# Compatibility fixes for Windows
if sys.platform == 'win32':
# https://github.com/ytdl-org/youtube-dl/issues/820
codecs.register(lambda name: codecs.lookup('utf-8') if name == 'cp65001' else None)
workaround_optparse_bug9161()
setproctitle('yt-dlp')
parser, opts, args = parseOpts(argv)
warnings, deprecation_warnings = [], []
# Set user agent
if opts.user_agent is not None:
std_headers['User-Agent'] = opts.user_agent
# Set referer
if opts.referer is not None:
std_headers['Referer'] = opts.referer
# Custom HTTP headers
std_headers.update(opts.headers)
# Dump user agent
if opts.dump_user_agent:
write_string(std_headers['User-Agent'] + '\n', out=sys.stdout)
sys.exit(0)
# Batch file verification
batch_urls = []
if opts.batchfile is not None:
try:
if opts.batchfile == '-':
write_string('Reading URLs from stdin - EOF (%s) to end:\n' % (
'Ctrl+Z' if compat_os_name == 'nt' else 'Ctrl+D'))
batchfd = sys.stdin
else:
batchfd = io.open(
expand_path(opts.batchfile),
'r', encoding='utf-8', errors='ignore')
batch_urls = read_batch_urls(batchfd)
if opts.verbose:
write_string('[debug] Batch file urls: ' + repr(batch_urls) + '\n')
except IOError:
sys.exit('ERROR: batch file %s could not be read' % opts.batchfile)
all_urls = batch_urls + [url.strip() for url in args] # batch_urls are already striped in read_batch_urls
_enc = preferredencoding()
all_urls = [url.decode(_enc, 'ignore') if isinstance(url, bytes) else url for url in all_urls]
if opts.list_extractors:
for ie in list_extractors(opts.age_limit):
write_string(ie.IE_NAME + (' (CURRENTLY BROKEN)' if not ie.working() else '') + '\n', out=sys.stdout)
matchedUrls = [url for url in all_urls if ie.suitable(url)]
for mu in matchedUrls:
write_string(' ' + mu + '\n', out=sys.stdout)
sys.exit(0)
if opts.list_extractor_descriptions:
for ie in list_extractors(opts.age_limit):
if not ie.working():
continue
desc = getattr(ie, 'IE_DESC', ie.IE_NAME)
if desc is False:
continue
if getattr(ie, 'SEARCH_KEY', None) is not None:
_SEARCHES = ('cute kittens', 'slithering pythons', 'falling cat', 'angry poodle', 'purple fish', 'running tortoise', 'sleeping bunny', 'burping cow')
_COUNTS = ('', '5', '10', 'all')
desc += f'; "{ie.SEARCH_KEY}:" prefix (Example: "{ie.SEARCH_KEY}{random.choice(_COUNTS)}:{random.choice(_SEARCHES)}")'
write_string(desc + '\n', out=sys.stdout)
sys.exit(0)
if opts.ap_list_mso:
table = [[mso_id, mso_info['name']] for mso_id, mso_info in MSO_INFO.items()]
write_string('Supported TV Providers:\n' + render_table(['mso', 'mso name'], table) + '\n', out=sys.stdout)
sys.exit(0)
# Conflicting, missing and erroneous options
if opts.format == 'best':
warnings.append('.\n '.join((
'"-f best" selects the best pre-merged format which is often not the best option',
'To let yt-dlp download and merge the best available formats, simply do not pass any format selection',
'If you know what you are doing and want only the best pre-merged format, use "-f b" instead to suppress this warning')))
if opts.exec_cmd.get('before_dl') and opts.exec_before_dl_cmd:
parser.error('using "--exec-before-download" conflicts with "--exec before_dl:"')
if opts.usenetrc and (opts.username is not None or opts.password is not None):
parser.error('using .netrc conflicts with giving username/password')
if opts.password is not None and opts.username is None:
parser.error('account username missing\n')
if opts.ap_password is not None and opts.ap_username is None:
parser.error('TV Provider account username missing\n')
if opts.autonumber_size is not None:
if opts.autonumber_size <= 0:
parser.error('auto number size must be positive')
if opts.autonumber_start is not None:
if opts.autonumber_start < 0:
parser.error('auto number start must be positive or 0')
if opts.username is not None and opts.password is None:
opts.password = compat_getpass('Type account password and press [Return]: ')
if opts.ap_username is not None and opts.ap_password is None:
opts.ap_password = compat_getpass('Type TV provider account password and press [Return]: ')
if opts.ratelimit is not None:
numeric_limit = FileDownloader.parse_bytes(opts.ratelimit)
if numeric_limit is None:
parser.error('invalid rate limit specified')
opts.ratelimit = numeric_limit
if opts.throttledratelimit is not None:
numeric_limit = FileDownloader.parse_bytes(opts.throttledratelimit)
if numeric_limit is None:
parser.error('invalid rate limit specified')
opts.throttledratelimit = numeric_limit
if opts.min_filesize is not None:
numeric_limit = FileDownloader.parse_bytes(opts.min_filesize)
if numeric_limit is None:
parser.error('invalid min_filesize specified')
opts.min_filesize = numeric_limit
if opts.max_filesize is not None:
numeric_limit = FileDownloader.parse_bytes(opts.max_filesize)
if numeric_limit is None:
parser.error('invalid max_filesize specified')
opts.max_filesize = numeric_limit
if opts.sleep_interval is not None:
if opts.sleep_interval < 0:
parser.error('sleep interval must be positive or 0')
if opts.max_sleep_interval is not None:
if opts.max_sleep_interval < 0:
parser.error('max sleep interval must be positive or 0')
if opts.sleep_interval is None:
parser.error('min sleep interval must be specified, use --min-sleep-interval')
if opts.max_sleep_interval < opts.sleep_interval:
parser.error('max sleep interval must be greater than or equal to min sleep interval')
else:
opts.max_sleep_interval = opts.sleep_interval
if opts.sleep_interval_subtitles is not None:
if opts.sleep_interval_subtitles < 0:
parser.error('subtitles sleep interval must be positive or 0')
if opts.sleep_interval_requests is not None:
if opts.sleep_interval_requests < 0:
parser.error('requests sleep interval must be positive or 0')
if opts.ap_mso and opts.ap_mso not in MSO_INFO:
parser.error('Unsupported TV Provider, use --ap-list-mso to get a list of supported TV Providers')
if opts.overwrites: # --yes-overwrites implies --no-continue
opts.continue_dl = False
if opts.concurrent_fragment_downloads <= 0:
parser.error('Concurrent fragments must be positive')
if opts.wait_for_video is not None:
min_wait, max_wait, *_ = map(parse_duration, opts.wait_for_video.split('-', 1) + [None])
if min_wait is None or (max_wait is None and '-' in opts.wait_for_video):
parser.error('Invalid time range to wait')
elif max_wait is not None and max_wait < min_wait:
parser.error('Minimum time range to wait must not be longer than the maximum')
opts.wait_for_video = (min_wait, max_wait)
def parse_retries(retries, name=''):
if retries in ('inf', 'infinite'):
parsed_retries = float('inf')
else:
try:
parsed_retries = int(retries)
except (TypeError, ValueError):
parser.error('invalid %sretry count specified' % name)
return parsed_retries
if opts.retries is not None:
opts.retries = parse_retries(opts.retries)
if opts.file_access_retries is not None:
opts.file_access_retries = parse_retries(opts.file_access_retries, 'file access ')
if opts.fragment_retries is not None:
opts.fragment_retries = parse_retries(opts.fragment_retries, 'fragment ')
if opts.extractor_retries is not None:
opts.extractor_retries = parse_retries(opts.extractor_retries, 'extractor ')
if opts.buffersize is not None:
numeric_buffersize = FileDownloader.parse_bytes(opts.buffersize)
if numeric_buffersize is None:
parser.error('invalid buffer size specified')
opts.buffersize = numeric_buffersize
if opts.http_chunk_size is not None:
numeric_chunksize = FileDownloader.parse_bytes(opts.http_chunk_size)
if not numeric_chunksize:
parser.error('invalid http chunk size specified')
opts.http_chunk_size = numeric_chunksize
if opts.playliststart <= 0:
raise parser.error('Playlist start must be positive')
if opts.playlistend not in (-1, None) and opts.playlistend < opts.playliststart:
raise parser.error('Playlist end must be greater than playlist start')
if opts.extractaudio:
opts.audioformat = opts.audioformat.lower()
if opts.audioformat not in ['best'] + list(FFmpegExtractAudioPP.SUPPORTED_EXTS):
parser.error('invalid audio format specified')
if opts.audioquality:
opts.audioquality = opts.audioquality.strip('k').strip('K')
audioquality = int_or_none(float_or_none(opts.audioquality)) # int_or_none prevents inf, nan
if audioquality is None or audioquality < 0:
parser.error('invalid audio quality specified')
if opts.recodevideo is not None:
opts.recodevideo = opts.recodevideo.replace(' ', '')
if not re.match(FFmpegVideoConvertorPP.FORMAT_RE, opts.recodevideo):
parser.error('invalid video remux format specified')
if opts.remuxvideo is not None:
opts.remuxvideo = opts.remuxvideo.replace(' ', '')
if not re.match(FFmpegVideoRemuxerPP.FORMAT_RE, opts.remuxvideo):
parser.error('invalid video remux format specified')
if opts.convertsubtitles is not None:
if opts.convertsubtitles not in FFmpegSubtitlesConvertorPP.SUPPORTED_EXTS:
parser.error('invalid subtitle format specified')
if opts.convertthumbnails is not None:
if opts.convertthumbnails not in FFmpegThumbnailsConvertorPP.SUPPORTED_EXTS:
parser.error('invalid thumbnail format specified')
if opts.cookiesfrombrowser is not None:
mobj = re.match(r'(?P<name>[^+:]+)(\s*\+\s*(?P<keyring>[^:]+))?(\s*:(?P<profile>.+))?', opts.cookiesfrombrowser)
if mobj is None:
parser.error(f'invalid cookies from browser arguments: {opts.cookiesfrombrowser}')
browser_name, keyring, profile = mobj.group('name', 'keyring', 'profile')
browser_name = browser_name.lower()
if browser_name not in SUPPORTED_BROWSERS:
parser.error(f'unsupported browser specified for cookies: "{browser_name}". '
f'Supported browsers are: {", ".join(sorted(SUPPORTED_BROWSERS))}')
if keyring is not None:
keyring = keyring.upper()
if keyring not in SUPPORTED_KEYRINGS:
parser.error(f'unsupported keyring specified for cookies: "{keyring}". '
f'Supported keyrings are: {", ".join(sorted(SUPPORTED_KEYRINGS))}')
opts.cookiesfrombrowser = (browser_name, profile, keyring)
geo_bypass_code = opts.geo_bypass_ip_block or opts.geo_bypass_country
if geo_bypass_code is not None:
try:
GeoUtils.random_ipv4(geo_bypass_code)
except Exception:
parser.error('unsupported geo-bypass country or ip-block')
if opts.date is not None:
date = DateRange.day(opts.date)
else:
date = DateRange(opts.dateafter, opts.datebefore)
compat_opts = opts.compat_opts
def report_conflict(arg1, arg2):
warnings.append(f'{arg2} is ignored since {arg1} was given')
def _unused_compat_opt(name):
if name not in compat_opts:
return False
compat_opts.discard(name)
compat_opts.update(['*%s' % name])
return True
def set_default_compat(compat_name, opt_name, default=True, remove_compat=True):
attr = getattr(opts, opt_name)
if compat_name in compat_opts:
if attr is None:
setattr(opts, opt_name, not default)
return True
else:
if remove_compat:
_unused_compat_opt(compat_name)
return False
elif attr is None:
setattr(opts, opt_name, default)
return None
set_default_compat('abort-on-error', 'ignoreerrors', 'only_download')
set_default_compat('no-playlist-metafiles', 'allow_playlist_files')
set_default_compat('no-clean-infojson', 'clean_infojson')
if 'no-attach-info-json' in compat_opts:
if opts.embed_infojson:
_unused_compat_opt('no-attach-info-json')
else:
opts.embed_infojson = False
if 'format-sort' in compat_opts:
opts.format_sort.extend(InfoExtractor.FormatSort.ytdl_default)
_video_multistreams_set = set_default_compat('multistreams', 'allow_multiple_video_streams', False, remove_compat=False)
_audio_multistreams_set = set_default_compat('multistreams', 'allow_multiple_audio_streams', False, remove_compat=False)
if _video_multistreams_set is False and _audio_multistreams_set is False:
_unused_compat_opt('multistreams')
outtmpl_default = opts.outtmpl.get('default')
if outtmpl_default == '':
outtmpl_default, opts.skip_download = None, True
del opts.outtmpl['default']
if opts.useid:
if outtmpl_default is None:
outtmpl_default = opts.outtmpl['default'] = '%(id)s.%(ext)s'
else:
report_conflict('--output', '--id')
if 'filename' in compat_opts:
if outtmpl_default is None:
outtmpl_default = opts.outtmpl['default'] = '%(title)s-%(id)s.%(ext)s'
else:
_unused_compat_opt('filename')
def validate_outtmpl(tmpl, msg):
err = YoutubeDL.validate_outtmpl(tmpl)
if err:
parser.error('invalid %s %r: %s' % (msg, tmpl, error_to_compat_str(err)))
for k, tmpl in opts.outtmpl.items():
validate_outtmpl(tmpl, f'{k} output template')
for type_, tmpl_list in opts.forceprint.items():
for tmpl in tmpl_list:
validate_outtmpl(tmpl, f'{type_} print template')
for type_, tmpl_list in opts.print_to_file.items():
for tmpl, file in tmpl_list:
validate_outtmpl(tmpl, f'{type_} print-to-file template')
validate_outtmpl(file, f'{type_} print-to-file filename')
validate_outtmpl(opts.sponsorblock_chapter_title, 'SponsorBlock chapter title')
for k, tmpl in opts.progress_template.items():
k = f'{k[:-6]} console title' if '-title' in k else f'{k} progress'
validate_outtmpl(tmpl, f'{k} template')
if opts.extractaudio and not opts.keepvideo and opts.format is None:
opts.format = 'bestaudio/best'
if outtmpl_default is not None and not os.path.splitext(outtmpl_default)[1] and opts.extractaudio:
parser.error('Cannot download a video and extract audio into the same'
' file! Use "{0}.%(ext)s" instead of "{0}" as the output'
' template'.format(outtmpl_default))
for f in opts.format_sort:
if re.match(InfoExtractor.FormatSort.regex, f) is None:
parser.error('invalid format sort string "%s" specified' % f)
def metadataparser_actions(f):
if isinstance(f, str):
cmd = '--parse-metadata %s' % compat_shlex_quote(f)
try:
actions = [MetadataFromFieldPP.to_action(f)]
except Exception as err:
parser.error(f'{cmd} is invalid; {err}')
else:
cmd = '--replace-in-metadata %s' % ' '.join(map(compat_shlex_quote, f))
actions = ((MetadataParserPP.Actions.REPLACE, x, *f[1:]) for x in f[0].split(','))
for action in actions:
try:
MetadataParserPP.validate_action(*action)
except Exception as err:
parser.error(f'{cmd} is invalid; {err}')
yield action
if opts.parse_metadata is None:
opts.parse_metadata = []
if opts.metafromtitle is not None:
opts.parse_metadata.append('title:%s' % opts.metafromtitle)
opts.parse_metadata = list(itertools.chain(*map(metadataparser_actions, opts.parse_metadata)))
any_getting = (any(opts.forceprint.values()) or opts.dumpjson or opts.dump_single_json
or opts.geturl or opts.gettitle or opts.getid or opts.getthumbnail
or opts.getdescription or opts.getfilename or opts.getformat or opts.getduration)
any_printing = opts.print_json
download_archive_fn = expand_path(opts.download_archive) if opts.download_archive is not None else opts.download_archive
# If JSON is not printed anywhere, but comments are requested, save it to file
printing_json = opts.dumpjson or opts.print_json or opts.dump_single_json
if opts.getcomments and not printing_json:
opts.writeinfojson = True
if opts.no_sponsorblock:
opts.sponsorblock_mark = set()
opts.sponsorblock_remove = set()
sponsorblock_query = opts.sponsorblock_mark | opts.sponsorblock_remove
opts.remove_chapters = opts.remove_chapters or []
if (opts.remove_chapters or sponsorblock_query) and opts.sponskrub is not False:
if opts.sponskrub:
if opts.remove_chapters:
report_conflict('--remove-chapters', '--sponskrub')
if opts.sponsorblock_mark:
report_conflict('--sponsorblock-mark', '--sponskrub')
if opts.sponsorblock_remove:
report_conflict('--sponsorblock-remove', '--sponskrub')
opts.sponskrub = False
if opts.sponskrub_cut and opts.split_chapters and opts.sponskrub is not False:
report_conflict('--split-chapter', '--sponskrub-cut')
opts.sponskrub_cut = False
if opts.remuxvideo and opts.recodevideo:
report_conflict('--recode-video', '--remux-video')
opts.remuxvideo = False
if opts.allow_unplayable_formats:
def report_unplayable_conflict(opt_name, arg, default=False, allowed=None):
val = getattr(opts, opt_name)
if (not allowed and val) or (allowed and not allowed(val)):
report_conflict('--allow-unplayable-formats', arg)
setattr(opts, opt_name, default)
report_unplayable_conflict('extractaudio', '--extract-audio')
report_unplayable_conflict('remuxvideo', '--remux-video')
report_unplayable_conflict('recodevideo', '--recode-video')
report_unplayable_conflict('addmetadata', '--embed-metadata')
report_unplayable_conflict('addchapters', '--embed-chapters')
report_unplayable_conflict('embed_infojson', '--embed-info-json')
opts.embed_infojson = False
report_unplayable_conflict('embedsubtitles', '--embed-subs')
report_unplayable_conflict('embedthumbnail', '--embed-thumbnail')
report_unplayable_conflict('xattrs', '--xattrs')
report_unplayable_conflict('fixup', '--fixup', default='never', allowed=lambda x: x in (None, 'never', 'ignore'))
opts.fixup = 'never'
report_unplayable_conflict('remove_chapters', '--remove-chapters', default=[])
report_unplayable_conflict('sponsorblock_remove', '--sponsorblock-remove', default=set())
report_unplayable_conflict('sponskrub', '--sponskrub', default=set())
opts.sponskrub = False
if (opts.addmetadata or opts.sponsorblock_mark) and opts.addchapters is None:
opts.addchapters = True
# PostProcessors
postprocessors = list(opts.add_postprocessors)
if sponsorblock_query:
postprocessors.append({
'key': 'SponsorBlock',
'categories': sponsorblock_query,
'api': opts.sponsorblock_api,
# Run this immediately after extraction is complete
'when': 'pre_process'
})
if opts.parse_metadata:
postprocessors.append({
'key': 'MetadataParser',
'actions': opts.parse_metadata,
# Run this immediately after extraction is complete
'when': 'pre_process'
})
if opts.convertsubtitles:
postprocessors.append({
'key': 'FFmpegSubtitlesConvertor',
'format': opts.convertsubtitles,
# Run this before the actual video download
'when': 'before_dl'
})
if opts.convertthumbnails:
postprocessors.append({
'key': 'FFmpegThumbnailsConvertor',
'format': opts.convertthumbnails,
# Run this before the actual video download
'when': 'before_dl'
})
if opts.extractaudio:
postprocessors.append({
'key': 'FFmpegExtractAudio',
'preferredcodec': opts.audioformat,
'preferredquality': opts.audioquality,
'nopostoverwrites': opts.nopostoverwrites,
})
if opts.remuxvideo:
postprocessors.append({
'key': 'FFmpegVideoRemuxer',
'preferedformat': opts.remuxvideo,
})
if opts.recodevideo:
postprocessors.append({
'key': 'FFmpegVideoConvertor',
'preferedformat': opts.recodevideo,
})
# If ModifyChapters is going to remove chapters, subtitles must already be in the container.
if opts.embedsubtitles:
already_have_subtitle = opts.writesubtitles and 'no-keep-subs' not in compat_opts
postprocessors.append({
'key': 'FFmpegEmbedSubtitle',
# already_have_subtitle = True prevents the file from being deleted after embedding
'already_have_subtitle': already_have_subtitle
})
if not opts.writeautomaticsub and 'no-keep-subs' not in compat_opts:
opts.writesubtitles = True
# --all-sub automatically sets --write-sub if --write-auto-sub is not given
# this was the old behaviour if only --all-sub was given.
if opts.allsubtitles and not opts.writeautomaticsub:
opts.writesubtitles = True
# ModifyChapters must run before FFmpegMetadataPP
remove_chapters_patterns, remove_ranges = [], []
for regex in opts.remove_chapters:
if regex.startswith('*'):
dur = list(map(parse_duration, regex[1:].split('-')))
if len(dur) == 2 and all(t is not None for t in dur):
remove_ranges.append(tuple(dur))
continue
parser.error(f'invalid --remove-chapters time range {regex!r}. Must be of the form *start-end')
try:
remove_chapters_patterns.append(re.compile(regex))
except re.error as err:
parser.error(f'invalid --remove-chapters regex {regex!r} - {err}')
if opts.remove_chapters or sponsorblock_query:
postprocessors.append({
'key': 'ModifyChapters',
'remove_chapters_patterns': remove_chapters_patterns,
'remove_sponsor_segments': opts.sponsorblock_remove,
'remove_ranges': remove_ranges,
'sponsorblock_chapter_title': opts.sponsorblock_chapter_title,
'force_keyframes': opts.force_keyframes_at_cuts
})
# FFmpegMetadataPP should be run after FFmpegVideoConvertorPP and
# FFmpegExtractAudioPP as containers before conversion may not support
# metadata (3gp, webm, etc.)
# By default ffmpeg preserves metadata applicable for both
# source and target containers. From this point the container won't change,
# so metadata can be added here.
if opts.addmetadata or opts.addchapters or opts.embed_infojson:
if opts.embed_infojson is None:
opts.embed_infojson = 'if_exists'
postprocessors.append({
'key': 'FFmpegMetadata',
'add_chapters': opts.addchapters,
'add_metadata': opts.addmetadata,
'add_infojson': opts.embed_infojson,
})
# Deprecated
# This should be above EmbedThumbnail since sponskrub removes the thumbnail attachment
# but must be below EmbedSubtitle and FFmpegMetadata
# See https://github.com/yt-dlp/yt-dlp/issues/204 , https://github.com/faissaloo/SponSkrub/issues/29
# If opts.sponskrub is None, sponskrub is used, but it silently fails if the executable can't be found
if opts.sponskrub is not False:
postprocessors.append({
'key': 'SponSkrub',
'path': opts.sponskrub_path,
'args': opts.sponskrub_args,
'cut': opts.sponskrub_cut,
'force': opts.sponskrub_force,
'ignoreerror': opts.sponskrub is None,
'_from_cli': True,
})
if opts.embedthumbnail:
postprocessors.append({
'key': 'EmbedThumbnail',
# already_have_thumbnail = True prevents the file from being deleted after embedding
'already_have_thumbnail': opts.writethumbnail
})
if not opts.writethumbnail:
opts.writethumbnail = True
opts.outtmpl['pl_thumbnail'] = ''
if opts.split_chapters:
postprocessors.append({
'key': 'FFmpegSplitChapters',
'force_keyframes': opts.force_keyframes_at_cuts,
})
# XAttrMetadataPP should be run after post-processors that may change file contents
if opts.xattrs:
postprocessors.append({'key': 'XAttrMetadata'})
if opts.concat_playlist != 'never':
postprocessors.append({
'key': 'FFmpegConcat',
'only_multi_video': opts.concat_playlist != 'always',
'when': 'playlist',
})
# Exec must be the last PP of each category
if opts.exec_before_dl_cmd:
opts.exec_cmd.setdefault('before_dl', opts.exec_before_dl_cmd)
for when, exec_cmd in opts.exec_cmd.items():
postprocessors.append({
'key': 'Exec',
'exec_cmd': exec_cmd,
# Run this only after the files have been moved to their final locations
'when': when,
})
def report_args_compat(arg, name):
warnings.append('%s given without specifying name. The arguments will be given to all %s' % (arg, name))
if 'default' in opts.external_downloader_args:
report_args_compat('--downloader-args', 'external downloaders')
if 'default-compat' in opts.postprocessor_args and 'default' not in opts.postprocessor_args:
report_args_compat('--post-processor-args', 'post-processors')
opts.postprocessor_args.setdefault('sponskrub', [])
opts.postprocessor_args['default'] = opts.postprocessor_args['default-compat']
def report_deprecation(val, old, new=None):
if not val:
return
deprecation_warnings.append(
f'{old} is deprecated and may be removed in a future version. Use {new} instead' if new
else f'{old} is deprecated and may not work as expected')
report_deprecation(opts.sponskrub, '--sponskrub', '--sponsorblock-mark or --sponsorblock-remove')
report_deprecation(not opts.prefer_ffmpeg, '--prefer-avconv', 'ffmpeg')
report_deprecation(opts.include_ads, '--include-ads')
# report_deprecation(opts.call_home, '--call-home') # We may re-implement this in future
# report_deprecation(opts.writeannotations, '--write-annotations') # It's just that no website has it
final_ext = (
opts.recodevideo if opts.recodevideo in FFmpegVideoConvertorPP.SUPPORTED_EXTS
else opts.remuxvideo if opts.remuxvideo in FFmpegVideoRemuxerPP.SUPPORTED_EXTS
else opts.audioformat if (opts.extractaudio and opts.audioformat != 'best')
else None)
match_filter = (
None if opts.match_filter is None
else match_filter_func(opts.match_filter))
ydl_opts = {
'usenetrc': opts.usenetrc,
'netrc_location': opts.netrc_location,
'username': opts.username,
'password': opts.password,
'twofactor': opts.twofactor,
'videopassword': opts.videopassword,
'ap_mso': opts.ap_mso,
'ap_username': opts.ap_username,
'ap_password': opts.ap_password,
'quiet': (opts.quiet or any_getting or any_printing),
'no_warnings': opts.no_warnings,
'forceurl': opts.geturl,
'forcetitle': opts.gettitle,
'forceid': opts.getid,
'forcethumbnail': opts.getthumbnail,
'forcedescription': opts.getdescription,
'forceduration': opts.getduration,
'forcefilename': opts.getfilename,
'forceformat': opts.getformat,
'forceprint': opts.forceprint,
'print_to_file': opts.print_to_file,
'forcejson': opts.dumpjson or opts.print_json,
'dump_single_json': opts.dump_single_json,
'force_write_download_archive': opts.force_write_download_archive,
'simulate': (any_getting or None) if opts.simulate is None else opts.simulate,
'skip_download': opts.skip_download,
'format': opts.format,
'allow_unplayable_formats': opts.allow_unplayable_formats,
'ignore_no_formats_error': opts.ignore_no_formats_error,
'format_sort': opts.format_sort,
'format_sort_force': opts.format_sort_force,
'allow_multiple_video_streams': opts.allow_multiple_video_streams,
'allow_multiple_audio_streams': opts.allow_multiple_audio_streams,
'check_formats': opts.check_formats,
'listformats': opts.listformats,
'listformats_table': opts.listformats_table,
'outtmpl': opts.outtmpl,
'outtmpl_na_placeholder': opts.outtmpl_na_placeholder,
'paths': opts.paths,
'autonumber_size': opts.autonumber_size,
'autonumber_start': opts.autonumber_start,
'restrictfilenames': opts.restrictfilenames,
'windowsfilenames': opts.windowsfilenames,
'ignoreerrors': opts.ignoreerrors,
'force_generic_extractor': opts.force_generic_extractor,
'ratelimit': opts.ratelimit,
'throttledratelimit': opts.throttledratelimit,
'overwrites': opts.overwrites,
'retries': opts.retries,
'file_access_retries': opts.file_access_retries,
'fragment_retries': opts.fragment_retries,
'extractor_retries': opts.extractor_retries,
'skip_unavailable_fragments': opts.skip_unavailable_fragments,
'keep_fragments': opts.keep_fragments,
'concurrent_fragment_downloads': opts.concurrent_fragment_downloads,
'buffersize': opts.buffersize,
'noresizebuffer': opts.noresizebuffer,
'http_chunk_size': opts.http_chunk_size,
'continuedl': opts.continue_dl,
'noprogress': opts.quiet if opts.noprogress is None else opts.noprogress,
'progress_with_newline': opts.progress_with_newline,
'progress_template': opts.progress_template,
'playliststart': opts.playliststart,
'playlistend': opts.playlistend,
'playlistreverse': opts.playlist_reverse,
'playlistrandom': opts.playlist_random,
'noplaylist': opts.noplaylist,
'logtostderr': outtmpl_default == '-',
'consoletitle': opts.consoletitle,
'nopart': opts.nopart,
'updatetime': opts.updatetime,
'writedescription': opts.writedescription,
'writeannotations': opts.writeannotations,
'writeinfojson': opts.writeinfojson,
'allow_playlist_files': opts.allow_playlist_files,
'clean_infojson': opts.clean_infojson,
'getcomments': opts.getcomments,
'writethumbnail': opts.writethumbnail is True,
'write_all_thumbnails': opts.writethumbnail == 'all',
'writelink': opts.writelink,
'writeurllink': opts.writeurllink,
'writewebloclink': opts.writewebloclink,
'writedesktoplink': opts.writedesktoplink,
'writesubtitles': opts.writesubtitles,
'writeautomaticsub': opts.writeautomaticsub,
'allsubtitles': opts.allsubtitles,
'listsubtitles': opts.listsubtitles,
'subtitlesformat': opts.subtitlesformat,
'subtitleslangs': opts.subtitleslangs,
'matchtitle': decodeOption(opts.matchtitle),
'rejecttitle': decodeOption(opts.rejecttitle),
'max_downloads': opts.max_downloads,
'prefer_free_formats': opts.prefer_free_formats,
'trim_file_name': opts.trim_file_name,
'verbose': opts.verbose,
'dump_intermediate_pages': opts.dump_intermediate_pages,
'write_pages': opts.write_pages,
'test': opts.test,
'keepvideo': opts.keepvideo,
'min_filesize': opts.min_filesize,
'max_filesize': opts.max_filesize,
'min_views': opts.min_views,
'max_views': opts.max_views,
'daterange': date,
'cachedir': opts.cachedir,
'youtube_print_sig_code': opts.youtube_print_sig_code,
'age_limit': opts.age_limit,
'download_archive': download_archive_fn,
'break_on_existing': opts.break_on_existing,
'break_on_reject': opts.break_on_reject,
'break_per_url': opts.break_per_url,
'skip_playlist_after_errors': opts.skip_playlist_after_errors,
'cookiefile': opts.cookiefile,
'cookiesfrombrowser': opts.cookiesfrombrowser,
'legacyserverconnect': opts.legacy_server_connect,
'nocheckcertificate': opts.no_check_certificate,
'prefer_insecure': opts.prefer_insecure,
'proxy': opts.proxy,
'socket_timeout': opts.socket_timeout,
'bidi_workaround': opts.bidi_workaround,
'debug_printtraffic': opts.debug_printtraffic,
'prefer_ffmpeg': opts.prefer_ffmpeg,
'include_ads': opts.include_ads,
'default_search': opts.default_search,
'dynamic_mpd': opts.dynamic_mpd,
'extractor_args': opts.extractor_args,
'youtube_include_dash_manifest': opts.youtube_include_dash_manifest,
'youtube_include_hls_manifest': opts.youtube_include_hls_manifest,
'encoding': opts.encoding,
'extract_flat': opts.extract_flat,
'live_from_start': opts.live_from_start,
'wait_for_video': opts.wait_for_video,
'mark_watched': opts.mark_watched,
'merge_output_format': opts.merge_output_format,
'final_ext': final_ext,
'postprocessors': postprocessors,
'fixup': opts.fixup,
'source_address': opts.source_address,
'call_home': opts.call_home,
'sleep_interval_requests': opts.sleep_interval_requests,
'sleep_interval': opts.sleep_interval,
'max_sleep_interval': opts.max_sleep_interval,
'sleep_interval_subtitles': opts.sleep_interval_subtitles,
'external_downloader': opts.external_downloader,
'list_thumbnails': opts.list_thumbnails,
'playlist_items': opts.playlist_items,
'xattr_set_filesize': opts.xattr_set_filesize,
'match_filter': match_filter,
'no_color': opts.no_color,
'ffmpeg_location': opts.ffmpeg_location,
'hls_prefer_native': opts.hls_prefer_native,
'hls_use_mpegts': opts.hls_use_mpegts,
'hls_split_discontinuity': opts.hls_split_discontinuity,
'external_downloader_args': opts.external_downloader_args,
'postprocessor_args': opts.postprocessor_args,
'cn_verification_proxy': opts.cn_verification_proxy,
'geo_verification_proxy': opts.geo_verification_proxy,
'geo_bypass': opts.geo_bypass,
'geo_bypass_country': opts.geo_bypass_country,
'geo_bypass_ip_block': opts.geo_bypass_ip_block,
'_warnings': warnings,
'_deprecation_warnings': deprecation_warnings,
'compat_opts': compat_opts,
}
with YoutubeDL(ydl_opts) as ydl:
actual_use = all_urls or opts.load_info_filename
# Remove cache dir
if opts.rm_cachedir:
ydl.cache.remove()
# Update version
if opts.update_self:
# If updater returns True, exit. Required for windows
if run_update(ydl):
if actual_use:
sys.exit('ERROR: The program must exit for the update to complete')
sys.exit()
# Maybe do nothing
if not actual_use:
if opts.update_self or opts.rm_cachedir:
sys.exit()
ydl.warn_if_short_id(sys.argv[1:] if argv is None else argv)
parser.error(
'You must provide at least one URL.\n'
'Type yt-dlp --help to see a list of all options.')
try:
if opts.load_info_filename is not None:
retcode = ydl.download_with_info_file(expand_path(opts.load_info_filename))
else:
retcode = ydl.download(all_urls)
except DownloadCancelled:
ydl.to_screen('Aborting remaining downloads')
retcode = 101
sys.exit(retcode)
def main(argv=None):
try:
_real_main(argv)
except DownloadError:
sys.exit(1)
except SameFileError as e:
sys.exit(f'ERROR: {e}')
except KeyboardInterrupt:
sys.exit('\nERROR: Interrupted by user')
except BrokenPipeError as e:
# https://docs.python.org/3/library/signal.html#note-on-sigpipe
devnull = os.open(os.devnull, os.O_WRONLY)
os.dup2(devnull, sys.stdout.fileno())
sys.exit(f'\nERROR: {e}')
__all__ = ['main', 'YoutubeDL', 'gen_extractors', 'list_extractors']

19
plugins/youtube_download/yt_dlp/__main__.py Normal file
View File

@ -0,0 +1,19 @@
#!/usr/bin/env python3
from __future__ import unicode_literals
# Execute with
# $ python yt_dlp/__main__.py (2.6+)
# $ python -m yt_dlp (2.7+)
import sys
if __package__ is None and not hasattr(sys, 'frozen'):
# direct call of __main__.py
import os.path
path = os.path.realpath(os.path.abspath(__file__))
sys.path.insert(0, os.path.dirname(os.path.dirname(path)))
import yt_dlp
if __name__ == '__main__':
yt_dlp.main()

522
plugins/youtube_download/yt_dlp/aes.py Normal file
View File

@ -0,0 +1,522 @@
from __future__ import unicode_literals
from math import ceil
from .compat import (
compat_b64decode,
compat_ord,
compat_pycrypto_AES,
)
from .utils import (
bytes_to_intlist,
intlist_to_bytes,
)
if compat_pycrypto_AES:
def aes_cbc_decrypt_bytes(data, key, iv):
""" Decrypt bytes with AES-CBC using pycryptodome """
return compat_pycrypto_AES.new(key, compat_pycrypto_AES.MODE_CBC, iv).decrypt(data)
def aes_gcm_decrypt_and_verify_bytes(data, key, tag, nonce):
""" Decrypt bytes with AES-GCM using pycryptodome """
return compat_pycrypto_AES.new(key, compat_pycrypto_AES.MODE_GCM, nonce).decrypt_and_verify(data, tag)
else:
def aes_cbc_decrypt_bytes(data, key, iv):
""" Decrypt bytes with AES-CBC using native implementation since pycryptodome is unavailable """
return intlist_to_bytes(aes_cbc_decrypt(*map(bytes_to_intlist, (data, key, iv))))
def aes_gcm_decrypt_and_verify_bytes(data, key, tag, nonce):
""" Decrypt bytes with AES-GCM using native implementation since pycryptodome is unavailable """
return intlist_to_bytes(aes_gcm_decrypt_and_verify(*map(bytes_to_intlist, (data, key, tag, nonce))))
def unpad_pkcs7(data):
return data[:-compat_ord(data[-1])]
BLOCK_SIZE_BYTES = 16
def aes_ecb_encrypt(data, key, iv=None):
"""
Encrypt with aes in ECB mode
@param {int[]} data cleartext
@param {int[]} key 16/24/32-Byte cipher key
@param {int[]} iv Unused for this mode
@returns {int[]} encrypted data
"""
expanded_key = key_expansion(key)
block_count = int(ceil(float(len(data)) / BLOCK_SIZE_BYTES))
encrypted_data = []
for i in range(block_count):
block = data[i * BLOCK_SIZE_BYTES: (i + 1) * BLOCK_SIZE_BYTES]
encrypted_data += aes_encrypt(block, expanded_key)
encrypted_data = encrypted_data[:len(data)]
return encrypted_data
def aes_ecb_decrypt(data, key, iv=None):
"""
Decrypt with aes in ECB mode
@param {int[]} data cleartext
@param {int[]} key 16/24/32-Byte cipher key
@param {int[]} iv Unused for this mode
@returns {int[]} decrypted data
"""
expanded_key = key_expansion(key)
block_count = int(ceil(float(len(data)) / BLOCK_SIZE_BYTES))
encrypted_data = []
for i in range(block_count):
block = data[i * BLOCK_SIZE_BYTES: (i + 1) * BLOCK_SIZE_BYTES]
encrypted_data += aes_decrypt(block, expanded_key)
encrypted_data = encrypted_data[:len(data)]
return encrypted_data
def aes_ctr_decrypt(data, key, iv):
"""
Decrypt with aes in counter mode
@param {int[]} data cipher
@param {int[]} key 16/24/32-Byte cipher key
@param {int[]} iv 16-Byte initialization vector
@returns {int[]} decrypted data
"""
return aes_ctr_encrypt(data, key, iv)
def aes_ctr_encrypt(data, key, iv):
"""
Encrypt with aes in counter mode
@param {int[]} data cleartext
@param {int[]} key 16/24/32-Byte cipher key
@param {int[]} iv 16-Byte initialization vector
@returns {int[]} encrypted data
"""
expanded_key = key_expansion(key)
block_count = int(ceil(float(len(data)) / BLOCK_SIZE_BYTES))
counter = iter_vector(iv)
encrypted_data = []
for i in range(block_count):
counter_block = next(counter)
block = data[i * BLOCK_SIZE_BYTES: (i + 1) * BLOCK_SIZE_BYTES]
block += [0] * (BLOCK_SIZE_BYTES - len(block))
cipher_counter_block = aes_encrypt(counter_block, expanded_key)
encrypted_data += xor(block, cipher_counter_block)
encrypted_data = encrypted_data[:len(data)]
return encrypted_data
def aes_cbc_decrypt(data, key, iv):
"""
Decrypt with aes in CBC mode
@param {int[]} data cipher
@param {int[]} key 16/24/32-Byte cipher key
@param {int[]} iv 16-Byte IV
@returns {int[]} decrypted data
"""
expanded_key = key_expansion(key)
block_count = int(ceil(float(len(data)) / BLOCK_SIZE_BYTES))
decrypted_data = []
previous_cipher_block = iv
for i in range(block_count):
block = data[i * BLOCK_SIZE_BYTES: (i + 1) * BLOCK_SIZE_BYTES]
block += [0] * (BLOCK_SIZE_BYTES - len(block))
decrypted_block = aes_decrypt(block, expanded_key)
decrypted_data += xor(decrypted_block, previous_cipher_block)
previous_cipher_block = block
decrypted_data = decrypted_data[:len(data)]
return decrypted_data
def aes_cbc_encrypt(data, key, iv):
"""
Encrypt with aes in CBC mode. Using PKCS#7 padding
@param {int[]} data cleartext
@param {int[]} key 16/24/32-Byte cipher key
@param {int[]} iv 16-Byte IV
@returns {int[]} encrypted data
"""
expanded_key = key_expansion(key)
block_count = int(ceil(float(len(data)) / BLOCK_SIZE_BYTES))
encrypted_data = []
previous_cipher_block = iv
for i in range(block_count):
block = data[i * BLOCK_SIZE_BYTES: (i + 1) * BLOCK_SIZE_BYTES]
remaining_length = BLOCK_SIZE_BYTES - len(block)
block += [remaining_length] * remaining_length
mixed_block = xor(block, previous_cipher_block)
encrypted_block = aes_encrypt(mixed_block, expanded_key)
encrypted_data += encrypted_block
previous_cipher_block = encrypted_block
return encrypted_data
def aes_gcm_decrypt_and_verify(data, key, tag, nonce):
"""
Decrypt with aes in GBM mode and checks authenticity using tag
@param {int[]} data cipher
@param {int[]} key 16-Byte cipher key
@param {int[]} tag authentication tag
@param {int[]} nonce IV (recommended 12-Byte)
@returns {int[]} decrypted data
"""
# XXX: check aes, gcm param
hash_subkey = aes_encrypt([0] * BLOCK_SIZE_BYTES, key_expansion(key))
if len(nonce) == 12:
j0 = nonce + [0, 0, 0, 1]
else:
fill = (BLOCK_SIZE_BYTES - (len(nonce) % BLOCK_SIZE_BYTES)) % BLOCK_SIZE_BYTES + 8
ghash_in = nonce + [0] * fill + bytes_to_intlist((8 * len(nonce)).to_bytes(8, 'big'))
j0 = ghash(hash_subkey, ghash_in)
# TODO: add nonce support to aes_ctr_decrypt
# nonce_ctr = j0[:12]
iv_ctr = inc(j0)
decrypted_data = aes_ctr_decrypt(data, key, iv_ctr + [0] * (BLOCK_SIZE_BYTES - len(iv_ctr)))
pad_len = len(data) // 16 * 16
s_tag = ghash(
hash_subkey,
data
+ [0] * (BLOCK_SIZE_BYTES - len(data) + pad_len) # pad
+ bytes_to_intlist((0 * 8).to_bytes(8, 'big') # length of associated data
+ ((len(data) * 8).to_bytes(8, 'big'))) # length of data
)
if tag != aes_ctr_encrypt(s_tag, key, j0):
raise ValueError("Mismatching authentication tag")
return decrypted_data
def aes_encrypt(data, expanded_key):
"""
Encrypt one block with aes
@param {int[]} data 16-Byte state
@param {int[]} expanded_key 176/208/240-Byte expanded key
@returns {int[]} 16-Byte cipher
"""
rounds = len(expanded_key) // BLOCK_SIZE_BYTES - 1
data = xor(data, expanded_key[:BLOCK_SIZE_BYTES])
for i in range(1, rounds + 1):
data = sub_bytes(data)
data = shift_rows(data)
if i != rounds:
data = list(iter_mix_columns(data, MIX_COLUMN_MATRIX))
data = xor(data, expanded_key[i * BLOCK_SIZE_BYTES: (i + 1) * BLOCK_SIZE_BYTES])
return data
def aes_decrypt(data, expanded_key):
"""
Decrypt one block with aes
@param {int[]} data 16-Byte cipher
@param {int[]} expanded_key 176/208/240-Byte expanded key
@returns {int[]} 16-Byte state
"""
rounds = len(expanded_key) // BLOCK_SIZE_BYTES - 1
for i in range(rounds, 0, -1):
data = xor(data, expanded_key[i * BLOCK_SIZE_BYTES: (i + 1) * BLOCK_SIZE_BYTES])
if i != rounds:
data = list(iter_mix_columns(data, MIX_COLUMN_MATRIX_INV))
data = shift_rows_inv(data)
data = sub_bytes_inv(data)
data = xor(data, expanded_key[:BLOCK_SIZE_BYTES])
return data
def aes_decrypt_text(data, password, key_size_bytes):
"""
Decrypt text
- The first 8 Bytes of decoded 'data' are the 8 high Bytes of the counter
- The cipher key is retrieved by encrypting the first 16 Byte of 'password'
with the first 'key_size_bytes' Bytes from 'password' (if necessary filled with 0's)
- Mode of operation is 'counter'
@param {str} data Base64 encoded string
@param {str,unicode} password Password (will be encoded with utf-8)
@param {int} key_size_bytes Possible values: 16 for 128-Bit, 24 for 192-Bit or 32 for 256-Bit
@returns {str} Decrypted data
"""
NONCE_LENGTH_BYTES = 8
data = bytes_to_intlist(compat_b64decode(data))
password = bytes_to_intlist(password.encode('utf-8'))
key = password[:key_size_bytes] + [0] * (key_size_bytes - len(password))
key = aes_encrypt(key[:BLOCK_SIZE_BYTES], key_expansion(key)) * (key_size_bytes // BLOCK_SIZE_BYTES)
nonce = data[:NONCE_LENGTH_BYTES]
cipher = data[NONCE_LENGTH_BYTES:]
decrypted_data = aes_ctr_decrypt(cipher, key, nonce + [0] * (BLOCK_SIZE_BYTES - NONCE_LENGTH_BYTES))
plaintext = intlist_to_bytes(decrypted_data)
return plaintext
RCON = (0x8d, 0x01, 0x02, 0x04, 0x08, 0x10, 0x20, 0x40, 0x80, 0x1b, 0x36)
SBOX = (0x63, 0x7C, 0x77, 0x7B, 0xF2, 0x6B, 0x6F, 0xC5, 0x30, 0x01, 0x67, 0x2B, 0xFE, 0xD7, 0xAB, 0x76,
0xCA, 0x82, 0xC9, 0x7D, 0xFA, 0x59, 0x47, 0xF0, 0xAD, 0xD4, 0xA2, 0xAF, 0x9C, 0xA4, 0x72, 0xC0,
0xB7, 0xFD, 0x93, 0x26, 0x36, 0x3F, 0xF7, 0xCC, 0x34, 0xA5, 0xE5, 0xF1, 0x71, 0xD8, 0x31, 0x15,
0x04, 0xC7, 0x23, 0xC3, 0x18, 0x96, 0x05, 0x9A, 0x07, 0x12, 0x80, 0xE2, 0xEB, 0x27, 0xB2, 0x75,
0x09, 0x83, 0x2C, 0x1A, 0x1B, 0x6E, 0x5A, 0xA0, 0x52, 0x3B, 0xD6, 0xB3, 0x29, 0xE3, 0x2F, 0x84,
0x53, 0xD1, 0x00, 0xED, 0x20, 0xFC, 0xB1, 0x5B, 0x6A, 0xCB, 0xBE, 0x39, 0x4A, 0x4C, 0x58, 0xCF,
0xD0, 0xEF, 0xAA, 0xFB, 0x43, 0x4D, 0x33, 0x85, 0x45, 0xF9, 0x02, 0x7F, 0x50, 0x3C, 0x9F, 0xA8,
0x51, 0xA3, 0x40, 0x8F, 0x92, 0x9D, 0x38, 0xF5, 0xBC, 0xB6, 0xDA, 0x21, 0x10, 0xFF, 0xF3, 0xD2,
0xCD, 0x0C, 0x13, 0xEC, 0x5F, 0x97, 0x44, 0x17, 0xC4, 0xA7, 0x7E, 0x3D, 0x64, 0x5D, 0x19, 0x73,
0x60, 0x81, 0x4F, 0xDC, 0x22, 0x2A, 0x90, 0x88, 0x46, 0xEE, 0xB8, 0x14, 0xDE, 0x5E, 0x0B, 0xDB,
0xE0, 0x32, 0x3A, 0x0A, 0x49, 0x06, 0x24, 0x5C, 0xC2, 0xD3, 0xAC, 0x62, 0x91, 0x95, 0xE4, 0x79,
0xE7, 0xC8, 0x37, 0x6D, 0x8D, 0xD5, 0x4E, 0xA9, 0x6C, 0x56, 0xF4, 0xEA, 0x65, 0x7A, 0xAE, 0x08,
0xBA, 0x78, 0x25, 0x2E, 0x1C, 0xA6, 0xB4, 0xC6, 0xE8, 0xDD, 0x74, 0x1F, 0x4B, 0xBD, 0x8B, 0x8A,
0x70, 0x3E, 0xB5, 0x66, 0x48, 0x03, 0xF6, 0x0E, 0x61, 0x35, 0x57, 0xB9, 0x86, 0xC1, 0x1D, 0x9E,
0xE1, 0xF8, 0x98, 0x11, 0x69, 0xD9, 0x8E, 0x94, 0x9B, 0x1E, 0x87, 0xE9, 0xCE, 0x55, 0x28, 0xDF,
0x8C, 0xA1, 0x89, 0x0D, 0xBF, 0xE6, 0x42, 0x68, 0x41, 0x99, 0x2D, 0x0F, 0xB0, 0x54, 0xBB, 0x16)
SBOX_INV = (0x52, 0x09, 0x6a, 0xd5, 0x30, 0x36, 0xa5, 0x38, 0xbf, 0x40, 0xa3, 0x9e, 0x81, 0xf3, 0xd7, 0xfb,
0x7c, 0xe3, 0x39, 0x82, 0x9b, 0x2f, 0xff, 0x87, 0x34, 0x8e, 0x43, 0x44, 0xc4, 0xde, 0xe9, 0xcb,
0x54, 0x7b, 0x94, 0x32, 0xa6, 0xc2, 0x23, 0x3d, 0xee, 0x4c, 0x95, 0x0b, 0x42, 0xfa, 0xc3, 0x4e,
0x08, 0x2e, 0xa1, 0x66, 0x28, 0xd9, 0x24, 0xb2, 0x76, 0x5b, 0xa2, 0x49, 0x6d, 0x8b, 0xd1, 0x25,
0x72, 0xf8, 0xf6, 0x64, 0x86, 0x68, 0x98, 0x16, 0xd4, 0xa4, 0x5c, 0xcc, 0x5d, 0x65, 0xb6, 0x92,
0x6c, 0x70, 0x48, 0x50, 0xfd, 0xed, 0xb9, 0xda, 0x5e, 0x15, 0x46, 0x57, 0xa7, 0x8d, 0x9d, 0x84,
0x90, 0xd8, 0xab, 0x00, 0x8c, 0xbc, 0xd3, 0x0a, 0xf7, 0xe4, 0x58, 0x05, 0xb8, 0xb3, 0x45, 0x06,
0xd0, 0x2c, 0x1e, 0x8f, 0xca, 0x3f, 0x0f, 0x02, 0xc1, 0xaf, 0xbd, 0x03, 0x01, 0x13, 0x8a, 0x6b,
0x3a, 0x91, 0x11, 0x41, 0x4f, 0x67, 0xdc, 0xea, 0x97, 0xf2, 0xcf, 0xce, 0xf0, 0xb4, 0xe6, 0x73,
0x96, 0xac, 0x74, 0x22, 0xe7, 0xad, 0x35, 0x85, 0xe2, 0xf9, 0x37, 0xe8, 0x1c, 0x75, 0xdf, 0x6e,
0x47, 0xf1, 0x1a, 0x71, 0x1d, 0x29, 0xc5, 0x89, 0x6f, 0xb7, 0x62, 0x0e, 0xaa, 0x18, 0xbe, 0x1b,
0xfc, 0x56, 0x3e, 0x4b, 0xc6, 0xd2, 0x79, 0x20, 0x9a, 0xdb, 0xc0, 0xfe, 0x78, 0xcd, 0x5a, 0xf4,
0x1f, 0xdd, 0xa8, 0x33, 0x88, 0x07, 0xc7, 0x31, 0xb1, 0x12, 0x10, 0x59, 0x27, 0x80, 0xec, 0x5f,
0x60, 0x51, 0x7f, 0xa9, 0x19, 0xb5, 0x4a, 0x0d, 0x2d, 0xe5, 0x7a, 0x9f, 0x93, 0xc9, 0x9c, 0xef,
0xa0, 0xe0, 0x3b, 0x4d, 0xae, 0x2a, 0xf5, 0xb0, 0xc8, 0xeb, 0xbb, 0x3c, 0x83, 0x53, 0x99, 0x61,
0x17, 0x2b, 0x04, 0x7e, 0xba, 0x77, 0xd6, 0x26, 0xe1, 0x69, 0x14, 0x63, 0x55, 0x21, 0x0c, 0x7d)
MIX_COLUMN_MATRIX = ((0x2, 0x3, 0x1, 0x1),
(0x1, 0x2, 0x3, 0x1),
(0x1, 0x1, 0x2, 0x3),
(0x3, 0x1, 0x1, 0x2))
MIX_COLUMN_MATRIX_INV = ((0xE, 0xB, 0xD, 0x9),
(0x9, 0xE, 0xB, 0xD),
(0xD, 0x9, 0xE, 0xB),
(0xB, 0xD, 0x9, 0xE))
RIJNDAEL_EXP_TABLE = (0x01, 0x03, 0x05, 0x0F, 0x11, 0x33, 0x55, 0xFF, 0x1A, 0x2E, 0x72, 0x96, 0xA1, 0xF8, 0x13, 0x35,
0x5F, 0xE1, 0x38, 0x48, 0xD8, 0x73, 0x95, 0xA4, 0xF7, 0x02, 0x06, 0x0A, 0x1E, 0x22, 0x66, 0xAA,
0xE5, 0x34, 0x5C, 0xE4, 0x37, 0x59, 0xEB, 0x26, 0x6A, 0xBE, 0xD9, 0x70, 0x90, 0xAB, 0xE6, 0x31,
0x53, 0xF5, 0x04, 0x0C, 0x14, 0x3C, 0x44, 0xCC, 0x4F, 0xD1, 0x68, 0xB8, 0xD3, 0x6E, 0xB2, 0xCD,
0x4C, 0xD4, 0x67, 0xA9, 0xE0, 0x3B, 0x4D, 0xD7, 0x62, 0xA6, 0xF1, 0x08, 0x18, 0x28, 0x78, 0x88,
0x83, 0x9E, 0xB9, 0xD0, 0x6B, 0xBD, 0xDC, 0x7F, 0x81, 0x98, 0xB3, 0xCE, 0x49, 0xDB, 0x76, 0x9A,
0xB5, 0xC4, 0x57, 0xF9, 0x10, 0x30, 0x50, 0xF0, 0x0B, 0x1D, 0x27, 0x69, 0xBB, 0xD6, 0x61, 0xA3,
0xFE, 0x19, 0x2B, 0x7D, 0x87, 0x92, 0xAD, 0xEC, 0x2F, 0x71, 0x93, 0xAE, 0xE9, 0x20, 0x60, 0xA0,
0xFB, 0x16, 0x3A, 0x4E, 0xD2, 0x6D, 0xB7, 0xC2, 0x5D, 0xE7, 0x32, 0x56, 0xFA, 0x15, 0x3F, 0x41,
0xC3, 0x5E, 0xE2, 0x3D, 0x47, 0xC9, 0x40, 0xC0, 0x5B, 0xED, 0x2C, 0x74, 0x9C, 0xBF, 0xDA, 0x75,
0x9F, 0xBA, 0xD5, 0x64, 0xAC, 0xEF, 0x2A, 0x7E, 0x82, 0x9D, 0xBC, 0xDF, 0x7A, 0x8E, 0x89, 0x80,
0x9B, 0xB6, 0xC1, 0x58, 0xE8, 0x23, 0x65, 0xAF, 0xEA, 0x25, 0x6F, 0xB1, 0xC8, 0x43, 0xC5, 0x54,
0xFC, 0x1F, 0x21, 0x63, 0xA5, 0xF4, 0x07, 0x09, 0x1B, 0x2D, 0x77, 0x99, 0xB0, 0xCB, 0x46, 0xCA,
0x45, 0xCF, 0x4A, 0xDE, 0x79, 0x8B, 0x86, 0x91, 0xA8, 0xE3, 0x3E, 0x42, 0xC6, 0x51, 0xF3, 0x0E,
0x12, 0x36, 0x5A, 0xEE, 0x29, 0x7B, 0x8D, 0x8C, 0x8F, 0x8A, 0x85, 0x94, 0xA7, 0xF2, 0x0D, 0x17,
0x39, 0x4B, 0xDD, 0x7C, 0x84, 0x97, 0xA2, 0xFD, 0x1C, 0x24, 0x6C, 0xB4, 0xC7, 0x52, 0xF6, 0x01)
RIJNDAEL_LOG_TABLE = (0x00, 0x00, 0x19, 0x01, 0x32, 0x02, 0x1a, 0xc6, 0x4b, 0xc7, 0x1b, 0x68, 0x33, 0xee, 0xdf, 0x03,
0x64, 0x04, 0xe0, 0x0e, 0x34, 0x8d, 0x81, 0xef, 0x4c, 0x71, 0x08, 0xc8, 0xf8, 0x69, 0x1c, 0xc1,
0x7d, 0xc2, 0x1d, 0xb5, 0xf9, 0xb9, 0x27, 0x6a, 0x4d, 0xe4, 0xa6, 0x72, 0x9a, 0xc9, 0x09, 0x78,
0x65, 0x2f, 0x8a, 0x05, 0x21, 0x0f, 0xe1, 0x24, 0x12, 0xf0, 0x82, 0x45, 0x35, 0x93, 0xda, 0x8e,
0x96, 0x8f, 0xdb, 0xbd, 0x36, 0xd0, 0xce, 0x94, 0x13, 0x5c, 0xd2, 0xf1, 0x40, 0x46, 0x83, 0x38,
0x66, 0xdd, 0xfd, 0x30, 0xbf, 0x06, 0x8b, 0x62, 0xb3, 0x25, 0xe2, 0x98, 0x22, 0x88, 0x91, 0x10,
0x7e, 0x6e, 0x48, 0xc3, 0xa3, 0xb6, 0x1e, 0x42, 0x3a, 0x6b, 0x28, 0x54, 0xfa, 0x85, 0x3d, 0xba,
0x2b, 0x79, 0x0a, 0x15, 0x9b, 0x9f, 0x5e, 0xca, 0x4e, 0xd4, 0xac, 0xe5, 0xf3, 0x73, 0xa7, 0x57,
0xaf, 0x58, 0xa8, 0x50, 0xf4, 0xea, 0xd6, 0x74, 0x4f, 0xae, 0xe9, 0xd5, 0xe7, 0xe6, 0xad, 0xe8,
0x2c, 0xd7, 0x75, 0x7a, 0xeb, 0x16, 0x0b, 0xf5, 0x59, 0xcb, 0x5f, 0xb0, 0x9c, 0xa9, 0x51, 0xa0,
0x7f, 0x0c, 0xf6, 0x6f, 0x17, 0xc4, 0x49, 0xec, 0xd8, 0x43, 0x1f, 0x2d, 0xa4, 0x76, 0x7b, 0xb7,
0xcc, 0xbb, 0x3e, 0x5a, 0xfb, 0x60, 0xb1, 0x86, 0x3b, 0x52, 0xa1, 0x6c, 0xaa, 0x55, 0x29, 0x9d,
0x97, 0xb2, 0x87, 0x90, 0x61, 0xbe, 0xdc, 0xfc, 0xbc, 0x95, 0xcf, 0xcd, 0x37, 0x3f, 0x5b, 0xd1,
0x53, 0x39, 0x84, 0x3c, 0x41, 0xa2, 0x6d, 0x47, 0x14, 0x2a, 0x9e, 0x5d, 0x56, 0xf2, 0xd3, 0xab,
0x44, 0x11, 0x92, 0xd9, 0x23, 0x20, 0x2e, 0x89, 0xb4, 0x7c, 0xb8, 0x26, 0x77, 0x99, 0xe3, 0xa5,
0x67, 0x4a, 0xed, 0xde, 0xc5, 0x31, 0xfe, 0x18, 0x0d, 0x63, 0x8c, 0x80, 0xc0, 0xf7, 0x70, 0x07)
def key_expansion(data):
"""
Generate key schedule
@param {int[]} data 16/24/32-Byte cipher key
@returns {int[]} 176/208/240-Byte expanded key
"""
data = data[:] # copy
rcon_iteration = 1
key_size_bytes = len(data)
expanded_key_size_bytes = (key_size_bytes // 4 + 7) * BLOCK_SIZE_BYTES
while len(data) < expanded_key_size_bytes:
temp = data[-4:]
temp = key_schedule_core(temp, rcon_iteration)
rcon_iteration += 1
data += xor(temp, data[-key_size_bytes: 4 - key_size_bytes])
for _ in range(3):
temp = data[-4:]
data += xor(temp, data[-key_size_bytes: 4 - key_size_bytes])
if key_size_bytes == 32:
temp = data[-4:]
temp = sub_bytes(temp)
data += xor(temp, data[-key_size_bytes: 4 - key_size_bytes])
for _ in range(3 if key_size_bytes == 32 else 2 if key_size_bytes == 24 else 0):
temp = data[-4:]
data += xor(temp, data[-key_size_bytes: 4 - key_size_bytes])
data = data[:expanded_key_size_bytes]
return data
def iter_vector(iv):
while True:
yield iv
iv = inc(iv)
def sub_bytes(data):
return [SBOX[x] for x in data]
def sub_bytes_inv(data):
return [SBOX_INV[x] for x in data]
def rotate(data):
return data[1:] + [data[0]]
def key_schedule_core(data, rcon_iteration):
data = rotate(data)
data = sub_bytes(data)
data[0] = data[0] ^ RCON[rcon_iteration]
return data
def xor(data1, data2):
return [x ^ y for x, y in zip(data1, data2)]
def iter_mix_columns(data, matrix):
for i in (0, 4, 8, 12):
for row in matrix:
mixed = 0
for j in range(4):
# xor is (+) and (-)
mixed ^= (0 if data[i:i + 4][j] == 0 or row[j] == 0 else
RIJNDAEL_EXP_TABLE[(RIJNDAEL_LOG_TABLE[data[i + j]] + RIJNDAEL_LOG_TABLE[row[j]]) % 0xFF])
yield mixed
def shift_rows(data):
return [data[((column + row) & 0b11) * 4 + row] for column in range(4) for row in range(4)]
def shift_rows_inv(data):
return [data[((column - row) & 0b11) * 4 + row] for column in range(4) for row in range(4)]
def shift_block(data):
data_shifted = []
bit = 0
for n in data:
if bit:
n |= 0x100
bit = n & 1
n >>= 1
data_shifted.append(n)
return data_shifted
def inc(data):
data = data[:] # copy
for i in range(len(data) - 1, -1, -1):
if data[i] == 255:
data[i] = 0
else:
data[i] = data[i] + 1
break
return data
def block_product(block_x, block_y):
# NIST SP 800-38D, Algorithm 1
if len(block_x) != BLOCK_SIZE_BYTES or len(block_y) != BLOCK_SIZE_BYTES:
raise ValueError("Length of blocks need to be %d bytes" % BLOCK_SIZE_BYTES)
block_r = [0xE1] + [0] * (BLOCK_SIZE_BYTES - 1)
block_v = block_y[:]
block_z = [0] * BLOCK_SIZE_BYTES
for i in block_x:
for bit in range(7, -1, -1):
if i & (1 << bit):
block_z = xor(block_z, block_v)
do_xor = block_v[-1] & 1
block_v = shift_block(block_v)
if do_xor:
block_v = xor(block_v, block_r)
return block_z
def ghash(subkey, data):
# NIST SP 800-38D, Algorithm 2
if len(data) % BLOCK_SIZE_BYTES:
raise ValueError("Length of data should be %d bytes" % BLOCK_SIZE_BYTES)
last_y = [0] * BLOCK_SIZE_BYTES
for i in range(0, len(data), BLOCK_SIZE_BYTES):
block = data[i : i + BLOCK_SIZE_BYTES] # noqa: E203
last_y = block_product(xor(last_y, block), subkey)
return last_y
__all__ = [
'aes_ctr_decrypt',
'aes_cbc_decrypt',
'aes_cbc_decrypt_bytes',
'aes_decrypt_text',
'aes_encrypt',
'aes_gcm_decrypt_and_verify',
'aes_gcm_decrypt_and_verify_bytes',
'key_expansion',
'unpad_pkcs7',
]

98
plugins/youtube_download/yt_dlp/cache.py Normal file
View File

@ -0,0 +1,98 @@
from __future__ import unicode_literals
import errno
import io
import json
import os
import re
import shutil
import traceback
from .compat import compat_getenv
from .utils import (
expand_path,
write_json_file,
)
class Cache(object):
def __init__(self, ydl):
self._ydl = ydl
def _get_root_dir(self):
res = self._ydl.params.get('cachedir')
if res is None:
cache_root = compat_getenv('XDG_CACHE_HOME', '~/.cache')
res = os.path.join(cache_root, 'yt-dlp')
return expand_path(res)
def _get_cache_fn(self, section, key, dtype):
assert re.match(r'^[a-zA-Z0-9_.-]+$', section), \
'invalid section %r' % section
assert re.match(r'^[a-zA-Z0-9_.-]+$', key), 'invalid key %r' % key
return os.path.join(
self._get_root_dir(), section, '%s.%s' % (key, dtype))
@property
def enabled(self):
return self._ydl.params.get('cachedir') is not False
def store(self, section, key, data, dtype='json'):
assert dtype in ('json',)
if not self.enabled:
return
fn = self._get_cache_fn(section, key, dtype)
try:
try:
os.makedirs(os.path.dirname(fn))
except OSError as ose:
if ose.errno != errno.EEXIST:
raise
self._ydl.write_debug(f'Saving {section}.{key} to cache')
write_json_file(data, fn)
except Exception:
tb = traceback.format_exc()
self._ydl.report_warning(
'Writing cache to %r failed: %s' % (fn, tb))
def load(self, section, key, dtype='json', default=None):
assert dtype in ('json',)
if not self.enabled:
return default
cache_fn = self._get_cache_fn(section, key, dtype)
try:
try:
with io.open(cache_fn, 'r', encoding='utf-8') as cachef:
self._ydl.write_debug(f'Loading {section}.{key} from cache')
return json.load(cachef)
except ValueError:
try:
file_size = os.path.getsize(cache_fn)
except (OSError, IOError) as oe:
file_size = str(oe)
self._ydl.report_warning(
'Cache retrieval from %s failed (%s)' % (cache_fn, file_size))
except IOError:
pass # No cache available
return default
def remove(self):
if not self.enabled:
self._ydl.to_screen('Cache is disabled (Did you combine --no-cache-dir and --rm-cache-dir?)')
return
cachedir = self._get_root_dir()
if not any((term in cachedir) for term in ('cache', 'tmp')):
raise Exception('Not removing directory %s - this does not look like a cache dir' % cachedir)
self._ydl.to_screen(
'Removing cache dir %s .' % cachedir, skip_eol=True)
if os.path.exists(cachedir):
self._ydl.to_screen('.', skip_eol=True)
shutil.rmtree(cachedir)
self._ydl.to_screen('.')

311
plugins/youtube_download/yt_dlp/compat.py Normal file
View File

@ -0,0 +1,311 @@
# coding: utf-8
import asyncio
import base64
import collections
import ctypes
import getpass
import html
import html.parser
import http
import http.client
import http.cookiejar
import http.cookies
import http.server
import itertools
import optparse
import os
import re
import shlex
import shutil
import socket
import struct
import subprocess
import sys
import tokenize
import urllib
import xml.etree.ElementTree as etree
from subprocess import DEVNULL
# HTMLParseError has been deprecated in Python 3.3 and removed in
# Python 3.5. Introducing dummy exception for Python >3.5 for compatible
# and uniform cross-version exception handling
class compat_HTMLParseError(Exception):
pass
# compat_ctypes_WINFUNCTYPE = ctypes.WINFUNCTYPE
# will not work since ctypes.WINFUNCTYPE does not exist in UNIX machines
def compat_ctypes_WINFUNCTYPE(*args, **kwargs):
return ctypes.WINFUNCTYPE(*args, **kwargs)
class _TreeBuilder(etree.TreeBuilder):
def doctype(self, name, pubid, system):
pass
def compat_etree_fromstring(text):
return etree.XML(text, parser=etree.XMLParser(target=_TreeBuilder()))
compat_os_name = os._name if os.name == 'java' else os.name
if compat_os_name == 'nt':
def compat_shlex_quote(s):
return s if re.match(r'^[-_\w./]+$', s) else '"%s"' % s.replace('"', '\\"')
else:
from shlex import quote as compat_shlex_quote
def compat_ord(c):
if type(c) is int:
return c
else:
return ord(c)
def compat_setenv(key, value, env=os.environ):
env[key] = value
if compat_os_name == 'nt' and sys.version_info < (3, 8):
# os.path.realpath on Windows does not follow symbolic links
# prior to Python 3.8 (see https://bugs.python.org/issue9949)
def compat_realpath(path):
while os.path.islink(path):
path = os.path.abspath(os.readlink(path))
return path
else:
compat_realpath = os.path.realpath
def compat_print(s):
assert isinstance(s, compat_str)
print(s)
# Fix https://github.com/ytdl-org/youtube-dl/issues/4223
# See http://bugs.python.org/issue9161 for what is broken
def workaround_optparse_bug9161():
op = optparse.OptionParser()
og = optparse.OptionGroup(op, 'foo')
try:
og.add_option('-t')
except TypeError:
real_add_option = optparse.OptionGroup.add_option
def _compat_add_option(self, *args, **kwargs):
enc = lambda v: (
v.encode('ascii', 'replace') if isinstance(v, compat_str)
else v)
bargs = [enc(a) for a in args]
bkwargs = dict(
(k, enc(v)) for k, v in kwargs.items())
return real_add_option(self, *bargs, **bkwargs)
optparse.OptionGroup.add_option = _compat_add_option
try:
compat_Pattern = re.Pattern
except AttributeError:
compat_Pattern = type(re.compile(''))
try:
compat_Match = re.Match
except AttributeError:
compat_Match = type(re.compile('').match(''))
try:
compat_asyncio_run = asyncio.run # >= 3.7
except AttributeError:
def compat_asyncio_run(coro):
try:
loop = asyncio.get_event_loop()
except RuntimeError:
loop = asyncio.new_event_loop()
asyncio.set_event_loop(loop)
loop.run_until_complete(coro)
asyncio.run = compat_asyncio_run
# Python 3.8+ does not honor %HOME% on windows, but this breaks compatibility with youtube-dl
# See https://github.com/yt-dlp/yt-dlp/issues/792
# https://docs.python.org/3/library/os.path.html#os.path.expanduser
if compat_os_name in ('nt', 'ce') and 'HOME' in os.environ:
_userhome = os.environ['HOME']
def compat_expanduser(path):
if not path.startswith('~'):
return path
i = path.replace('\\', '/', 1).find('/') # ~user
if i < 0:
i = len(path)
userhome = os.path.join(os.path.dirname(_userhome), path[1:i]) if i > 1 else _userhome
return userhome + path[i:]
else:
compat_expanduser = os.path.expanduser
try:
from Cryptodome.Cipher import AES as compat_pycrypto_AES
except ImportError:
try:
from Crypto.Cipher import AES as compat_pycrypto_AES
except ImportError:
compat_pycrypto_AES = None
WINDOWS_VT_MODE = False if compat_os_name == 'nt' else None
def windows_enable_vt_mode(): # TODO: Do this the proper way https://bugs.python.org/issue30075
if compat_os_name != 'nt':
return
global WINDOWS_VT_MODE
startupinfo = subprocess.STARTUPINFO()
startupinfo.dwFlags |= subprocess.STARTF_USESHOWWINDOW
try:
subprocess.Popen('', shell=True, startupinfo=startupinfo)
WINDOWS_VT_MODE = True
except Exception:
pass
# Deprecated
compat_basestring = str
compat_chr = chr
compat_filter = filter
compat_input = input
compat_integer_types = (int, )
compat_kwargs = lambda kwargs: kwargs
compat_map = map
compat_numeric_types = (int, float, complex)
compat_str = str
compat_xpath = lambda xpath: xpath
compat_zip = zip
compat_collections_abc = collections.abc
compat_HTMLParser = html.parser.HTMLParser
compat_HTTPError = urllib.error.HTTPError
compat_Struct = struct.Struct
compat_b64decode = base64.b64decode
compat_cookiejar = http.cookiejar
compat_cookiejar_Cookie = compat_cookiejar.Cookie
compat_cookies = http.cookies
compat_cookies_SimpleCookie = compat_cookies.SimpleCookie
compat_etree_Element = etree.Element
compat_etree_register_namespace = etree.register_namespace
compat_get_terminal_size = shutil.get_terminal_size
compat_getenv = os.getenv
compat_getpass = getpass.getpass
compat_html_entities = html.entities
compat_html_entities_html5 = compat_html_entities.html5
compat_http_client = http.client
compat_http_server = http.server
compat_itertools_count = itertools.count
compat_parse_qs = urllib.parse.parse_qs
compat_shlex_split = shlex.split
compat_socket_create_connection = socket.create_connection
compat_struct_pack = struct.pack
compat_struct_unpack = struct.unpack
compat_subprocess_get_DEVNULL = lambda: DEVNULL
compat_tokenize_tokenize = tokenize.tokenize
compat_urllib_error = urllib.error
compat_urllib_parse = urllib.parse
compat_urllib_parse_quote = urllib.parse.quote
compat_urllib_parse_quote_plus = urllib.parse.quote_plus
compat_urllib_parse_unquote = urllib.parse.unquote
compat_urllib_parse_unquote_plus = urllib.parse.unquote_plus
compat_urllib_parse_unquote_to_bytes = urllib.parse.unquote_to_bytes
compat_urllib_parse_urlencode = urllib.parse.urlencode
compat_urllib_parse_urlparse = urllib.parse.urlparse
compat_urllib_parse_urlunparse = urllib.parse.urlunparse
compat_urllib_request = urllib.request
compat_urllib_request_DataHandler = urllib.request.DataHandler
compat_urllib_response = urllib.response
compat_urlparse = urllib.parse
compat_urlretrieve = urllib.request.urlretrieve
compat_xml_parse_error = etree.ParseError
# Set public objects
__all__ = [
'WINDOWS_VT_MODE',
'compat_HTMLParseError',
'compat_HTMLParser',
'compat_HTTPError',
'compat_Match',
'compat_Pattern',
'compat_Struct',
'compat_asyncio_run',
'compat_b64decode',
'compat_basestring',
'compat_chr',
'compat_collections_abc',
'compat_cookiejar',
'compat_cookiejar_Cookie',
'compat_cookies',
'compat_cookies_SimpleCookie',
'compat_ctypes_WINFUNCTYPE',
'compat_etree_Element',
'compat_etree_fromstring',
'compat_etree_register_namespace',
'compat_expanduser',
'compat_filter',
'compat_get_terminal_size',
'compat_getenv',
'compat_getpass',
'compat_html_entities',
'compat_html_entities_html5',
'compat_http_client',
'compat_http_server',
'compat_input',
'compat_integer_types',
'compat_itertools_count',
'compat_kwargs',
'compat_map',
'compat_numeric_types',
'compat_ord',
'compat_os_name',
'compat_parse_qs',
'compat_print',
'compat_pycrypto_AES',
'compat_realpath',
'compat_setenv',
'compat_shlex_quote',
'compat_shlex_split',
'compat_socket_create_connection',
'compat_str',
'compat_struct_pack',
'compat_struct_unpack',
'compat_subprocess_get_DEVNULL',
'compat_tokenize_tokenize',
'compat_urllib_error',
'compat_urllib_parse',
'compat_urllib_parse_quote',
'compat_urllib_parse_quote_plus',
'compat_urllib_parse_unquote',
'compat_urllib_parse_unquote_plus',
'compat_urllib_parse_unquote_to_bytes',
'compat_urllib_parse_urlencode',
'compat_urllib_parse_urlparse',
'compat_urllib_parse_urlunparse',
'compat_urllib_request',
'compat_urllib_request_DataHandler',
'compat_urllib_response',
'compat_urlparse',
'compat_urlretrieve',
'compat_xml_parse_error',
'compat_xpath',
'compat_zip',
'windows_enable_vt_mode',
'workaround_optparse_bug9161',
]

955
plugins/youtube_download/yt_dlp/cookies.py Normal file
View File

@ -0,0 +1,955 @@
import contextlib
import ctypes
import json
import os
import shutil
import struct
import subprocess
import sys
import tempfile
from datetime import datetime, timedelta, timezone
from enum import Enum, auto
from hashlib import pbkdf2_hmac
from .aes import (
aes_cbc_decrypt_bytes,
aes_gcm_decrypt_and_verify_bytes,
unpad_pkcs7,
)
from .compat import (
compat_b64decode,
compat_cookiejar_Cookie,
)
from .utils import (
expand_path,
Popen,
YoutubeDLCookieJar,
)
try:
import sqlite3
SQLITE_AVAILABLE = True
except ImportError:
# although sqlite3 is part of the standard library, it is possible to compile python without
# sqlite support. See: https://github.com/yt-dlp/yt-dlp/issues/544
SQLITE_AVAILABLE = False
try:
import secretstorage
SECRETSTORAGE_AVAILABLE = True
except ImportError:
SECRETSTORAGE_AVAILABLE = False
SECRETSTORAGE_UNAVAILABLE_REASON = (
'as the `secretstorage` module is not installed. '
'Please install by running `python3 -m pip install secretstorage`.')
except Exception as _err:
SECRETSTORAGE_AVAILABLE = False
SECRETSTORAGE_UNAVAILABLE_REASON = f'as the `secretstorage` module could not be initialized. {_err}'
CHROMIUM_BASED_BROWSERS = {'brave', 'chrome', 'chromium', 'edge', 'opera', 'vivaldi'}
SUPPORTED_BROWSERS = CHROMIUM_BASED_BROWSERS | {'firefox', 'safari'}
class YDLLogger:
def __init__(self, ydl=None):
self._ydl = ydl
def debug(self, message):
if self._ydl:
self._ydl.write_debug(message)
def info(self, message):
if self._ydl:
self._ydl.to_screen(f'[Cookies] {message}')
def warning(self, message, only_once=False):
if self._ydl:
self._ydl.report_warning(message, only_once)
def error(self, message):
if self._ydl:
self._ydl.report_error(message)
def load_cookies(cookie_file, browser_specification, ydl):
cookie_jars = []
if browser_specification is not None:
browser_name, profile, keyring = _parse_browser_specification(*browser_specification)
cookie_jars.append(extract_cookies_from_browser(browser_name, profile, YDLLogger(ydl), keyring=keyring))
if cookie_file is not None:
cookie_file = expand_path(cookie_file)
jar = YoutubeDLCookieJar(cookie_file)
if os.access(cookie_file, os.R_OK):
jar.load(ignore_discard=True, ignore_expires=True)
cookie_jars.append(jar)
return _merge_cookie_jars(cookie_jars)
def extract_cookies_from_browser(browser_name, profile=None, logger=YDLLogger(), *, keyring=None):
if browser_name == 'firefox':
return _extract_firefox_cookies(profile, logger)
elif browser_name == 'safari':
return _extract_safari_cookies(profile, logger)
elif browser_name in CHROMIUM_BASED_BROWSERS:
return _extract_chrome_cookies(browser_name, profile, keyring, logger)
else:
raise ValueError('unknown browser: {}'.format(browser_name))
def _extract_firefox_cookies(profile, logger):
logger.info('Extracting cookies from firefox')
if not SQLITE_AVAILABLE:
logger.warning('Cannot extract cookies from firefox without sqlite3 support. '
'Please use a python interpreter compiled with sqlite3 support')
return YoutubeDLCookieJar()
if profile is None:
search_root = _firefox_browser_dir()
elif _is_path(profile):
search_root = profile
else:
search_root = os.path.join(_firefox_browser_dir(), profile)
cookie_database_path = _find_most_recently_used_file(search_root, 'cookies.sqlite')
if cookie_database_path is None:
raise FileNotFoundError('could not find firefox cookies database in {}'.format(search_root))
logger.debug('Extracting cookies from: "{}"'.format(cookie_database_path))
with tempfile.TemporaryDirectory(prefix='yt_dlp') as tmpdir:
cursor = None
try:
cursor = _open_database_copy(cookie_database_path, tmpdir)
cursor.execute('SELECT host, name, value, path, expiry, isSecure FROM moz_cookies')
jar = YoutubeDLCookieJar()
for host, name, value, path, expiry, is_secure in cursor.fetchall():
cookie = compat_cookiejar_Cookie(
version=0, name=name, value=value, port=None, port_specified=False,
domain=host, domain_specified=bool(host), domain_initial_dot=host.startswith('.'),
path=path, path_specified=bool(path), secure=is_secure, expires=expiry, discard=False,
comment=None, comment_url=None, rest={})
jar.set_cookie(cookie)
logger.info('Extracted {} cookies from firefox'.format(len(jar)))
return jar
finally:
if cursor is not None:
cursor.connection.close()
def _firefox_browser_dir():
if sys.platform in ('linux', 'linux2'):
return os.path.expanduser('~/.mozilla/firefox')
elif sys.platform == 'win32':
return os.path.expandvars(r'%APPDATA%\Mozilla\Firefox\Profiles')
elif sys.platform == 'darwin':
return os.path.expanduser('~/Library/Application Support/Firefox')
else:
raise ValueError('unsupported platform: {}'.format(sys.platform))
def _get_chromium_based_browser_settings(browser_name):
# https://chromium.googlesource.com/chromium/src/+/HEAD/docs/user_data_dir.md
if sys.platform in ('linux', 'linux2'):
config = _config_home()
browser_dir = {
'brave': os.path.join(config, 'BraveSoftware/Brave-Browser'),
'chrome': os.path.join(config, 'google-chrome'),
'chromium': os.path.join(config, 'chromium'),
'edge': os.path.join(config, 'microsoft-edge'),
'opera': os.path.join(config, 'opera'),
'vivaldi': os.path.join(config, 'vivaldi'),
}[browser_name]
elif sys.platform == 'win32':
appdata_local = os.path.expandvars('%LOCALAPPDATA%')
appdata_roaming = os.path.expandvars('%APPDATA%')
browser_dir = {
'brave': os.path.join(appdata_local, r'BraveSoftware\Brave-Browser\User Data'),
'chrome': os.path.join(appdata_local, r'Google\Chrome\User Data'),
'chromium': os.path.join(appdata_local, r'Chromium\User Data'),
'edge': os.path.join(appdata_local, r'Microsoft\Edge\User Data'),
'opera': os.path.join(appdata_roaming, r'Opera Software\Opera Stable'),
'vivaldi': os.path.join(appdata_local, r'Vivaldi\User Data'),
}[browser_name]
elif sys.platform == 'darwin':
appdata = os.path.expanduser('~/Library/Application Support')
browser_dir = {
'brave': os.path.join(appdata, 'BraveSoftware/Brave-Browser'),
'chrome': os.path.join(appdata, 'Google/Chrome'),
'chromium': os.path.join(appdata, 'Chromium'),
'edge': os.path.join(appdata, 'Microsoft Edge'),
'opera': os.path.join(appdata, 'com.operasoftware.Opera'),
'vivaldi': os.path.join(appdata, 'Vivaldi'),
}[browser_name]
else:
raise ValueError('unsupported platform: {}'.format(sys.platform))
# Linux keyring names can be determined by snooping on dbus while opening the browser in KDE:
# dbus-monitor "interface='org.kde.KWallet'" "type=method_return"
keyring_name = {
'brave': 'Brave',
'chrome': 'Chrome',
'chromium': 'Chromium',
'edge': 'Microsoft Edge' if sys.platform == 'darwin' else 'Chromium',
'opera': 'Opera' if sys.platform == 'darwin' else 'Chromium',
'vivaldi': 'Vivaldi' if sys.platform == 'darwin' else 'Chrome',
}[browser_name]
browsers_without_profiles = {'opera'}
return {
'browser_dir': browser_dir,
'keyring_name': keyring_name,
'supports_profiles': browser_name not in browsers_without_profiles
}
def _extract_chrome_cookies(browser_name, profile, keyring, logger):
logger.info('Extracting cookies from {}'.format(browser_name))
if not SQLITE_AVAILABLE:
logger.warning(('Cannot extract cookies from {} without sqlite3 support. '
'Please use a python interpreter compiled with sqlite3 support').format(browser_name))
return YoutubeDLCookieJar()
config = _get_chromium_based_browser_settings(browser_name)
if profile is None:
search_root = config['browser_dir']
elif _is_path(profile):
search_root = profile
config['browser_dir'] = os.path.dirname(profile) if config['supports_profiles'] else profile
else:
if config['supports_profiles']:
search_root = os.path.join(config['browser_dir'], profile)
else:
logger.error('{} does not support profiles'.format(browser_name))
search_root = config['browser_dir']
cookie_database_path = _find_most_recently_used_file(search_root, 'Cookies')
if cookie_database_path is None:
raise FileNotFoundError('could not find {} cookies database in "{}"'.format(browser_name, search_root))
logger.debug('Extracting cookies from: "{}"'.format(cookie_database_path))
decryptor = get_cookie_decryptor(config['browser_dir'], config['keyring_name'], logger, keyring=keyring)
with tempfile.TemporaryDirectory(prefix='yt_dlp') as tmpdir:
cursor = None
try:
cursor = _open_database_copy(cookie_database_path, tmpdir)
cursor.connection.text_factory = bytes
column_names = _get_column_names(cursor, 'cookies')
secure_column = 'is_secure' if 'is_secure' in column_names else 'secure'
cursor.execute('SELECT host_key, name, value, encrypted_value, path, '
'expires_utc, {} FROM cookies'.format(secure_column))
jar = YoutubeDLCookieJar()
failed_cookies = 0
unencrypted_cookies = 0
for host_key, name, value, encrypted_value, path, expires_utc, is_secure in cursor.fetchall():
host_key = host_key.decode('utf-8')
name = name.decode('utf-8')
value = value.decode('utf-8')
path = path.decode('utf-8')
if not value and encrypted_value:
value = decryptor.decrypt(encrypted_value)
if value is None:
failed_cookies += 1
continue
else:
unencrypted_cookies += 1
cookie = compat_cookiejar_Cookie(
version=0, name=name, value=value, port=None, port_specified=False,
domain=host_key, domain_specified=bool(host_key), domain_initial_dot=host_key.startswith('.'),
path=path, path_specified=bool(path), secure=is_secure, expires=expires_utc, discard=False,
comment=None, comment_url=None, rest={})
jar.set_cookie(cookie)
if failed_cookies > 0:
failed_message = ' ({} could not be decrypted)'.format(failed_cookies)
else:
failed_message = ''
logger.info('Extracted {} cookies from {}{}'.format(len(jar), browser_name, failed_message))
counts = decryptor.cookie_counts.copy()
counts['unencrypted'] = unencrypted_cookies
logger.debug('cookie version breakdown: {}'.format(counts))
return jar
finally:
if cursor is not None:
cursor.connection.close()
class ChromeCookieDecryptor:
"""
Overview:
Linux:
- cookies are either v10 or v11
- v10: AES-CBC encrypted with a fixed key
- v11: AES-CBC encrypted with an OS protected key (keyring)
- v11 keys can be stored in various places depending on the activate desktop environment [2]
Mac:
- cookies are either v10 or not v10
- v10: AES-CBC encrypted with an OS protected key (keyring) and more key derivation iterations than linux
- not v10: 'old data' stored as plaintext
Windows:
- cookies are either v10 or not v10
- v10: AES-GCM encrypted with a key which is encrypted with DPAPI
- not v10: encrypted with DPAPI
Sources:
- [1] https://chromium.googlesource.com/chromium/src/+/refs/heads/main/components/os_crypt/
- [2] https://chromium.googlesource.com/chromium/src/+/refs/heads/main/components/os_crypt/key_storage_linux.cc
- KeyStorageLinux::CreateService
"""
def decrypt(self, encrypted_value):
raise NotImplementedError
@property
def cookie_counts(self):
raise NotImplementedError
def get_cookie_decryptor(browser_root, browser_keyring_name, logger, *, keyring=None):
if sys.platform in ('linux', 'linux2'):
return LinuxChromeCookieDecryptor(browser_keyring_name, logger, keyring=keyring)
elif sys.platform == 'darwin':
return MacChromeCookieDecryptor(browser_keyring_name, logger)
elif sys.platform == 'win32':
return WindowsChromeCookieDecryptor(browser_root, logger)
else:
raise NotImplementedError('Chrome cookie decryption is not supported '
'on this platform: {}'.format(sys.platform))
class LinuxChromeCookieDecryptor(ChromeCookieDecryptor):
def __init__(self, browser_keyring_name, logger, *, keyring=None):
self._logger = logger
self._v10_key = self.derive_key(b'peanuts')
password = _get_linux_keyring_password(browser_keyring_name, keyring, logger)
self._v11_key = None if password is None else self.derive_key(password)
self._cookie_counts = {'v10': 0, 'v11': 0, 'other': 0}
@staticmethod
def derive_key(password):
# values from
# https://chromium.googlesource.com/chromium/src/+/refs/heads/main/components/os_crypt/os_crypt_linux.cc
return pbkdf2_sha1(password, salt=b'saltysalt', iterations=1, key_length=16)
@property
def cookie_counts(self):
return self._cookie_counts
def decrypt(self, encrypted_value):
version = encrypted_value[:3]
ciphertext = encrypted_value[3:]
if version == b'v10':
self._cookie_counts['v10'] += 1
return _decrypt_aes_cbc(ciphertext, self._v10_key, self._logger)
elif version == b'v11':
self._cookie_counts['v11'] += 1
if self._v11_key is None:
self._logger.warning('cannot decrypt v11 cookies: no key found', only_once=True)
return None
return _decrypt_aes_cbc(ciphertext, self._v11_key, self._logger)
else:
self._cookie_counts['other'] += 1
return None
class MacChromeCookieDecryptor(ChromeCookieDecryptor):
def __init__(self, browser_keyring_name, logger):
self._logger = logger
password = _get_mac_keyring_password(browser_keyring_name, logger)
self._v10_key = None if password is None else self.derive_key(password)
self._cookie_counts = {'v10': 0, 'other': 0}
@staticmethod
def derive_key(password):
# values from
# https://chromium.googlesource.com/chromium/src/+/refs/heads/main/components/os_crypt/os_crypt_mac.mm
return pbkdf2_sha1(password, salt=b'saltysalt', iterations=1003, key_length=16)
@property
def cookie_counts(self):
return self._cookie_counts
def decrypt(self, encrypted_value):
version = encrypted_value[:3]
ciphertext = encrypted_value[3:]
if version == b'v10':
self._cookie_counts['v10'] += 1
if self._v10_key is None:
self._logger.warning('cannot decrypt v10 cookies: no key found', only_once=True)
return None
return _decrypt_aes_cbc(ciphertext, self._v10_key, self._logger)
else:
self._cookie_counts['other'] += 1
# other prefixes are considered 'old data' which were stored as plaintext
# https://chromium.googlesource.com/chromium/src/+/refs/heads/main/components/os_crypt/os_crypt_mac.mm
return encrypted_value
class WindowsChromeCookieDecryptor(ChromeCookieDecryptor):
def __init__(self, browser_root, logger):
self._logger = logger
self._v10_key = _get_windows_v10_key(browser_root, logger)
self._cookie_counts = {'v10': 0, 'other': 0}
@property
def cookie_counts(self):
return self._cookie_counts
def decrypt(self, encrypted_value):
version = encrypted_value[:3]
ciphertext = encrypted_value[3:]
if version == b'v10':
self._cookie_counts['v10'] += 1
if self._v10_key is None:
self._logger.warning('cannot decrypt v10 cookies: no key found', only_once=True)
return None
# https://chromium.googlesource.com/chromium/src/+/refs/heads/main/components/os_crypt/os_crypt_win.cc
# kNonceLength
nonce_length = 96 // 8
# boringssl
# EVP_AEAD_AES_GCM_TAG_LEN
authentication_tag_length = 16
raw_ciphertext = ciphertext
nonce = raw_ciphertext[:nonce_length]
ciphertext = raw_ciphertext[nonce_length:-authentication_tag_length]
authentication_tag = raw_ciphertext[-authentication_tag_length:]
return _decrypt_aes_gcm(ciphertext, self._v10_key, nonce, authentication_tag, self._logger)
else:
self._cookie_counts['other'] += 1
# any other prefix means the data is DPAPI encrypted
# https://chromium.googlesource.com/chromium/src/+/refs/heads/main/components/os_crypt/os_crypt_win.cc
return _decrypt_windows_dpapi(encrypted_value, self._logger).decode('utf-8')
def _extract_safari_cookies(profile, logger):
if profile is not None:
logger.error('safari does not support profiles')
if sys.platform != 'darwin':
raise ValueError('unsupported platform: {}'.format(sys.platform))
cookies_path = os.path.expanduser('~/Library/Cookies/Cookies.binarycookies')
if not os.path.isfile(cookies_path):
raise FileNotFoundError('could not find safari cookies database')
with open(cookies_path, 'rb') as f:
cookies_data = f.read()
jar = parse_safari_cookies(cookies_data, logger=logger)
logger.info('Extracted {} cookies from safari'.format(len(jar)))
return jar
class ParserError(Exception):
pass
class DataParser:
def __init__(self, data, logger):
self._data = data
self.cursor = 0
self._logger = logger
def read_bytes(self, num_bytes):
if num_bytes < 0:
raise ParserError('invalid read of {} bytes'.format(num_bytes))
end = self.cursor + num_bytes
if end > len(self._data):
raise ParserError('reached end of input')
data = self._data[self.cursor:end]
self.cursor = end
return data
def expect_bytes(self, expected_value, message):
value = self.read_bytes(len(expected_value))
if value != expected_value:
raise ParserError('unexpected value: {} != {} ({})'.format(value, expected_value, message))
def read_uint(self, big_endian=False):
data_format = '>I' if big_endian else '<I'
return struct.unpack(data_format, self.read_bytes(4))[0]
def read_double(self, big_endian=False):
data_format = '>d' if big_endian else '<d'
return struct.unpack(data_format, self.read_bytes(8))[0]
def read_cstring(self):
buffer = []
while True:
c = self.read_bytes(1)
if c == b'\x00':
return b''.join(buffer).decode('utf-8')
else:
buffer.append(c)
def skip(self, num_bytes, description='unknown'):
if num_bytes > 0:
self._logger.debug('skipping {} bytes ({}): {}'.format(
num_bytes, description, self.read_bytes(num_bytes)))
elif num_bytes < 0:
raise ParserError('invalid skip of {} bytes'.format(num_bytes))
def skip_to(self, offset, description='unknown'):
self.skip(offset - self.cursor, description)
def skip_to_end(self, description='unknown'):
self.skip_to(len(self._data), description)
def _mac_absolute_time_to_posix(timestamp):
return int((datetime(2001, 1, 1, 0, 0, tzinfo=timezone.utc) + timedelta(seconds=timestamp)).timestamp())
def _parse_safari_cookies_header(data, logger):
p = DataParser(data, logger)
p.expect_bytes(b'cook', 'database signature')
number_of_pages = p.read_uint(big_endian=True)
page_sizes = [p.read_uint(big_endian=True) for _ in range(number_of_pages)]
return page_sizes, p.cursor
def _parse_safari_cookies_page(data, jar, logger):
p = DataParser(data, logger)
p.expect_bytes(b'\x00\x00\x01\x00', 'page signature')
number_of_cookies = p.read_uint()
record_offsets = [p.read_uint() for _ in range(number_of_cookies)]
if number_of_cookies == 0:
logger.debug('a cookies page of size {} has no cookies'.format(len(data)))
return
p.skip_to(record_offsets[0], 'unknown page header field')
for record_offset in record_offsets:
p.skip_to(record_offset, 'space between records')
record_length = _parse_safari_cookies_record(data[record_offset:], jar, logger)
p.read_bytes(record_length)
p.skip_to_end('space in between pages')
def _parse_safari_cookies_record(data, jar, logger):
p = DataParser(data, logger)
record_size = p.read_uint()
p.skip(4, 'unknown record field 1')
flags = p.read_uint()
is_secure = bool(flags & 0x0001)
p.skip(4, 'unknown record field 2')
domain_offset = p.read_uint()
name_offset = p.read_uint()
path_offset = p.read_uint()
value_offset = p.read_uint()
p.skip(8, 'unknown record field 3')
expiration_date = _mac_absolute_time_to_posix(p.read_double())
_creation_date = _mac_absolute_time_to_posix(p.read_double()) # noqa: F841
try:
p.skip_to(domain_offset)
domain = p.read_cstring()
p.skip_to(name_offset)
name = p.read_cstring()
p.skip_to(path_offset)
path = p.read_cstring()
p.skip_to(value_offset)
value = p.read_cstring()
except UnicodeDecodeError:
logger.warning('failed to parse Safari cookie because UTF-8 decoding failed', only_once=True)
return record_size
p.skip_to(record_size, 'space at the end of the record')
cookie = compat_cookiejar_Cookie(
version=0, name=name, value=value, port=None, port_specified=False,
domain=domain, domain_specified=bool(domain), domain_initial_dot=domain.startswith('.'),
path=path, path_specified=bool(path), secure=is_secure, expires=expiration_date, discard=False,
comment=None, comment_url=None, rest={})
jar.set_cookie(cookie)
return record_size
def parse_safari_cookies(data, jar=None, logger=YDLLogger()):
"""
References:
- https://github.com/libyal/dtformats/blob/main/documentation/Safari%20Cookies.asciidoc
- this data appears to be out of date but the important parts of the database structure is the same
- there are a few bytes here and there which are skipped during parsing
"""
if jar is None:
jar = YoutubeDLCookieJar()
page_sizes, body_start = _parse_safari_cookies_header(data, logger)
p = DataParser(data[body_start:], logger)
for page_size in page_sizes:
_parse_safari_cookies_page(p.read_bytes(page_size), jar, logger)
p.skip_to_end('footer')
return jar
class _LinuxDesktopEnvironment(Enum):
"""
https://chromium.googlesource.com/chromium/src/+/refs/heads/main/base/nix/xdg_util.h
DesktopEnvironment
"""
OTHER = auto()
CINNAMON = auto()
GNOME = auto()
KDE = auto()
PANTHEON = auto()
UNITY = auto()
XFCE = auto()
class _LinuxKeyring(Enum):
"""
https://chromium.googlesource.com/chromium/src/+/refs/heads/main/components/os_crypt/key_storage_util_linux.h
SelectedLinuxBackend
"""
KWALLET = auto()
GNOMEKEYRING = auto()
BASICTEXT = auto()
SUPPORTED_KEYRINGS = _LinuxKeyring.__members__.keys()
def _get_linux_desktop_environment(env):
"""
https://chromium.googlesource.com/chromium/src/+/refs/heads/main/base/nix/xdg_util.cc
GetDesktopEnvironment
"""
xdg_current_desktop = env.get('XDG_CURRENT_DESKTOP', None)
desktop_session = env.get('DESKTOP_SESSION', None)
if xdg_current_desktop is not None:
xdg_current_desktop = xdg_current_desktop.split(':')[0].strip()
if xdg_current_desktop == 'Unity':
if desktop_session is not None and 'gnome-fallback' in desktop_session:
return _LinuxDesktopEnvironment.GNOME
else:
return _LinuxDesktopEnvironment.UNITY
elif xdg_current_desktop == 'GNOME':
return _LinuxDesktopEnvironment.GNOME
elif xdg_current_desktop == 'X-Cinnamon':
return _LinuxDesktopEnvironment.CINNAMON
elif xdg_current_desktop == 'KDE':
return _LinuxDesktopEnvironment.KDE
elif xdg_current_desktop == 'Pantheon':
return _LinuxDesktopEnvironment.PANTHEON
elif xdg_current_desktop == 'XFCE':
return _LinuxDesktopEnvironment.XFCE
elif desktop_session is not None:
if desktop_session in ('mate', 'gnome'):
return _LinuxDesktopEnvironment.GNOME
elif 'kde' in desktop_session:
return _LinuxDesktopEnvironment.KDE
elif 'xfce' in desktop_session:
return _LinuxDesktopEnvironment.XFCE
else:
if 'GNOME_DESKTOP_SESSION_ID' in env:
return _LinuxDesktopEnvironment.GNOME
elif 'KDE_FULL_SESSION' in env:
return _LinuxDesktopEnvironment.KDE
return _LinuxDesktopEnvironment.OTHER
def _choose_linux_keyring(logger):
"""
https://chromium.googlesource.com/chromium/src/+/refs/heads/main/components/os_crypt/key_storage_util_linux.cc
SelectBackend
"""
desktop_environment = _get_linux_desktop_environment(os.environ)
logger.debug('detected desktop environment: {}'.format(desktop_environment.name))
if desktop_environment == _LinuxDesktopEnvironment.KDE:
linux_keyring = _LinuxKeyring.KWALLET
elif desktop_environment == _LinuxDesktopEnvironment.OTHER:
linux_keyring = _LinuxKeyring.BASICTEXT
else:
linux_keyring = _LinuxKeyring.GNOMEKEYRING
return linux_keyring
def _get_kwallet_network_wallet(logger):
""" The name of the wallet used to store network passwords.
https://chromium.googlesource.com/chromium/src/+/refs/heads/main/components/os_crypt/kwallet_dbus.cc
KWalletDBus::NetworkWallet
which does a dbus call to the following function:
https://api.kde.org/frameworks/kwallet/html/classKWallet_1_1Wallet.html
Wallet::NetworkWallet
"""
default_wallet = 'kdewallet'
try:
proc = Popen([
'dbus-send', '--session', '--print-reply=literal',
'--dest=org.kde.kwalletd5',
'/modules/kwalletd5',
'org.kde.KWallet.networkWallet'
], stdout=subprocess.PIPE, stderr=subprocess.DEVNULL)
stdout, stderr = proc.communicate_or_kill()
if proc.returncode != 0:
logger.warning('failed to read NetworkWallet')
return default_wallet
else:
network_wallet = stdout.decode('utf-8').strip()
logger.debug('NetworkWallet = "{}"'.format(network_wallet))
return network_wallet
except BaseException as e:
logger.warning('exception while obtaining NetworkWallet: {}'.format(e))
return default_wallet
def _get_kwallet_password(browser_keyring_name, logger):
logger.debug('using kwallet-query to obtain password from kwallet')
if shutil.which('kwallet-query') is None:
logger.error('kwallet-query command not found. KWallet and kwallet-query '
'must be installed to read from KWallet. kwallet-query should be'
'included in the kwallet package for your distribution')
return b''
network_wallet = _get_kwallet_network_wallet(logger)
try:
proc = Popen([
'kwallet-query',
'--read-password', '{} Safe Storage'.format(browser_keyring_name),
'--folder', '{} Keys'.format(browser_keyring_name),
network_wallet
], stdout=subprocess.PIPE, stderr=subprocess.DEVNULL)
stdout, stderr = proc.communicate_or_kill()
if proc.returncode != 0:
logger.error('kwallet-query failed with return code {}. Please consult '
'the kwallet-query man page for details'.format(proc.returncode))
return b''
else:
if stdout.lower().startswith(b'failed to read'):
logger.debug('failed to read password from kwallet. Using empty string instead')
# this sometimes occurs in KDE because chrome does not check hasEntry and instead
# just tries to read the value (which kwallet returns "") whereas kwallet-query
# checks hasEntry. To verify this:
# dbus-monitor "interface='org.kde.KWallet'" "type=method_return"
# while starting chrome.
# this may be a bug as the intended behaviour is to generate a random password and store
# it, but that doesn't matter here.
return b''
else:
logger.debug('password found')
if stdout[-1:] == b'\n':
stdout = stdout[:-1]
return stdout
except BaseException as e:
logger.warning(f'exception running kwallet-query: {type(e).__name__}({e})')
return b''
def _get_gnome_keyring_password(browser_keyring_name, logger):
if not SECRETSTORAGE_AVAILABLE:
logger.error('secretstorage not available {}'.format(SECRETSTORAGE_UNAVAILABLE_REASON))
return b''
# the Gnome keyring does not seem to organise keys in the same way as KWallet,
# using `dbus-monitor` during startup, it can be observed that chromium lists all keys
# and presumably searches for its key in the list. It appears that we must do the same.
# https://github.com/jaraco/keyring/issues/556
with contextlib.closing(secretstorage.dbus_init()) as con:
col = secretstorage.get_default_collection(con)
for item in col.get_all_items():
if item.get_label() == '{} Safe Storage'.format(browser_keyring_name):
return item.get_secret()
else:
logger.error('failed to read from keyring')
return b''
def _get_linux_keyring_password(browser_keyring_name, keyring, logger):
# note: chrome/chromium can be run with the following flags to determine which keyring backend
# it has chosen to use
# chromium --enable-logging=stderr --v=1 2>&1 | grep key_storage_
# Chromium supports a flag: --password-store=<basic|gnome|kwallet> so the automatic detection
# will not be sufficient in all cases.
keyring = _LinuxKeyring[keyring] if keyring else _choose_linux_keyring(logger)
logger.debug(f'Chosen keyring: {keyring.name}')
if keyring == _LinuxKeyring.KWALLET:
return _get_kwallet_password(browser_keyring_name, logger)
elif keyring == _LinuxKeyring.GNOMEKEYRING:
return _get_gnome_keyring_password(browser_keyring_name, logger)
elif keyring == _LinuxKeyring.BASICTEXT:
# when basic text is chosen, all cookies are stored as v10 (so no keyring password is required)
return None
assert False, f'Unknown keyring {keyring}'
def _get_mac_keyring_password(browser_keyring_name, logger):
logger.debug('using find-generic-password to obtain password from OSX keychain')
try:
proc = Popen(
['security', 'find-generic-password',
'-w', # write password to stdout
'-a', browser_keyring_name, # match 'account'
'-s', '{} Safe Storage'.format(browser_keyring_name)], # match 'service'
stdout=subprocess.PIPE, stderr=subprocess.DEVNULL)
stdout, stderr = proc.communicate_or_kill()
if stdout[-1:] == b'\n':
stdout = stdout[:-1]
return stdout
except BaseException as e:
logger.warning(f'exception running find-generic-password: {type(e).__name__}({e})')
return None
def _get_windows_v10_key(browser_root, logger):
path = _find_most_recently_used_file(browser_root, 'Local State')
if path is None:
logger.error('could not find local state file')
return None
with open(path, 'r', encoding='utf8') as f:
data = json.load(f)
try:
base64_key = data['os_crypt']['encrypted_key']
except KeyError:
logger.error('no encrypted key in Local State')
return None
encrypted_key = compat_b64decode(base64_key)
prefix = b'DPAPI'
if not encrypted_key.startswith(prefix):
logger.error('invalid key')
return None
return _decrypt_windows_dpapi(encrypted_key[len(prefix):], logger)
def pbkdf2_sha1(password, salt, iterations, key_length):
return pbkdf2_hmac('sha1', password, salt, iterations, key_length)
def _decrypt_aes_cbc(ciphertext, key, logger, initialization_vector=b' ' * 16):
plaintext = unpad_pkcs7(aes_cbc_decrypt_bytes(ciphertext, key, initialization_vector))
try:
return plaintext.decode('utf-8')
except UnicodeDecodeError:
logger.warning('failed to decrypt cookie (AES-CBC) because UTF-8 decoding failed. Possibly the key is wrong?', only_once=True)
return None
def _decrypt_aes_gcm(ciphertext, key, nonce, authentication_tag, logger):
try:
plaintext = aes_gcm_decrypt_and_verify_bytes(ciphertext, key, authentication_tag, nonce)
except ValueError:
logger.warning('failed to decrypt cookie (AES-GCM) because the MAC check failed. Possibly the key is wrong?', only_once=True)
return None
try:
return plaintext.decode('utf-8')
except UnicodeDecodeError:
logger.warning('failed to decrypt cookie (AES-GCM) because UTF-8 decoding failed. Possibly the key is wrong?', only_once=True)
return None
def _decrypt_windows_dpapi(ciphertext, logger):
"""
References:
- https://docs.microsoft.com/en-us/windows/win32/api/dpapi/nf-dpapi-cryptunprotectdata
"""
from ctypes.wintypes import DWORD
class DATA_BLOB(ctypes.Structure):
_fields_ = [('cbData', DWORD),
('pbData', ctypes.POINTER(ctypes.c_char))]
buffer = ctypes.create_string_buffer(ciphertext)
blob_in = DATA_BLOB(ctypes.sizeof(buffer), buffer)
blob_out = DATA_BLOB()
ret = ctypes.windll.crypt32.CryptUnprotectData(
ctypes.byref(blob_in), # pDataIn
None, # ppszDataDescr: human readable description of pDataIn
None, # pOptionalEntropy: salt?
None, # pvReserved: must be NULL
None, # pPromptStruct: information about prompts to display
0, # dwFlags
ctypes.byref(blob_out) # pDataOut
)
if not ret:
logger.warning('failed to decrypt with DPAPI', only_once=True)
return None
result = ctypes.string_at(blob_out.pbData, blob_out.cbData)
ctypes.windll.kernel32.LocalFree(blob_out.pbData)
return result
def _config_home():
return os.environ.get('XDG_CONFIG_HOME', os.path.expanduser('~/.config'))
def _open_database_copy(database_path, tmpdir):
# cannot open sqlite databases if they are already in use (e.g. by the browser)
database_copy_path = os.path.join(tmpdir, 'temporary.sqlite')
shutil.copy(database_path, database_copy_path)
conn = sqlite3.connect(database_copy_path)
return conn.cursor()
def _get_column_names(cursor, table_name):
table_info = cursor.execute('PRAGMA table_info({})'.format(table_name)).fetchall()
return [row[1].decode('utf-8') for row in table_info]
def _find_most_recently_used_file(root, filename):
# if there are multiple browser profiles, take the most recently used one
paths = []
for root, dirs, files in os.walk(root):
for file in files:
if file == filename:
paths.append(os.path.join(root, file))
return None if not paths else max(paths, key=lambda path: os.lstat(path).st_mtime)
def _merge_cookie_jars(jars):
output_jar = YoutubeDLCookieJar()
for jar in jars:
for cookie in jar:
output_jar.set_cookie(cookie)
if jar.filename is not None:
output_jar.filename = jar.filename
return output_jar
def _is_path(value):
return os.path.sep in value
def _parse_browser_specification(browser_name, profile=None, keyring=None):
if browser_name not in SUPPORTED_BROWSERS:
raise ValueError(f'unsupported browser: "{browser_name}"')
if keyring not in (None, *SUPPORTED_KEYRINGS):
raise ValueError(f'unsupported keyring: "{keyring}"')
if profile is not None and _is_path(profile):
profile = os.path.expanduser(profile)
return browser_name, profile, keyring

135
plugins/youtube_download/yt_dlp/downloader/__init__.py Normal file
View File

@ -0,0 +1,135 @@
from __future__ import unicode_literals
from ..compat import compat_str
from ..utils import (
determine_protocol,
NO_DEFAULT
)
def get_suitable_downloader(info_dict, params={}, default=NO_DEFAULT, protocol=None, to_stdout=False):
info_dict['protocol'] = determine_protocol(info_dict)
info_copy = info_dict.copy()
info_copy['to_stdout'] = to_stdout
protocols = (protocol or info_copy['protocol']).split('+')
downloaders = [_get_suitable_downloader(info_copy, proto, params, default) for proto in protocols]
if set(downloaders) == {FFmpegFD} and FFmpegFD.can_merge_formats(info_copy, params):
return FFmpegFD
elif (set(downloaders) == {DashSegmentsFD}
and not (to_stdout and len(protocols) > 1)
and set(protocols) == {'http_dash_segments_generator'}):
return DashSegmentsFD
elif len(downloaders) == 1:
return downloaders[0]
return None
# Some of these require get_suitable_downloader
from .common import FileDownloader
from .dash import DashSegmentsFD
from .f4m import F4mFD
from .hls import HlsFD
from .http import HttpFD
from .rtmp import RtmpFD
from .rtsp import RtspFD
from .ism import IsmFD
from .mhtml import MhtmlFD
from .niconico import NiconicoDmcFD
from .websocket import WebSocketFragmentFD
from .youtube_live_chat import YoutubeLiveChatFD
from .external import (
get_external_downloader,
FFmpegFD,
)
PROTOCOL_MAP = {
'rtmp': RtmpFD,
'rtmpe': RtmpFD,
'rtmp_ffmpeg': FFmpegFD,
'm3u8_native': HlsFD,
'm3u8': FFmpegFD,
'mms': RtspFD,
'rtsp': RtspFD,
'f4m': F4mFD,
'http_dash_segments': DashSegmentsFD,
'http_dash_segments_generator': DashSegmentsFD,
'ism': IsmFD,
'mhtml': MhtmlFD,
'niconico_dmc': NiconicoDmcFD,
'websocket_frag': WebSocketFragmentFD,
'youtube_live_chat': YoutubeLiveChatFD,
'youtube_live_chat_replay': YoutubeLiveChatFD,
}
def shorten_protocol_name(proto, simplify=False):
short_protocol_names = {
'm3u8_native': 'm3u8_n',
'rtmp_ffmpeg': 'rtmp_f',
'http_dash_segments': 'dash',
'http_dash_segments_generator': 'dash_g',
'niconico_dmc': 'dmc',
'websocket_frag': 'WSfrag',
}
if simplify:
short_protocol_names.update({
'https': 'http',
'ftps': 'ftp',
'm3u8_native': 'm3u8',
'http_dash_segments_generator': 'dash',
'rtmp_ffmpeg': 'rtmp',
'm3u8_frag_urls': 'm3u8',
'dash_frag_urls': 'dash',
})
return short_protocol_names.get(proto, proto)
def _get_suitable_downloader(info_dict, protocol, params, default):
"""Get the downloader class that can handle the info dict."""
if default is NO_DEFAULT:
default = HttpFD
# if (info_dict.get('start_time') or info_dict.get('end_time')) and not info_dict.get('requested_formats') and FFmpegFD.can_download(info_dict):
# return FFmpegFD
info_dict['protocol'] = protocol
downloaders = params.get('external_downloader')
external_downloader = (
downloaders if isinstance(downloaders, compat_str) or downloaders is None
else downloaders.get(shorten_protocol_name(protocol, True), downloaders.get('default')))
if external_downloader is None:
if info_dict['to_stdout'] and FFmpegFD.can_merge_formats(info_dict, params):
return FFmpegFD
elif external_downloader.lower() != 'native':
ed = get_external_downloader(external_downloader)
if ed.can_download(info_dict, external_downloader):
return ed
if protocol == 'http_dash_segments':
if info_dict.get('is_live') and (external_downloader or '').lower() != 'native':
return FFmpegFD
if protocol in ('m3u8', 'm3u8_native'):
if info_dict.get('is_live'):
return FFmpegFD
elif (external_downloader or '').lower() == 'native':
return HlsFD
elif get_suitable_downloader(
info_dict, params, None, protocol='m3u8_frag_urls', to_stdout=info_dict['to_stdout']):
return HlsFD
elif params.get('hls_prefer_native') is True:
return HlsFD
elif params.get('hls_prefer_native') is False:
return FFmpegFD
return PROTOCOL_MAP.get(protocol, default)
__all__ = [
'FileDownloader',
'get_suitable_downloader',
'shorten_protocol_name',
]

472
plugins/youtube_download/yt_dlp/downloader/common.py Normal file
View File

@ -0,0 +1,472 @@
from __future__ import division, unicode_literals
import os
import re
import time
import random
import errno
from ..utils import (
decodeArgument,
encodeFilename,
error_to_compat_str,
format_bytes,
sanitize_open,
shell_quote,
timeconvert,
timetuple_from_msec,
)
from ..minicurses import (
MultilineLogger,
MultilinePrinter,
QuietMultilinePrinter,
BreaklineStatusPrinter
)
class FileDownloader(object):
"""File Downloader class.
File downloader objects are the ones responsible of downloading the
actual video file and writing it to disk.
File downloaders accept a lot of parameters. In order not to saturate
the object constructor with arguments, it receives a dictionary of
options instead.
Available options:
verbose: Print additional info to stdout.
quiet: Do not print messages to stdout.
ratelimit: Download speed limit, in bytes/sec.
throttledratelimit: Assume the download is being throttled below this speed (bytes/sec)
retries: Number of times to retry for HTTP error 5xx
file_access_retries: Number of times to retry on file access error
buffersize: Size of download buffer in bytes.
noresizebuffer: Do not automatically resize the download buffer.
continuedl: Try to continue downloads if possible.
noprogress: Do not print the progress bar.
nopart: Do not use temporary .part files.
updatetime: Use the Last-modified header to set output file timestamps.
test: Download only first bytes to test the downloader.
min_filesize: Skip files smaller than this size
max_filesize: Skip files larger than this size
xattr_set_filesize: Set ytdl.filesize user xattribute with expected size.
external_downloader_args: A dictionary of downloader keys (in lower case)
and a list of additional command-line arguments for the
executable. Use 'default' as the name for arguments to be
passed to all downloaders. For compatibility with youtube-dl,
a single list of args can also be used
hls_use_mpegts: Use the mpegts container for HLS videos.
http_chunk_size: Size of a chunk for chunk-based HTTP downloading. May be
useful for bypassing bandwidth throttling imposed by
a webserver (experimental)
progress_template: See YoutubeDL.py
Subclasses of this one must re-define the real_download method.
"""
_TEST_FILE_SIZE = 10241
params = None
def __init__(self, ydl, params):
"""Create a FileDownloader object with the given options."""
self.ydl = ydl
self._progress_hooks = []
self.params = params
self._prepare_multiline_status()
self.add_progress_hook(self.report_progress)
@staticmethod
def format_seconds(seconds):
time = timetuple_from_msec(seconds * 1000)
if time.hours > 99:
return '--:--:--'
if not time.hours:
return '%02d:%02d' % time[1:-1]
return '%02d:%02d:%02d' % time[:-1]
@staticmethod
def calc_percent(byte_counter, data_len):
if data_len is None:
return None
return float(byte_counter) / float(data_len) * 100.0
@staticmethod
def format_percent(percent):
if percent is None:
return '---.-%'
elif percent == 100:
return '100%'
return '%6s' % ('%3.1f%%' % percent)
@staticmethod
def calc_eta(start, now, total, current):
if total is None:
return None
if now is None:
now = time.time()
dif = now - start
if current == 0 or dif < 0.001: # One millisecond
return None
rate = float(current) / dif
return int((float(total) - float(current)) / rate)
@staticmethod
def format_eta(eta):
if eta is None:
return '--:--'
return FileDownloader.format_seconds(eta)
@staticmethod
def calc_speed(start, now, bytes):
dif = now - start
if bytes == 0 or dif < 0.001: # One millisecond
return None
return float(bytes) / dif
@staticmethod
def format_speed(speed):
if speed is None:
return '%10s' % '---b/s'
return '%10s' % ('%s/s' % format_bytes(speed))
@staticmethod
def format_retries(retries):
return 'inf' if retries == float('inf') else '%.0f' % retries
@staticmethod
def best_block_size(elapsed_time, bytes):
new_min = max(bytes / 2.0, 1.0)
new_max = min(max(bytes * 2.0, 1.0), 4194304) # Do not surpass 4 MB
if elapsed_time < 0.001:
return int(new_max)
rate = bytes / elapsed_time
if rate > new_max:
return int(new_max)
if rate < new_min:
return int(new_min)
return int(rate)
@staticmethod
def parse_bytes(bytestr):
"""Parse a string indicating a byte quantity into an integer."""
matchobj = re.match(r'(?i)^(\d+(?:\.\d+)?)([kMGTPEZY]?)$', bytestr)
if matchobj is None:
return None
number = float(matchobj.group(1))
multiplier = 1024.0 ** 'bkmgtpezy'.index(matchobj.group(2).lower())
return int(round(number * multiplier))
def to_screen(self, *args, **kargs):
self.ydl.to_stdout(*args, quiet=self.params.get('quiet'), **kargs)
def to_stderr(self, message):
self.ydl.to_stderr(message)
def to_console_title(self, message):
self.ydl.to_console_title(message)
def trouble(self, *args, **kargs):
self.ydl.trouble(*args, **kargs)
def report_warning(self, *args, **kargs):
self.ydl.report_warning(*args, **kargs)
def report_error(self, *args, **kargs):
self.ydl.report_error(*args, **kargs)
def write_debug(self, *args, **kargs):
self.ydl.write_debug(*args, **kargs)
def slow_down(self, start_time, now, byte_counter):
"""Sleep if the download speed is over the rate limit."""
rate_limit = self.params.get('ratelimit')
if rate_limit is None or byte_counter == 0:
return
if now is None:
now = time.time()
elapsed = now - start_time
if elapsed <= 0.0:
return
speed = float(byte_counter) / elapsed
if speed > rate_limit:
sleep_time = float(byte_counter) / rate_limit - elapsed
if sleep_time > 0:
time.sleep(sleep_time)
def temp_name(self, filename):
"""Returns a temporary filename for the given filename."""
if self.params.get('nopart', False) or filename == '-' or \
(os.path.exists(encodeFilename(filename)) and not os.path.isfile(encodeFilename(filename))):
return filename
return filename + '.part'
def undo_temp_name(self, filename):
if filename.endswith('.part'):
return filename[:-len('.part')]
return filename
def ytdl_filename(self, filename):
return filename + '.ytdl'
def sanitize_open(self, filename, open_mode):
file_access_retries = self.params.get('file_access_retries', 10)
retry = 0
while True:
try:
return sanitize_open(filename, open_mode)
except (IOError, OSError) as err:
retry = retry + 1
if retry > file_access_retries or err.errno not in (errno.EACCES,):
raise
self.to_screen(
'[download] Got file access error. Retrying (attempt %d of %s) ...'
% (retry, self.format_retries(file_access_retries)))
time.sleep(0.01)
def try_rename(self, old_filename, new_filename):
if old_filename == new_filename:
return
try:
os.replace(old_filename, new_filename)
except (IOError, OSError) as err:
self.report_error(f'unable to rename file: {err}')
def try_utime(self, filename, last_modified_hdr):
"""Try to set the last-modified time of the given file."""
if last_modified_hdr is None:
return
if not os.path.isfile(encodeFilename(filename)):
return
timestr = last_modified_hdr
if timestr is None:
return
filetime = timeconvert(timestr)
if filetime is None:
return filetime
# Ignore obviously invalid dates
if filetime == 0:
return
try:
os.utime(filename, (time.time(), filetime))
except Exception:
pass
return filetime
def report_destination(self, filename):
"""Report destination filename."""
self.to_screen('[download] Destination: ' + filename)
def _prepare_multiline_status(self, lines=1):
if self.params.get('noprogress'):
self._multiline = QuietMultilinePrinter()
elif self.ydl.params.get('logger'):
self._multiline = MultilineLogger(self.ydl.params['logger'], lines)
elif self.params.get('progress_with_newline'):
self._multiline = BreaklineStatusPrinter(self.ydl._screen_file, lines)
else:
self._multiline = MultilinePrinter(self.ydl._screen_file, lines, not self.params.get('quiet'))
self._multiline.allow_colors = self._multiline._HAVE_FULLCAP and not self.params.get('no_color')
def _finish_multiline_status(self):
self._multiline.end()
_progress_styles = {
'downloaded_bytes': 'light blue',
'percent': 'light blue',
'eta': 'yellow',
'speed': 'green',
'elapsed': 'bold white',
'total_bytes': '',
'total_bytes_estimate': '',
}
def _report_progress_status(self, s, default_template):
for name, style in self._progress_styles.items():
name = f'_{name}_str'
if name not in s:
continue
s[name] = self._format_progress(s[name], style)
s['_default_template'] = default_template % s
progress_dict = s.copy()
progress_dict.pop('info_dict')
progress_dict = {'info': s['info_dict'], 'progress': progress_dict}
progress_template = self.params.get('progress_template', {})
self._multiline.print_at_line(self.ydl.evaluate_outtmpl(
progress_template.get('download') or '[download] %(progress._default_template)s',
progress_dict), s.get('progress_idx') or 0)
self.to_console_title(self.ydl.evaluate_outtmpl(
progress_template.get('download-title') or 'yt-dlp %(progress._default_template)s',
progress_dict))
def _format_progress(self, *args, **kwargs):
return self.ydl._format_text(
self._multiline.stream, self._multiline.allow_colors, *args, **kwargs)
def report_progress(self, s):
if s['status'] == 'finished':
if self.params.get('noprogress'):
self.to_screen('[download] Download completed')
msg_template = '100%%'
if s.get('total_bytes') is not None:
s['_total_bytes_str'] = format_bytes(s['total_bytes'])
msg_template += ' of %(_total_bytes_str)s'
if s.get('elapsed') is not None:
s['_elapsed_str'] = self.format_seconds(s['elapsed'])
msg_template += ' in %(_elapsed_str)s'
s['_percent_str'] = self.format_percent(100)
self._report_progress_status(s, msg_template)
return
if s['status'] != 'downloading':
return
if s.get('eta') is not None:
s['_eta_str'] = self.format_eta(s['eta'])
else:
s['_eta_str'] = 'Unknown'
if s.get('total_bytes') and s.get('downloaded_bytes') is not None:
s['_percent_str'] = self.format_percent(100 * s['downloaded_bytes'] / s['total_bytes'])
elif s.get('total_bytes_estimate') and s.get('downloaded_bytes') is not None:
s['_percent_str'] = self.format_percent(100 * s['downloaded_bytes'] / s['total_bytes_estimate'])
else:
if s.get('downloaded_bytes') == 0:
s['_percent_str'] = self.format_percent(0)
else:
s['_percent_str'] = 'Unknown %'
if s.get('speed') is not None:
s['_speed_str'] = self.format_speed(s['speed'])
else:
s['_speed_str'] = 'Unknown speed'
if s.get('total_bytes') is not None:
s['_total_bytes_str'] = format_bytes(s['total_bytes'])
msg_template = '%(_percent_str)s of %(_total_bytes_str)s at %(_speed_str)s ETA %(_eta_str)s'
elif s.get('total_bytes_estimate') is not None:
s['_total_bytes_estimate_str'] = format_bytes(s['total_bytes_estimate'])
msg_template = '%(_percent_str)s of ~%(_total_bytes_estimate_str)s at %(_speed_str)s ETA %(_eta_str)s'
else:
if s.get('downloaded_bytes') is not None:
s['_downloaded_bytes_str'] = format_bytes(s['downloaded_bytes'])
if s.get('elapsed'):
s['_elapsed_str'] = self.format_seconds(s['elapsed'])
msg_template = '%(_downloaded_bytes_str)s at %(_speed_str)s (%(_elapsed_str)s)'
else:
msg_template = '%(_downloaded_bytes_str)s at %(_speed_str)s'
else:
msg_template = '%(_percent_str)s at %(_speed_str)s ETA %(_eta_str)s'
if s.get('fragment_index') and s.get('fragment_count'):
msg_template += ' (frag %(fragment_index)s/%(fragment_count)s)'
elif s.get('fragment_index'):
msg_template += ' (frag %(fragment_index)s)'
self._report_progress_status(s, msg_template)
def report_resuming_byte(self, resume_len):
"""Report attempt to resume at given byte."""
self.to_screen('[download] Resuming download at byte %s' % resume_len)
def report_retry(self, err, count, retries):
"""Report retry in case of HTTP error 5xx"""
self.to_screen(
'[download] Got server HTTP error: %s. Retrying (attempt %d of %s) ...'
% (error_to_compat_str(err), count, self.format_retries(retries)))
def report_file_already_downloaded(self, *args, **kwargs):
"""Report file has already been fully downloaded."""
return self.ydl.report_file_already_downloaded(*args, **kwargs)
def report_unable_to_resume(self):
"""Report it was impossible to resume download."""
self.to_screen('[download] Unable to resume')
@staticmethod
def supports_manifest(manifest):
""" Whether the downloader can download the fragments from the manifest.
Redefine in subclasses if needed. """
pass
def download(self, filename, info_dict, subtitle=False):
"""Download to a filename using the info from info_dict
Return True on success and False otherwise
"""
nooverwrites_and_exists = (
not self.params.get('overwrites', True)
and os.path.exists(encodeFilename(filename))
)
if not hasattr(filename, 'write'):
continuedl_and_exists = (
self.params.get('continuedl', True)
and os.path.isfile(encodeFilename(filename))
and not self.params.get('nopart', False)
)
# Check file already present
if filename != '-' and (nooverwrites_and_exists or continuedl_and_exists):
self.report_file_already_downloaded(filename)
self._hook_progress({
'filename': filename,
'status': 'finished',
'total_bytes': os.path.getsize(encodeFilename(filename)),
}, info_dict)
self._finish_multiline_status()
return True, False
if subtitle is False:
min_sleep_interval = self.params.get('sleep_interval')
if min_sleep_interval:
max_sleep_interval = self.params.get('max_sleep_interval', min_sleep_interval)
sleep_interval = random.uniform(min_sleep_interval, max_sleep_interval)
self.to_screen(
'[download] Sleeping %s seconds ...' % (
int(sleep_interval) if sleep_interval.is_integer()
else '%.2f' % sleep_interval))
time.sleep(sleep_interval)
else:
sleep_interval_sub = 0
if type(self.params.get('sleep_interval_subtitles')) is int:
sleep_interval_sub = self.params.get('sleep_interval_subtitles')
if sleep_interval_sub > 0:
self.to_screen(
'[download] Sleeping %s seconds ...' % (
sleep_interval_sub))
time.sleep(sleep_interval_sub)
ret = self.real_download(filename, info_dict)
self._finish_multiline_status()
return ret, True
def real_download(self, filename, info_dict):
"""Real download process. Redefine in subclasses."""
raise NotImplementedError('This method must be implemented by subclasses')
def _hook_progress(self, status, info_dict):
if not self._progress_hooks:
return
status['info_dict'] = info_dict
# youtube-dl passes the same status object to all the hooks.
# Some third party scripts seems to be relying on this.
# So keep this behavior if possible
for ph in self._progress_hooks:
ph(status)
def add_progress_hook(self, ph):
# See YoutubeDl.py (search for progress_hooks) for a description of
# this interface
self._progress_hooks.append(ph)
def _debug_cmd(self, args, exe=None):
if not self.params.get('verbose', False):
return
str_args = [decodeArgument(a) for a in args]
if exe is None:
exe = os.path.basename(str_args[0])
self.write_debug('%s command line: %s' % (exe, shell_quote(str_args)))

80
plugins/youtube_download/yt_dlp/downloader/dash.py Normal file
View File

@ -0,0 +1,80 @@
from __future__ import unicode_literals
import time
from ..downloader import get_suitable_downloader
from .fragment import FragmentFD
from ..utils import urljoin
class DashSegmentsFD(FragmentFD):
"""
Download segments in a DASH manifest. External downloaders can take over
the fragment downloads by supporting the 'dash_frag_urls' protocol
"""
FD_NAME = 'dashsegments'
def real_download(self, filename, info_dict):
if info_dict.get('is_live') and set(info_dict['protocol'].split('+')) != {'http_dash_segments_generator'}:
self.report_error('Live DASH videos are not supported')
real_start = time.time()
real_downloader = get_suitable_downloader(
info_dict, self.params, None, protocol='dash_frag_urls', to_stdout=(filename == '-'))
requested_formats = [{**info_dict, **fmt} for fmt in info_dict.get('requested_formats', [])]
args = []
for fmt in requested_formats or [info_dict]:
try:
fragment_count = 1 if self.params.get('test') else len(fmt['fragments'])
except TypeError:
fragment_count = None
ctx = {
'filename': fmt.get('filepath') or filename,
'live': 'is_from_start' if fmt.get('is_from_start') else fmt.get('is_live'),
'total_frags': fragment_count,
}
if real_downloader:
self._prepare_external_frag_download(ctx)
else:
self._prepare_and_start_frag_download(ctx, fmt)
ctx['start'] = real_start
fragments_to_download = self._get_fragments(fmt, ctx)
if real_downloader:
self.to_screen(
'[%s] Fragment downloads will be delegated to %s' % (self.FD_NAME, real_downloader.get_basename()))
info_dict['fragments'] = list(fragments_to_download)
fd = real_downloader(self.ydl, self.params)
return fd.real_download(filename, info_dict)
args.append([ctx, fragments_to_download, fmt])
return self.download_and_append_fragments_multiple(*args)
def _resolve_fragments(self, fragments, ctx):
fragments = fragments(ctx) if callable(fragments) else fragments
return [next(iter(fragments))] if self.params.get('test') else fragments
def _get_fragments(self, fmt, ctx):
fragment_base_url = fmt.get('fragment_base_url')
fragments = self._resolve_fragments(fmt['fragments'], ctx)
frag_index = 0
for i, fragment in enumerate(fragments):
frag_index += 1
if frag_index <= ctx['fragment_index']:
continue
fragment_url = fragment.get('url')
if not fragment_url:
assert fragment_base_url
fragment_url = urljoin(fragment_base_url, fragment['path'])
yield {
'frag_index': frag_index,
'index': i,
'url': fragment_url,
}

526
plugins/youtube_download/yt_dlp/downloader/external.py Normal file
View File

@ -0,0 +1,526 @@
from __future__ import unicode_literals
import os.path
import re
import subprocess
import sys
import time
from .fragment import FragmentFD
from ..compat import (
compat_setenv,
compat_str,
)
from ..postprocessor.ffmpeg import FFmpegPostProcessor, EXT_TO_OUT_FORMATS
from ..utils import (
cli_option,
cli_valueless_option,
cli_bool_option,
_configuration_args,
determine_ext,
encodeFilename,
encodeArgument,
handle_youtubedl_headers,
check_executable,
Popen,
remove_end,
)
class ExternalFD(FragmentFD):
SUPPORTED_PROTOCOLS = ('http', 'https', 'ftp', 'ftps')
can_download_to_stdout = False
def real_download(self, filename, info_dict):
self.report_destination(filename)
tmpfilename = self.temp_name(filename)
try:
started = time.time()
retval = self._call_downloader(tmpfilename, info_dict)
except KeyboardInterrupt:
if not info_dict.get('is_live'):
raise
# Live stream downloading cancellation should be considered as
# correct and expected termination thus all postprocessing
# should take place
retval = 0
self.to_screen('[%s] Interrupted by user' % self.get_basename())
if retval == 0:
status = {
'filename': filename,
'status': 'finished',
'elapsed': time.time() - started,
}
if filename != '-':
fsize = os.path.getsize(encodeFilename(tmpfilename))
self.to_screen('\r[%s] Downloaded %s bytes' % (self.get_basename(), fsize))
self.try_rename(tmpfilename, filename)
status.update({
'downloaded_bytes': fsize,
'total_bytes': fsize,
})
self._hook_progress(status, info_dict)
return True
else:
self.to_stderr('\n')
self.report_error('%s exited with code %d' % (
self.get_basename(), retval))
return False
@classmethod
def get_basename(cls):
return cls.__name__[:-2].lower()
@property
def exe(self):
return self.get_basename()
@classmethod
def available(cls, path=None):
path = check_executable(path or cls.get_basename(), [cls.AVAILABLE_OPT])
if path:
cls.exe = path
return path
return False
@classmethod
def supports(cls, info_dict):
return (
(cls.can_download_to_stdout or not info_dict.get('to_stdout'))
and info_dict['protocol'] in cls.SUPPORTED_PROTOCOLS)
@classmethod
def can_download(cls, info_dict, path=None):
return cls.available(path) and cls.supports(info_dict)
def _option(self, command_option, param):
return cli_option(self.params, command_option, param)
def _bool_option(self, command_option, param, true_value='true', false_value='false', separator=None):
return cli_bool_option(self.params, command_option, param, true_value, false_value, separator)
def _valueless_option(self, command_option, param, expected_value=True):
return cli_valueless_option(self.params, command_option, param, expected_value)
def _configuration_args(self, keys=None, *args, **kwargs):
return _configuration_args(
self.get_basename(), self.params.get('external_downloader_args'), self.get_basename(),
keys, *args, **kwargs)
def _call_downloader(self, tmpfilename, info_dict):
""" Either overwrite this or implement _make_cmd """
cmd = [encodeArgument(a) for a in self._make_cmd(tmpfilename, info_dict)]
self._debug_cmd(cmd)
if 'fragments' not in info_dict:
p = Popen(cmd, stderr=subprocess.PIPE)
_, stderr = p.communicate_or_kill()
if p.returncode != 0:
self.to_stderr(stderr.decode('utf-8', 'replace'))
return p.returncode
fragment_retries = self.params.get('fragment_retries', 0)
skip_unavailable_fragments = self.params.get('skip_unavailable_fragments', True)
count = 0
while count <= fragment_retries:
p = Popen(cmd, stderr=subprocess.PIPE)
_, stderr = p.communicate_or_kill()
if p.returncode == 0:
break
# TODO: Decide whether to retry based on error code
# https://aria2.github.io/manual/en/html/aria2c.html#exit-status
self.to_stderr(stderr.decode('utf-8', 'replace'))
count += 1
if count <= fragment_retries:
self.to_screen(
'[%s] Got error. Retrying fragments (attempt %d of %s)...'
% (self.get_basename(), count, self.format_retries(fragment_retries)))
if count > fragment_retries:
if not skip_unavailable_fragments:
self.report_error('Giving up after %s fragment retries' % fragment_retries)
return -1
decrypt_fragment = self.decrypter(info_dict)
dest, _ = self.sanitize_open(tmpfilename, 'wb')
for frag_index, fragment in enumerate(info_dict['fragments']):
fragment_filename = '%s-Frag%d' % (tmpfilename, frag_index)
try:
src, _ = self.sanitize_open(fragment_filename, 'rb')
except IOError as err:
if skip_unavailable_fragments and frag_index > 1:
self.report_skip_fragment(frag_index, err)
continue
self.report_error(f'Unable to open fragment {frag_index}; {err}')
return -1
dest.write(decrypt_fragment(fragment, src.read()))
src.close()
if not self.params.get('keep_fragments', False):
os.remove(encodeFilename(fragment_filename))
dest.close()
os.remove(encodeFilename('%s.frag.urls' % tmpfilename))
return 0
class CurlFD(ExternalFD):
AVAILABLE_OPT = '-V'
def _make_cmd(self, tmpfilename, info_dict):
cmd = [self.exe, '--location', '-o', tmpfilename]
if info_dict.get('http_headers') is not None:
for key, val in info_dict['http_headers'].items():
cmd += ['--header', '%s: %s' % (key, val)]
cmd += self._bool_option('--continue-at', 'continuedl', '-', '0')
cmd += self._valueless_option('--silent', 'noprogress')
cmd += self._valueless_option('--verbose', 'verbose')
cmd += self._option('--limit-rate', 'ratelimit')
retry = self._option('--retry', 'retries')
if len(retry) == 2:
if retry[1] in ('inf', 'infinite'):
retry[1] = '2147483647'
cmd += retry
cmd += self._option('--max-filesize', 'max_filesize')
cmd += self._option('--interface', 'source_address')
cmd += self._option('--proxy', 'proxy')
cmd += self._valueless_option('--insecure', 'nocheckcertificate')
cmd += self._configuration_args()
cmd += ['--', info_dict['url']]
return cmd
def _call_downloader(self, tmpfilename, info_dict):
cmd = [encodeArgument(a) for a in self._make_cmd(tmpfilename, info_dict)]
self._debug_cmd(cmd)
# curl writes the progress to stderr so don't capture it.
p = Popen(cmd)
p.communicate_or_kill()
return p.returncode
class AxelFD(ExternalFD):
AVAILABLE_OPT = '-V'
def _make_cmd(self, tmpfilename, info_dict):
cmd = [self.exe, '-o', tmpfilename]
if info_dict.get('http_headers') is not None:
for key, val in info_dict['http_headers'].items():
cmd += ['-H', '%s: %s' % (key, val)]
cmd += self._configuration_args()
cmd += ['--', info_dict['url']]
return cmd
class WgetFD(ExternalFD):
AVAILABLE_OPT = '--version'
def _make_cmd(self, tmpfilename, info_dict):
cmd = [self.exe, '-O', tmpfilename, '-nv', '--no-cookies']
if info_dict.get('http_headers') is not None:
for key, val in info_dict['http_headers'].items():
cmd += ['--header', '%s: %s' % (key, val)]
cmd += self._option('--limit-rate', 'ratelimit')
retry = self._option('--tries', 'retries')
if len(retry) == 2:
if retry[1] in ('inf', 'infinite'):
retry[1] = '0'
cmd += retry
cmd += self._option('--bind-address', 'source_address')
cmd += self._option('--proxy', 'proxy')
cmd += self._valueless_option('--no-check-certificate', 'nocheckcertificate')
cmd += self._configuration_args()
cmd += ['--', info_dict['url']]
return cmd
class Aria2cFD(ExternalFD):
AVAILABLE_OPT = '-v'
SUPPORTED_PROTOCOLS = ('http', 'https', 'ftp', 'ftps', 'dash_frag_urls', 'm3u8_frag_urls')
@staticmethod
def supports_manifest(manifest):
UNSUPPORTED_FEATURES = [
r'#EXT-X-BYTERANGE', # playlists composed of byte ranges of media files [1]
# 1. https://tools.ietf.org/html/draft-pantos-http-live-streaming-17#section-4.3.2.2
]
check_results = (not re.search(feature, manifest) for feature in UNSUPPORTED_FEATURES)
return all(check_results)
def _make_cmd(self, tmpfilename, info_dict):
cmd = [self.exe, '-c',
'--console-log-level=warn', '--summary-interval=0', '--download-result=hide',
'--file-allocation=none', '-x16', '-j16', '-s16']
if 'fragments' in info_dict:
cmd += ['--allow-overwrite=true', '--allow-piece-length-change=true']
else:
cmd += ['--min-split-size', '1M']
if info_dict.get('http_headers') is not None:
for key, val in info_dict['http_headers'].items():
cmd += ['--header', '%s: %s' % (key, val)]
cmd += self._option('--max-overall-download-limit', 'ratelimit')
cmd += self._option('--interface', 'source_address')
cmd += self._option('--all-proxy', 'proxy')
cmd += self._bool_option('--check-certificate', 'nocheckcertificate', 'false', 'true', '=')
cmd += self._bool_option('--remote-time', 'updatetime', 'true', 'false', '=')
cmd += self._bool_option('--show-console-readout', 'noprogress', 'false', 'true', '=')
cmd += self._configuration_args()
# aria2c strips out spaces from the beginning/end of filenames and paths.
# We work around this issue by adding a "./" to the beginning of the
# filename and relative path, and adding a "/" at the end of the path.
# See: https://github.com/yt-dlp/yt-dlp/issues/276
# https://github.com/ytdl-org/youtube-dl/issues/20312
# https://github.com/aria2/aria2/issues/1373
dn = os.path.dirname(tmpfilename)
if dn:
if not os.path.isabs(dn):
dn = '.%s%s' % (os.path.sep, dn)
cmd += ['--dir', dn + os.path.sep]
if 'fragments' not in info_dict:
cmd += ['--out', '.%s%s' % (os.path.sep, os.path.basename(tmpfilename))]
cmd += ['--auto-file-renaming=false']
if 'fragments' in info_dict:
cmd += ['--file-allocation=none', '--uri-selector=inorder']
url_list_file = '%s.frag.urls' % tmpfilename
url_list = []
for frag_index, fragment in enumerate(info_dict['fragments']):
fragment_filename = '%s-Frag%d' % (os.path.basename(tmpfilename), frag_index)
url_list.append('%s\n\tout=%s' % (fragment['url'], fragment_filename))
stream, _ = self.sanitize_open(url_list_file, 'wb')
stream.write('\n'.join(url_list).encode('utf-8'))
stream.close()
cmd += ['-i', url_list_file]
else:
cmd += ['--', info_dict['url']]
return cmd
class HttpieFD(ExternalFD):
AVAILABLE_OPT = '--version'
@classmethod
def available(cls, path=None):
return super().available(path or 'http')
def _make_cmd(self, tmpfilename, info_dict):
cmd = ['http', '--download', '--output', tmpfilename, info_dict['url']]
if info_dict.get('http_headers') is not None:
for key, val in info_dict['http_headers'].items():
cmd += ['%s:%s' % (key, val)]
return cmd
class FFmpegFD(ExternalFD):
SUPPORTED_PROTOCOLS = ('http', 'https', 'ftp', 'ftps', 'm3u8', 'm3u8_native', 'rtsp', 'rtmp', 'rtmp_ffmpeg', 'mms', 'http_dash_segments')
can_download_to_stdout = True
@classmethod
def available(cls, path=None):
# TODO: Fix path for ffmpeg
# Fixme: This may be wrong when --ffmpeg-location is used
return FFmpegPostProcessor().available
@classmethod
def supports(cls, info_dict):
return all(proto in cls.SUPPORTED_PROTOCOLS for proto in info_dict['protocol'].split('+'))
def on_process_started(self, proc, stdin):
""" Override this in subclasses """
pass
@classmethod
def can_merge_formats(cls, info_dict, params):
return (
info_dict.get('requested_formats')
and info_dict.get('protocol')
and not params.get('allow_unplayable_formats')
and 'no-direct-merge' not in params.get('compat_opts', [])
and cls.can_download(info_dict))
def _call_downloader(self, tmpfilename, info_dict):
urls = [f['url'] for f in info_dict.get('requested_formats', [])] or [info_dict['url']]
ffpp = FFmpegPostProcessor(downloader=self)
if not ffpp.available:
self.report_error('m3u8 download detected but ffmpeg could not be found. Please install')
return False
ffpp.check_version()
args = [ffpp.executable, '-y']
for log_level in ('quiet', 'verbose'):
if self.params.get(log_level, False):
args += ['-loglevel', log_level]
break
if not self.params.get('verbose'):
args += ['-hide_banner']
args += info_dict.get('_ffmpeg_args', [])
# This option exists only for compatibility. Extractors should use `_ffmpeg_args` instead
seekable = info_dict.get('_seekable')
if seekable is not None:
# setting -seekable prevents ffmpeg from guessing if the server
# supports seeking(by adding the header `Range: bytes=0-`), which
# can cause problems in some cases
# https://github.com/ytdl-org/youtube-dl/issues/11800#issuecomment-275037127
# http://trac.ffmpeg.org/ticket/6125#comment:10
args += ['-seekable', '1' if seekable else '0']
# start_time = info_dict.get('start_time') or 0
# if start_time:
# args += ['-ss', compat_str(start_time)]
# end_time = info_dict.get('end_time')
# if end_time:
# args += ['-t', compat_str(end_time - start_time)]
if info_dict.get('http_headers') is not None and re.match(r'^https?://', urls[0]):
# Trailing \r\n after each HTTP header is important to prevent warning from ffmpeg/avconv:
# [http @ 00000000003d2fa0] No trailing CRLF found in HTTP header.
headers = handle_youtubedl_headers(info_dict['http_headers'])
args += [
'-headers',
''.join('%s: %s\r\n' % (key, val) for key, val in headers.items())]
env = None
proxy = self.params.get('proxy')
if proxy:
if not re.match(r'^[\da-zA-Z]+://', proxy):
proxy = 'http://%s' % proxy
if proxy.startswith('socks'):
self.report_warning(
'%s does not support SOCKS proxies. Downloading is likely to fail. '
'Consider adding --hls-prefer-native to your command.' % self.get_basename())
# Since December 2015 ffmpeg supports -http_proxy option (see
# http://git.videolan.org/?p=ffmpeg.git;a=commit;h=b4eb1f29ebddd60c41a2eb39f5af701e38e0d3fd)
# We could switch to the following code if we are able to detect version properly
# args += ['-http_proxy', proxy]
env = os.environ.copy()
compat_setenv('HTTP_PROXY', proxy, env=env)
compat_setenv('http_proxy', proxy, env=env)
protocol = info_dict.get('protocol')
if protocol == 'rtmp':
player_url = info_dict.get('player_url')
page_url = info_dict.get('page_url')
app = info_dict.get('app')
play_path = info_dict.get('play_path')
tc_url = info_dict.get('tc_url')
flash_version = info_dict.get('flash_version')
live = info_dict.get('rtmp_live', False)
conn = info_dict.get('rtmp_conn')
if player_url is not None:
args += ['-rtmp_swfverify', player_url]
if page_url is not None:
args += ['-rtmp_pageurl', page_url]
if app is not None:
args += ['-rtmp_app', app]
if play_path is not None:
args += ['-rtmp_playpath', play_path]
if tc_url is not None:
args += ['-rtmp_tcurl', tc_url]
if flash_version is not None:
args += ['-rtmp_flashver', flash_version]
if live:
args += ['-rtmp_live', 'live']
if isinstance(conn, list):
for entry in conn:
args += ['-rtmp_conn', entry]
elif isinstance(conn, compat_str):
args += ['-rtmp_conn', conn]
for i, url in enumerate(urls):
args += self._configuration_args((f'_i{i + 1}', '_i')) + ['-i', url]
args += ['-c', 'copy']
if info_dict.get('requested_formats') or protocol == 'http_dash_segments':
for (i, fmt) in enumerate(info_dict.get('requested_formats') or [info_dict]):
stream_number = fmt.get('manifest_stream_number', 0)
args.extend(['-map', f'{i}:{stream_number}'])
if self.params.get('test', False):
args += ['-fs', compat_str(self._TEST_FILE_SIZE)]
ext = info_dict['ext']
if protocol in ('m3u8', 'm3u8_native'):
use_mpegts = (tmpfilename == '-') or self.params.get('hls_use_mpegts')
if use_mpegts is None:
use_mpegts = info_dict.get('is_live')
if use_mpegts:
args += ['-f', 'mpegts']
else:
args += ['-f', 'mp4']
if (ffpp.basename == 'ffmpeg' and ffpp._features.get('needs_adtstoasc')) and (not info_dict.get('acodec') or info_dict['acodec'].split('.')[0] in ('aac', 'mp4a')):
args += ['-bsf:a', 'aac_adtstoasc']
elif protocol == 'rtmp':
args += ['-f', 'flv']
elif ext == 'mp4' and tmpfilename == '-':
args += ['-f', 'mpegts']
elif ext == 'unknown_video':
ext = determine_ext(remove_end(tmpfilename, '.part'))
if ext == 'unknown_video':
self.report_warning(
'The video format is unknown and cannot be downloaded by ffmpeg. '
'Explicitly set the extension in the filename to attempt download in that format')
else:
self.report_warning(f'The video format is unknown. Trying to download as {ext} according to the filename')
args += ['-f', EXT_TO_OUT_FORMATS.get(ext, ext)]
else:
args += ['-f', EXT_TO_OUT_FORMATS.get(ext, ext)]
args += self._configuration_args(('_o1', '_o', ''))
args = [encodeArgument(opt) for opt in args]
args.append(encodeFilename(ffpp._ffmpeg_filename_argument(tmpfilename), True))
self._debug_cmd(args)
proc = Popen(args, stdin=subprocess.PIPE, env=env)
if url in ('-', 'pipe:'):
self.on_process_started(proc, proc.stdin)
try:
retval = proc.wait()
except BaseException as e:
# subprocces.run would send the SIGKILL signal to ffmpeg and the
# mp4 file couldn't be played, but if we ask ffmpeg to quit it
# produces a file that is playable (this is mostly useful for live
# streams). Note that Windows is not affected and produces playable
# files (see https://github.com/ytdl-org/youtube-dl/issues/8300).
if isinstance(e, KeyboardInterrupt) and sys.platform != 'win32' and url not in ('-', 'pipe:'):
proc.communicate_or_kill(b'q')
else:
proc.kill()
proc.wait()
raise
return retval
class AVconvFD(FFmpegFD):
pass
_BY_NAME = dict(
(klass.get_basename(), klass)
for name, klass in globals().items()
if name.endswith('FD') and name not in ('ExternalFD', 'FragmentFD')
)
def list_external_downloaders():
return sorted(_BY_NAME.keys())
def get_external_downloader(external_downloader):
""" Given the name of the executable, see whether we support the given
downloader . """
# Drop .exe extension on Windows
bn = os.path.splitext(os.path.basename(external_downloader))[0]
return _BY_NAME.get(bn)

439
plugins/youtube_download/yt_dlp/downloader/f4m.py Normal file
View File

@ -0,0 +1,439 @@
from __future__ import division, unicode_literals
import io
import itertools
import time
from .fragment import FragmentFD
from ..compat import (
compat_b64decode,
compat_etree_fromstring,
compat_urlparse,
compat_urllib_error,
compat_urllib_parse_urlparse,
compat_struct_pack,
compat_struct_unpack,
)
from ..utils import (
fix_xml_ampersands,
xpath_text,
)
class DataTruncatedError(Exception):
pass
class FlvReader(io.BytesIO):
"""
Reader for Flv files
The file format is documented in https://www.adobe.com/devnet/f4v.html
"""
def read_bytes(self, n):
data = self.read(n)
if len(data) < n:
raise DataTruncatedError(
'FlvReader error: need %d bytes while only %d bytes got' % (
n, len(data)))
return data
# Utility functions for reading numbers and strings
def read_unsigned_long_long(self):
return compat_struct_unpack('!Q', self.read_bytes(8))[0]
def read_unsigned_int(self):
return compat_struct_unpack('!I', self.read_bytes(4))[0]
def read_unsigned_char(self):
return compat_struct_unpack('!B', self.read_bytes(1))[0]
def read_string(self):
res = b''
while True:
char = self.read_bytes(1)
if char == b'\x00':
break
res += char
return res
def read_box_info(self):
"""
Read a box and return the info as a tuple: (box_size, box_type, box_data)
"""
real_size = size = self.read_unsigned_int()
box_type = self.read_bytes(4)
header_end = 8
if size == 1:
real_size = self.read_unsigned_long_long()
header_end = 16
return real_size, box_type, self.read_bytes(real_size - header_end)
def read_asrt(self):
# version
self.read_unsigned_char()
# flags
self.read_bytes(3)
quality_entry_count = self.read_unsigned_char()
# QualityEntryCount
for i in range(quality_entry_count):
self.read_string()
segment_run_count = self.read_unsigned_int()
segments = []
for i in range(segment_run_count):
first_segment = self.read_unsigned_int()
fragments_per_segment = self.read_unsigned_int()
segments.append((first_segment, fragments_per_segment))
return {
'segment_run': segments,
}
def read_afrt(self):
# version
self.read_unsigned_char()
# flags
self.read_bytes(3)
# time scale
self.read_unsigned_int()
quality_entry_count = self.read_unsigned_char()
# QualitySegmentUrlModifiers
for i in range(quality_entry_count):
self.read_string()
fragments_count = self.read_unsigned_int()
fragments = []
for i in range(fragments_count):
first = self.read_unsigned_int()
first_ts = self.read_unsigned_long_long()
duration = self.read_unsigned_int()
if duration == 0:
discontinuity_indicator = self.read_unsigned_char()
else:
discontinuity_indicator = None
fragments.append({
'first': first,
'ts': first_ts,
'duration': duration,
'discontinuity_indicator': discontinuity_indicator,
})
return {
'fragments': fragments,
}
def read_abst(self):
# version
self.read_unsigned_char()
# flags
self.read_bytes(3)
self.read_unsigned_int() # BootstrapinfoVersion
# Profile,Live,Update,Reserved
flags = self.read_unsigned_char()
live = flags & 0x20 != 0
# time scale
self.read_unsigned_int()
# CurrentMediaTime
self.read_unsigned_long_long()
# SmpteTimeCodeOffset
self.read_unsigned_long_long()
self.read_string() # MovieIdentifier
server_count = self.read_unsigned_char()
# ServerEntryTable
for i in range(server_count):
self.read_string()
quality_count = self.read_unsigned_char()
# QualityEntryTable
for i in range(quality_count):
self.read_string()
# DrmData
self.read_string()
# MetaData
self.read_string()
segments_count = self.read_unsigned_char()
segments = []
for i in range(segments_count):
box_size, box_type, box_data = self.read_box_info()
assert box_type == b'asrt'
segment = FlvReader(box_data).read_asrt()
segments.append(segment)
fragments_run_count = self.read_unsigned_char()
fragments = []
for i in range(fragments_run_count):
box_size, box_type, box_data = self.read_box_info()
assert box_type == b'afrt'
fragments.append(FlvReader(box_data).read_afrt())
return {
'segments': segments,
'fragments': fragments,
'live': live,
}
def read_bootstrap_info(self):
total_size, box_type, box_data = self.read_box_info()
assert box_type == b'abst'
return FlvReader(box_data).read_abst()
def read_bootstrap_info(bootstrap_bytes):
return FlvReader(bootstrap_bytes).read_bootstrap_info()
def build_fragments_list(boot_info):
""" Return a list of (segment, fragment) for each fragment in the video """
res = []
segment_run_table = boot_info['segments'][0]
fragment_run_entry_table = boot_info['fragments'][0]['fragments']
first_frag_number = fragment_run_entry_table[0]['first']
fragments_counter = itertools.count(first_frag_number)
for segment, fragments_count in segment_run_table['segment_run']:
# In some live HDS streams (for example Rai), `fragments_count` is
# abnormal and causing out-of-memory errors. It's OK to change the
# number of fragments for live streams as they are updated periodically
if fragments_count == 4294967295 and boot_info['live']:
fragments_count = 2
for _ in range(fragments_count):
res.append((segment, next(fragments_counter)))
if boot_info['live']:
res = res[-2:]
return res
def write_unsigned_int(stream, val):
stream.write(compat_struct_pack('!I', val))
def write_unsigned_int_24(stream, val):
stream.write(compat_struct_pack('!I', val)[1:])
def write_flv_header(stream):
"""Writes the FLV header to stream"""
# FLV header
stream.write(b'FLV\x01')
stream.write(b'\x05')
stream.write(b'\x00\x00\x00\x09')
stream.write(b'\x00\x00\x00\x00')
def write_metadata_tag(stream, metadata):
"""Writes optional metadata tag to stream"""
SCRIPT_TAG = b'\x12'
FLV_TAG_HEADER_LEN = 11
if metadata:
stream.write(SCRIPT_TAG)
write_unsigned_int_24(stream, len(metadata))
stream.write(b'\x00\x00\x00\x00\x00\x00\x00')
stream.write(metadata)
write_unsigned_int(stream, FLV_TAG_HEADER_LEN + len(metadata))
def remove_encrypted_media(media):
return list(filter(lambda e: 'drmAdditionalHeaderId' not in e.attrib
and 'drmAdditionalHeaderSetId' not in e.attrib,
media))
def _add_ns(prop, ver=1):
return '{http://ns.adobe.com/f4m/%d.0}%s' % (ver, prop)
def get_base_url(manifest):
base_url = xpath_text(
manifest, [_add_ns('baseURL'), _add_ns('baseURL', 2)],
'base URL', default=None)
if base_url:
base_url = base_url.strip()
return base_url
class F4mFD(FragmentFD):
"""
A downloader for f4m manifests or AdobeHDS.
"""
FD_NAME = 'f4m'
def _get_unencrypted_media(self, doc):
media = doc.findall(_add_ns('media'))
if not media:
self.report_error('No media found')
if not self.params.get('allow_unplayable_formats'):
for e in (doc.findall(_add_ns('drmAdditionalHeader'))
+ doc.findall(_add_ns('drmAdditionalHeaderSet'))):
# If id attribute is missing it's valid for all media nodes
# without drmAdditionalHeaderId or drmAdditionalHeaderSetId attribute
if 'id' not in e.attrib:
self.report_error('Missing ID in f4m DRM')
media = remove_encrypted_media(media)
if not media:
self.report_error('Unsupported DRM')
return media
def _get_bootstrap_from_url(self, bootstrap_url):
bootstrap = self.ydl.urlopen(bootstrap_url).read()
return read_bootstrap_info(bootstrap)
def _update_live_fragments(self, bootstrap_url, latest_fragment):
fragments_list = []
retries = 30
while (not fragments_list) and (retries > 0):
boot_info = self._get_bootstrap_from_url(bootstrap_url)
fragments_list = build_fragments_list(boot_info)
fragments_list = [f for f in fragments_list if f[1] > latest_fragment]
if not fragments_list:
# Retry after a while
time.sleep(5.0)
retries -= 1
if not fragments_list:
self.report_error('Failed to update fragments')
return fragments_list
def _parse_bootstrap_node(self, node, base_url):
# Sometimes non empty inline bootstrap info can be specified along
# with bootstrap url attribute (e.g. dummy inline bootstrap info
# contains whitespace characters in [1]). We will prefer bootstrap
# url over inline bootstrap info when present.
# 1. http://live-1-1.rutube.ru/stream/1024/HDS/SD/C2NKsS85HQNckgn5HdEmOQ/1454167650/S-s604419906/move/four/dirs/upper/1024-576p.f4m
bootstrap_url = node.get('url')
if bootstrap_url:
bootstrap_url = compat_urlparse.urljoin(
base_url, bootstrap_url)
boot_info = self._get_bootstrap_from_url(bootstrap_url)
else:
bootstrap_url = None
bootstrap = compat_b64decode(node.text)
boot_info = read_bootstrap_info(bootstrap)
return boot_info, bootstrap_url
def real_download(self, filename, info_dict):
man_url = info_dict['url']
requested_bitrate = info_dict.get('tbr')
self.to_screen('[%s] Downloading f4m manifest' % self.FD_NAME)
urlh = self.ydl.urlopen(self._prepare_url(info_dict, man_url))
man_url = urlh.geturl()
# Some manifests may be malformed, e.g. prosiebensat1 generated manifests
# (see https://github.com/ytdl-org/youtube-dl/issues/6215#issuecomment-121704244
# and https://github.com/ytdl-org/youtube-dl/issues/7823)
manifest = fix_xml_ampersands(urlh.read().decode('utf-8', 'ignore')).strip()
doc = compat_etree_fromstring(manifest)
formats = [(int(f.attrib.get('bitrate', -1)), f)
for f in self._get_unencrypted_media(doc)]
if requested_bitrate is None or len(formats) == 1:
# get the best format
formats = sorted(formats, key=lambda f: f[0])
rate, media = formats[-1]
else:
rate, media = list(filter(
lambda f: int(f[0]) == requested_bitrate, formats))[0]
# Prefer baseURL for relative URLs as per 11.2 of F4M 3.0 spec.
man_base_url = get_base_url(doc) or man_url
base_url = compat_urlparse.urljoin(man_base_url, media.attrib['url'])
bootstrap_node = doc.find(_add_ns('bootstrapInfo'))
boot_info, bootstrap_url = self._parse_bootstrap_node(
bootstrap_node, man_base_url)
live = boot_info['live']
metadata_node = media.find(_add_ns('metadata'))
if metadata_node is not None:
metadata = compat_b64decode(metadata_node.text)
else:
metadata = None
fragments_list = build_fragments_list(boot_info)
test = self.params.get('test', False)
if test:
# We only download the first fragment
fragments_list = fragments_list[:1]
total_frags = len(fragments_list)
# For some akamai manifests we'll need to add a query to the fragment url
akamai_pv = xpath_text(doc, _add_ns('pv-2.0'))
ctx = {
'filename': filename,
'total_frags': total_frags,
'live': bool(live),
}
self._prepare_frag_download(ctx)
dest_stream = ctx['dest_stream']
if ctx['complete_frags_downloaded_bytes'] == 0:
write_flv_header(dest_stream)
if not live:
write_metadata_tag(dest_stream, metadata)
base_url_parsed = compat_urllib_parse_urlparse(base_url)
self._start_frag_download(ctx, info_dict)
frag_index = 0
while fragments_list:
seg_i, frag_i = fragments_list.pop(0)
frag_index += 1
if frag_index <= ctx['fragment_index']:
continue
name = 'Seg%d-Frag%d' % (seg_i, frag_i)
query = []
if base_url_parsed.query:
query.append(base_url_parsed.query)
if akamai_pv:
query.append(akamai_pv.strip(';'))
if info_dict.get('extra_param_to_segment_url'):
query.append(info_dict['extra_param_to_segment_url'])
url_parsed = base_url_parsed._replace(path=base_url_parsed.path + name, query='&'.join(query))
try:
success, down_data = self._download_fragment(ctx, url_parsed.geturl(), info_dict)
if not success:
return False
reader = FlvReader(down_data)
while True:
try:
_, box_type, box_data = reader.read_box_info()
except DataTruncatedError:
if test:
# In tests, segments may be truncated, and thus
# FlvReader may not be able to parse the whole
# chunk. If so, write the segment as is
# See https://github.com/ytdl-org/youtube-dl/issues/9214
dest_stream.write(down_data)
break
raise
if box_type == b'mdat':
self._append_fragment(ctx, box_data)
break
except (compat_urllib_error.HTTPError, ) as err:
if live and (err.code == 404 or err.code == 410):
# We didn't keep up with the live window. Continue
# with the next available fragment.
msg = 'Fragment %d unavailable' % frag_i
self.report_warning(msg)
fragments_list = []
else:
raise
if not fragments_list and not test and live and bootstrap_url:
fragments_list = self._update_live_fragments(bootstrap_url, frag_i)
total_frags += len(fragments_list)
if fragments_list and (fragments_list[0][1] > frag_i + 1):
msg = 'Missed %d fragments' % (fragments_list[0][1] - (frag_i + 1))
self.report_warning(msg)
self._finish_frag_download(ctx, info_dict)
return True

523
plugins/youtube_download/yt_dlp/downloader/fragment.py Normal file
View File

@ -0,0 +1,523 @@
from __future__ import division, unicode_literals
import http.client
import json
import math
import os
import time
try:
import concurrent.futures
can_threaded_download = True
except ImportError:
can_threaded_download = False
from .common import FileDownloader
from .http import HttpFD
from ..aes import aes_cbc_decrypt_bytes, unpad_pkcs7
from ..compat import (
compat_os_name,
compat_urllib_error,
compat_struct_pack,
)
from ..utils import (
DownloadError,
error_to_compat_str,
encodeFilename,
sanitized_Request,
)
class HttpQuietDownloader(HttpFD):
def to_screen(self, *args, **kargs):
pass
def report_retry(self, err, count, retries):
super().to_screen(
f'[download] Got server HTTP error: {err}. Retrying (attempt {count} of {self.format_retries(retries)}) ...')
class FragmentFD(FileDownloader):
"""
A base file downloader class for fragmented media (e.g. f4m/m3u8 manifests).
Available options:
fragment_retries: Number of times to retry a fragment for HTTP error (DASH
and hlsnative only)
skip_unavailable_fragments:
Skip unavailable fragments (DASH and hlsnative only)
keep_fragments: Keep downloaded fragments on disk after downloading is
finished
concurrent_fragment_downloads: The number of threads to use for native hls and dash downloads
_no_ytdl_file: Don't use .ytdl file
For each incomplete fragment download yt-dlp keeps on disk a special
bookkeeping file with download state and metadata (in future such files will
be used for any incomplete download handled by yt-dlp). This file is
used to properly handle resuming, check download file consistency and detect
potential errors. The file has a .ytdl extension and represents a standard
JSON file of the following format:
extractor:
Dictionary of extractor related data. TBD.
downloader:
Dictionary of downloader related data. May contain following data:
current_fragment:
Dictionary with current (being downloaded) fragment data:
index: 0-based index of current fragment among all fragments
fragment_count:
Total count of fragments
This feature is experimental and file format may change in future.
"""
def report_retry_fragment(self, err, frag_index, count, retries):
self.to_screen(
'\r[download] Got server HTTP error: %s. Retrying fragment %d (attempt %d of %s) ...'
% (error_to_compat_str(err), frag_index, count, self.format_retries(retries)))
def report_skip_fragment(self, frag_index, err=None):
err = f' {err};' if err else ''
self.to_screen(f'[download]{err} Skipping fragment {frag_index:d} ...')
def _prepare_url(self, info_dict, url):
headers = info_dict.get('http_headers')
return sanitized_Request(url, None, headers) if headers else url
def _prepare_and_start_frag_download(self, ctx, info_dict):
self._prepare_frag_download(ctx)
self._start_frag_download(ctx, info_dict)
def __do_ytdl_file(self, ctx):
return ctx['live'] is not True and ctx['tmpfilename'] != '-' and not self.params.get('_no_ytdl_file')
def _read_ytdl_file(self, ctx):
assert 'ytdl_corrupt' not in ctx
stream, _ = self.sanitize_open(self.ytdl_filename(ctx['filename']), 'r')
try:
ytdl_data = json.loads(stream.read())
ctx['fragment_index'] = ytdl_data['downloader']['current_fragment']['index']
if 'extra_state' in ytdl_data['downloader']:
ctx['extra_state'] = ytdl_data['downloader']['extra_state']
except Exception:
ctx['ytdl_corrupt'] = True
finally:
stream.close()
def _write_ytdl_file(self, ctx):
frag_index_stream, _ = self.sanitize_open(self.ytdl_filename(ctx['filename']), 'w')
try:
downloader = {
'current_fragment': {
'index': ctx['fragment_index'],
},
}
if 'extra_state' in ctx:
downloader['extra_state'] = ctx['extra_state']
if ctx.get('fragment_count') is not None:
downloader['fragment_count'] = ctx['fragment_count']
frag_index_stream.write(json.dumps({'downloader': downloader}))
finally:
frag_index_stream.close()
def _download_fragment(self, ctx, frag_url, info_dict, headers=None, request_data=None):
fragment_filename = '%s-Frag%d' % (ctx['tmpfilename'], ctx['fragment_index'])
fragment_info_dict = {
'url': frag_url,
'http_headers': headers or info_dict.get('http_headers'),
'request_data': request_data,
'ctx_id': ctx.get('ctx_id'),
}
success = ctx['dl'].download(fragment_filename, fragment_info_dict)
if not success:
return False, None
if fragment_info_dict.get('filetime'):
ctx['fragment_filetime'] = fragment_info_dict.get('filetime')
ctx['fragment_filename_sanitized'] = fragment_filename
return True, self._read_fragment(ctx)
def _read_fragment(self, ctx):
down, frag_sanitized = self.sanitize_open(ctx['fragment_filename_sanitized'], 'rb')
ctx['fragment_filename_sanitized'] = frag_sanitized
frag_content = down.read()
down.close()
return frag_content
def _append_fragment(self, ctx, frag_content):
try:
ctx['dest_stream'].write(frag_content)
ctx['dest_stream'].flush()
finally:
if self.__do_ytdl_file(ctx):
self._write_ytdl_file(ctx)
if not self.params.get('keep_fragments', False):
os.remove(encodeFilename(ctx['fragment_filename_sanitized']))
del ctx['fragment_filename_sanitized']
def _prepare_frag_download(self, ctx):
if 'live' not in ctx:
ctx['live'] = False
if not ctx['live']:
total_frags_str = '%d' % ctx['total_frags']
ad_frags = ctx.get('ad_frags', 0)
if ad_frags:
total_frags_str += ' (not including %d ad)' % ad_frags
else:
total_frags_str = 'unknown (live)'
self.to_screen(
'[%s] Total fragments: %s' % (self.FD_NAME, total_frags_str))
self.report_destination(ctx['filename'])
dl = HttpQuietDownloader(
self.ydl,
{
'continuedl': True,
'quiet': self.params.get('quiet'),
'noprogress': True,
'ratelimit': self.params.get('ratelimit'),
'retries': self.params.get('retries', 0),
'nopart': self.params.get('nopart', False),
'test': self.params.get('test', False),
}
)
tmpfilename = self.temp_name(ctx['filename'])
open_mode = 'wb'
resume_len = 0
# Establish possible resume length
if os.path.isfile(encodeFilename(tmpfilename)):
open_mode = 'ab'
resume_len = os.path.getsize(encodeFilename(tmpfilename))
# Should be initialized before ytdl file check
ctx.update({
'tmpfilename': tmpfilename,
'fragment_index': 0,
})
if self.__do_ytdl_file(ctx):
if os.path.isfile(encodeFilename(self.ytdl_filename(ctx['filename']))):
self._read_ytdl_file(ctx)
is_corrupt = ctx.get('ytdl_corrupt') is True
is_inconsistent = ctx['fragment_index'] > 0 and resume_len == 0
if is_corrupt or is_inconsistent:
message = (
'.ytdl file is corrupt' if is_corrupt else
'Inconsistent state of incomplete fragment download')
self.report_warning(
'%s. Restarting from the beginning ...' % message)
ctx['fragment_index'] = resume_len = 0
if 'ytdl_corrupt' in ctx:
del ctx['ytdl_corrupt']
self._write_ytdl_file(ctx)
else:
self._write_ytdl_file(ctx)
assert ctx['fragment_index'] == 0
dest_stream, tmpfilename = self.sanitize_open(tmpfilename, open_mode)
ctx.update({
'dl': dl,
'dest_stream': dest_stream,
'tmpfilename': tmpfilename,
# Total complete fragments downloaded so far in bytes
'complete_frags_downloaded_bytes': resume_len,
})
def _start_frag_download(self, ctx, info_dict):
resume_len = ctx['complete_frags_downloaded_bytes']
total_frags = ctx['total_frags']
ctx_id = ctx.get('ctx_id')
# This dict stores the download progress, it's updated by the progress
# hook
state = {
'status': 'downloading',
'downloaded_bytes': resume_len,
'fragment_index': ctx['fragment_index'],
'fragment_count': total_frags,
'filename': ctx['filename'],
'tmpfilename': ctx['tmpfilename'],
}
start = time.time()
ctx.update({
'started': start,
'fragment_started': start,
# Amount of fragment's bytes downloaded by the time of the previous
# frag progress hook invocation
'prev_frag_downloaded_bytes': 0,
})
def frag_progress_hook(s):
if s['status'] not in ('downloading', 'finished'):
return
if ctx_id is not None and s.get('ctx_id') != ctx_id:
return
state['max_progress'] = ctx.get('max_progress')
state['progress_idx'] = ctx.get('progress_idx')
time_now = time.time()
state['elapsed'] = time_now - start
frag_total_bytes = s.get('total_bytes') or 0
s['fragment_info_dict'] = s.pop('info_dict', {})
if not ctx['live']:
estimated_size = (
(ctx['complete_frags_downloaded_bytes'] + frag_total_bytes)
/ (state['fragment_index'] + 1) * total_frags)
state['total_bytes_estimate'] = estimated_size
if s['status'] == 'finished':
state['fragment_index'] += 1
ctx['fragment_index'] = state['fragment_index']
state['downloaded_bytes'] += frag_total_bytes - ctx['prev_frag_downloaded_bytes']
ctx['complete_frags_downloaded_bytes'] = state['downloaded_bytes']
ctx['speed'] = state['speed'] = self.calc_speed(
ctx['fragment_started'], time_now, frag_total_bytes)
ctx['fragment_started'] = time.time()
ctx['prev_frag_downloaded_bytes'] = 0
else:
frag_downloaded_bytes = s['downloaded_bytes']
state['downloaded_bytes'] += frag_downloaded_bytes - ctx['prev_frag_downloaded_bytes']
if not ctx['live']:
state['eta'] = self.calc_eta(
start, time_now, estimated_size - resume_len,
state['downloaded_bytes'] - resume_len)
ctx['speed'] = state['speed'] = self.calc_speed(
ctx['fragment_started'], time_now, frag_downloaded_bytes)
ctx['prev_frag_downloaded_bytes'] = frag_downloaded_bytes
self._hook_progress(state, info_dict)
ctx['dl'].add_progress_hook(frag_progress_hook)
return start
def _finish_frag_download(self, ctx, info_dict):
ctx['dest_stream'].close()
if self.__do_ytdl_file(ctx):
ytdl_filename = encodeFilename(self.ytdl_filename(ctx['filename']))
if os.path.isfile(ytdl_filename):
os.remove(ytdl_filename)
elapsed = time.time() - ctx['started']
if ctx['tmpfilename'] == '-':
downloaded_bytes = ctx['complete_frags_downloaded_bytes']
else:
self.try_rename(ctx['tmpfilename'], ctx['filename'])
if self.params.get('updatetime', True):
filetime = ctx.get('fragment_filetime')
if filetime:
try:
os.utime(ctx['filename'], (time.time(), filetime))
except Exception:
pass
downloaded_bytes = os.path.getsize(encodeFilename(ctx['filename']))
self._hook_progress({
'downloaded_bytes': downloaded_bytes,
'total_bytes': downloaded_bytes,
'filename': ctx['filename'],
'status': 'finished',
'elapsed': elapsed,
'ctx_id': ctx.get('ctx_id'),
'max_progress': ctx.get('max_progress'),
'progress_idx': ctx.get('progress_idx'),
}, info_dict)
def _prepare_external_frag_download(self, ctx):
if 'live' not in ctx:
ctx['live'] = False
if not ctx['live']:
total_frags_str = '%d' % ctx['total_frags']
ad_frags = ctx.get('ad_frags', 0)
if ad_frags:
total_frags_str += ' (not including %d ad)' % ad_frags
else:
total_frags_str = 'unknown (live)'
self.to_screen(
'[%s] Total fragments: %s' % (self.FD_NAME, total_frags_str))
tmpfilename = self.temp_name(ctx['filename'])
# Should be initialized before ytdl file check
ctx.update({
'tmpfilename': tmpfilename,
'fragment_index': 0,
})
def decrypter(self, info_dict):
_key_cache = {}
def _get_key(url):
if url not in _key_cache:
_key_cache[url] = self.ydl.urlopen(self._prepare_url(info_dict, url)).read()
return _key_cache[url]
def decrypt_fragment(fragment, frag_content):
decrypt_info = fragment.get('decrypt_info')
if not decrypt_info or decrypt_info['METHOD'] != 'AES-128':
return frag_content
iv = decrypt_info.get('IV') or compat_struct_pack('>8xq', fragment['media_sequence'])
decrypt_info['KEY'] = decrypt_info.get('KEY') or _get_key(info_dict.get('_decryption_key_url') or decrypt_info['URI'])
# Don't decrypt the content in tests since the data is explicitly truncated and it's not to a valid block
# size (see https://github.com/ytdl-org/youtube-dl/pull/27660). Tests only care that the correct data downloaded,
# not what it decrypts to.
if self.params.get('test', False):
return frag_content
return unpad_pkcs7(aes_cbc_decrypt_bytes(frag_content, decrypt_info['KEY'], iv))
return decrypt_fragment
def download_and_append_fragments_multiple(self, *args, pack_func=None, finish_func=None):
'''
@params (ctx1, fragments1, info_dict1), (ctx2, fragments2, info_dict2), ...
all args must be either tuple or list
'''
interrupt_trigger = [True]
max_progress = len(args)
if max_progress == 1:
return self.download_and_append_fragments(*args[0], pack_func=pack_func, finish_func=finish_func)
max_workers = self.params.get('concurrent_fragment_downloads', 1)
if max_progress > 1:
self._prepare_multiline_status(max_progress)
def thread_func(idx, ctx, fragments, info_dict, tpe):
ctx['max_progress'] = max_progress
ctx['progress_idx'] = idx
return self.download_and_append_fragments(
ctx, fragments, info_dict, pack_func=pack_func, finish_func=finish_func,
tpe=tpe, interrupt_trigger=interrupt_trigger)
class FTPE(concurrent.futures.ThreadPoolExecutor):
# has to stop this or it's going to wait on the worker thread itself
def __exit__(self, exc_type, exc_val, exc_tb):
pass
spins = []
if compat_os_name == 'nt':
self.report_warning('Ctrl+C does not work on Windows when used with parallel threads. '
'This is a known issue and patches are welcome')
for idx, (ctx, fragments, info_dict) in enumerate(args):
tpe = FTPE(math.ceil(max_workers / max_progress))
job = tpe.submit(thread_func, idx, ctx, fragments, info_dict, tpe)
spins.append((tpe, job))
result = True
for tpe, job in spins:
try:
result = result and job.result()
except KeyboardInterrupt:
interrupt_trigger[0] = False
finally:
tpe.shutdown(wait=True)
if not interrupt_trigger[0]:
raise KeyboardInterrupt()
return result
def download_and_append_fragments(
self, ctx, fragments, info_dict, *, pack_func=None, finish_func=None,
tpe=None, interrupt_trigger=None):
if not interrupt_trigger:
interrupt_trigger = (True, )
fragment_retries = self.params.get('fragment_retries', 0)
is_fatal = (
((lambda _: False) if info_dict.get('is_live') else (lambda idx: idx == 0))
if self.params.get('skip_unavailable_fragments', True) else (lambda _: True))
if not pack_func:
pack_func = lambda frag_content, _: frag_content
def download_fragment(fragment, ctx):
frag_index = ctx['fragment_index'] = fragment['frag_index']
ctx['last_error'] = None
if not interrupt_trigger[0]:
return False, frag_index
headers = info_dict.get('http_headers', {}).copy()
byte_range = fragment.get('byte_range')
if byte_range:
headers['Range'] = 'bytes=%d-%d' % (byte_range['start'], byte_range['end'] - 1)
# Never skip the first fragment
fatal = is_fatal(fragment.get('index') or (frag_index - 1))
count, frag_content = 0, None
while count <= fragment_retries:
try:
success, frag_content = self._download_fragment(ctx, fragment['url'], info_dict, headers)
if not success:
return False, frag_index
break
except (compat_urllib_error.HTTPError, http.client.IncompleteRead) as err:
# Unavailable (possibly temporary) fragments may be served.
# First we try to retry then either skip or abort.
# See https://github.com/ytdl-org/youtube-dl/issues/10165,
# https://github.com/ytdl-org/youtube-dl/issues/10448).
count += 1
ctx['last_error'] = err
if count <= fragment_retries:
self.report_retry_fragment(err, frag_index, count, fragment_retries)
except DownloadError:
# Don't retry fragment if error occurred during HTTP downloading
# itself since it has own retry settings
if not fatal:
break
raise
if count > fragment_retries:
if not fatal:
return False, frag_index
ctx['dest_stream'].close()
self.report_error('Giving up after %s fragment retries' % fragment_retries)
return False, frag_index
return frag_content, frag_index
def append_fragment(frag_content, frag_index, ctx):
if not frag_content:
if not is_fatal(frag_index - 1):
self.report_skip_fragment(frag_index, 'fragment not found')
return True
else:
ctx['dest_stream'].close()
self.report_error(
'fragment %s not found, unable to continue' % frag_index)
return False
self._append_fragment(ctx, pack_func(frag_content, frag_index))
return True
decrypt_fragment = self.decrypter(info_dict)
max_workers = math.ceil(
self.params.get('concurrent_fragment_downloads', 1) / ctx.get('max_progress', 1))
if can_threaded_download and max_workers > 1:
def _download_fragment(fragment):
ctx_copy = ctx.copy()
frag_content, frag_index = download_fragment(fragment, ctx_copy)
return fragment, frag_content, frag_index, ctx_copy.get('fragment_filename_sanitized')
self.report_warning('The download speed shown is only of one thread. This is a known issue and patches are welcome')
with tpe or concurrent.futures.ThreadPoolExecutor(max_workers) as pool:
for fragment, frag_content, frag_index, frag_filename in pool.map(_download_fragment, fragments):
if not interrupt_trigger[0]:
break
ctx['fragment_filename_sanitized'] = frag_filename
ctx['fragment_index'] = frag_index
result = append_fragment(decrypt_fragment(fragment, frag_content), frag_index, ctx)
if not result:
return False
else:
for fragment in fragments:
if not interrupt_trigger[0]:
break
frag_content, frag_index = download_fragment(fragment, ctx)
result = append_fragment(decrypt_fragment(fragment, frag_content), frag_index, ctx)
if not result:
return False
if finish_func is not None:
ctx['dest_stream'].write(finish_func())
ctx['dest_stream'].flush()
self._finish_frag_download(ctx, info_dict)
return True

358
plugins/youtube_download/yt_dlp/downloader/hls.py Normal file
View File

@ -0,0 +1,358 @@
from __future__ import unicode_literals
import re
import io
import binascii
from ..downloader import get_suitable_downloader
from .fragment import FragmentFD
from .external import FFmpegFD
from ..compat import (
compat_pycrypto_AES,
compat_urlparse,
)
from ..utils import (
parse_m3u8_attributes,
update_url_query,
bug_reports_message,
)
from .. import webvtt
class HlsFD(FragmentFD):
"""
Download segments in a m3u8 manifest. External downloaders can take over
the fragment downloads by supporting the 'm3u8_frag_urls' protocol and
re-defining 'supports_manifest' function
"""
FD_NAME = 'hlsnative'
@staticmethod
def can_download(manifest, info_dict, allow_unplayable_formats=False):
UNSUPPORTED_FEATURES = [
# r'#EXT-X-BYTERANGE', # playlists composed of byte ranges of media files [2]
# Live streams heuristic does not always work (e.g. geo restricted to Germany
# http://hls-geo.daserste.de/i/videoportal/Film/c_620000/622873/format,716451,716457,716450,716458,716459,.mp4.csmil/index_4_av.m3u8?null=0)
# r'#EXT-X-MEDIA-SEQUENCE:(?!0$)', # live streams [3]
# This heuristic also is not correct since segments may not be appended as well.
# Twitch vods of finished streams have EXT-X-PLAYLIST-TYPE:EVENT despite
# no segments will definitely be appended to the end of the playlist.
# r'#EXT-X-PLAYLIST-TYPE:EVENT', # media segments may be appended to the end of
# # event media playlists [4]
# r'#EXT-X-MAP:', # media initialization [5]
# 1. https://tools.ietf.org/html/draft-pantos-http-live-streaming-17#section-4.3.2.4
# 2. https://tools.ietf.org/html/draft-pantos-http-live-streaming-17#section-4.3.2.2
# 3. https://tools.ietf.org/html/draft-pantos-http-live-streaming-17#section-4.3.3.2
# 4. https://tools.ietf.org/html/draft-pantos-http-live-streaming-17#section-4.3.3.5
# 5. https://tools.ietf.org/html/draft-pantos-http-live-streaming-17#section-4.3.2.5
]
if not allow_unplayable_formats:
UNSUPPORTED_FEATURES += [
r'#EXT-X-KEY:METHOD=(?!NONE|AES-128)', # encrypted streams [1]
]
def check_results():
yield not info_dict.get('is_live')
for feature in UNSUPPORTED_FEATURES:
yield not re.search(feature, manifest)
return all(check_results())
def real_download(self, filename, info_dict):
man_url = info_dict['url']
self.to_screen('[%s] Downloading m3u8 manifest' % self.FD_NAME)
urlh = self.ydl.urlopen(self._prepare_url(info_dict, man_url))
man_url = urlh.geturl()
s = urlh.read().decode('utf-8', 'ignore')
can_download, message = self.can_download(s, info_dict, self.params.get('allow_unplayable_formats')), None
if can_download and not compat_pycrypto_AES and '#EXT-X-KEY:METHOD=AES-128' in s:
if FFmpegFD.available():
can_download, message = False, 'The stream has AES-128 encryption and pycryptodomex is not available'
else:
message = ('The stream has AES-128 encryption and neither ffmpeg nor pycryptodomex are available; '
'Decryption will be performed natively, but will be extremely slow')
if not can_download:
has_drm = re.search('|'.join([
r'#EXT-X-FAXS-CM:', # Adobe Flash Access
r'#EXT-X-(?:SESSION-)?KEY:.*?URI="skd://', # Apple FairPlay
]), s)
if has_drm and not self.params.get('allow_unplayable_formats'):
self.report_error(
'This video is DRM protected; Try selecting another format with --format or '
'add --check-formats to automatically fallback to the next best format')
return False
message = message or 'Unsupported features have been detected'
fd = FFmpegFD(self.ydl, self.params)
self.report_warning(f'{message}; extraction will be delegated to {fd.get_basename()}')
return fd.real_download(filename, info_dict)
elif message:
self.report_warning(message)
is_webvtt = info_dict['ext'] == 'vtt'
if is_webvtt:
real_downloader = None # Packing the fragments is not currently supported for external downloader
else:
real_downloader = get_suitable_downloader(
info_dict, self.params, None, protocol='m3u8_frag_urls', to_stdout=(filename == '-'))
if real_downloader and not real_downloader.supports_manifest(s):
real_downloader = None
if real_downloader:
self.to_screen(
'[%s] Fragment downloads will be delegated to %s' % (self.FD_NAME, real_downloader.get_basename()))
def is_ad_fragment_start(s):
return (s.startswith('#ANVATO-SEGMENT-INFO') and 'type=ad' in s
or s.startswith('#UPLYNK-SEGMENT') and s.endswith(',ad'))
def is_ad_fragment_end(s):
return (s.startswith('#ANVATO-SEGMENT-INFO') and 'type=master' in s
or s.startswith('#UPLYNK-SEGMENT') and s.endswith(',segment'))
fragments = []
media_frags = 0
ad_frags = 0
ad_frag_next = False
for line in s.splitlines():
line = line.strip()
if not line:
continue
if line.startswith('#'):
if is_ad_fragment_start(line):
ad_frag_next = True
elif is_ad_fragment_end(line):
ad_frag_next = False
continue
if ad_frag_next:
ad_frags += 1
continue
media_frags += 1
ctx = {
'filename': filename,
'total_frags': media_frags,
'ad_frags': ad_frags,
}
if real_downloader:
self._prepare_external_frag_download(ctx)
else:
self._prepare_and_start_frag_download(ctx, info_dict)
extra_state = ctx.setdefault('extra_state', {})
format_index = info_dict.get('format_index')
extra_query = None
extra_param_to_segment_url = info_dict.get('extra_param_to_segment_url')
if extra_param_to_segment_url:
extra_query = compat_urlparse.parse_qs(extra_param_to_segment_url)
i = 0
media_sequence = 0
decrypt_info = {'METHOD': 'NONE'}
byte_range = {}
discontinuity_count = 0
frag_index = 0
ad_frag_next = False
for line in s.splitlines():
line = line.strip()
if line:
if not line.startswith('#'):
if format_index and discontinuity_count != format_index:
continue
if ad_frag_next:
continue
frag_index += 1
if frag_index <= ctx['fragment_index']:
continue
frag_url = (
line
if re.match(r'^https?://', line)
else compat_urlparse.urljoin(man_url, line))
if extra_query:
frag_url = update_url_query(frag_url, extra_query)
fragments.append({
'frag_index': frag_index,
'url': frag_url,
'decrypt_info': decrypt_info,
'byte_range': byte_range,
'media_sequence': media_sequence,
})
media_sequence += 1
elif line.startswith('#EXT-X-MAP'):
if format_index and discontinuity_count != format_index:
continue
if frag_index > 0:
self.report_error(
'Initialization fragment found after media fragments, unable to download')
return False
frag_index += 1
map_info = parse_m3u8_attributes(line[11:])
frag_url = (
map_info.get('URI')
if re.match(r'^https?://', map_info.get('URI'))
else compat_urlparse.urljoin(man_url, map_info.get('URI')))
if extra_query:
frag_url = update_url_query(frag_url, extra_query)
fragments.append({
'frag_index': frag_index,
'url': frag_url,
'decrypt_info': decrypt_info,
'byte_range': byte_range,
'media_sequence': media_sequence
})
media_sequence += 1
if map_info.get('BYTERANGE'):
splitted_byte_range = map_info.get('BYTERANGE').split('@')
sub_range_start = int(splitted_byte_range[1]) if len(splitted_byte_range) == 2 else byte_range['end']
byte_range = {
'start': sub_range_start,
'end': sub_range_start + int(splitted_byte_range[0]),
}
elif line.startswith('#EXT-X-KEY'):
decrypt_url = decrypt_info.get('URI')
decrypt_info = parse_m3u8_attributes(line[11:])
if decrypt_info['METHOD'] == 'AES-128':
if 'IV' in decrypt_info:
decrypt_info['IV'] = binascii.unhexlify(decrypt_info['IV'][2:].zfill(32))
if not re.match(r'^https?://', decrypt_info['URI']):
decrypt_info['URI'] = compat_urlparse.urljoin(
man_url, decrypt_info['URI'])
if extra_query:
decrypt_info['URI'] = update_url_query(decrypt_info['URI'], extra_query)
if decrypt_url != decrypt_info['URI']:
decrypt_info['KEY'] = None
elif line.startswith('#EXT-X-MEDIA-SEQUENCE'):
media_sequence = int(line[22:])
elif line.startswith('#EXT-X-BYTERANGE'):
splitted_byte_range = line[17:].split('@')
sub_range_start = int(splitted_byte_range[1]) if len(splitted_byte_range) == 2 else byte_range['end']
byte_range = {
'start': sub_range_start,
'end': sub_range_start + int(splitted_byte_range[0]),
}
elif is_ad_fragment_start(line):
ad_frag_next = True
elif is_ad_fragment_end(line):
ad_frag_next = False
elif line.startswith('#EXT-X-DISCONTINUITY'):
discontinuity_count += 1
i += 1
# We only download the first fragment during the test
if self.params.get('test', False):
fragments = [fragments[0] if fragments else None]
if real_downloader:
info_dict['fragments'] = fragments
fd = real_downloader(self.ydl, self.params)
# TODO: Make progress updates work without hooking twice
# for ph in self._progress_hooks:
# fd.add_progress_hook(ph)
return fd.real_download(filename, info_dict)
if is_webvtt:
def pack_fragment(frag_content, frag_index):
output = io.StringIO()
adjust = 0
overflow = False
mpegts_last = None
for block in webvtt.parse_fragment(frag_content):
if isinstance(block, webvtt.CueBlock):
extra_state['webvtt_mpegts_last'] = mpegts_last
if overflow:
extra_state['webvtt_mpegts_adjust'] += 1
overflow = False
block.start += adjust
block.end += adjust
dedup_window = extra_state.setdefault('webvtt_dedup_window', [])
ready = []
i = 0
is_new = True
while i < len(dedup_window):
wcue = dedup_window[i]
wblock = webvtt.CueBlock.from_json(wcue)
i += 1
if wblock.hinges(block):
wcue['end'] = block.end
is_new = False
continue
if wblock == block:
is_new = False
continue
if wblock.end > block.start:
continue
ready.append(wblock)
i -= 1
del dedup_window[i]
if is_new:
dedup_window.append(block.as_json)
for block in ready:
block.write_into(output)
# we only emit cues once they fall out of the duplicate window
continue
elif isinstance(block, webvtt.Magic):
# take care of MPEG PES timestamp overflow
if block.mpegts is None:
block.mpegts = 0
extra_state.setdefault('webvtt_mpegts_adjust', 0)
block.mpegts += extra_state['webvtt_mpegts_adjust'] << 33
if block.mpegts < extra_state.get('webvtt_mpegts_last', 0):
overflow = True
block.mpegts += 1 << 33
mpegts_last = block.mpegts
if frag_index == 1:
extra_state['webvtt_mpegts'] = block.mpegts or 0
extra_state['webvtt_local'] = block.local or 0
# XXX: block.local = block.mpegts = None ?
else:
if block.mpegts is not None and block.local is not None:
adjust = (
(block.mpegts - extra_state.get('webvtt_mpegts', 0))
- (block.local - extra_state.get('webvtt_local', 0))
)
continue
elif isinstance(block, webvtt.HeaderBlock):
if frag_index != 1:
# XXX: this should probably be silent as well
# or verify that all segments contain the same data
self.report_warning(bug_reports_message(
'Discarding a %s block found in the middle of the stream; '
'if the subtitles display incorrectly,'
% (type(block).__name__)))
continue
block.write_into(output)
return output.getvalue().encode('utf-8')
def fin_fragments():
dedup_window = extra_state.get('webvtt_dedup_window')
if not dedup_window:
return b''
output = io.StringIO()
for cue in dedup_window:
webvtt.CueBlock.from_json(cue).write_into(output)
return output.getvalue().encode('utf-8')
self.download_and_append_fragments(
ctx, fragments, info_dict, pack_func=pack_fragment, finish_func=fin_fragments)
else:
return self.download_and_append_fragments(ctx, fragments, info_dict)

386
plugins/youtube_download/yt_dlp/downloader/http.py Normal file
View File

@ -0,0 +1,386 @@
from __future__ import unicode_literals
import errno
import os
import socket
import time
import random
import re
from .common import FileDownloader
from ..compat import (
compat_str,
compat_urllib_error,
)
from ..utils import (
ContentTooShortError,
encodeFilename,
int_or_none,
sanitized_Request,
ThrottledDownload,
write_xattr,
XAttrMetadataError,
XAttrUnavailableError,
)
class HttpFD(FileDownloader):
def real_download(self, filename, info_dict):
url = info_dict['url']
request_data = info_dict.get('request_data', None)
class DownloadContext(dict):
__getattr__ = dict.get
__setattr__ = dict.__setitem__
__delattr__ = dict.__delitem__
ctx = DownloadContext()
ctx.filename = filename
ctx.tmpfilename = self.temp_name(filename)
ctx.stream = None
# Do not include the Accept-Encoding header
headers = {'Youtubedl-no-compression': 'True'}
add_headers = info_dict.get('http_headers')
if add_headers:
headers.update(add_headers)
is_test = self.params.get('test', False)
chunk_size = self._TEST_FILE_SIZE if is_test else (
self.params.get('http_chunk_size')
or info_dict.get('downloader_options', {}).get('http_chunk_size')
or 0)
ctx.open_mode = 'wb'
ctx.resume_len = 0
ctx.data_len = None
ctx.block_size = self.params.get('buffersize', 1024)
ctx.start_time = time.time()
ctx.chunk_size = None
throttle_start = None
if self.params.get('continuedl', True):
# Establish possible resume length
if os.path.isfile(encodeFilename(ctx.tmpfilename)):
ctx.resume_len = os.path.getsize(
encodeFilename(ctx.tmpfilename))
ctx.is_resume = ctx.resume_len > 0
count = 0
retries = self.params.get('retries', 0)
class SucceedDownload(Exception):
pass
class RetryDownload(Exception):
def __init__(self, source_error):
self.source_error = source_error
class NextFragment(Exception):
pass
def set_range(req, start, end):
range_header = 'bytes=%d-' % start
if end:
range_header += compat_str(end)
req.add_header('Range', range_header)
def establish_connection():
ctx.chunk_size = (random.randint(int(chunk_size * 0.95), chunk_size)
if not is_test and chunk_size else chunk_size)
if ctx.resume_len > 0:
range_start = ctx.resume_len
if ctx.is_resume:
self.report_resuming_byte(ctx.resume_len)
ctx.open_mode = 'ab'
elif ctx.chunk_size > 0:
range_start = 0
else:
range_start = None
ctx.is_resume = False
range_end = range_start + ctx.chunk_size - 1 if ctx.chunk_size else None
if range_end and ctx.data_len is not None and range_end >= ctx.data_len:
range_end = ctx.data_len - 1
has_range = range_start is not None
ctx.has_range = has_range
request = sanitized_Request(url, request_data, headers)
if has_range:
set_range(request, range_start, range_end)
# Establish connection
try:
try:
ctx.data = self.ydl.urlopen(request)
except (compat_urllib_error.URLError, ) as err:
# reason may not be available, e.g. for urllib2.HTTPError on python 2.6
reason = getattr(err, 'reason', None)
if isinstance(reason, socket.timeout):
raise RetryDownload(err)
raise err
# When trying to resume, Content-Range HTTP header of response has to be checked
# to match the value of requested Range HTTP header. This is due to a webservers
# that don't support resuming and serve a whole file with no Content-Range
# set in response despite of requested Range (see
# https://github.com/ytdl-org/youtube-dl/issues/6057#issuecomment-126129799)
if has_range:
content_range = ctx.data.headers.get('Content-Range')
if content_range:
content_range_m = re.search(r'bytes (\d+)-(\d+)?(?:/(\d+))?', content_range)
# Content-Range is present and matches requested Range, resume is possible
if content_range_m:
if range_start == int(content_range_m.group(1)):
content_range_end = int_or_none(content_range_m.group(2))
content_len = int_or_none(content_range_m.group(3))
accept_content_len = (
# Non-chunked download
not ctx.chunk_size
# Chunked download and requested piece or
# its part is promised to be served
or content_range_end == range_end
or content_len < range_end)
if accept_content_len:
ctx.data_len = content_len
return
# Content-Range is either not present or invalid. Assuming remote webserver is
# trying to send the whole file, resume is not possible, so wiping the local file
# and performing entire redownload
self.report_unable_to_resume()
ctx.resume_len = 0
ctx.open_mode = 'wb'
ctx.data_len = int_or_none(ctx.data.info().get('Content-length', None))
return
except (compat_urllib_error.HTTPError, ) as err:
if err.code == 416:
# Unable to resume (requested range not satisfiable)
try:
# Open the connection again without the range header
ctx.data = self.ydl.urlopen(
sanitized_Request(url, request_data, headers))
content_length = ctx.data.info()['Content-Length']
except (compat_urllib_error.HTTPError, ) as err:
if err.code < 500 or err.code >= 600:
raise
else:
# Examine the reported length
if (content_length is not None
and (ctx.resume_len - 100 < int(content_length) < ctx.resume_len + 100)):
# The file had already been fully downloaded.
# Explanation to the above condition: in issue #175 it was revealed that
# YouTube sometimes adds or removes a few bytes from the end of the file,
# changing the file size slightly and causing problems for some users. So
# I decided to implement a suggested change and consider the file
# completely downloaded if the file size differs less than 100 bytes from
# the one in the hard drive.
self.report_file_already_downloaded(ctx.filename)
self.try_rename(ctx.tmpfilename, ctx.filename)
self._hook_progress({
'filename': ctx.filename,
'status': 'finished',
'downloaded_bytes': ctx.resume_len,
'total_bytes': ctx.resume_len,
}, info_dict)
raise SucceedDownload()
else:
# The length does not match, we start the download over
self.report_unable_to_resume()
ctx.resume_len = 0
ctx.open_mode = 'wb'
return
elif err.code < 500 or err.code >= 600:
# Unexpected HTTP error
raise
raise RetryDownload(err)
except socket.timeout as err:
raise RetryDownload(err)
except socket.error as err:
if err.errno in (errno.ECONNRESET, errno.ETIMEDOUT):
# Connection reset is no problem, just retry
raise RetryDownload(err)
raise
def download():
nonlocal throttle_start
data_len = ctx.data.info().get('Content-length', None)
# Range HTTP header may be ignored/unsupported by a webserver
# (e.g. extractor/scivee.py, extractor/bambuser.py).
# However, for a test we still would like to download just a piece of a file.
# To achieve this we limit data_len to _TEST_FILE_SIZE and manually control
# block size when downloading a file.
if is_test and (data_len is None or int(data_len) > self._TEST_FILE_SIZE):
data_len = self._TEST_FILE_SIZE
if data_len is not None:
data_len = int(data_len) + ctx.resume_len
min_data_len = self.params.get('min_filesize')
max_data_len = self.params.get('max_filesize')
if min_data_len is not None and data_len < min_data_len:
self.to_screen('\r[download] File is smaller than min-filesize (%s bytes < %s bytes). Aborting.' % (data_len, min_data_len))
return False
if max_data_len is not None and data_len > max_data_len:
self.to_screen('\r[download] File is larger than max-filesize (%s bytes > %s bytes). Aborting.' % (data_len, max_data_len))
return False
byte_counter = 0 + ctx.resume_len
block_size = ctx.block_size
start = time.time()
# measure time over whole while-loop, so slow_down() and best_block_size() work together properly
now = None # needed for slow_down() in the first loop run
before = start # start measuring
def retry(e):
to_stdout = ctx.tmpfilename == '-'
if ctx.stream is not None:
if not to_stdout:
ctx.stream.close()
ctx.stream = None
ctx.resume_len = byte_counter if to_stdout else os.path.getsize(encodeFilename(ctx.tmpfilename))
raise RetryDownload(e)
while True:
try:
# Download and write
data_block = ctx.data.read(block_size if not is_test else min(block_size, data_len - byte_counter))
# socket.timeout is a subclass of socket.error but may not have
# errno set
except socket.timeout as e:
retry(e)
except socket.error as e:
# SSLError on python 2 (inherits socket.error) may have
# no errno set but this error message
if e.errno in (errno.ECONNRESET, errno.ETIMEDOUT) or getattr(e, 'message', None) == 'The read operation timed out':
retry(e)
raise
byte_counter += len(data_block)
# exit loop when download is finished
if len(data_block) == 0:
break
# Open destination file just in time
if ctx.stream is None:
try:
ctx.stream, ctx.tmpfilename = self.sanitize_open(
ctx.tmpfilename, ctx.open_mode)
assert ctx.stream is not None
ctx.filename = self.undo_temp_name(ctx.tmpfilename)
self.report_destination(ctx.filename)
except (OSError, IOError) as err:
self.report_error('unable to open for writing: %s' % str(err))
return False
if self.params.get('xattr_set_filesize', False) and data_len is not None:
try:
write_xattr(ctx.tmpfilename, 'user.ytdl.filesize', str(data_len).encode('utf-8'))
except (XAttrUnavailableError, XAttrMetadataError) as err:
self.report_error('unable to set filesize xattr: %s' % str(err))
try:
ctx.stream.write(data_block)
except (IOError, OSError) as err:
self.to_stderr('\n')
self.report_error('unable to write data: %s' % str(err))
return False
# Apply rate limit
self.slow_down(start, now, byte_counter - ctx.resume_len)
# end measuring of one loop run
now = time.time()
after = now
# Adjust block size
if not self.params.get('noresizebuffer', False):
block_size = self.best_block_size(after - before, len(data_block))
before = after
# Progress message
speed = self.calc_speed(start, now, byte_counter - ctx.resume_len)
if ctx.data_len is None:
eta = None
else:
eta = self.calc_eta(start, time.time(), ctx.data_len - ctx.resume_len, byte_counter - ctx.resume_len)
self._hook_progress({
'status': 'downloading',
'downloaded_bytes': byte_counter,
'total_bytes': ctx.data_len,
'tmpfilename': ctx.tmpfilename,
'filename': ctx.filename,
'eta': eta,
'speed': speed,
'elapsed': now - ctx.start_time,
'ctx_id': info_dict.get('ctx_id'),
}, info_dict)
if data_len is not None and byte_counter == data_len:
break
if speed and speed < (self.params.get('throttledratelimit') or 0):
# The speed must stay below the limit for 3 seconds
# This prevents raising error when the speed temporarily goes down
if throttle_start is None:
throttle_start = now
elif now - throttle_start > 3:
if ctx.stream is not None and ctx.tmpfilename != '-':
ctx.stream.close()
raise ThrottledDownload()
elif speed:
throttle_start = None
if not is_test and ctx.chunk_size and ctx.data_len is not None and byte_counter < ctx.data_len:
ctx.resume_len = byte_counter
# ctx.block_size = block_size
raise NextFragment()
if ctx.stream is None:
self.to_stderr('\n')
self.report_error('Did not get any data blocks')
return False
if ctx.tmpfilename != '-':
ctx.stream.close()
if data_len is not None and byte_counter != data_len:
err = ContentTooShortError(byte_counter, int(data_len))
if count <= retries:
retry(err)
raise err
self.try_rename(ctx.tmpfilename, ctx.filename)
# Update file modification time
if self.params.get('updatetime', True):
info_dict['filetime'] = self.try_utime(ctx.filename, ctx.data.info().get('last-modified', None))
self._hook_progress({
'downloaded_bytes': byte_counter,
'total_bytes': byte_counter,
'filename': ctx.filename,
'status': 'finished',
'elapsed': time.time() - ctx.start_time,
'ctx_id': info_dict.get('ctx_id'),
}, info_dict)
return True
while count <= retries:
try:
establish_connection()
return download()
except RetryDownload as e:
count += 1
if count <= retries:
self.report_retry(e.source_error, count, retries)
else:
self.to_screen(f'[download] Got server HTTP error: {e.source_error}')
continue
except NextFragment:
continue
except SucceedDownload:
return True
self.report_error('giving up after %s retries' % retries)
return False

289
plugins/youtube_download/yt_dlp/downloader/ism.py Normal file
View File

@ -0,0 +1,289 @@
from __future__ import unicode_literals
import time
import binascii
import io
from .fragment import FragmentFD
from ..compat import (
compat_Struct,
compat_urllib_error,
)
u8 = compat_Struct('>B')
u88 = compat_Struct('>Bx')
u16 = compat_Struct('>H')
u1616 = compat_Struct('>Hxx')
u32 = compat_Struct('>I')
u64 = compat_Struct('>Q')
s88 = compat_Struct('>bx')
s16 = compat_Struct('>h')
s1616 = compat_Struct('>hxx')
s32 = compat_Struct('>i')
unity_matrix = (s32.pack(0x10000) + s32.pack(0) * 3) * 2 + s32.pack(0x40000000)
TRACK_ENABLED = 0x1
TRACK_IN_MOVIE = 0x2
TRACK_IN_PREVIEW = 0x4
SELF_CONTAINED = 0x1
def box(box_type, payload):
return u32.pack(8 + len(payload)) + box_type + payload
def full_box(box_type, version, flags, payload):
return box(box_type, u8.pack(version) + u32.pack(flags)[1:] + payload)
def write_piff_header(stream, params):
track_id = params['track_id']
fourcc = params['fourcc']
duration = params['duration']
timescale = params.get('timescale', 10000000)
language = params.get('language', 'und')
height = params.get('height', 0)
width = params.get('width', 0)
stream_type = params['stream_type']
creation_time = modification_time = int(time.time())
ftyp_payload = b'isml' # major brand
ftyp_payload += u32.pack(1) # minor version
ftyp_payload += b'piff' + b'iso2' # compatible brands
stream.write(box(b'ftyp', ftyp_payload)) # File Type Box
mvhd_payload = u64.pack(creation_time)
mvhd_payload += u64.pack(modification_time)
mvhd_payload += u32.pack(timescale)
mvhd_payload += u64.pack(duration)
mvhd_payload += s1616.pack(1) # rate
mvhd_payload += s88.pack(1) # volume
mvhd_payload += u16.pack(0) # reserved
mvhd_payload += u32.pack(0) * 2 # reserved
mvhd_payload += unity_matrix
mvhd_payload += u32.pack(0) * 6 # pre defined
mvhd_payload += u32.pack(0xffffffff) # next track id
moov_payload = full_box(b'mvhd', 1, 0, mvhd_payload) # Movie Header Box
tkhd_payload = u64.pack(creation_time)
tkhd_payload += u64.pack(modification_time)
tkhd_payload += u32.pack(track_id) # track id
tkhd_payload += u32.pack(0) # reserved
tkhd_payload += u64.pack(duration)
tkhd_payload += u32.pack(0) * 2 # reserved
tkhd_payload += s16.pack(0) # layer
tkhd_payload += s16.pack(0) # alternate group
tkhd_payload += s88.pack(1 if stream_type == 'audio' else 0) # volume
tkhd_payload += u16.pack(0) # reserved
tkhd_payload += unity_matrix
tkhd_payload += u1616.pack(width)
tkhd_payload += u1616.pack(height)
trak_payload = full_box(b'tkhd', 1, TRACK_ENABLED | TRACK_IN_MOVIE | TRACK_IN_PREVIEW, tkhd_payload) # Track Header Box
mdhd_payload = u64.pack(creation_time)
mdhd_payload += u64.pack(modification_time)
mdhd_payload += u32.pack(timescale)
mdhd_payload += u64.pack(duration)
mdhd_payload += u16.pack(((ord(language[0]) - 0x60) << 10) | ((ord(language[1]) - 0x60) << 5) | (ord(language[2]) - 0x60))
mdhd_payload += u16.pack(0) # pre defined
mdia_payload = full_box(b'mdhd', 1, 0, mdhd_payload) # Media Header Box
hdlr_payload = u32.pack(0) # pre defined
if stream_type == 'audio': # handler type
hdlr_payload += b'soun'
hdlr_payload += u32.pack(0) * 3 # reserved
hdlr_payload += b'SoundHandler\0' # name
elif stream_type == 'video':
hdlr_payload += b'vide'
hdlr_payload += u32.pack(0) * 3 # reserved
hdlr_payload += b'VideoHandler\0' # name
elif stream_type == 'text':
hdlr_payload += b'subt'
hdlr_payload += u32.pack(0) * 3 # reserved
hdlr_payload += b'SubtitleHandler\0' # name
else:
assert False
mdia_payload += full_box(b'hdlr', 0, 0, hdlr_payload) # Handler Reference Box
if stream_type == 'audio':
smhd_payload = s88.pack(0) # balance
smhd_payload += u16.pack(0) # reserved
media_header_box = full_box(b'smhd', 0, 0, smhd_payload) # Sound Media Header
elif stream_type == 'video':
vmhd_payload = u16.pack(0) # graphics mode
vmhd_payload += u16.pack(0) * 3 # opcolor
media_header_box = full_box(b'vmhd', 0, 1, vmhd_payload) # Video Media Header
elif stream_type == 'text':
media_header_box = full_box(b'sthd', 0, 0, b'') # Subtitle Media Header
else:
assert False
minf_payload = media_header_box
dref_payload = u32.pack(1) # entry count
dref_payload += full_box(b'url ', 0, SELF_CONTAINED, b'') # Data Entry URL Box
dinf_payload = full_box(b'dref', 0, 0, dref_payload) # Data Reference Box
minf_payload += box(b'dinf', dinf_payload) # Data Information Box
stsd_payload = u32.pack(1) # entry count
sample_entry_payload = u8.pack(0) * 6 # reserved
sample_entry_payload += u16.pack(1) # data reference index
if stream_type == 'audio':
sample_entry_payload += u32.pack(0) * 2 # reserved
sample_entry_payload += u16.pack(params.get('channels', 2))
sample_entry_payload += u16.pack(params.get('bits_per_sample', 16))
sample_entry_payload += u16.pack(0) # pre defined
sample_entry_payload += u16.pack(0) # reserved
sample_entry_payload += u1616.pack(params['sampling_rate'])
if fourcc == 'AACL':
sample_entry_box = box(b'mp4a', sample_entry_payload)
elif stream_type == 'video':
sample_entry_payload += u16.pack(0) # pre defined
sample_entry_payload += u16.pack(0) # reserved
sample_entry_payload += u32.pack(0) * 3 # pre defined
sample_entry_payload += u16.pack(width)
sample_entry_payload += u16.pack(height)
sample_entry_payload += u1616.pack(0x48) # horiz resolution 72 dpi
sample_entry_payload += u1616.pack(0x48) # vert resolution 72 dpi
sample_entry_payload += u32.pack(0) # reserved
sample_entry_payload += u16.pack(1) # frame count
sample_entry_payload += u8.pack(0) * 32 # compressor name
sample_entry_payload += u16.pack(0x18) # depth
sample_entry_payload += s16.pack(-1) # pre defined
codec_private_data = binascii.unhexlify(params['codec_private_data'].encode('utf-8'))
if fourcc in ('H264', 'AVC1'):
sps, pps = codec_private_data.split(u32.pack(1))[1:]
avcc_payload = u8.pack(1) # configuration version
avcc_payload += sps[1:4] # avc profile indication + profile compatibility + avc level indication
avcc_payload += u8.pack(0xfc | (params.get('nal_unit_length_field', 4) - 1)) # complete representation (1) + reserved (11111) + length size minus one
avcc_payload += u8.pack(1) # reserved (0) + number of sps (0000001)
avcc_payload += u16.pack(len(sps))
avcc_payload += sps
avcc_payload += u8.pack(1) # number of pps
avcc_payload += u16.pack(len(pps))
avcc_payload += pps
sample_entry_payload += box(b'avcC', avcc_payload) # AVC Decoder Configuration Record
sample_entry_box = box(b'avc1', sample_entry_payload) # AVC Simple Entry
else:
assert False
elif stream_type == 'text':
if fourcc == 'TTML':
sample_entry_payload += b'http://www.w3.org/ns/ttml\0' # namespace
sample_entry_payload += b'\0' # schema location
sample_entry_payload += b'\0' # auxilary mime types(??)
sample_entry_box = box(b'stpp', sample_entry_payload)
else:
assert False
else:
assert False
stsd_payload += sample_entry_box
stbl_payload = full_box(b'stsd', 0, 0, stsd_payload) # Sample Description Box
stts_payload = u32.pack(0) # entry count
stbl_payload += full_box(b'stts', 0, 0, stts_payload) # Decoding Time to Sample Box
stsc_payload = u32.pack(0) # entry count
stbl_payload += full_box(b'stsc', 0, 0, stsc_payload) # Sample To Chunk Box
stco_payload = u32.pack(0) # entry count
stbl_payload += full_box(b'stco', 0, 0, stco_payload) # Chunk Offset Box
minf_payload += box(b'stbl', stbl_payload) # Sample Table Box
mdia_payload += box(b'minf', minf_payload) # Media Information Box
trak_payload += box(b'mdia', mdia_payload) # Media Box
moov_payload += box(b'trak', trak_payload) # Track Box
mehd_payload = u64.pack(duration)
mvex_payload = full_box(b'mehd', 1, 0, mehd_payload) # Movie Extends Header Box
trex_payload = u32.pack(track_id) # track id
trex_payload += u32.pack(1) # default sample description index
trex_payload += u32.pack(0) # default sample duration
trex_payload += u32.pack(0) # default sample size
trex_payload += u32.pack(0) # default sample flags
mvex_payload += full_box(b'trex', 0, 0, trex_payload) # Track Extends Box
moov_payload += box(b'mvex', mvex_payload) # Movie Extends Box
stream.write(box(b'moov', moov_payload)) # Movie Box
def extract_box_data(data, box_sequence):
data_reader = io.BytesIO(data)
while True:
box_size = u32.unpack(data_reader.read(4))[0]
box_type = data_reader.read(4)
if box_type == box_sequence[0]:
box_data = data_reader.read(box_size - 8)
if len(box_sequence) == 1:
return box_data
return extract_box_data(box_data, box_sequence[1:])
data_reader.seek(box_size - 8, 1)
class IsmFD(FragmentFD):
"""
Download segments in a ISM manifest
"""
FD_NAME = 'ism'
def real_download(self, filename, info_dict):
segments = info_dict['fragments'][:1] if self.params.get(
'test', False) else info_dict['fragments']
ctx = {
'filename': filename,
'total_frags': len(segments),
}
self._prepare_and_start_frag_download(ctx, info_dict)
extra_state = ctx.setdefault('extra_state', {
'ism_track_written': False,
})
fragment_retries = self.params.get('fragment_retries', 0)
skip_unavailable_fragments = self.params.get('skip_unavailable_fragments', True)
frag_index = 0
for i, segment in enumerate(segments):
frag_index += 1
if frag_index <= ctx['fragment_index']:
continue
count = 0
while count <= fragment_retries:
try:
success, frag_content = self._download_fragment(ctx, segment['url'], info_dict)
if not success:
return False
if not extra_state['ism_track_written']:
tfhd_data = extract_box_data(frag_content, [b'moof', b'traf', b'tfhd'])
info_dict['_download_params']['track_id'] = u32.unpack(tfhd_data[4:8])[0]
write_piff_header(ctx['dest_stream'], info_dict['_download_params'])
extra_state['ism_track_written'] = True
self._append_fragment(ctx, frag_content)
break
except compat_urllib_error.HTTPError as err:
count += 1
if count <= fragment_retries:
self.report_retry_fragment(err, frag_index, count, fragment_retries)
if count > fragment_retries:
if skip_unavailable_fragments:
self.report_skip_fragment(frag_index)
continue
self.report_error('giving up after %s fragment retries' % fragment_retries)
return False
self._finish_frag_download(ctx, info_dict)
return True

202
plugins/youtube_download/yt_dlp/downloader/mhtml.py Normal file
View File

@ -0,0 +1,202 @@
# coding: utf-8
from __future__ import unicode_literals
import io
import quopri
import re
import uuid
from .fragment import FragmentFD
from ..utils import (
escapeHTML,
formatSeconds,
srt_subtitles_timecode,
urljoin,
)
from ..version import __version__ as YT_DLP_VERSION
class MhtmlFD(FragmentFD):
FD_NAME = 'mhtml'
_STYLESHEET = """\
html, body {
margin: 0;
padding: 0;
height: 100vh;
}
html {
overflow-y: scroll;
scroll-snap-type: y mandatory;
}
body {
scroll-snap-type: y mandatory;
display: flex;
flex-flow: column;
}
body > figure {
max-width: 100vw;
max-height: 100vh;
scroll-snap-align: center;
}
body > figure > figcaption {
text-align: center;
height: 2.5em;
}
body > figure > img {
display: block;
margin: auto;
max-width: 100%;
max-height: calc(100vh - 5em);
}
"""
_STYLESHEET = re.sub(r'\s+', ' ', _STYLESHEET)
_STYLESHEET = re.sub(r'\B \B|(?<=[\w\-]) (?=[^\w\-])|(?<=[^\w\-]) (?=[\w\-])', '', _STYLESHEET)
@staticmethod
def _escape_mime(s):
return '=?utf-8?Q?' + (b''.join(
bytes((b,)) if b >= 0x20 else b'=%02X' % b
for b in quopri.encodestring(s.encode('utf-8'), header=True)
)).decode('us-ascii') + '?='
def _gen_cid(self, i, fragment, frag_boundary):
return '%u.%s@yt-dlp.github.io.invalid' % (i, frag_boundary)
def _gen_stub(self, *, fragments, frag_boundary, title):
output = io.StringIO()
output.write((
'<!DOCTYPE html>'
'<html>'
'<head>'
'' '<meta name="generator" content="yt-dlp {version}">'
'' '<title>{title}</title>'
'' '<style>{styles}</style>'
'<body>'
).format(
version=escapeHTML(YT_DLP_VERSION),
styles=self._STYLESHEET,
title=escapeHTML(title)
))
t0 = 0
for i, frag in enumerate(fragments):
output.write('<figure>')
try:
t1 = t0 + frag['duration']
output.write((
'<figcaption>Slide #{num}: {t0} – {t1} (duration: {duration})</figcaption>'
).format(
num=i + 1,
t0=srt_subtitles_timecode(t0),
t1=srt_subtitles_timecode(t1),
duration=formatSeconds(frag['duration'], msec=True)
))
except (KeyError, ValueError, TypeError):
t1 = None
output.write((
'<figcaption>Slide #{num}</figcaption>'
).format(num=i + 1))
output.write('<img src="cid:{cid}">'.format(
cid=self._gen_cid(i, frag, frag_boundary)))
output.write('</figure>')
t0 = t1
return output.getvalue()
def real_download(self, filename, info_dict):
fragment_base_url = info_dict.get('fragment_base_url')
fragments = info_dict['fragments'][:1] if self.params.get(
'test', False) else info_dict['fragments']
title = info_dict.get('title', info_dict['format_id'])
origin = info_dict.get('webpage_url', info_dict['url'])
ctx = {
'filename': filename,
'total_frags': len(fragments),
}
self._prepare_and_start_frag_download(ctx, info_dict)
extra_state = ctx.setdefault('extra_state', {
'header_written': False,
'mime_boundary': str(uuid.uuid4()).replace('-', ''),
})
frag_boundary = extra_state['mime_boundary']
if not extra_state['header_written']:
stub = self._gen_stub(
fragments=fragments,
frag_boundary=frag_boundary,
title=title
)
ctx['dest_stream'].write((
'MIME-Version: 1.0\r\n'
'From: <nowhere@yt-dlp.github.io.invalid>\r\n'
'To: <nowhere@yt-dlp.github.io.invalid>\r\n'
'Subject: {title}\r\n'
'Content-type: multipart/related; '
'' 'boundary="{boundary}"; '
'' 'type="text/html"\r\n'
'X.yt-dlp.Origin: {origin}\r\n'
'\r\n'
'--{boundary}\r\n'
'Content-Type: text/html; charset=utf-8\r\n'
'Content-Length: {length}\r\n'
'\r\n'
'{stub}\r\n'
).format(
origin=origin,
boundary=frag_boundary,
length=len(stub),
title=self._escape_mime(title),
stub=stub
).encode('utf-8'))
extra_state['header_written'] = True
for i, fragment in enumerate(fragments):
if (i + 1) <= ctx['fragment_index']:
continue
fragment_url = urljoin(fragment_base_url, fragment['path'])
success, frag_content = self._download_fragment(ctx, fragment_url, info_dict)
if not success:
continue
mime_type = b'image/jpeg'
if frag_content.startswith(b'\x89PNG\r\n\x1a\n'):
mime_type = b'image/png'
if frag_content.startswith((b'GIF87a', b'GIF89a')):
mime_type = b'image/gif'
if frag_content.startswith(b'RIFF') and frag_content[8:12] == 'WEBP':
mime_type = b'image/webp'
frag_header = io.BytesIO()
frag_header.write(
b'--%b\r\n' % frag_boundary.encode('us-ascii'))
frag_header.write(
b'Content-ID: <%b>\r\n' % self._gen_cid(i, fragment, frag_boundary).encode('us-ascii'))
frag_header.write(
b'Content-type: %b\r\n' % mime_type)
frag_header.write(
b'Content-length: %u\r\n' % len(frag_content))
frag_header.write(
b'Content-location: %b\r\n' % fragment_url.encode('us-ascii'))
frag_header.write(
b'X.yt-dlp.Duration: %f\r\n' % fragment['duration'])
frag_header.write(b'\r\n')
self._append_fragment(
ctx, frag_header.getvalue() + frag_content + b'\r\n')
ctx['dest_stream'].write(
b'--%b--\r\n\r\n' % frag_boundary.encode('us-ascii'))
self._finish_frag_download(ctx, info_dict)
return True

57
plugins/youtube_download/yt_dlp/downloader/niconico.py Normal file
View File

@ -0,0 +1,57 @@
# coding: utf-8
from __future__ import unicode_literals
import threading
from .common import FileDownloader
from ..downloader import get_suitable_downloader
from ..extractor.niconico import NiconicoIE
from ..utils import sanitized_Request
class NiconicoDmcFD(FileDownloader):
""" Downloading niconico douga from DMC with heartbeat """
FD_NAME = 'niconico_dmc'
def real_download(self, filename, info_dict):
self.to_screen('[%s] Downloading from DMC' % self.FD_NAME)
ie = NiconicoIE(self.ydl)
info_dict, heartbeat_info_dict = ie._get_heartbeat_info(info_dict)
fd = get_suitable_downloader(info_dict, params=self.params)(self.ydl, self.params)
success = download_complete = False
timer = [None]
heartbeat_lock = threading.Lock()
heartbeat_url = heartbeat_info_dict['url']
heartbeat_data = heartbeat_info_dict['data'].encode()
heartbeat_interval = heartbeat_info_dict.get('interval', 30)
request = sanitized_Request(heartbeat_url, heartbeat_data)
def heartbeat():
try:
self.ydl.urlopen(request).read()
except Exception:
self.to_screen('[%s] Heartbeat failed' % self.FD_NAME)
with heartbeat_lock:
if not download_complete:
timer[0] = threading.Timer(heartbeat_interval, heartbeat)
timer[0].start()
heartbeat_info_dict['ping']()
self.to_screen('[%s] Heartbeat with %d second interval ...' % (self.FD_NAME, heartbeat_interval))
try:
heartbeat()
if type(fd).__name__ == 'HlsFD':
info_dict.update(ie._extract_m3u8_formats(info_dict['url'], info_dict['id'])[0])
success = fd.real_download(filename, info_dict)
finally:
if heartbeat_lock:
with heartbeat_lock:
timer[0].cancel()
download_complete = True
return success

217
plugins/youtube_download/yt_dlp/downloader/rtmp.py Normal file
View File

@ -0,0 +1,217 @@
from __future__ import unicode_literals
import os
import re
import subprocess
import time
from .common import FileDownloader
from ..compat import compat_str
from ..utils import (
check_executable,
encodeFilename,
encodeArgument,
get_exe_version,
Popen,
)
def rtmpdump_version():
return get_exe_version(
'rtmpdump', ['--help'], r'(?i)RTMPDump\s*v?([0-9a-zA-Z._-]+)')
class RtmpFD(FileDownloader):
def real_download(self, filename, info_dict):
def run_rtmpdump(args):
start = time.time()
resume_percent = None
resume_downloaded_data_len = None
proc = Popen(args, stderr=subprocess.PIPE)
cursor_in_new_line = True
proc_stderr_closed = False
try:
while not proc_stderr_closed:
# read line from stderr
line = ''
while True:
char = proc.stderr.read(1)
if not char:
proc_stderr_closed = True
break
if char in [b'\r', b'\n']:
break
line += char.decode('ascii', 'replace')
if not line:
# proc_stderr_closed is True
continue
mobj = re.search(r'([0-9]+\.[0-9]{3}) kB / [0-9]+\.[0-9]{2} sec \(([0-9]{1,2}\.[0-9])%\)', line)
if mobj:
downloaded_data_len = int(float(mobj.group(1)) * 1024)
percent = float(mobj.group(2))
if not resume_percent:
resume_percent = percent
resume_downloaded_data_len = downloaded_data_len
time_now = time.time()
eta = self.calc_eta(start, time_now, 100 - resume_percent, percent - resume_percent)
speed = self.calc_speed(start, time_now, downloaded_data_len - resume_downloaded_data_len)
data_len = None
if percent > 0:
data_len = int(downloaded_data_len * 100 / percent)
self._hook_progress({
'status': 'downloading',
'downloaded_bytes': downloaded_data_len,
'total_bytes_estimate': data_len,
'tmpfilename': tmpfilename,
'filename': filename,
'eta': eta,
'elapsed': time_now - start,
'speed': speed,
}, info_dict)
cursor_in_new_line = False
else:
# no percent for live streams
mobj = re.search(r'([0-9]+\.[0-9]{3}) kB / [0-9]+\.[0-9]{2} sec', line)
if mobj:
downloaded_data_len = int(float(mobj.group(1)) * 1024)
time_now = time.time()
speed = self.calc_speed(start, time_now, downloaded_data_len)
self._hook_progress({
'downloaded_bytes': downloaded_data_len,
'tmpfilename': tmpfilename,
'filename': filename,
'status': 'downloading',
'elapsed': time_now - start,
'speed': speed,
}, info_dict)
cursor_in_new_line = False
elif self.params.get('verbose', False):
if not cursor_in_new_line:
self.to_screen('')
cursor_in_new_line = True
self.to_screen('[rtmpdump] ' + line)
if not cursor_in_new_line:
self.to_screen('')
return proc.wait()
except BaseException: # Including KeyboardInterrupt
proc.kill()
proc.wait()
raise
url = info_dict['url']
player_url = info_dict.get('player_url')
page_url = info_dict.get('page_url')
app = info_dict.get('app')
play_path = info_dict.get('play_path')
tc_url = info_dict.get('tc_url')
flash_version = info_dict.get('flash_version')
live = info_dict.get('rtmp_live', False)
conn = info_dict.get('rtmp_conn')
protocol = info_dict.get('rtmp_protocol')
real_time = info_dict.get('rtmp_real_time', False)
no_resume = info_dict.get('no_resume', False)
continue_dl = self.params.get('continuedl', True)
self.report_destination(filename)
tmpfilename = self.temp_name(filename)
test = self.params.get('test', False)
# Check for rtmpdump first
if not check_executable('rtmpdump', ['-h']):
self.report_error('RTMP download detected but "rtmpdump" could not be run. Please install')
return False
# Download using rtmpdump. rtmpdump returns exit code 2 when
# the connection was interrupted and resuming appears to be
# possible. This is part of rtmpdump's normal usage, AFAIK.
basic_args = [
'rtmpdump', '--verbose', '-r', url,
'-o', tmpfilename]
if player_url is not None:
basic_args += ['--swfVfy', player_url]
if page_url is not None:
basic_args += ['--pageUrl', page_url]
if app is not None:
basic_args += ['--app', app]
if play_path is not None:
basic_args += ['--playpath', play_path]
if tc_url is not None:
basic_args += ['--tcUrl', tc_url]
if test:
basic_args += ['--stop', '1']
if flash_version is not None:
basic_args += ['--flashVer', flash_version]
if live:
basic_args += ['--live']
if isinstance(conn, list):
for entry in conn:
basic_args += ['--conn', entry]
elif isinstance(conn, compat_str):
basic_args += ['--conn', conn]
if protocol is not None:
basic_args += ['--protocol', protocol]
if real_time:
basic_args += ['--realtime']
args = basic_args
if not no_resume and continue_dl and not live:
args += ['--resume']
if not live and continue_dl:
args += ['--skip', '1']
args = [encodeArgument(a) for a in args]
self._debug_cmd(args, exe='rtmpdump')
RD_SUCCESS = 0
RD_FAILED = 1
RD_INCOMPLETE = 2
RD_NO_CONNECT = 3
started = time.time()
try:
retval = run_rtmpdump(args)
except KeyboardInterrupt:
if not info_dict.get('is_live'):
raise
retval = RD_SUCCESS
self.to_screen('\n[rtmpdump] Interrupted by user')
if retval == RD_NO_CONNECT:
self.report_error('[rtmpdump] Could not connect to RTMP server.')
return False
while retval in (RD_INCOMPLETE, RD_FAILED) and not test and not live:
prevsize = os.path.getsize(encodeFilename(tmpfilename))
self.to_screen('[rtmpdump] Downloaded %s bytes' % prevsize)
time.sleep(5.0) # This seems to be needed
args = basic_args + ['--resume']
if retval == RD_FAILED:
args += ['--skip', '1']
args = [encodeArgument(a) for a in args]
retval = run_rtmpdump(args)
cursize = os.path.getsize(encodeFilename(tmpfilename))
if prevsize == cursize and retval == RD_FAILED:
break
# Some rtmp streams seem abort after ~ 99.8%. Don't complain for those
if prevsize == cursize and retval == RD_INCOMPLETE and cursize > 1024:
self.to_screen('[rtmpdump] Could not download the whole video. This can happen for some advertisements.')
retval = RD_SUCCESS
break
if retval == RD_SUCCESS or (test and retval == RD_INCOMPLETE):
fsize = os.path.getsize(encodeFilename(tmpfilename))
self.to_screen('[rtmpdump] Downloaded %s bytes' % fsize)
self.try_rename(tmpfilename, filename)
self._hook_progress({
'downloaded_bytes': fsize,
'total_bytes': fsize,
'filename': filename,
'status': 'finished',
'elapsed': time.time() - started,
}, info_dict)
return True
else:
self.to_stderr('\n')
self.report_error('rtmpdump exited with code %d' % retval)
return False

47
plugins/youtube_download/yt_dlp/downloader/rtsp.py Normal file
View File

@ -0,0 +1,47 @@
from __future__ import unicode_literals
import os
import subprocess
from .common import FileDownloader
from ..utils import (
check_executable,
encodeFilename,
)
class RtspFD(FileDownloader):
def real_download(self, filename, info_dict):
url = info_dict['url']
self.report_destination(filename)
tmpfilename = self.temp_name(filename)
if check_executable('mplayer', ['-h']):
args = [
'mplayer', '-really-quiet', '-vo', 'null', '-vc', 'dummy',
'-dumpstream', '-dumpfile', tmpfilename, url]
elif check_executable('mpv', ['-h']):
args = [
'mpv', '-really-quiet', '--vo=null', '--stream-dump=' + tmpfilename, url]
else:
self.report_error('MMS or RTSP download detected but neither "mplayer" nor "mpv" could be run. Please install one')
return False
self._debug_cmd(args)
retval = subprocess.call(args)
if retval == 0:
fsize = os.path.getsize(encodeFilename(tmpfilename))
self.to_screen('\r[%s] %s bytes' % (args[0], fsize))
self.try_rename(tmpfilename, filename)
self._hook_progress({
'downloaded_bytes': fsize,
'total_bytes': fsize,
'filename': filename,
'status': 'finished',
}, info_dict)
return True
else:
self.to_stderr('\n')
self.report_error('%s exited with code %d' % (args[0], retval))
return False

62
plugins/youtube_download/yt_dlp/downloader/websocket.py Normal file
View File

@ -0,0 +1,62 @@
import os
import signal
import asyncio
import threading
try:
import websockets
except (ImportError, SyntaxError):
# websockets 3.10 on python 3.6 causes SyntaxError
# See https://github.com/yt-dlp/yt-dlp/issues/2633
has_websockets = False
else:
has_websockets = True
from .common import FileDownloader
from .external import FFmpegFD
class FFmpegSinkFD(FileDownloader):
""" A sink to ffmpeg for downloading fragments in any form """
def real_download(self, filename, info_dict):
info_copy = info_dict.copy()
info_copy['url'] = '-'
async def call_conn(proc, stdin):
try:
await self.real_connection(stdin, info_dict)
except (BrokenPipeError, OSError):
pass
finally:
try:
stdin.flush()
stdin.close()
except OSError:
pass
os.kill(os.getpid(), signal.SIGINT)
class FFmpegStdinFD(FFmpegFD):
@classmethod
def get_basename(cls):
return FFmpegFD.get_basename()
def on_process_started(self, proc, stdin):
thread = threading.Thread(target=asyncio.run, daemon=True, args=(call_conn(proc, stdin), ))
thread.start()
return FFmpegStdinFD(self.ydl, self.params or {}).download(filename, info_copy)
async def real_connection(self, sink, info_dict):
""" Override this in subclasses """
raise NotImplementedError('This method must be implemented by subclasses')
class WebSocketFragmentFD(FFmpegSinkFD):
async def real_connection(self, sink, info_dict):
async with websockets.connect(info_dict['url'], extra_headers=info_dict.get('http_headers', {})) as ws:
while True:
recv = await ws.recv()
if isinstance(recv, str):
recv = recv.encode('utf8')
sink.write(recv)

236
plugins/youtube_download/yt_dlp/downloader/youtube_live_chat.py Normal file
View File

@ -0,0 +1,236 @@
from __future__ import division, unicode_literals
import json
import time
from .fragment import FragmentFD
from ..compat import compat_urllib_error
from ..utils import (
try_get,
dict_get,
int_or_none,
RegexNotFoundError,
)
from ..extractor.youtube import YoutubeBaseInfoExtractor as YT_BaseIE
class YoutubeLiveChatFD(FragmentFD):
""" Downloads YouTube live chats fragment by fragment """
FD_NAME = 'youtube_live_chat'
def real_download(self, filename, info_dict):
video_id = info_dict['video_id']
self.to_screen('[%s] Downloading live chat' % self.FD_NAME)
fragment_retries = self.params.get('fragment_retries', 0)
test = self.params.get('test', False)
ctx = {
'filename': filename,
'live': True,
'total_frags': None,
}
ie = YT_BaseIE(self.ydl)
start_time = int(time.time() * 1000)
def dl_fragment(url, data=None, headers=None):
http_headers = info_dict.get('http_headers', {})
if headers:
http_headers = http_headers.copy()
http_headers.update(headers)
return self._download_fragment(ctx, url, info_dict, http_headers, data)
def parse_actions_replay(live_chat_continuation):
offset = continuation_id = click_tracking_params = None
processed_fragment = bytearray()
for action in live_chat_continuation.get('actions', []):
if 'replayChatItemAction' in action:
replay_chat_item_action = action['replayChatItemAction']
offset = int(replay_chat_item_action['videoOffsetTimeMsec'])
processed_fragment.extend(
json.dumps(action, ensure_ascii=False).encode('utf-8') + b'\n')
if offset is not None:
continuation = try_get(
live_chat_continuation,
lambda x: x['continuations'][0]['liveChatReplayContinuationData'], dict)
if continuation:
continuation_id = continuation.get('continuation')
click_tracking_params = continuation.get('clickTrackingParams')
self._append_fragment(ctx, processed_fragment)
return continuation_id, offset, click_tracking_params
def try_refresh_replay_beginning(live_chat_continuation):
# choose the second option that contains the unfiltered live chat replay
refresh_continuation = try_get(
live_chat_continuation,
lambda x: x['header']['liveChatHeaderRenderer']['viewSelector']['sortFilterSubMenuRenderer']['subMenuItems'][1]['continuation']['reloadContinuationData'], dict)
if refresh_continuation:
# no data yet but required to call _append_fragment
self._append_fragment(ctx, b'')
refresh_continuation_id = refresh_continuation.get('continuation')
offset = 0
click_tracking_params = refresh_continuation.get('trackingParams')
return refresh_continuation_id, offset, click_tracking_params
return parse_actions_replay(live_chat_continuation)
live_offset = 0
def parse_actions_live(live_chat_continuation):
nonlocal live_offset
continuation_id = click_tracking_params = None
processed_fragment = bytearray()
for action in live_chat_continuation.get('actions', []):
timestamp = self.parse_live_timestamp(action)
if timestamp is not None:
live_offset = timestamp - start_time
# compatibility with replay format
pseudo_action = {
'replayChatItemAction': {'actions': [action]},
'videoOffsetTimeMsec': str(live_offset),
'isLive': True,
}
processed_fragment.extend(
json.dumps(pseudo_action, ensure_ascii=False).encode('utf-8') + b'\n')
continuation_data_getters = [
lambda x: x['continuations'][0]['invalidationContinuationData'],
lambda x: x['continuations'][0]['timedContinuationData'],
]
continuation_data = try_get(live_chat_continuation, continuation_data_getters, dict)
if continuation_data:
continuation_id = continuation_data.get('continuation')
click_tracking_params = continuation_data.get('clickTrackingParams')
timeout_ms = int_or_none(continuation_data.get('timeoutMs'))
if timeout_ms is not None:
time.sleep(timeout_ms / 1000)
self._append_fragment(ctx, processed_fragment)
return continuation_id, live_offset, click_tracking_params
def download_and_parse_fragment(url, frag_index, request_data=None, headers=None):
count = 0
while count <= fragment_retries:
try:
success, raw_fragment = dl_fragment(url, request_data, headers)
if not success:
return False, None, None, None
try:
data = ie.extract_yt_initial_data(video_id, raw_fragment.decode('utf-8', 'replace'))
except RegexNotFoundError:
data = None
if not data:
data = json.loads(raw_fragment)
live_chat_continuation = try_get(
data,
lambda x: x['continuationContents']['liveChatContinuation'], dict) or {}
if info_dict['protocol'] == 'youtube_live_chat_replay':
if frag_index == 1:
continuation_id, offset, click_tracking_params = try_refresh_replay_beginning(live_chat_continuation)
else:
continuation_id, offset, click_tracking_params = parse_actions_replay(live_chat_continuation)
elif info_dict['protocol'] == 'youtube_live_chat':
continuation_id, offset, click_tracking_params = parse_actions_live(live_chat_continuation)
return True, continuation_id, offset, click_tracking_params
except compat_urllib_error.HTTPError as err:
count += 1
if count <= fragment_retries:
self.report_retry_fragment(err, frag_index, count, fragment_retries)
if count > fragment_retries:
self.report_error('giving up after %s fragment retries' % fragment_retries)
return False, None, None, None
self._prepare_and_start_frag_download(ctx, info_dict)
success, raw_fragment = dl_fragment(info_dict['url'])
if not success:
return False
try:
data = ie.extract_yt_initial_data(video_id, raw_fragment.decode('utf-8', 'replace'))
except RegexNotFoundError:
return False
continuation_id = try_get(
data,
lambda x: x['contents']['twoColumnWatchNextResults']['conversationBar']['liveChatRenderer']['continuations'][0]['reloadContinuationData']['continuation'])
# no data yet but required to call _append_fragment
self._append_fragment(ctx, b'')
ytcfg = ie.extract_ytcfg(video_id, raw_fragment.decode('utf-8', 'replace'))
if not ytcfg:
return False
api_key = try_get(ytcfg, lambda x: x['INNERTUBE_API_KEY'])
innertube_context = try_get(ytcfg, lambda x: x['INNERTUBE_CONTEXT'])
if not api_key or not innertube_context:
return False
visitor_data = try_get(innertube_context, lambda x: x['client']['visitorData'], str)
if info_dict['protocol'] == 'youtube_live_chat_replay':
url = 'https://www.youtube.com/youtubei/v1/live_chat/get_live_chat_replay?key=' + api_key
chat_page_url = 'https://www.youtube.com/live_chat_replay?continuation=' + continuation_id
elif info_dict['protocol'] == 'youtube_live_chat':
url = 'https://www.youtube.com/youtubei/v1/live_chat/get_live_chat?key=' + api_key
chat_page_url = 'https://www.youtube.com/live_chat?continuation=' + continuation_id
frag_index = offset = 0
click_tracking_params = None
while continuation_id is not None:
frag_index += 1
request_data = {
'context': innertube_context,
'continuation': continuation_id,
}
if frag_index > 1:
request_data['currentPlayerState'] = {'playerOffsetMs': str(max(offset - 5000, 0))}
if click_tracking_params:
request_data['context']['clickTracking'] = {'clickTrackingParams': click_tracking_params}
headers = ie.generate_api_headers(ytcfg=ytcfg, visitor_data=visitor_data)
headers.update({'content-type': 'application/json'})
fragment_request_data = json.dumps(request_data, ensure_ascii=False).encode('utf-8') + b'\n'
success, continuation_id, offset, click_tracking_params = download_and_parse_fragment(
url, frag_index, fragment_request_data, headers)
else:
success, continuation_id, offset, click_tracking_params = download_and_parse_fragment(
chat_page_url, frag_index)
if not success:
return False
if test:
break
self._finish_frag_download(ctx, info_dict)
return True
@staticmethod
def parse_live_timestamp(action):
action_content = dict_get(
action,
['addChatItemAction', 'addLiveChatTickerItemAction', 'addBannerToLiveChatCommand'])
if not isinstance(action_content, dict):
return None
item = dict_get(action_content, ['item', 'bannerRenderer'])
if not isinstance(item, dict):
return None
renderer = dict_get(item, [
# text
'liveChatTextMessageRenderer', 'liveChatPaidMessageRenderer',
'liveChatMembershipItemRenderer', 'liveChatPaidStickerRenderer',
# ticker
'liveChatTickerPaidMessageItemRenderer',
'liveChatTickerSponsorItemRenderer',
# banner
'liveChatBannerRenderer',
])
if not isinstance(renderer, dict):
return None
parent_item_getters = [
lambda x: x['showItemEndpoint']['showLiveChatItemEndpoint']['renderer'],
lambda x: x['contents'],
]
parent_item = try_get(renderer, parent_item_getters, dict)
if parent_item:
renderer = dict_get(parent_item, [
'liveChatTextMessageRenderer', 'liveChatPaidMessageRenderer',
'liveChatMembershipItemRenderer', 'liveChatPaidStickerRenderer',
])
if not isinstance(renderer, dict):
return None
return int_or_none(renderer.get('timestampUsec'), 1000)

54
plugins/youtube_download/yt_dlp/extractor/__init__.py Normal file
View File

@ -0,0 +1,54 @@
import os
from ..utils import load_plugins
_LAZY_LOADER = False
if not os.environ.get('YTDLP_NO_LAZY_EXTRACTORS'):
try:
from .lazy_extractors import *
from .lazy_extractors import _ALL_CLASSES
_LAZY_LOADER = True
except ImportError:
pass
if not _LAZY_LOADER:
from .extractors import *
_ALL_CLASSES = [
klass
for name, klass in globals().items()
if name.endswith('IE') and name != 'GenericIE'
]
_ALL_CLASSES.append(GenericIE)
_PLUGIN_CLASSES = load_plugins('extractor', 'IE', globals())
_ALL_CLASSES = list(_PLUGIN_CLASSES.values()) + _ALL_CLASSES
def gen_extractor_classes():
""" Return a list of supported extractors.
The order does matter; the first extractor matched is the one handling the URL.
"""
return _ALL_CLASSES
def gen_extractors():
""" Return a list of an instance of every supported extractor.
The order does matter; the first extractor matched is the one handling the URL.
"""
return [klass() for klass in gen_extractor_classes()]
def list_extractors(age_limit):
"""
Return a list of extractors that are suitable for the given age,
sorted by extractor ID.
"""
return sorted(
filter(lambda ie: ie.is_suitable(age_limit), gen_extractors()),
key=lambda ie: ie.IE_NAME.lower())
def get_info_extractor(ie_name):
"""Returns the info extractor class with the given ie_name"""
return globals()[ie_name + 'IE']

318
plugins/youtube_download/yt_dlp/extractor/abc.py Normal file
View File

@ -0,0 +1,318 @@
from __future__ import unicode_literals
import hashlib
import hmac
import re
import time
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
dict_get,
ExtractorError,
js_to_json,
int_or_none,
parse_iso8601,
str_or_none,
try_get,
unescapeHTML,
update_url_query,
)
class ABCIE(InfoExtractor):
IE_NAME = 'abc.net.au'
_VALID_URL = r'https?://(?:www\.)?abc\.net\.au/(?:news|btn)/(?:[^/]+/){1,4}(?P<id>\d{5,})'
_TESTS = [{
'url': 'http://www.abc.net.au/news/2014-11-05/australia-to-staff-ebola-treatment-centre-in-sierra-leone/5868334',
'md5': 'cb3dd03b18455a661071ee1e28344d9f',
'info_dict': {
'id': '5868334',
'ext': 'mp4',
'title': 'Australia to help staff Ebola treatment centre in Sierra Leone',
'description': 'md5:809ad29c67a05f54eb41f2a105693a67',
},
'skip': 'this video has expired',
}, {
'url': 'http://www.abc.net.au/news/2015-08-17/warren-entsch-introduces-same-sex-marriage-bill/6702326',
'md5': '4ebd61bdc82d9a8b722f64f1f4b4d121',
'info_dict': {
'id': 'NvqvPeNZsHU',
'ext': 'mp4',
'upload_date': '20150816',
'uploader': 'ABC News (Australia)',
'description': 'Government backbencher Warren Entsch introduces a cross-party sponsored bill to legalise same-sex marriage, saying the bill is designed to promote "an inclusive Australia, not a divided one.". Read more here: http://ab.co/1Mwc6ef',
'uploader_id': 'NewsOnABC',
'title': 'Marriage Equality: Warren Entsch introduces same sex marriage bill',
},
'add_ie': ['Youtube'],
'skip': 'Not accessible from Travis CI server',
}, {
'url': 'http://www.abc.net.au/news/2015-10-23/nab-lifts-interest-rates-following-westpac-and-cba/6880080',
'md5': 'b96eee7c9edf4fc5a358a0252881cc1f',
'info_dict': {
'id': '6880080',
'ext': 'mp3',
'title': 'NAB lifts interest rates, following Westpac and CBA',
'description': 'md5:f13d8edc81e462fce4a0437c7dc04728',
},
}, {
'url': 'http://www.abc.net.au/news/2015-10-19/6866214',
'only_matching': True,
}, {
'url': 'https://www.abc.net.au/btn/classroom/wwi-centenary/10527914',
'info_dict': {
'id': '10527914',
'ext': 'mp4',
'title': 'WWI Centenary',
'description': 'md5:c2379ec0ca84072e86b446e536954546',
}
}, {
'url': 'https://www.abc.net.au/news/programs/the-world/2020-06-10/black-lives-matter-protests-spawn-support-for/12342074',
'info_dict': {
'id': '12342074',
'ext': 'mp4',
'title': 'Black Lives Matter protests spawn support for Papuans in Indonesia',
'description': 'md5:2961a17dc53abc558589ccd0fb8edd6f',
}
}, {
'url': 'https://www.abc.net.au/btn/newsbreak/btn-newsbreak-20200814/12560476',
'info_dict': {
'id': 'tDL8Ld4dK_8',
'ext': 'mp4',
'title': 'Fortnite Banned From Apple and Google App Stores',
'description': 'md5:a6df3f36ce8f816b74af4bd6462f5651',
'upload_date': '20200813',
'uploader': 'Behind the News',
'uploader_id': 'behindthenews',
}
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
mobj = re.search(r'<a\s+href="(?P<url>[^"]+)"\s+data-duration="\d+"\s+title="Download audio directly">', webpage)
if mobj:
urls_info = mobj.groupdict()
youtube = False
video = False
else:
mobj = re.search(r'<a href="(?P<url>http://www\.youtube\.com/watch\?v=[^"]+)"><span><strong>External Link:</strong>',
webpage)
if mobj is None:
mobj = re.search(r'<iframe width="100%" src="(?P<url>//www\.youtube-nocookie\.com/embed/[^?"]+)', webpage)
if mobj:
urls_info = mobj.groupdict()
youtube = True
video = True
if mobj is None:
mobj = re.search(r'(?P<type>)"sources": (?P<json_data>\[[^\]]+\]),', webpage)
if mobj is None:
mobj = re.search(
r'inline(?P<type>Video|Audio|YouTube)Data\.push\((?P<json_data>[^)]+)\);',
webpage)
if mobj is None:
expired = self._html_search_regex(r'(?s)class="expired-(?:video|audio)".+?<span>(.+?)</span>', webpage, 'expired', None)
if expired:
raise ExtractorError('%s said: %s' % (self.IE_NAME, expired), expected=True)
raise ExtractorError('Unable to extract video urls')
urls_info = self._parse_json(
mobj.group('json_data'), video_id, transform_source=js_to_json)
youtube = mobj.group('type') == 'YouTube'
video = mobj.group('type') == 'Video' or urls_info[0]['contentType'] == 'video/mp4'
if not isinstance(urls_info, list):
urls_info = [urls_info]
if youtube:
return self.playlist_result([
self.url_result(url_info['url']) for url_info in urls_info])
formats = []
for url_info in urls_info:
height = int_or_none(url_info.get('height'))
bitrate = int_or_none(url_info.get('bitrate'))
width = int_or_none(url_info.get('width'))
format_id = None
mobj = re.search(r'_(?:(?P<height>\d+)|(?P<bitrate>\d+)k)\.mp4$', url_info['url'])
if mobj:
height_from_url = mobj.group('height')
if height_from_url:
height = height or int_or_none(height_from_url)
width = width or int_or_none(url_info.get('label'))
else:
bitrate = bitrate or int_or_none(mobj.group('bitrate'))
format_id = str_or_none(url_info.get('label'))
formats.append({
'url': url_info['url'],
'vcodec': url_info.get('codec') if video else 'none',
'width': width,
'height': height,
'tbr': bitrate,
'filesize': int_or_none(url_info.get('filesize')),
'format_id': format_id
})
self._sort_formats(formats)
return {
'id': video_id,
'title': self._og_search_title(webpage),
'formats': formats,
'description': self._og_search_description(webpage),
'thumbnail': self._og_search_thumbnail(webpage),
}
class ABCIViewIE(InfoExtractor):
IE_NAME = 'abc.net.au:iview'
_VALID_URL = r'https?://iview\.abc\.net\.au/(?:[^/]+/)*video/(?P<id>[^/?#]+)'
_GEO_COUNTRIES = ['AU']
# ABC iview programs are normally available for 14 days only.
_TESTS = [{
'url': 'https://iview.abc.net.au/show/gruen/series/11/video/LE1927H001S00',
'md5': '67715ce3c78426b11ba167d875ac6abf',
'info_dict': {
'id': 'LE1927H001S00',
'ext': 'mp4',
'title': "Series 11 Ep 1",
'series': "Gruen",
'description': 'md5:52cc744ad35045baf6aded2ce7287f67',
'upload_date': '20190925',
'uploader_id': 'abc1',
'timestamp': 1569445289,
},
'params': {
'skip_download': True,
},
}]
def _real_extract(self, url):
video_id = self._match_id(url)
video_params = self._download_json(
'https://iview.abc.net.au/api/programs/' + video_id, video_id)
title = unescapeHTML(video_params.get('title') or video_params['seriesTitle'])
stream = next(s for s in video_params['playlist'] if s.get('type') in ('program', 'livestream'))
house_number = video_params.get('episodeHouseNumber') or video_id
path = '/auth/hls/sign?ts={0}&hn={1}&d=android-tablet'.format(
int(time.time()), house_number)
sig = hmac.new(
b'android.content.res.Resources',
path.encode('utf-8'), hashlib.sha256).hexdigest()
token = self._download_webpage(
'http://iview.abc.net.au{0}&sig={1}'.format(path, sig), video_id)
def tokenize_url(url, token):
return update_url_query(url, {
'hdnea': token,
})
for sd in ('720', 'sd', 'sd-low'):
sd_url = try_get(
stream, lambda x: x['streams']['hls'][sd], compat_str)
if not sd_url:
continue
formats = self._extract_m3u8_formats(
tokenize_url(sd_url, token), video_id, 'mp4',
entry_protocol='m3u8_native', m3u8_id='hls', fatal=False)
if formats:
break
self._sort_formats(formats)
subtitles = {}
src_vtt = stream.get('captions', {}).get('src-vtt')
if src_vtt:
subtitles['en'] = [{
'url': src_vtt,
'ext': 'vtt',
}]
is_live = video_params.get('livestream') == '1'
return {
'id': video_id,
'title': title,
'description': video_params.get('description'),
'thumbnail': video_params.get('thumbnail'),
'duration': int_or_none(video_params.get('eventDuration')),
'timestamp': parse_iso8601(video_params.get('pubDate'), ' '),
'series': unescapeHTML(video_params.get('seriesTitle')),
'series_id': video_params.get('seriesHouseNumber') or video_id[:7],
'season_number': int_or_none(self._search_regex(
r'\bSeries\s+(\d+)\b', title, 'season number', default=None)),
'episode_number': int_or_none(self._search_regex(
r'\bEp\s+(\d+)\b', title, 'episode number', default=None)),
'episode_id': house_number,
'uploader_id': video_params.get('channel'),
'formats': formats,
'subtitles': subtitles,
'is_live': is_live,
}
class ABCIViewShowSeriesIE(InfoExtractor):
IE_NAME = 'abc.net.au:iview:showseries'
_VALID_URL = r'https?://iview\.abc\.net\.au/show/(?P<id>[^/]+)(?:/series/\d+)?$'
_GEO_COUNTRIES = ['AU']
_TESTS = [{
'url': 'https://iview.abc.net.au/show/upper-middle-bogan',
'info_dict': {
'id': '124870-1',
'title': 'Series 1',
'description': 'md5:93119346c24a7c322d446d8eece430ff',
'series': 'Upper Middle Bogan',
'season': 'Series 1',
'thumbnail': r're:^https?://cdn\.iview\.abc\.net\.au/thumbs/.*\.jpg$'
},
'playlist_count': 8,
}, {
'url': 'https://iview.abc.net.au/show/upper-middle-bogan',
'info_dict': {
'id': 'CO1108V001S00',
'ext': 'mp4',
'title': 'Series 1 Ep 1 I\'m A Swan',
'description': 'md5:7b676758c1de11a30b79b4d301e8da93',
'series': 'Upper Middle Bogan',
'uploader_id': 'abc1',
'upload_date': '20210630',
'timestamp': 1625036400,
},
'params': {
'noplaylist': True,
'skip_download': 'm3u8',
},
}]
def _real_extract(self, url):
show_id = self._match_id(url)
webpage = self._download_webpage(url, show_id)
webpage_data = self._search_regex(
r'window\.__INITIAL_STATE__\s*=\s*[\'"](.+?)[\'"]\s*;',
webpage, 'initial state')
video_data = self._parse_json(
unescapeHTML(webpage_data).encode('utf-8').decode('unicode_escape'), show_id)
video_data = video_data['route']['pageData']['_embedded']
highlight = try_get(video_data, lambda x: x['highlightVideo']['shareUrl'])
if not self._yes_playlist(show_id, bool(highlight), video_label='highlight video'):
return self.url_result(highlight, ie=ABCIViewIE.ie_key())
series = video_data['selectedSeries']
return {
'_type': 'playlist',
'entries': [self.url_result(episode['shareUrl'])
for episode in series['_embedded']['videoEpisodes']],
'id': series.get('id'),
'title': dict_get(series, ('title', 'displaySubtitle')),
'description': series.get('description'),
'series': dict_get(series, ('showTitle', 'displayTitle')),
'season': dict_get(series, ('title', 'displaySubtitle')),
'thumbnail': series.get('thumbnail'),
}

157
plugins/youtube_download/yt_dlp/extractor/abcnews.py Normal file
View File

@ -0,0 +1,157 @@
# coding: utf-8
from __future__ import unicode_literals
from .amp import AMPIE
from .common import InfoExtractor
from ..utils import (
parse_duration,
parse_iso8601,
try_get,
)
class AbcNewsVideoIE(AMPIE):
IE_NAME = 'abcnews:video'
_VALID_URL = r'''(?x)
https?://
(?:
abcnews\.go\.com/
(?:
(?:[^/]+/)*video/(?P<display_id>[0-9a-z-]+)-|
video/(?:embed|itemfeed)\?.*?\bid=
)|
fivethirtyeight\.abcnews\.go\.com/video/embed/\d+/
)
(?P<id>\d+)
'''
_TESTS = [{
'url': 'http://abcnews.go.com/ThisWeek/video/week-exclusive-irans-foreign-minister-zarif-20411932',
'info_dict': {
'id': '20411932',
'ext': 'mp4',
'display_id': 'week-exclusive-irans-foreign-minister-zarif',
'title': '\'This Week\' Exclusive: Iran\'s Foreign Minister Zarif',
'description': 'George Stephanopoulos goes one-on-one with Iranian Foreign Minister Dr. Javad Zarif.',
'duration': 180,
'thumbnail': r're:^https?://.*\.jpg$',
'timestamp': 1380454200,
'upload_date': '20130929',
},
'params': {
# m3u8 download
'skip_download': True,
},
}, {
'url': 'http://abcnews.go.com/video/embed?id=46979033',
'only_matching': True,
}, {
'url': 'http://abcnews.go.com/2020/video/2020-husband-stands-teacher-jail-student-affairs-26119478',
'only_matching': True,
}, {
'url': 'http://abcnews.go.com/video/itemfeed?id=46979033',
'only_matching': True,
}, {
'url': 'https://abcnews.go.com/GMA/News/video/history-christmas-story-67894761',
'only_matching': True,
}]
def _real_extract(self, url):
mobj = self._match_valid_url(url)
display_id = mobj.group('display_id')
video_id = mobj.group('id')
info_dict = self._extract_feed_info(
'http://abcnews.go.com/video/itemfeed?id=%s' % video_id)
info_dict.update({
'id': video_id,
'display_id': display_id,
})
return info_dict
class AbcNewsIE(InfoExtractor):
IE_NAME = 'abcnews'
_VALID_URL = r'https?://abcnews\.go\.com/(?:[^/]+/)+(?P<display_id>[0-9a-z-]+)/story\?id=(?P<id>\d+)'
_TESTS = [{
# Youtube Embeds
'url': 'https://abcnews.go.com/Entertainment/peter-billingsley-child-actor-christmas-story-hollywood-power/story?id=51286501',
'info_dict': {
'id': '51286501',
'title': "Peter Billingsley: From child actor in 'A Christmas Story' to Hollywood power player",
'description': 'Billingsley went from a child actor to Hollywood power player.',
},
'playlist_count': 5,
}, {
'url': 'http://abcnews.go.com/Entertainment/justin-timberlake-performs-stop-feeling-eurovision-2016/story?id=39125818',
'info_dict': {
'id': '38897857',
'ext': 'mp4',
'title': 'Justin Timberlake Drops Hints For Secret Single',
'description': 'Lara Spencer reports the buzziest stories of the day in "GMA" Pop News.',
'upload_date': '20160505',
'timestamp': 1462442280,
},
'params': {
# m3u8 download
'skip_download': True,
# The embedded YouTube video is blocked due to copyright issues
'playlist_items': '1',
},
'add_ie': ['AbcNewsVideo'],
}, {
'url': 'http://abcnews.go.com/Technology/exclusive-apple-ceo-tim-cook-iphone-cracking-software/story?id=37173343',
'only_matching': True,
}, {
# inline.type == 'video'
'url': 'http://abcnews.go.com/Technology/exclusive-apple-ceo-tim-cook-iphone-cracking-software/story?id=37173343',
'only_matching': True,
}]
def _real_extract(self, url):
story_id = self._match_id(url)
webpage = self._download_webpage(url, story_id)
story = self._parse_json(self._search_regex(
r"window\['__abcnews__'\]\s*=\s*({.+?});",
webpage, 'data'), story_id)['page']['content']['story']['everscroll'][0]
article_contents = story.get('articleContents') or {}
def entries():
featured_video = story.get('featuredVideo') or {}
feed = try_get(featured_video, lambda x: x['video']['feed'])
if feed:
yield {
'_type': 'url',
'id': featured_video.get('id'),
'title': featured_video.get('name'),
'url': feed,
'thumbnail': featured_video.get('images'),
'description': featured_video.get('description'),
'timestamp': parse_iso8601(featured_video.get('uploadDate')),
'duration': parse_duration(featured_video.get('duration')),
'ie_key': AbcNewsVideoIE.ie_key(),
}
for inline in (article_contents.get('inlines') or []):
inline_type = inline.get('type')
if inline_type == 'iframe':
iframe_url = try_get(inline, lambda x: x['attrs']['src'])
if iframe_url:
yield self.url_result(iframe_url)
elif inline_type == 'video':
video_id = inline.get('id')
if video_id:
yield {
'_type': 'url',
'id': video_id,
'url': 'http://abcnews.go.com/video/embed?id=' + video_id,
'thumbnail': inline.get('imgSrc') or inline.get('imgDefault'),
'description': inline.get('description'),
'duration': parse_duration(inline.get('duration')),
'ie_key': AbcNewsVideoIE.ie_key(),
}
return self.playlist_result(
entries(), story_id, article_contents.get('headline'),
article_contents.get('subHead'))

136
plugins/youtube_download/yt_dlp/extractor/abcotvs.py Normal file
View File

@ -0,0 +1,136 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
dict_get,
int_or_none,
try_get,
)
class ABCOTVSIE(InfoExtractor):
IE_NAME = 'abcotvs'
IE_DESC = 'ABC Owned Television Stations'
_VALID_URL = r'https?://(?P<site>abc(?:7(?:news|ny|chicago)?|11|13|30)|6abc)\.com(?:(?:/[^/]+)*/(?P<display_id>[^/]+))?/(?P<id>\d+)'
_TESTS = [
{
'url': 'http://abc7news.com/entertainment/east-bay-museum-celebrates-vintage-synthesizers/472581/',
'info_dict': {
'id': '472548',
'display_id': 'east-bay-museum-celebrates-vintage-synthesizers',
'ext': 'mp4',
'title': 'East Bay museum celebrates synthesized music',
'description': 'md5:24ed2bd527096ec2a5c67b9d5a9005f3',
'thumbnail': r're:^https?://.*\.jpg$',
'timestamp': 1421118520,
'upload_date': '20150113',
},
'params': {
# m3u8 download
'skip_download': True,
},
},
{
'url': 'http://abc7news.com/472581',
'only_matching': True,
},
{
'url': 'https://6abc.com/man-75-killed-after-being-struck-by-vehicle-in-chester/5725182/',
'only_matching': True,
},
]
_SITE_MAP = {
'6abc': 'wpvi',
'abc11': 'wtvd',
'abc13': 'ktrk',
'abc30': 'kfsn',
'abc7': 'kabc',
'abc7chicago': 'wls',
'abc7news': 'kgo',
'abc7ny': 'wabc',
}
def _real_extract(self, url):
site, display_id, video_id = self._match_valid_url(url).groups()
display_id = display_id or video_id
station = self._SITE_MAP[site]
data = self._download_json(
'https://api.abcotvs.com/v2/content', display_id, query={
'id': video_id,
'key': 'otv.web.%s.story' % station,
'station': station,
})['data']
video = try_get(data, lambda x: x['featuredMedia']['video'], dict) or data
video_id = compat_str(dict_get(video, ('id', 'publishedKey'), video_id))
title = video.get('title') or video['linkText']
formats = []
m3u8_url = video.get('m3u8')
if m3u8_url:
formats = self._extract_m3u8_formats(
video['m3u8'].split('?')[0], display_id, 'mp4', m3u8_id='hls', fatal=False)
mp4_url = video.get('mp4')
if mp4_url:
formats.append({
'abr': 128,
'format_id': 'https',
'height': 360,
'url': mp4_url,
'width': 640,
})
self._sort_formats(formats)
image = video.get('image') or {}
return {
'id': video_id,
'display_id': display_id,
'title': title,
'description': dict_get(video, ('description', 'caption'), try_get(video, lambda x: x['meta']['description'])),
'thumbnail': dict_get(image, ('source', 'dynamicSource')),
'timestamp': int_or_none(video.get('date')),
'duration': int_or_none(video.get('length')),
'formats': formats,
}
class ABCOTVSClipsIE(InfoExtractor):
IE_NAME = 'abcotvs:clips'
_VALID_URL = r'https?://clips\.abcotvs\.com/(?:[^/]+/)*video/(?P<id>\d+)'
_TEST = {
'url': 'https://clips.abcotvs.com/kabc/video/214814',
'info_dict': {
'id': '214814',
'ext': 'mp4',
'title': 'SpaceX launch pad explosion destroys rocket, satellite',
'description': 'md5:9f186e5ad8f490f65409965ee9c7be1b',
'upload_date': '20160901',
'timestamp': 1472756695,
},
'params': {
# m3u8 download
'skip_download': True,
},
}
def _real_extract(self, url):
video_id = self._match_id(url)
video_data = self._download_json('https://clips.abcotvs.com/vogo/video/getByIds?ids=' + video_id, video_id)['results'][0]
title = video_data['title']
formats = self._extract_m3u8_formats(
video_data['videoURL'].split('?')[0], video_id, 'mp4')
self._sort_formats(formats)
return {
'id': video_id,
'title': title,
'description': video_data.get('description'),
'thumbnail': video_data.get('thumbnailURL'),
'duration': int_or_none(video_data.get('duration')),
'timestamp': int_or_none(video_data.get('pubDate')),
'formats': formats,
}

41
plugins/youtube_download/yt_dlp/extractor/academicearth.py Normal file
View File

@ -0,0 +1,41 @@
from __future__ import unicode_literals
import re
from .common import InfoExtractor
class AcademicEarthCourseIE(InfoExtractor):
_VALID_URL = r'^https?://(?:www\.)?academicearth\.org/playlists/(?P<id>[^?#/]+)'
IE_NAME = 'AcademicEarth:Course'
_TEST = {
'url': 'http://academicearth.org/playlists/laws-of-nature/',
'info_dict': {
'id': 'laws-of-nature',
'title': 'Laws of Nature',
'description': 'Introduce yourself to the laws of nature with these free online college lectures from Yale, Harvard, and MIT.',
},
'playlist_count': 3,
}
def _real_extract(self, url):
playlist_id = self._match_id(url)
webpage = self._download_webpage(url, playlist_id)
title = self._html_search_regex(
r'<h1 class="playlist-name"[^>]*?>(.*?)</h1>', webpage, 'title')
description = self._html_search_regex(
r'<p class="excerpt"[^>]*?>(.*?)</p>',
webpage, 'description', fatal=False)
urls = re.findall(
r'<li class="lecture-preview">\s*?<a target="_blank" href="([^"]+)">',
webpage)
entries = [self.url_result(u) for u in urls]
return {
'_type': 'playlist',
'id': playlist_id,
'title': title,
'description': description,
'entries': entries,
}

125
plugins/youtube_download/yt_dlp/extractor/acast.py Normal file
View File

@ -0,0 +1,125 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import (
clean_html,
clean_podcast_url,
int_or_none,
parse_iso8601,
)
class ACastBaseIE(InfoExtractor):
def _extract_episode(self, episode, show_info):
title = episode['title']
info = {
'id': episode['id'],
'display_id': episode.get('episodeUrl'),
'url': clean_podcast_url(episode['url']),
'title': title,
'description': clean_html(episode.get('description') or episode.get('summary')),
'thumbnail': episode.get('image'),
'timestamp': parse_iso8601(episode.get('publishDate')),
'duration': int_or_none(episode.get('duration')),
'filesize': int_or_none(episode.get('contentLength')),
'season_number': int_or_none(episode.get('season')),
'episode': title,
'episode_number': int_or_none(episode.get('episode')),
}
info.update(show_info)
return info
def _extract_show_info(self, show):
return {
'creator': show.get('author'),
'series': show.get('title'),
}
def _call_api(self, path, video_id, query=None):
return self._download_json(
'https://feeder.acast.com/api/v1/shows/' + path, video_id, query=query)
class ACastIE(ACastBaseIE):
IE_NAME = 'acast'
_VALID_URL = r'''(?x)
https?://
(?:
(?:(?:embed|www)\.)?acast\.com/|
play\.acast\.com/s/
)
(?P<channel>[^/]+)/(?P<id>[^/#?]+)
'''
_TESTS = [{
'url': 'https://www.acast.com/sparpodcast/2.raggarmordet-rosterurdetforflutna',
'md5': 'f5598f3ad1e4776fed12ec1407153e4b',
'info_dict': {
'id': '2a92b283-1a75-4ad8-8396-499c641de0d9',
'ext': 'mp3',
'title': '2. Raggarmordet - Röster ur det förflutna',
'description': 'md5:a992ae67f4d98f1c0141598f7bebbf67',
'timestamp': 1477346700,
'upload_date': '20161024',
'duration': 2766,
'creator': 'Anton Berg & Martin Johnson',
'series': 'Spår',
'episode': '2. Raggarmordet - Röster ur det förflutna',
}
}, {
'url': 'http://embed.acast.com/adambuxton/ep.12-adam-joeschristmaspodcast2015',
'only_matching': True,
}, {
'url': 'https://play.acast.com/s/rattegangspodden/s04e09styckmordetihelenelund-del2-2',
'only_matching': True,
}, {
'url': 'https://play.acast.com/s/sparpodcast/2a92b283-1a75-4ad8-8396-499c641de0d9',
'only_matching': True,
}]
def _real_extract(self, url):
channel, display_id = self._match_valid_url(url).groups()
episode = self._call_api(
'%s/episodes/%s' % (channel, display_id),
display_id, {'showInfo': 'true'})
return self._extract_episode(
episode, self._extract_show_info(episode.get('show') or {}))
class ACastChannelIE(ACastBaseIE):
IE_NAME = 'acast:channel'
_VALID_URL = r'''(?x)
https?://
(?:
(?:www\.)?acast\.com/|
play\.acast\.com/s/
)
(?P<id>[^/#?]+)
'''
_TESTS = [{
'url': 'https://www.acast.com/todayinfocus',
'info_dict': {
'id': '4efc5294-5385-4847-98bd-519799ce5786',
'title': 'Today in Focus',
'description': 'md5:c09ce28c91002ce4ffce71d6504abaae',
},
'playlist_mincount': 200,
}, {
'url': 'http://play.acast.com/s/ft-banking-weekly',
'only_matching': True,
}]
@classmethod
def suitable(cls, url):
return False if ACastIE.suitable(url) else super(ACastChannelIE, cls).suitable(url)
def _real_extract(self, url):
show_slug = self._match_id(url)
show = self._call_api(show_slug, show_slug)
show_info = self._extract_show_info(show)
entries = []
for episode in (show.get('episodes') or []):
entries.append(self._extract_episode(episode, show_info))
return self.playlist_result(
entries, show.get('id'), show.get('title'), show.get('description'))

262
plugins/youtube_download/yt_dlp/extractor/adn.py Normal file
View File

@ -0,0 +1,262 @@
# coding: utf-8
from __future__ import unicode_literals
import base64
import binascii
import json
import os
import random
from .common import InfoExtractor
from ..aes import aes_cbc_decrypt_bytes, unpad_pkcs7
from ..compat import (
compat_HTTPError,
compat_b64decode,
)
from ..utils import (
ass_subtitles_timecode,
bytes_to_intlist,
bytes_to_long,
ExtractorError,
float_or_none,
int_or_none,
intlist_to_bytes,
long_to_bytes,
pkcs1pad,
strip_or_none,
try_get,
unified_strdate,
urlencode_postdata,
)
class ADNIE(InfoExtractor):
IE_DESC = 'Anime Digital Network'
_VALID_URL = r'https?://(?:www\.)?animedigitalnetwork\.fr/video/[^/]+/(?P<id>\d+)'
_TEST = {
'url': 'http://animedigitalnetwork.fr/video/blue-exorcist-kyoto-saga/7778-episode-1-debut-des-hostilites',
'md5': '0319c99885ff5547565cacb4f3f9348d',
'info_dict': {
'id': '7778',
'ext': 'mp4',
'title': 'Blue Exorcist - Kyôto Saga - Episode 1',
'description': 'md5:2f7b5aa76edbc1a7a92cedcda8a528d5',
'series': 'Blue Exorcist - Kyôto Saga',
'duration': 1467,
'release_date': '20170106',
'comment_count': int,
'average_rating': float,
'season_number': 2,
'episode': 'Début des hostilités',
'episode_number': 1,
}
}
_NETRC_MACHINE = 'animedigitalnetwork'
_BASE_URL = 'http://animedigitalnetwork.fr'
_API_BASE_URL = 'https://gw.api.animedigitalnetwork.fr/'
_PLAYER_BASE_URL = _API_BASE_URL + 'player/'
_HEADERS = {}
_LOGIN_ERR_MESSAGE = 'Unable to log in'
_RSA_KEY = (0x9B42B08905199A5CCE2026274399CA560ECB209EE9878A708B1C0812E1BB8CB5D1FB7441861147C1A1F2F3A0476DD63A9CAC20D3E983613346850AA6CB38F16DC7D720FD7D86FC6E5B3D5BBC72E14CD0BF9E869F2CEA2CCAD648F1DCE38F1FF916CEFB2D339B64AA0264372344BC775E265E8A852F88144AB0BD9AA06C1A4ABB, 65537)
_POS_ALIGN_MAP = {
'start': 1,
'end': 3,
}
_LINE_ALIGN_MAP = {
'middle': 8,
'end': 4,
}
def _get_subtitles(self, sub_url, video_id):
if not sub_url:
return None
enc_subtitles = self._download_webpage(
sub_url, video_id, 'Downloading subtitles location', fatal=False) or '{}'
subtitle_location = (self._parse_json(enc_subtitles, video_id, fatal=False) or {}).get('location')
if subtitle_location:
enc_subtitles = self._download_webpage(
subtitle_location, video_id, 'Downloading subtitles data',
fatal=False, headers={'Origin': 'https://animedigitalnetwork.fr'})
if not enc_subtitles:
return None
# http://animedigitalnetwork.fr/components/com_vodvideo/videojs/adn-vjs.min.js
dec_subtitles = unpad_pkcs7(aes_cbc_decrypt_bytes(
compat_b64decode(enc_subtitles[24:]),
binascii.unhexlify(self._K + 'ab9f52f5baae7c72'),
compat_b64decode(enc_subtitles[:24])))
subtitles_json = self._parse_json(dec_subtitles.decode(), None, fatal=False)
if not subtitles_json:
return None
subtitles = {}
for sub_lang, sub in subtitles_json.items():
ssa = '''[Script Info]
ScriptType:V4.00
[V4 Styles]
Format: Name,Fontname,Fontsize,PrimaryColour,SecondaryColour,TertiaryColour,BackColour,Bold,Italic,BorderStyle,Outline,Shadow,Alignment,MarginL,MarginR,MarginV,AlphaLevel,Encoding
Style: Default,Arial,18,16777215,16777215,16777215,0,-1,0,1,1,0,2,20,20,20,0,0
[Events]
Format: Marked,Start,End,Style,Name,MarginL,MarginR,MarginV,Effect,Text'''
for current in sub:
start, end, text, line_align, position_align = (
float_or_none(current.get('startTime')),
float_or_none(current.get('endTime')),
current.get('text'), current.get('lineAlign'),
current.get('positionAlign'))
if start is None or end is None or text is None:
continue
alignment = self._POS_ALIGN_MAP.get(position_align, 2) + self._LINE_ALIGN_MAP.get(line_align, 0)
ssa += os.linesep + 'Dialogue: Marked=0,%s,%s,Default,,0,0,0,,%s%s' % (
ass_subtitles_timecode(start),
ass_subtitles_timecode(end),
'{\\a%d}' % alignment if alignment != 2 else '',
text.replace('\n', '\\N').replace('<i>', '{\\i1}').replace('</i>', '{\\i0}'))
if sub_lang == 'vostf':
sub_lang = 'fr'
subtitles.setdefault(sub_lang, []).extend([{
'ext': 'json',
'data': json.dumps(sub),
}, {
'ext': 'ssa',
'data': ssa,
}])
return subtitles
def _real_initialize(self):
username, password = self._get_login_info()
if not username:
return
try:
access_token = (self._download_json(
self._API_BASE_URL + 'authentication/login', None,
'Logging in', self._LOGIN_ERR_MESSAGE, fatal=False,
data=urlencode_postdata({
'password': password,
'rememberMe': False,
'source': 'Web',
'username': username,
})) or {}).get('accessToken')
if access_token:
self._HEADERS = {'authorization': 'Bearer ' + access_token}
except ExtractorError as e:
message = None
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401:
resp = self._parse_json(
e.cause.read().decode(), None, fatal=False) or {}
message = resp.get('message') or resp.get('code')
self.report_warning(message or self._LOGIN_ERR_MESSAGE)
def _real_extract(self, url):
video_id = self._match_id(url)
video_base_url = self._PLAYER_BASE_URL + 'video/%s/' % video_id
player = self._download_json(
video_base_url + 'configuration', video_id,
'Downloading player config JSON metadata',
headers=self._HEADERS)['player']
options = player['options']
user = options['user']
if not user.get('hasAccess'):
self.raise_login_required()
token = self._download_json(
user.get('refreshTokenUrl') or (self._PLAYER_BASE_URL + 'refresh/token'),
video_id, 'Downloading access token', headers={
'x-player-refresh-token': user['refreshToken']
}, data=b'')['token']
links_url = try_get(options, lambda x: x['video']['url']) or (video_base_url + 'link')
self._K = ''.join([random.choice('0123456789abcdef') for _ in range(16)])
message = bytes_to_intlist(json.dumps({
'k': self._K,
't': token,
}))
# Sometimes authentication fails for no good reason, retry with
# a different random padding
links_data = None
for _ in range(3):
padded_message = intlist_to_bytes(pkcs1pad(message, 128))
n, e = self._RSA_KEY
encrypted_message = long_to_bytes(pow(bytes_to_long(padded_message), e, n))
authorization = base64.b64encode(encrypted_message).decode()
try:
links_data = self._download_json(
links_url, video_id, 'Downloading links JSON metadata', headers={
'X-Player-Token': authorization
}, query={
'freeWithAds': 'true',
'adaptive': 'false',
'withMetadata': 'true',
'source': 'Web'
})
break
except ExtractorError as e:
if not isinstance(e.cause, compat_HTTPError):
raise e
if e.cause.code == 401:
# This usually goes away with a different random pkcs1pad, so retry
continue
error = self._parse_json(e.cause.read(), video_id)
message = error.get('message')
if e.cause.code == 403 and error.get('code') == 'player-bad-geolocation-country':
self.raise_geo_restricted(msg=message)
raise ExtractorError(message)
else:
raise ExtractorError('Giving up retrying')
links = links_data.get('links') or {}
metas = links_data.get('metadata') or {}
sub_url = (links.get('subtitles') or {}).get('all')
video_info = links_data.get('video') or {}
title = metas['title']
formats = []
for format_id, qualities in (links.get('streaming') or {}).items():
if not isinstance(qualities, dict):
continue
for quality, load_balancer_url in qualities.items():
load_balancer_data = self._download_json(
load_balancer_url, video_id,
'Downloading %s %s JSON metadata' % (format_id, quality),
fatal=False) or {}
m3u8_url = load_balancer_data.get('location')
if not m3u8_url:
continue
m3u8_formats = self._extract_m3u8_formats(
m3u8_url, video_id, 'mp4', 'm3u8_native',
m3u8_id=format_id, fatal=False)
if format_id == 'vf':
for f in m3u8_formats:
f['language'] = 'fr'
formats.extend(m3u8_formats)
self._sort_formats(formats)
video = (self._download_json(
self._API_BASE_URL + 'video/%s' % video_id, video_id,
'Downloading additional video metadata', fatal=False) or {}).get('video') or {}
show = video.get('show') or {}
return {
'id': video_id,
'title': title,
'description': strip_or_none(metas.get('summary') or video.get('summary')),
'thumbnail': video_info.get('image') or player.get('image'),
'formats': formats,
'subtitles': self.extract_subtitles(sub_url, video_id),
'episode': metas.get('subtitle') or video.get('name'),
'episode_number': int_or_none(video.get('shortNumber')),
'series': show.get('title'),
'season_number': int_or_none(video.get('season')),
'duration': int_or_none(video_info.get('duration') or video.get('duration')),
'release_date': unified_strdate(video.get('releaseDate')),
'average_rating': float_or_none(video.get('rating') or metas.get('rating')),
'comment_count': int_or_none(video.get('commentsCount')),
}

37
plugins/youtube_download/yt_dlp/extractor/adobeconnect.py Normal file
View File

@ -0,0 +1,37 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..compat import (
compat_parse_qs,
compat_urlparse,
)
class AdobeConnectIE(InfoExtractor):
_VALID_URL = r'https?://\w+\.adobeconnect\.com/(?P<id>[\w-]+)'
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
title = self._html_search_regex(r'<title>(.+?)</title>', webpage, 'title')
qs = compat_parse_qs(self._search_regex(r"swfUrl\s*=\s*'([^']+)'", webpage, 'swf url').split('?')[1])
is_live = qs.get('isLive', ['false'])[0] == 'true'
formats = []
for con_string in qs['conStrings'][0].split(','):
formats.append({
'format_id': con_string.split('://')[0],
'app': compat_urlparse.quote('?' + con_string.split('?')[1] + 'flvplayerapp/' + qs['appInstance'][0]),
'ext': 'flv',
'play_path': 'mp4:' + qs['streamName'][0],
'rtmp_conn': 'S:' + qs['ticket'][0],
'rtmp_live': is_live,
'url': con_string,
})
return {
'id': video_id,
'title': title,
'formats': formats,
'is_live': is_live,
}

1715
plugins/youtube_download/yt_dlp/extractor/adobepass.py Normal file
View File

File diff suppressed because it is too large Load Diff

289
plugins/youtube_download/yt_dlp/extractor/adobetv.py Normal file
View File

@ -0,0 +1,289 @@
from __future__ import unicode_literals
import functools
import re
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
float_or_none,
int_or_none,
ISO639Utils,
join_nonempty,
OnDemandPagedList,
parse_duration,
str_or_none,
str_to_int,
unified_strdate,
)
class AdobeTVBaseIE(InfoExtractor):
def _call_api(self, path, video_id, query, note=None):
return self._download_json(
'http://tv.adobe.com/api/v4/' + path,
video_id, note, query=query)['data']
def _parse_subtitles(self, video_data, url_key):
subtitles = {}
for translation in video_data.get('translations', []):
vtt_path = translation.get(url_key)
if not vtt_path:
continue
lang = translation.get('language_w3c') or ISO639Utils.long2short(translation['language_medium'])
subtitles.setdefault(lang, []).append({
'ext': 'vtt',
'url': vtt_path,
})
return subtitles
def _parse_video_data(self, video_data):
video_id = compat_str(video_data['id'])
title = video_data['title']
s3_extracted = False
formats = []
for source in video_data.get('videos', []):
source_url = source.get('url')
if not source_url:
continue
f = {
'format_id': source.get('quality_level'),
'fps': int_or_none(source.get('frame_rate')),
'height': int_or_none(source.get('height')),
'tbr': int_or_none(source.get('video_data_rate')),
'width': int_or_none(source.get('width')),
'url': source_url,
}
original_filename = source.get('original_filename')
if original_filename:
if not (f.get('height') and f.get('width')):
mobj = re.search(r'_(\d+)x(\d+)', original_filename)
if mobj:
f.update({
'height': int(mobj.group(2)),
'width': int(mobj.group(1)),
})
if original_filename.startswith('s3://') and not s3_extracted:
formats.append({
'format_id': 'original',
'quality': 1,
'url': original_filename.replace('s3://', 'https://s3.amazonaws.com/'),
})
s3_extracted = True
formats.append(f)
self._sort_formats(formats)
return {
'id': video_id,
'title': title,
'description': video_data.get('description'),
'thumbnail': video_data.get('thumbnail'),
'upload_date': unified_strdate(video_data.get('start_date')),
'duration': parse_duration(video_data.get('duration')),
'view_count': str_to_int(video_data.get('playcount')),
'formats': formats,
'subtitles': self._parse_subtitles(video_data, 'vtt'),
}
class AdobeTVEmbedIE(AdobeTVBaseIE):
IE_NAME = 'adobetv:embed'
_VALID_URL = r'https?://tv\.adobe\.com/embed/\d+/(?P<id>\d+)'
_TEST = {
'url': 'https://tv.adobe.com/embed/22/4153',
'md5': 'c8c0461bf04d54574fc2b4d07ac6783a',
'info_dict': {
'id': '4153',
'ext': 'flv',
'title': 'Creating Graphics Optimized for BlackBerry',
'description': 'md5:eac6e8dced38bdaae51cd94447927459',
'thumbnail': r're:https?://.*\.jpg$',
'upload_date': '20091109',
'duration': 377,
'view_count': int,
},
}
def _real_extract(self, url):
video_id = self._match_id(url)
video_data = self._call_api(
'episode/' + video_id, video_id, {'disclosure': 'standard'})[0]
return self._parse_video_data(video_data)
class AdobeTVIE(AdobeTVBaseIE):
IE_NAME = 'adobetv'
_VALID_URL = r'https?://tv\.adobe\.com/(?:(?P<language>fr|de|es|jp)/)?watch/(?P<show_urlname>[^/]+)/(?P<id>[^/]+)'
_TEST = {
'url': 'http://tv.adobe.com/watch/the-complete-picture-with-julieanne-kost/quick-tip-how-to-draw-a-circle-around-an-object-in-photoshop/',
'md5': '9bc5727bcdd55251f35ad311ca74fa1e',
'info_dict': {
'id': '10981',
'ext': 'mp4',
'title': 'Quick Tip - How to Draw a Circle Around an Object in Photoshop',
'description': 'md5:99ec318dc909d7ba2a1f2b038f7d2311',
'thumbnail': r're:https?://.*\.jpg$',
'upload_date': '20110914',
'duration': 60,
'view_count': int,
},
}
def _real_extract(self, url):
language, show_urlname, urlname = self._match_valid_url(url).groups()
if not language:
language = 'en'
video_data = self._call_api(
'episode/get', urlname, {
'disclosure': 'standard',
'language': language,
'show_urlname': show_urlname,
'urlname': urlname,
})[0]
return self._parse_video_data(video_data)
class AdobeTVPlaylistBaseIE(AdobeTVBaseIE):
_PAGE_SIZE = 25
def _fetch_page(self, display_id, query, page):
page += 1
query['page'] = page
for element_data in self._call_api(
self._RESOURCE, display_id, query, 'Download Page %d' % page):
yield self._process_data(element_data)
def _extract_playlist_entries(self, display_id, query):
return OnDemandPagedList(functools.partial(
self._fetch_page, display_id, query), self._PAGE_SIZE)
class AdobeTVShowIE(AdobeTVPlaylistBaseIE):
IE_NAME = 'adobetv:show'
_VALID_URL = r'https?://tv\.adobe\.com/(?:(?P<language>fr|de|es|jp)/)?show/(?P<id>[^/]+)'
_TEST = {
'url': 'http://tv.adobe.com/show/the-complete-picture-with-julieanne-kost',
'info_dict': {
'id': '36',
'title': 'The Complete Picture with Julieanne Kost',
'description': 'md5:fa50867102dcd1aa0ddf2ab039311b27',
},
'playlist_mincount': 136,
}
_RESOURCE = 'episode'
_process_data = AdobeTVBaseIE._parse_video_data
def _real_extract(self, url):
language, show_urlname = self._match_valid_url(url).groups()
if not language:
language = 'en'
query = {
'disclosure': 'standard',
'language': language,
'show_urlname': show_urlname,
}
show_data = self._call_api(
'show/get', show_urlname, query)[0]
return self.playlist_result(
self._extract_playlist_entries(show_urlname, query),
str_or_none(show_data.get('id')),
show_data.get('show_name'),
show_data.get('show_description'))
class AdobeTVChannelIE(AdobeTVPlaylistBaseIE):
IE_NAME = 'adobetv:channel'
_VALID_URL = r'https?://tv\.adobe\.com/(?:(?P<language>fr|de|es|jp)/)?channel/(?P<id>[^/]+)(?:/(?P<category_urlname>[^/]+))?'
_TEST = {
'url': 'http://tv.adobe.com/channel/development',
'info_dict': {
'id': 'development',
},
'playlist_mincount': 96,
}
_RESOURCE = 'show'
def _process_data(self, show_data):
return self.url_result(
show_data['url'], 'AdobeTVShow', str_or_none(show_data.get('id')))
def _real_extract(self, url):
language, channel_urlname, category_urlname = self._match_valid_url(url).groups()
if not language:
language = 'en'
query = {
'channel_urlname': channel_urlname,
'language': language,
}
if category_urlname:
query['category_urlname'] = category_urlname
return self.playlist_result(
self._extract_playlist_entries(channel_urlname, query),
channel_urlname)
class AdobeTVVideoIE(AdobeTVBaseIE):
IE_NAME = 'adobetv:video'
_VALID_URL = r'https?://video\.tv\.adobe\.com/v/(?P<id>\d+)'
_TEST = {
# From https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners
'url': 'https://video.tv.adobe.com/v/2456/',
'md5': '43662b577c018ad707a63766462b1e87',
'info_dict': {
'id': '2456',
'ext': 'mp4',
'title': 'New experience with Acrobat DC',
'description': 'New experience with Acrobat DC',
'duration': 248.667,
},
}
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
video_data = self._parse_json(self._search_regex(
r'var\s+bridge\s*=\s*([^;]+);', webpage, 'bridged data'), video_id)
title = video_data['title']
formats = []
sources = video_data.get('sources') or []
for source in sources:
source_src = source.get('src')
if not source_src:
continue
formats.append({
'filesize': int_or_none(source.get('kilobytes') or None, invscale=1000),
'format_id': join_nonempty(source.get('format'), source.get('label')),
'height': int_or_none(source.get('height') or None),
'tbr': int_or_none(source.get('bitrate') or None),
'width': int_or_none(source.get('width') or None),
'url': source_src,
})
self._sort_formats(formats)
# For both metadata and downloaded files the duration varies among
# formats. I just pick the max one
duration = max(filter(None, [
float_or_none(source.get('duration'), scale=1000)
for source in sources]))
return {
'id': video_id,
'formats': formats,
'title': title,
'description': video_data.get('description'),
'thumbnail': video_data.get('video', {}).get('poster'),
'duration': duration,
'subtitles': self._parse_subtitles(video_data, 'vttPath'),
}

201
plugins/youtube_download/yt_dlp/extractor/adultswim.py Normal file
View File

@ -0,0 +1,201 @@
# coding: utf-8
from __future__ import unicode_literals
import json
from .turner import TurnerBaseIE
from ..utils import (
determine_ext,
float_or_none,
int_or_none,
mimetype2ext,
parse_age_limit,
parse_iso8601,
strip_or_none,
try_get,
)
class AdultSwimIE(TurnerBaseIE):
_VALID_URL = r'https?://(?:www\.)?adultswim\.com/videos/(?P<show_path>[^/?#]+)(?:/(?P<episode_path>[^/?#]+))?'
_TESTS = [{
'url': 'http://adultswim.com/videos/rick-and-morty/pilot',
'info_dict': {
'id': 'rQxZvXQ4ROaSOqq-or2Mow',
'ext': 'mp4',
'title': 'Rick and Morty - Pilot',
'description': 'Rick moves in with his daughter\'s family and establishes himself as a bad influence on his grandson, Morty.',
'timestamp': 1543294800,
'upload_date': '20181127',
},
'params': {
# m3u8 download
'skip_download': True,
},
'expected_warnings': ['Unable to download f4m manifest'],
}, {
'url': 'http://www.adultswim.com/videos/tim-and-eric-awesome-show-great-job/dr-steve-brule-for-your-wine/',
'info_dict': {
'id': 'sY3cMUR_TbuE4YmdjzbIcQ',
'ext': 'mp4',
'title': 'Tim and Eric Awesome Show Great Job! - Dr. Steve Brule, For Your Wine',
'description': 'Dr. Brule reports live from Wine Country with a special report on wines. \nWatch Tim and Eric Awesome Show Great Job! episode #20, "Embarrassed" on Adult Swim.',
'upload_date': '20080124',
'timestamp': 1201150800,
},
'params': {
# m3u8 download
'skip_download': True,
},
'skip': '404 Not Found',
}, {
'url': 'http://www.adultswim.com/videos/decker/inside-decker-a-new-hero/',
'info_dict': {
'id': 'I0LQFQkaSUaFp8PnAWHhoQ',
'ext': 'mp4',
'title': 'Decker - Inside Decker: A New Hero',
'description': 'The guys recap the conclusion of the season. They announce a new hero, take a peek into the Victorville Film Archive and welcome back the talented James Dean.',
'timestamp': 1469480460,
'upload_date': '20160725',
},
'params': {
# m3u8 download
'skip_download': True,
},
'expected_warnings': ['Unable to download f4m manifest'],
}, {
'url': 'http://www.adultswim.com/videos/attack-on-titan',
'info_dict': {
'id': 'attack-on-titan',
'title': 'Attack on Titan',
'description': 'md5:41caa9416906d90711e31dc00cb7db7e',
},
'playlist_mincount': 12,
}, {
'url': 'http://www.adultswim.com/videos/streams/williams-stream',
'info_dict': {
'id': 'd8DEBj7QRfetLsRgFnGEyg',
'ext': 'mp4',
'title': r're:^Williams Stream \d{4}-\d{2}-\d{2} \d{2}:\d{2}$',
'description': 'original programming',
},
'params': {
# m3u8 download
'skip_download': True,
},
'skip': '404 Not Found',
}]
def _real_extract(self, url):
show_path, episode_path = self._match_valid_url(url).groups()
display_id = episode_path or show_path
query = '''query {
getShowBySlug(slug:"%s") {
%%s
}
}''' % show_path
if episode_path:
query = query % '''title
getVideoBySlug(slug:"%s") {
_id
auth
description
duration
episodeNumber
launchDate
mediaID
seasonNumber
poster
title
tvRating
}''' % episode_path
['getVideoBySlug']
else:
query = query % '''metaDescription
title
videos(first:1000,sort:["episode_number"]) {
edges {
node {
_id
slug
}
}
}'''
show_data = self._download_json(
'https://www.adultswim.com/api/search', display_id,
data=json.dumps({'query': query}).encode(),
headers={'Content-Type': 'application/json'})['data']['getShowBySlug']
if episode_path:
video_data = show_data['getVideoBySlug']
video_id = video_data['_id']
episode_title = title = video_data['title']
series = show_data.get('title')
if series:
title = '%s - %s' % (series, title)
info = {
'id': video_id,
'title': title,
'description': strip_or_none(video_data.get('description')),
'duration': float_or_none(video_data.get('duration')),
'formats': [],
'subtitles': {},
'age_limit': parse_age_limit(video_data.get('tvRating')),
'thumbnail': video_data.get('poster'),
'timestamp': parse_iso8601(video_data.get('launchDate')),
'series': series,
'season_number': int_or_none(video_data.get('seasonNumber')),
'episode': episode_title,
'episode_number': int_or_none(video_data.get('episodeNumber')),
}
auth = video_data.get('auth')
media_id = video_data.get('mediaID')
if media_id:
info.update(self._extract_ngtv_info(media_id, {
# CDN_TOKEN_APP_ID from:
# https://d2gg02c3xr550i.cloudfront.net/assets/asvp.e9c8bef24322d060ef87.bundle.js
'appId': 'eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJhcHBJZCI6ImFzLXR2ZS1kZXNrdG9wLXB0enQ2bSIsInByb2R1Y3QiOiJ0dmUiLCJuZXR3b3JrIjoiYXMiLCJwbGF0Zm9ybSI6ImRlc2t0b3AiLCJpYXQiOjE1MzI3MDIyNzl9.BzSCk-WYOZ2GMCIaeVb8zWnzhlgnXuJTCu0jGp_VaZE',
}, {
'url': url,
'site_name': 'AdultSwim',
'auth_required': auth,
}))
if not auth:
extract_data = self._download_json(
'https://www.adultswim.com/api/shows/v1/videos/' + video_id,
video_id, query={'fields': 'stream'}, fatal=False) or {}
assets = try_get(extract_data, lambda x: x['data']['video']['stream']['assets'], list) or []
for asset in assets:
asset_url = asset.get('url')
if not asset_url:
continue
ext = determine_ext(asset_url, mimetype2ext(asset.get('mime_type')))
if ext == 'm3u8':
info['formats'].extend(self._extract_m3u8_formats(
asset_url, video_id, 'mp4', m3u8_id='hls', fatal=False))
elif ext == 'f4m':
continue
# info['formats'].extend(self._extract_f4m_formats(
# asset_url, video_id, f4m_id='hds', fatal=False))
elif ext in ('scc', 'ttml', 'vtt'):
info['subtitles'].setdefault('en', []).append({
'url': asset_url,
})
self._sort_formats(info['formats'])
return info
else:
entries = []
for edge in show_data.get('videos', {}).get('edges', []):
video = edge.get('node') or {}
slug = video.get('slug')
if not slug:
continue
entries.append(self.url_result(
'http://adultswim.com/videos/%s/%s' % (show_path, slug),
'AdultSwim', video.get('_id')))
return self.playlist_result(
entries, show_path, show_data.get('title'),
strip_or_none(show_data.get('metaDescription')))

341
plugins/youtube_download/yt_dlp/extractor/aenetworks.py Normal file
View File

@ -0,0 +1,341 @@
# coding: utf-8
from __future__ import unicode_literals
from .theplatform import ThePlatformIE
from ..utils import (
ExtractorError,
GeoRestrictedError,
int_or_none,
update_url_query,
urlencode_postdata,
)
class AENetworksBaseIE(ThePlatformIE):
_BASE_URL_REGEX = r'''(?x)https?://
(?:(?:www|play|watch)\.)?
(?P<domain>
(?:history(?:vault)?|aetv|mylifetime|lifetimemovieclub)\.com|
fyi\.tv
)/'''
_THEPLATFORM_KEY = '43jXaGRQud'
_THEPLATFORM_SECRET = 'S10BPXHMlb'
_DOMAIN_MAP = {
'history.com': ('HISTORY', 'history'),
'aetv.com': ('AETV', 'aetv'),
'mylifetime.com': ('LIFETIME', 'lifetime'),
'lifetimemovieclub.com': ('LIFETIMEMOVIECLUB', 'lmc'),
'fyi.tv': ('FYI', 'fyi'),
'historyvault.com': (None, 'historyvault'),
'biography.com': (None, 'biography'),
}
def _extract_aen_smil(self, smil_url, video_id, auth=None):
query = {'mbr': 'true'}
if auth:
query['auth'] = auth
TP_SMIL_QUERY = [{
'assetTypes': 'high_video_ak',
'switch': 'hls_high_ak'
}, {
'assetTypes': 'high_video_s3'
}, {
'assetTypes': 'high_video_s3',
'switch': 'hls_high_fastly',
}]
formats = []
subtitles = {}
last_e = None
for q in TP_SMIL_QUERY:
q.update(query)
m_url = update_url_query(smil_url, q)
m_url = self._sign_url(m_url, self._THEPLATFORM_KEY, self._THEPLATFORM_SECRET)
try:
tp_formats, tp_subtitles = self._extract_theplatform_smil(
m_url, video_id, 'Downloading %s SMIL data' % (q.get('switch') or q['assetTypes']))
except ExtractorError as e:
if isinstance(e, GeoRestrictedError):
raise
last_e = e
continue
formats.extend(tp_formats)
subtitles = self._merge_subtitles(subtitles, tp_subtitles)
if last_e and not formats:
raise last_e
self._sort_formats(formats)
return {
'id': video_id,
'formats': formats,
'subtitles': subtitles,
}
def _extract_aetn_info(self, domain, filter_key, filter_value, url):
requestor_id, brand = self._DOMAIN_MAP[domain]
result = self._download_json(
'https://feeds.video.aetnd.com/api/v2/%s/videos' % brand,
filter_value, query={'filter[%s]' % filter_key: filter_value})['results'][0]
title = result['title']
video_id = result['id']
media_url = result['publicUrl']
theplatform_metadata = self._download_theplatform_metadata(self._search_regex(
r'https?://link\.theplatform\.com/s/([^?]+)', media_url, 'theplatform_path'), video_id)
info = self._parse_theplatform_metadata(theplatform_metadata)
auth = None
if theplatform_metadata.get('AETN$isBehindWall'):
resource = self._get_mvpd_resource(
requestor_id, theplatform_metadata['title'],
theplatform_metadata.get('AETN$PPL_pplProgramId') or theplatform_metadata.get('AETN$PPL_pplProgramId_OLD'),
theplatform_metadata['ratings'][0]['rating'])
auth = self._extract_mvpd_auth(
url, video_id, requestor_id, resource)
info.update(self._extract_aen_smil(media_url, video_id, auth))
info.update({
'title': title,
'series': result.get('seriesName'),
'season_number': int_or_none(result.get('tvSeasonNumber')),
'episode_number': int_or_none(result.get('tvSeasonEpisodeNumber')),
})
return info
class AENetworksIE(AENetworksBaseIE):
IE_NAME = 'aenetworks'
IE_DESC = 'A+E Networks: A&E, Lifetime, History.com, FYI Network and History Vault'
_VALID_URL = AENetworksBaseIE._BASE_URL_REGEX + r'''(?P<id>
shows/[^/]+/season-\d+/episode-\d+|
(?:
(?:movie|special)s/[^/]+|
(?:shows/[^/]+/)?videos
)/[^/?#&]+
)'''
_TESTS = [{
'url': 'http://www.history.com/shows/mountain-men/season-1/episode-1',
'info_dict': {
'id': '22253814',
'ext': 'mp4',
'title': 'Winter is Coming',
'description': 'md5:641f424b7a19d8e24f26dea22cf59d74',
'timestamp': 1338306241,
'upload_date': '20120529',
'uploader': 'AENE-NEW',
},
'params': {
# m3u8 download
'skip_download': True,
},
'add_ie': ['ThePlatform'],
'skip': 'This video is only available for users of participating TV providers.',
}, {
'url': 'http://www.aetv.com/shows/duck-dynasty/season-9/episode-1',
'info_dict': {
'id': '600587331957',
'ext': 'mp4',
'title': 'Inlawful Entry',
'description': 'md5:57c12115a2b384d883fe64ca50529e08',
'timestamp': 1452634428,
'upload_date': '20160112',
'uploader': 'AENE-NEW',
},
'params': {
# m3u8 download
'skip_download': True,
},
'add_ie': ['ThePlatform'],
}, {
'url': 'http://www.fyi.tv/shows/tiny-house-nation/season-1/episode-8',
'only_matching': True
}, {
'url': 'http://www.mylifetime.com/shows/project-runway-junior/season-1/episode-6',
'only_matching': True
}, {
'url': 'http://www.mylifetime.com/movies/center-stage-on-pointe/full-movie',
'only_matching': True
}, {
'url': 'https://watch.lifetimemovieclub.com/movies/10-year-reunion/full-movie',
'only_matching': True
}, {
'url': 'http://www.history.com/specials/sniper-into-the-kill-zone/full-special',
'only_matching': True
}, {
'url': 'https://www.aetv.com/specials/hunting-jonbenets-killer-the-untold-story/preview-hunting-jonbenets-killer-the-untold-story',
'only_matching': True
}, {
'url': 'http://www.history.com/videos/history-of-valentines-day',
'only_matching': True
}, {
'url': 'https://play.aetv.com/shows/duck-dynasty/videos/best-of-duck-dynasty-getting-quack-in-shape',
'only_matching': True
}]
def _real_extract(self, url):
domain, canonical = self._match_valid_url(url).groups()
return self._extract_aetn_info(domain, 'canonical', '/' + canonical, url)
class AENetworksListBaseIE(AENetworksBaseIE):
def _call_api(self, resource, slug, brand, fields):
return self._download_json(
'https://yoga.appsvcs.aetnd.com/graphql',
slug, query={'brand': brand}, data=urlencode_postdata({
'query': '''{
%s(slug: "%s") {
%s
}
}''' % (resource, slug, fields),
}))['data'][resource]
def _real_extract(self, url):
domain, slug = self._match_valid_url(url).groups()
_, brand = self._DOMAIN_MAP[domain]
playlist = self._call_api(self._RESOURCE, slug, brand, self._FIELDS)
base_url = 'http://watch.%s' % domain
entries = []
for item in (playlist.get(self._ITEMS_KEY) or []):
doc = self._get_doc(item)
canonical = doc.get('canonical')
if not canonical:
continue
entries.append(self.url_result(
base_url + canonical, AENetworksIE.ie_key(), doc.get('id')))
description = None
if self._PLAYLIST_DESCRIPTION_KEY:
description = playlist.get(self._PLAYLIST_DESCRIPTION_KEY)
return self.playlist_result(
entries, playlist.get('id'),
playlist.get(self._PLAYLIST_TITLE_KEY), description)
class AENetworksCollectionIE(AENetworksListBaseIE):
IE_NAME = 'aenetworks:collection'
_VALID_URL = AENetworksBaseIE._BASE_URL_REGEX + r'(?:[^/]+/)*(?:list|collections)/(?P<id>[^/?#&]+)/?(?:[?#&]|$)'
_TESTS = [{
'url': 'https://watch.historyvault.com/list/america-the-story-of-us',
'info_dict': {
'id': '282',
'title': 'America The Story of Us',
},
'playlist_mincount': 12,
}, {
'url': 'https://watch.historyvault.com/shows/america-the-story-of-us-2/season-1/list/america-the-story-of-us',
'only_matching': True
}, {
'url': 'https://www.historyvault.com/collections/mysteryquest',
'only_matching': True
}]
_RESOURCE = 'list'
_ITEMS_KEY = 'items'
_PLAYLIST_TITLE_KEY = 'display_title'
_PLAYLIST_DESCRIPTION_KEY = None
_FIELDS = '''id
display_title
items {
... on ListVideoItem {
doc {
canonical
id
}
}
}'''
def _get_doc(self, item):
return item.get('doc') or {}
class AENetworksShowIE(AENetworksListBaseIE):
IE_NAME = 'aenetworks:show'
_VALID_URL = AENetworksBaseIE._BASE_URL_REGEX + r'shows/(?P<id>[^/?#&]+)/?(?:[?#&]|$)'
_TESTS = [{
'url': 'http://www.history.com/shows/ancient-aliens',
'info_dict': {
'id': 'SERIES1574',
'title': 'Ancient Aliens',
'description': 'md5:3f6d74daf2672ff3ae29ed732e37ea7f',
},
'playlist_mincount': 150,
}]
_RESOURCE = 'series'
_ITEMS_KEY = 'episodes'
_PLAYLIST_TITLE_KEY = 'title'
_PLAYLIST_DESCRIPTION_KEY = 'description'
_FIELDS = '''description
id
title
episodes {
canonical
id
}'''
def _get_doc(self, item):
return item
class HistoryTopicIE(AENetworksBaseIE):
IE_NAME = 'history:topic'
IE_DESC = 'History.com Topic'
_VALID_URL = r'https?://(?:www\.)?history\.com/topics/[^/]+/(?P<id>[\w+-]+?)-video'
_TESTS = [{
'url': 'https://www.history.com/topics/valentines-day/history-of-valentines-day-video',
'info_dict': {
'id': '40700995724',
'ext': 'mp4',
'title': "History of Valentine’s Day",
'description': 'md5:7b57ea4829b391995b405fa60bd7b5f7',
'timestamp': 1375819729,
'upload_date': '20130806',
'uploader': 'AENE-NEW',
},
'params': {
# m3u8 download
'skip_download': True,
},
'add_ie': ['ThePlatform'],
}]
def _real_extract(self, url):
display_id = self._match_id(url)
return self.url_result(
'http://www.history.com/videos/' + display_id,
AENetworksIE.ie_key())
class HistoryPlayerIE(AENetworksBaseIE):
IE_NAME = 'history:player'
_VALID_URL = r'https?://(?:www\.)?(?P<domain>(?:history|biography)\.com)/player/(?P<id>\d+)'
_TESTS = []
def _real_extract(self, url):
domain, video_id = self._match_valid_url(url).groups()
return self._extract_aetn_info(domain, 'id', video_id, url)
class BiographyIE(AENetworksBaseIE):
_VALID_URL = r'https?://(?:www\.)?biography\.com/video/(?P<id>[^/?#&]+)'
_TESTS = [{
'url': 'https://www.biography.com/video/vincent-van-gogh-full-episode-2075049808',
'info_dict': {
'id': '30322987',
'ext': 'mp4',
'title': 'Vincent Van Gogh - Full Episode',
'description': 'A full biography about the most influential 20th century painter, Vincent Van Gogh.',
'timestamp': 1311970571,
'upload_date': '20110729',
'uploader': 'AENE-NEW',
},
'params': {
# m3u8 download
'skip_download': True,
},
'add_ie': ['ThePlatform'],
}]
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
player_url = self._search_regex(
r'<phoenix-iframe[^>]+src="(%s)' % HistoryPlayerIE._VALID_URL,
webpage, 'player URL')
return self.url_result(player_url, HistoryPlayerIE.ie_key())

479
plugins/youtube_download/yt_dlp/extractor/afreecatv.py Normal file
View File

@ -0,0 +1,479 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import compat_xpath
from ..utils import (
date_from_str,
determine_ext,
ExtractorError,
int_or_none,
qualities,
traverse_obj,
unified_strdate,
unified_timestamp,
update_url_query,
url_or_none,
urlencode_postdata,
xpath_text,
)
class AfreecaTVIE(InfoExtractor):
IE_NAME = 'afreecatv'
IE_DESC = 'afreecatv.com'
_VALID_URL = r'''(?x)
https?://
(?:
(?:(?:live|afbbs|www)\.)?afreeca(?:tv)?\.com(?::\d+)?
(?:
/app/(?:index|read_ucc_bbs)\.cgi|
/player/[Pp]layer\.(?:swf|html)
)\?.*?\bnTitleNo=|
vod\.afreecatv\.com/PLAYER/STATION/
)
(?P<id>\d+)
'''
_NETRC_MACHINE = 'afreecatv'
_TESTS = [{
'url': 'http://live.afreecatv.com:8079/app/index.cgi?szType=read_ucc_bbs&szBjId=dailyapril&nStationNo=16711924&nBbsNo=18605867&nTitleNo=36164052&szSkin=',
'md5': 'f72c89fe7ecc14c1b5ce506c4996046e',
'info_dict': {
'id': '36164052',
'ext': 'mp4',
'title': '데일리 에이프릴 요정들의 시상식!',
'thumbnail': 're:^https?://(?:video|st)img.afreecatv.com/.*$',
'uploader': 'dailyapril',
'uploader_id': 'dailyapril',
'upload_date': '20160503',
},
'skip': 'Video is gone',
}, {
'url': 'http://afbbs.afreecatv.com:8080/app/read_ucc_bbs.cgi?nStationNo=16711924&nTitleNo=36153164&szBjId=dailyapril&nBbsNo=18605867',
'info_dict': {
'id': '36153164',
'title': "BJ유트루와 함께하는 '팅커벨 메이크업!'",
'thumbnail': 're:^https?://(?:video|st)img.afreecatv.com/.*$',
'uploader': 'dailyapril',
'uploader_id': 'dailyapril',
},
'playlist_count': 2,
'playlist': [{
'md5': 'd8b7c174568da61d774ef0203159bf97',
'info_dict': {
'id': '36153164_1',
'ext': 'mp4',
'title': "BJ유트루와 함께하는 '팅커벨 메이크업!'",
'upload_date': '20160502',
},
}, {
'md5': '58f2ce7f6044e34439ab2d50612ab02b',
'info_dict': {
'id': '36153164_2',
'ext': 'mp4',
'title': "BJ유트루와 함께하는 '팅커벨 메이크업!'",
'upload_date': '20160502',
},
}],
'skip': 'Video is gone',
}, {
'url': 'http://vod.afreecatv.com/PLAYER/STATION/18650793',
'info_dict': {
'id': '18650793',
'ext': 'mp4',
'title': '오늘은 다르다! 쏘님의 우월한 위아래~ 댄스리액션!',
'thumbnail': r're:^https?://.*\.jpg$',
'uploader': '윈아디',
'uploader_id': 'badkids',
'duration': 107,
},
'params': {
'skip_download': True,
},
}, {
'url': 'http://vod.afreecatv.com/PLAYER/STATION/10481652',
'info_dict': {
'id': '10481652',
'title': "BJ유트루와 함께하는 '팅커벨 메이크업!'",
'thumbnail': 're:^https?://(?:video|st)img.afreecatv.com/.*$',
'uploader': 'dailyapril',
'uploader_id': 'dailyapril',
'duration': 6492,
},
'playlist_count': 2,
'playlist': [{
'md5': 'd8b7c174568da61d774ef0203159bf97',
'info_dict': {
'id': '20160502_c4c62b9d_174361386_1',
'ext': 'mp4',
'title': "BJ유트루와 함께하는 '팅커벨 메이크업!' (part 1)",
'thumbnail': 're:^https?://(?:video|st)img.afreecatv.com/.*$',
'uploader': 'dailyapril',
'uploader_id': 'dailyapril',
'upload_date': '20160502',
'duration': 3601,
},
}, {
'md5': '58f2ce7f6044e34439ab2d50612ab02b',
'info_dict': {
'id': '20160502_39e739bb_174361386_2',
'ext': 'mp4',
'title': "BJ유트루와 함께하는 '팅커벨 메이크업!' (part 2)",
'thumbnail': 're:^https?://(?:video|st)img.afreecatv.com/.*$',
'uploader': 'dailyapril',
'uploader_id': 'dailyapril',
'upload_date': '20160502',
'duration': 2891,
},
}],
'params': {
'skip_download': True,
},
}, {
# non standard key
'url': 'http://vod.afreecatv.com/PLAYER/STATION/20515605',
'info_dict': {
'id': '20170411_BE689A0E_190960999_1_2_h',
'ext': 'mp4',
'title': '혼자사는여자집',
'thumbnail': 're:^https?://(?:video|st)img.afreecatv.com/.*$',
'uploader': '♥이슬이',
'uploader_id': 'dasl8121',
'upload_date': '20170411',
'duration': 213,
},
'params': {
'skip_download': True,
},
}, {
# PARTIAL_ADULT
'url': 'http://vod.afreecatv.com/PLAYER/STATION/32028439',
'info_dict': {
'id': '20180327_27901457_202289533_1',
'ext': 'mp4',
'title': '[생]빨개요♥ (part 1)',
'thumbnail': 're:^https?://(?:video|st)img.afreecatv.com/.*$',
'uploader': '[SA]서아',
'uploader_id': 'bjdyrksu',
'upload_date': '20180327',
'duration': 3601,
},
'params': {
'skip_download': True,
},
'expected_warnings': ['adult content'],
}, {
'url': 'http://www.afreecatv.com/player/Player.swf?szType=szBjId=djleegoon&nStationNo=11273158&nBbsNo=13161095&nTitleNo=36327652',
'only_matching': True,
}, {
'url': 'http://vod.afreecatv.com/PLAYER/STATION/15055030',
'only_matching': True,
}]
@staticmethod
def parse_video_key(key):
video_key = {}
m = re.match(r'^(?P<upload_date>\d{8})_\w+_(?P<part>\d+)$', key)
if m:
video_key['upload_date'] = m.group('upload_date')
video_key['part'] = int(m.group('part'))
return video_key
def _real_initialize(self):
self._login()
def _login(self):
username, password = self._get_login_info()
if username is None:
return
login_form = {
'szWork': 'login',
'szType': 'json',
'szUid': username,
'szPassword': password,
'isSaveId': 'false',
'szScriptVar': 'oLoginRet',
'szAction': '',
}
response = self._download_json(
'https://login.afreecatv.com/app/LoginAction.php', None,
'Logging in', data=urlencode_postdata(login_form))
_ERRORS = {
-4: 'Your account has been suspended due to a violation of our terms and policies.',
-5: 'https://member.afreecatv.com/app/user_delete_progress.php',
-6: 'https://login.afreecatv.com/membership/changeMember.php',
-8: "Hello! AfreecaTV here.\nThe username you have entered belongs to \n an account that requires a legal guardian's consent. \nIf you wish to use our services without restriction, \nplease make sure to go through the necessary verification process.",
-9: 'https://member.afreecatv.com/app/pop_login_block.php',
-11: 'https://login.afreecatv.com/afreeca/second_login.php',
-12: 'https://member.afreecatv.com/app/user_security.php',
0: 'The username does not exist or you have entered the wrong password.',
-1: 'The username does not exist or you have entered the wrong password.',
-3: 'You have entered your username/password incorrectly.',
-7: 'You cannot use your Global AfreecaTV account to access Korean AfreecaTV.',
-10: 'Sorry for the inconvenience. \nYour account has been blocked due to an unauthorized access. \nPlease contact our Help Center for assistance.',
-32008: 'You have failed to log in. Please contact our Help Center.',
}
result = int_or_none(response.get('RESULT'))
if result != 1:
error = _ERRORS.get(result, 'You have failed to log in.')
raise ExtractorError(
'Unable to login: %s said: %s' % (self.IE_NAME, error),
expected=True)
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
if re.search(r'alert\(["\']This video has been deleted', webpage):
raise ExtractorError(
'Video %s has been deleted' % video_id, expected=True)
station_id = self._search_regex(
r'nStationNo\s*=\s*(\d+)', webpage, 'station')
bbs_id = self._search_regex(
r'nBbsNo\s*=\s*(\d+)', webpage, 'bbs')
video_id = self._search_regex(
r'nTitleNo\s*=\s*(\d+)', webpage, 'title', default=video_id)
partial_view = False
adult_view = False
for _ in range(2):
query = {
'nTitleNo': video_id,
'nStationNo': station_id,
'nBbsNo': bbs_id,
}
if partial_view:
query['partialView'] = 'SKIP_ADULT'
if adult_view:
query['adultView'] = 'ADULT_VIEW'
video_xml = self._download_xml(
'http://afbbs.afreecatv.com:8080/api/video/get_video_info.php',
video_id, 'Downloading video info XML%s'
% (' (skipping adult)' if partial_view else ''),
video_id, headers={
'Referer': url,
}, query=query)
flag = xpath_text(video_xml, './track/flag', 'flag', default=None)
if flag and flag == 'SUCCEED':
break
if flag == 'PARTIAL_ADULT':
self.report_warning(
'In accordance with local laws and regulations, underage users are restricted from watching adult content. '
'Only content suitable for all ages will be downloaded. '
'Provide account credentials if you wish to download restricted content.')
partial_view = True
continue
elif flag == 'ADULT':
if not adult_view:
adult_view = True
continue
error = 'Only users older than 19 are able to watch this video. Provide account credentials to download this content.'
else:
error = flag
raise ExtractorError(
'%s said: %s' % (self.IE_NAME, error), expected=True)
else:
raise ExtractorError('Unable to download video info')
video_element = video_xml.findall(compat_xpath('./track/video'))[-1]
if video_element is None or video_element.text is None:
raise ExtractorError(
'Video %s does not exist' % video_id, expected=True)
video_url = video_element.text.strip()
title = xpath_text(video_xml, './track/title', 'title', fatal=True)
uploader = xpath_text(video_xml, './track/nickname', 'uploader')
uploader_id = xpath_text(video_xml, './track/bj_id', 'uploader id')
duration = int_or_none(xpath_text(
video_xml, './track/duration', 'duration'))
thumbnail = xpath_text(video_xml, './track/titleImage', 'thumbnail')
common_entry = {
'uploader': uploader,
'uploader_id': uploader_id,
'thumbnail': thumbnail,
}
info = common_entry.copy()
info.update({
'id': video_id,
'title': title,
'duration': duration,
})
if not video_url:
entries = []
file_elements = video_element.findall(compat_xpath('./file'))
one = len(file_elements) == 1
for file_num, file_element in enumerate(file_elements, start=1):
file_url = url_or_none(file_element.text)
if not file_url:
continue
key = file_element.get('key', '')
upload_date = unified_strdate(self._search_regex(
r'^(\d{8})_', key, 'upload date', default=None))
if upload_date is not None:
# sometimes the upload date isn't included in the file name
# instead, another random ID is, which may parse as a valid
# date but be wildly out of a reasonable range
parsed_date = date_from_str(upload_date)
if parsed_date.year < 2000 or parsed_date.year >= 2100:
upload_date = None
file_duration = int_or_none(file_element.get('duration'))
format_id = key if key else '%s_%s' % (video_id, file_num)
if determine_ext(file_url) == 'm3u8':
formats = self._extract_m3u8_formats(
file_url, video_id, 'mp4', entry_protocol='m3u8_native',
m3u8_id='hls',
note='Downloading part %d m3u8 information' % file_num)
else:
formats = [{
'url': file_url,
'format_id': 'http',
}]
if not formats and not self.get_param('ignore_no_formats'):
continue
self._sort_formats(formats)
file_info = common_entry.copy()
file_info.update({
'id': format_id,
'title': title if one else '%s (part %d)' % (title, file_num),
'upload_date': upload_date,
'duration': file_duration,
'formats': formats,
})
entries.append(file_info)
entries_info = info.copy()
entries_info.update({
'_type': 'multi_video',
'entries': entries,
})
return entries_info
info = {
'id': video_id,
'title': title,
'uploader': uploader,
'uploader_id': uploader_id,
'duration': duration,
'thumbnail': thumbnail,
}
if determine_ext(video_url) == 'm3u8':
info['formats'] = self._extract_m3u8_formats(
video_url, video_id, 'mp4', entry_protocol='m3u8_native',
m3u8_id='hls')
else:
app, playpath = video_url.split('mp4:')
info.update({
'url': app,
'ext': 'flv',
'play_path': 'mp4:' + playpath,
'rtmp_live': True, # downloading won't end without this
})
return info
class AfreecaTVLiveIE(AfreecaTVIE):
IE_NAME = 'afreecatv:live'
_VALID_URL = r'https?://play\.afreeca(?:tv)?\.com/(?P<id>[^/]+)(?:/(?P<bno>\d+))?'
_TESTS = [{
'url': 'https://play.afreecatv.com/pyh3646/237852185',
'info_dict': {
'id': '237852185',
'ext': 'mp4',
'title': '【 우루과이 오늘은 무슨일이? 】',
'uploader': '박진우[JINU]',
'uploader_id': 'pyh3646',
'timestamp': 1640661495,
'is_live': True,
},
'skip': 'Livestream has ended',
}, {
'url': 'http://play.afreeca.com/pyh3646/237852185',
'only_matching': True,
}, {
'url': 'http://play.afreeca.com/pyh3646',
'only_matching': True,
}]
_LIVE_API_URL = 'https://live.afreecatv.com/afreeca/player_live_api.php'
_QUALITIES = ('sd', 'hd', 'hd2k', 'original')
def _real_extract(self, url):
broadcaster_id, broadcast_no = self._match_valid_url(url).group('id', 'bno')
info = self._download_json(self._LIVE_API_URL, broadcaster_id, fatal=False,
data=urlencode_postdata({'bid': broadcaster_id})) or {}
channel_info = info.get('CHANNEL') or {}
broadcaster_id = channel_info.get('BJID') or broadcaster_id
broadcast_no = channel_info.get('BNO') or broadcast_no
if not broadcast_no:
raise ExtractorError(f'Unable to extract broadcast number ({broadcaster_id} may not be live)', expected=True)
formats = []
quality_key = qualities(self._QUALITIES)
for quality_str in self._QUALITIES:
aid_response = self._download_json(
self._LIVE_API_URL, broadcast_no, fatal=False,
data=urlencode_postdata({
'bno': broadcast_no,
'stream_type': 'common',
'type': 'aid',
'quality': quality_str,
}),
note=f'Downloading access token for {quality_str} stream',
errnote=f'Unable to download access token for {quality_str} stream')
aid = traverse_obj(aid_response, ('CHANNEL', 'AID'))
if not aid:
continue
stream_base_url = channel_info.get('RMD') or 'https://livestream-manager.afreecatv.com'
stream_info = self._download_json(
f'{stream_base_url}/broad_stream_assign.html', broadcast_no, fatal=False,
query={
'return_type': channel_info.get('CDN', 'gcp_cdn'),
'broad_key': f'{broadcast_no}-common-{quality_str}-hls',
},
note=f'Downloading metadata for {quality_str} stream',
errnote=f'Unable to download metadata for {quality_str} stream') or {}
if stream_info.get('view_url'):
formats.append({
'format_id': quality_str,
'url': update_url_query(stream_info['view_url'], {'aid': aid}),
'ext': 'mp4',
'protocol': 'm3u8',
'quality': quality_key(quality_str),
})
self._sort_formats(formats)
station_info = self._download_json(
'https://st.afreecatv.com/api/get_station_status.php', broadcast_no,
query={'szBjId': broadcaster_id}, fatal=False,
note='Downloading channel metadata', errnote='Unable to download channel metadata') or {}
return {
'id': broadcast_no,
'title': channel_info.get('TITLE') or station_info.get('station_title'),
'uploader': channel_info.get('BJNICK') or station_info.get('station_name'),
'uploader_id': broadcaster_id,
'timestamp': unified_timestamp(station_info.get('broad_start')),
'formats': formats,
'is_live': True,
}

66
plugins/youtube_download/yt_dlp/extractor/airmozilla.py Normal file
View File

@ -0,0 +1,66 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
int_or_none,
parse_duration,
parse_iso8601,
)
class AirMozillaIE(InfoExtractor):
_VALID_URL = r'https?://air\.mozilla\.org/(?P<id>[0-9a-z-]+)/?'
_TEST = {
'url': 'https://air.mozilla.org/privacy-lab-a-meetup-for-privacy-minded-people-in-san-francisco/',
'md5': '8d02f53ee39cf006009180e21df1f3ba',
'info_dict': {
'id': '6x4q2w',
'ext': 'mp4',
'title': 'Privacy Lab - a meetup for privacy minded people in San Francisco',
'thumbnail': r're:https?://.*/poster\.jpg',
'description': 'Brings together privacy professionals and others interested in privacy at for-profits, non-profits, and NGOs in an effort to contribute to the state of the ecosystem...',
'timestamp': 1422487800,
'upload_date': '20150128',
'location': 'SFO Commons',
'duration': 3780,
'view_count': int,
'categories': ['Main', 'Privacy'],
}
}
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
video_id = self._html_search_regex(r'//vid\.ly/(.*?)/embed', webpage, 'id')
embed_script = self._download_webpage('https://vid.ly/{0}/embed'.format(video_id), video_id)
jwconfig = self._parse_json(self._search_regex(
r'initCallback\((.*)\);', embed_script, 'metadata'), video_id)['config']
info_dict = self._parse_jwplayer_data(jwconfig, video_id)
view_count = int_or_none(self._html_search_regex(
r'Views since archived: ([0-9]+)',
webpage, 'view count', fatal=False))
timestamp = parse_iso8601(self._html_search_regex(
r'<time datetime="(.*?)"', webpage, 'timestamp', fatal=False))
duration = parse_duration(self._search_regex(
r'Duration:\s*(\d+\s*hours?\s*\d+\s*minutes?)',
webpage, 'duration', fatal=False))
info_dict.update({
'id': video_id,
'title': self._og_search_title(webpage),
'url': self._og_search_url(webpage),
'display_id': display_id,
'description': self._og_search_description(webpage),
'timestamp': timestamp,
'location': self._html_search_regex(r'Location: (.*)', webpage, 'location', default=None),
'duration': duration,
'view_count': view_count,
'categories': re.findall(r'<a href=".*?" class="channel">(.*?)</a>', webpage),
})
return info_dict

53
plugins/youtube_download/yt_dlp/extractor/aliexpress.py Normal file
View File

@ -0,0 +1,53 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
float_or_none,
try_get,
)
class AliExpressLiveIE(InfoExtractor):
_VALID_URL = r'https?://live\.aliexpress\.com/live/(?P<id>\d+)'
_TEST = {
'url': 'https://live.aliexpress.com/live/2800002704436634',
'md5': 'e729e25d47c5e557f2630eaf99b740a5',
'info_dict': {
'id': '2800002704436634',
'ext': 'mp4',
'title': 'CASIMA7.22',
'thumbnail': r're:http://.*\.jpg',
'uploader': 'CASIMA Official Store',
'timestamp': 1500717600,
'upload_date': '20170722',
},
}
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
data = self._parse_json(
self._search_regex(
r'(?s)runParams\s*=\s*({.+?})\s*;?\s*var',
webpage, 'runParams'),
video_id)
title = data['title']
formats = self._extract_m3u8_formats(
data['replyStreamUrl'], video_id, 'mp4',
entry_protocol='m3u8_native', m3u8_id='hls')
return {
'id': video_id,
'title': title,
'thumbnail': data.get('coverUrl'),
'uploader': try_get(
data, lambda x: x['followBar']['name'], compat_str),
'timestamp': float_or_none(data.get('startTimeLong'), scale=1000),
'formats': formats,
}

86
plugins/youtube_download/yt_dlp/extractor/aljazeera.py Normal file
View File

@ -0,0 +1,86 @@
# coding: utf-8
from __future__ import unicode_literals
import json
from .common import InfoExtractor
from ..utils import (
try_get,
)
class AlJazeeraIE(InfoExtractor):
_VALID_URL = r'https?://(?P<base>\w+\.aljazeera\.\w+)/(?P<type>programs?/[^/]+|(?:feature|video|new)s)?/\d{4}/\d{1,2}/\d{1,2}/(?P<id>[^/?&#]+)'
_TESTS = [{
'url': 'https://balkans.aljazeera.net/videos/2021/11/6/pojedini-domovi-u-sarajevu-jos-pod-vodom-mjestanima-se-dostavlja-hrana',
'info_dict': {
'id': '6280641530001',
'ext': 'mp4',
'title': 'Pojedini domovi u Sarajevu još pod vodom, mještanima se dostavlja hrana',
'timestamp': 1636219149,
'description': 'U sarajevskim naseljima Rajlovac i Reljevo stambeni objekti, ali i industrijska postrojenja i dalje su pod vodom.',
'upload_date': '20211106',
}
}, {
'url': 'https://balkans.aljazeera.net/videos/2021/11/6/djokovic-usao-u-finale-mastersa-u-parizu',
'info_dict': {
'id': '6280654936001',
'ext': 'mp4',
'title': 'Đoković ušao u finale Mastersa u Parizu',
'timestamp': 1636221686,
'description': 'Novak Đoković je u polufinalu Mastersa u Parizu nakon preokreta pobijedio Poljaka Huberta Hurkacza.',
'upload_date': '20211106',
},
}]
BRIGHTCOVE_URL_RE = r'https?://players.brightcove.net/(?P<account>\d+)/(?P<player_id>[a-zA-Z0-9]+)_(?P<embed>[^/]+)/index.html\?videoId=(?P<id>\d+)'
def _real_extract(self, url):
base, post_type, id = self._match_valid_url(url).groups()
wp = {
'balkans.aljazeera.net': 'ajb',
'chinese.aljazeera.net': 'chinese',
'mubasher.aljazeera.net': 'ajm',
}.get(base) or 'aje'
post_type = {
'features': 'post',
'program': 'episode',
'programs': 'episode',
'videos': 'video',
'news': 'news',
}[post_type.split('/')[0]]
video = self._download_json(
f'https://{base}/graphql', id, query={
'wp-site': wp,
'operationName': 'ArchipelagoSingleArticleQuery',
'variables': json.dumps({
'name': id,
'postType': post_type,
}),
}, headers={
'wp-site': wp,
})
video = try_get(video, lambda x: x['data']['article']['video']) or {}
video_id = video.get('id')
account = video.get('accountId') or '911432371001'
player_id = video.get('playerId') or 'csvTfAlKW'
embed = 'default'
if video_id is None:
webpage = self._download_webpage(url, id)
account, player_id, embed, video_id = self._search_regex(self.BRIGHTCOVE_URL_RE, webpage, 'video id',
group=(1, 2, 3, 4), default=(None, None, None, None))
if video_id is None:
return {
'_type': 'url_transparent',
'url': url,
'ie_key': 'Generic'
}
return {
'_type': 'url_transparent',
'url': f'https://players.brightcove.net/{account}/{player_id}_{embed}/index.html?videoId={video_id}',
'ie_key': 'BrightcoveNew'
}

132
plugins/youtube_download/yt_dlp/extractor/allocine.py Normal file
View File

@ -0,0 +1,132 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
int_or_none,
qualities,
remove_end,
try_get,
unified_timestamp,
url_basename,
)
class AllocineIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?allocine\.fr/(?:article|video|film)/(?:fichearticle_gen_carticle=|player_gen_cmedia=|fichefilm_gen_cfilm=|video-)(?P<id>[0-9]+)(?:\.html)?'
_TESTS = [{
'url': 'http://www.allocine.fr/article/fichearticle_gen_carticle=18635087.html',
'md5': '0c9fcf59a841f65635fa300ac43d8269',
'info_dict': {
'id': '19546517',
'display_id': '18635087',
'ext': 'mp4',
'title': 'Astérix - Le Domaine des Dieux Teaser VF',
'description': 'md5:4a754271d9c6f16c72629a8a993ee884',
'thumbnail': r're:http://.*\.jpg',
'duration': 39,
'timestamp': 1404273600,
'upload_date': '20140702',
'view_count': int,
},
}, {
'url': 'http://www.allocine.fr/video/player_gen_cmedia=19540403&cfilm=222257.html',
'md5': 'd0cdce5d2b9522ce279fdfec07ff16e0',
'info_dict': {
'id': '19540403',
'display_id': '19540403',
'ext': 'mp4',
'title': 'Planes 2 Bande-annonce VF',
'description': 'Regardez la bande annonce du film Planes 2 (Planes 2 Bande-annonce VF). Planes 2, un film de Roberts Gannaway',
'thumbnail': r're:http://.*\.jpg',
'duration': 69,
'timestamp': 1385659800,
'upload_date': '20131128',
'view_count': int,
},
}, {
'url': 'http://www.allocine.fr/video/player_gen_cmedia=19544709&cfilm=181290.html',
'md5': '101250fb127ef9ca3d73186ff22a47ce',
'info_dict': {
'id': '19544709',
'display_id': '19544709',
'ext': 'mp4',
'title': 'Dragons 2 - Bande annonce finale VF',
'description': 'md5:6cdd2d7c2687d4c6aafe80a35e17267a',
'thumbnail': r're:http://.*\.jpg',
'duration': 144,
'timestamp': 1397589900,
'upload_date': '20140415',
'view_count': int,
},
}, {
'url': 'http://www.allocine.fr/video/video-19550147/',
'md5': '3566c0668c0235e2d224fd8edb389f67',
'info_dict': {
'id': '19550147',
'ext': 'mp4',
'title': 'Faux Raccord N°123 - Les gaffes de Cliffhanger',
'description': 'md5:bc734b83ffa2d8a12188d9eb48bb6354',
'thumbnail': r're:http://.*\.jpg',
},
}]
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
formats = []
quality = qualities(['ld', 'md', 'hd'])
model = self._html_search_regex(
r'data-model="([^"]+)"', webpage, 'data model', default=None)
if model:
model_data = self._parse_json(model, display_id)
video = model_data['videos'][0]
title = video['title']
for video_url in video['sources'].values():
video_id, format_id = url_basename(video_url).split('_')[:2]
formats.append({
'format_id': format_id,
'quality': quality(format_id),
'url': video_url,
})
duration = int_or_none(video.get('duration'))
view_count = int_or_none(video.get('view_count'))
timestamp = unified_timestamp(try_get(
video, lambda x: x['added_at']['date'], compat_str))
else:
video_id = display_id
media_data = self._download_json(
'http://www.allocine.fr/ws/AcVisiondataV5.ashx?media=%s' % video_id, display_id)
title = remove_end(
self._html_search_regex(
r'(?s)<title>(.+?)</title>', webpage, 'title').strip(),
' - AlloCiné')
for key, value in media_data['video'].items():
if not key.endswith('Path'):
continue
format_id = key[:-len('Path')]
formats.append({
'format_id': format_id,
'quality': quality(format_id),
'url': value,
})
duration, view_count, timestamp = [None] * 3
self._sort_formats(formats)
return {
'id': video_id,
'display_id': display_id,
'title': title,
'description': self._og_search_description(webpage),
'thumbnail': self._og_search_thumbnail(webpage),
'duration': duration,
'timestamp': timestamp,
'view_count': view_count,
'formats': formats,
}

77
plugins/youtube_download/yt_dlp/extractor/alphaporno.py Normal file
View File

@ -0,0 +1,77 @@
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import (
parse_iso8601,
parse_duration,
parse_filesize,
int_or_none,
)
class AlphaPornoIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?alphaporno\.com/videos/(?P<id>[^/]+)'
_TEST = {
'url': 'http://www.alphaporno.com/videos/sensual-striptease-porn-with-samantha-alexandra/',
'md5': 'feb6d3bba8848cd54467a87ad34bd38e',
'info_dict': {
'id': '258807',
'display_id': 'sensual-striptease-porn-with-samantha-alexandra',
'ext': 'mp4',
'title': 'Sensual striptease porn with Samantha Alexandra',
'thumbnail': r're:https?://.*\.jpg$',
'timestamp': 1418694611,
'upload_date': '20141216',
'duration': 387,
'filesize_approx': 54120000,
'tbr': 1145,
'categories': list,
'age_limit': 18,
}
}
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
video_id = self._search_regex(
r"video_id\s*:\s*'([^']+)'", webpage, 'video id', default=None)
video_url = self._search_regex(
r"video_url\s*:\s*'([^']+)'", webpage, 'video url')
ext = self._html_search_meta(
'encodingFormat', webpage, 'ext', default='.mp4')[1:]
title = self._search_regex(
[r'<meta content="([^"]+)" itemprop="description">',
r'class="title" itemprop="name">([^<]+)<'],
webpage, 'title')
thumbnail = self._html_search_meta('thumbnail', webpage, 'thumbnail')
timestamp = parse_iso8601(self._html_search_meta(
'uploadDate', webpage, 'upload date'))
duration = parse_duration(self._html_search_meta(
'duration', webpage, 'duration'))
filesize_approx = parse_filesize(self._html_search_meta(
'contentSize', webpage, 'file size'))
bitrate = int_or_none(self._html_search_meta(
'bitrate', webpage, 'bitrate'))
categories = self._html_search_meta(
'keywords', webpage, 'categories', default='').split(',')
age_limit = self._rta_search(webpage)
return {
'id': video_id,
'display_id': display_id,
'url': video_url,
'ext': ext,
'title': title,
'thumbnail': thumbnail,
'timestamp': timestamp,
'duration': duration,
'filesize_approx': filesize_approx,
'tbr': bitrate,
'categories': categories,
'age_limit': age_limit,
}

179
plugins/youtube_download/yt_dlp/extractor/alura.py Normal file
View File

@ -0,0 +1,179 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import (
compat_urlparse,
)
from ..utils import (
urlencode_postdata,
urljoin,
int_or_none,
clean_html,
ExtractorError
)
class AluraIE(InfoExtractor):
_VALID_URL = r'https?://(?:cursos\.)?alura\.com\.br/course/(?P<course_name>[^/]+)/task/(?P<id>\d+)'
_LOGIN_URL = 'https://cursos.alura.com.br/loginForm?urlAfterLogin=/loginForm'
_VIDEO_URL = 'https://cursos.alura.com.br/course/%s/task/%s/video'
_NETRC_MACHINE = 'alura'
_TESTS = [{
'url': 'https://cursos.alura.com.br/course/clojure-mutabilidade-com-atoms-e-refs/task/60095',
'info_dict': {
'id': '60095',
'ext': 'mp4',
'title': 'Referências, ref-set e alter'
},
'skip': 'Requires alura account credentials'},
{
# URL without video
'url': 'https://cursos.alura.com.br/course/clojure-mutabilidade-com-atoms-e-refs/task/60098',
'only_matching': True},
{
'url': 'https://cursos.alura.com.br/course/fundamentos-market-digital/task/55219',
'only_matching': True}
]
def _real_extract(self, url):
course, video_id = self._match_valid_url(url)
video_url = self._VIDEO_URL % (course, video_id)
video_dict = self._download_json(video_url, video_id, 'Searching for videos')
if video_dict:
webpage = self._download_webpage(url, video_id)
video_title = clean_html(self._search_regex(
r'<span[^>]+class=(["\'])task-body-header-title-text\1[^>]*>(?P<title>[^<]+)',
webpage, 'title', group='title'))
formats = []
for video_obj in video_dict:
video_url_m3u8 = video_obj.get('link')
video_format = self._extract_m3u8_formats(
video_url_m3u8, None, 'mp4', entry_protocol='m3u8_native',
m3u8_id='hls', fatal=False)
for f in video_format:
m = re.search(r'^[\w \W]*-(?P<res>\w*).mp4[\W \w]*', f['url'])
if m:
if not f.get('height'):
f['height'] = int('720' if m.group('res') == 'hd' else '480')
formats.extend(video_format)
self._sort_formats(formats)
return {
'id': video_id,
'title': video_title,
"formats": formats
}
def _real_initialize(self):
self._login()
def _login(self):
username, password = self._get_login_info()
if username is None:
return
pass
login_page = self._download_webpage(
self._LOGIN_URL, None, 'Downloading login popup')
def is_logged(webpage):
return any(re.search(p, webpage) for p in (
r'href=[\"|\']?/signout[\"|\']',
r'>Logout<'))
# already logged in
if is_logged(login_page):
return
login_form = self._hidden_inputs(login_page)
login_form.update({
'username': username,
'password': password,
})
post_url = self._search_regex(
r'<form[^>]+class=["|\']signin-form["|\'] action=["|\'](?P<url>.+?)["|\']', login_page,
'post url', default=self._LOGIN_URL, group='url')
if not post_url.startswith('http'):
post_url = compat_urlparse.urljoin(self._LOGIN_URL, post_url)
response = self._download_webpage(
post_url, None, 'Logging in',
data=urlencode_postdata(login_form),
headers={'Content-Type': 'application/x-www-form-urlencoded'})
if not is_logged(response):
error = self._html_search_regex(
r'(?s)<p[^>]+class="alert-message[^"]*">(.+?)</p>',
response, 'error message', default=None)
if error:
raise ExtractorError('Unable to login: %s' % error, expected=True)
raise ExtractorError('Unable to log in')
class AluraCourseIE(AluraIE):
_VALID_URL = r'https?://(?:cursos\.)?alura\.com\.br/course/(?P<id>[^/]+)'
_LOGIN_URL = 'https://cursos.alura.com.br/loginForm?urlAfterLogin=/loginForm'
_NETRC_MACHINE = 'aluracourse'
_TESTS = [{
'url': 'https://cursos.alura.com.br/course/clojure-mutabilidade-com-atoms-e-refs',
'only_matching': True,
}]
@classmethod
def suitable(cls, url):
return False if AluraIE.suitable(url) else super(AluraCourseIE, cls).suitable(url)
def _real_extract(self, url):
course_path = self._match_id(url)
webpage = self._download_webpage(url, course_path)
course_title = self._search_regex(
r'<h1.*?>(.*?)<strong>(?P<course_title>.*?)</strong></h[0-9]>', webpage,
'course title', default=course_path, group='course_title')
entries = []
if webpage:
for path in re.findall(r'<a\b(?=[^>]* class="[^"]*(?<=[" ])courseSectionList-section[" ])(?=[^>]* href="([^"]*))', webpage):
page_url = urljoin(url, path)
section_path = self._download_webpage(page_url, course_path)
for path_video in re.findall(r'<a\b(?=[^>]* class="[^"]*(?<=[" ])task-menu-nav-item-link-VIDEO[" ])(?=[^>]* href="([^"]*))', section_path):
chapter = clean_html(
self._search_regex(
r'<h3[^>]+class=(["\'])task-menu-section-title-text\1[^>]*>(?P<chapter>[^<]+)',
section_path,
'chapter',
group='chapter'))
chapter_number = int_or_none(
self._search_regex(
r'<span[^>]+class=(["\'])task-menu-section-title-number[^>]*>(.*?)<strong>(?P<chapter_number>[^<]+)</strong>',
section_path,
'chapter number',
group='chapter_number'))
video_url = urljoin(url, path_video)
entry = {
'_type': 'url_transparent',
'id': self._match_id(video_url),
'url': video_url,
'id_key': self.ie_key(),
'chapter': chapter,
'chapter_number': chapter_number
}
entries.append(entry)
return self.playlist_result(entries, course_path, course_title)

103
plugins/youtube_download/yt_dlp/extractor/amara.py Normal file
View File

@ -0,0 +1,103 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from .youtube import YoutubeIE
from .vimeo import VimeoIE
from ..utils import (
int_or_none,
parse_iso8601,
update_url_query,
)
class AmaraIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?amara\.org/(?:\w+/)?videos/(?P<id>\w+)'
_TESTS = [{
# Youtube
'url': 'https://amara.org/en/videos/jVx79ZKGK1ky/info/why-jury-trials-are-becoming-less-common/?tab=video',
'md5': 'ea10daf2b6154b8c1ecf9922aca5e8ae',
'info_dict': {
'id': 'h6ZuVdvYnfE',
'ext': 'mp4',
'title': 'Why jury trials are becoming less common',
'description': 'md5:a61811c319943960b6ab1c23e0cbc2c1',
'thumbnail': r're:^https?://.*\.jpg$',
'subtitles': dict,
'upload_date': '20160813',
'uploader': 'PBS NewsHour',
'uploader_id': 'PBSNewsHour',
'timestamp': 1549639570,
}
}, {
# Vimeo
'url': 'https://amara.org/en/videos/kYkK1VUTWW5I/info/vimeo-at-ces-2011',
'md5': '99392c75fa05d432a8f11df03612195e',
'info_dict': {
'id': '18622084',
'ext': 'mov',
'title': 'Vimeo at CES 2011!',
'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
'thumbnail': r're:^https?://.*\.jpg$',
'subtitles': dict,
'timestamp': 1294763658,
'upload_date': '20110111',
'uploader': 'Sam Morrill',
'uploader_id': 'sammorrill'
}
}, {
# Direct Link
'url': 'https://amara.org/en/videos/s8KL7I3jLmh6/info/the-danger-of-a-single-story/',
'md5': 'd3970f08512738ee60c5807311ff5d3f',
'info_dict': {
'id': 's8KL7I3jLmh6',
'ext': 'mp4',
'title': 'The danger of a single story',
'description': 'md5:d769b31139c3b8bb5be9177f62ea3f23',
'thumbnail': r're:^https?://.*\.jpg$',
'subtitles': dict,
'upload_date': '20091007',
'timestamp': 1254942511,
}
}]
def _real_extract(self, url):
video_id = self._match_id(url)
meta = self._download_json(
'https://amara.org/api/videos/%s/' % video_id,
video_id, query={'format': 'json'})
title = meta['title']
video_url = meta['all_urls'][0]
subtitles = {}
for language in (meta.get('languages') or []):
subtitles_uri = language.get('subtitles_uri')
if not (subtitles_uri and language.get('published')):
continue
subtitle = subtitles.setdefault(language.get('code') or 'en', [])
for f in ('json', 'srt', 'vtt'):
subtitle.append({
'ext': f,
'url': update_url_query(subtitles_uri, {'format': f}),
})
info = {
'url': video_url,
'id': video_id,
'subtitles': subtitles,
'title': title,
'description': meta.get('description'),
'thumbnail': meta.get('thumbnail'),
'duration': int_or_none(meta.get('duration')),
'timestamp': parse_iso8601(meta.get('created')),
}
for ie in (YoutubeIE, VimeoIE):
if ie.suitable(video_url):
info.update({
'_type': 'url_transparent',
'ie_key': ie.ie_key(),
})
break
return info

53
plugins/youtube_download/yt_dlp/extractor/amazon.py Normal file
View File

@ -0,0 +1,53 @@
# coding: utf-8
from .common import InfoExtractor
from ..utils import int_or_none
class AmazonStoreIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?amazon\.(?:[a-z]{2,3})(?:\.[a-z]{2})?/(?:[^/]+/)?(?:dp|gp/product)/(?P<id>[^/&#$?]+)'
_TESTS = [{
'url': 'https://www.amazon.co.uk/dp/B098XNCHLD/',
'info_dict': {
'id': 'B098XNCHLD',
'title': 'md5:5f3194dbf75a8dcfc83079bd63a2abed',
},
'playlist_mincount': 1,
'playlist': [{
'info_dict': {
'id': 'A1F83G8C2ARO7P',
'ext': 'mp4',
'title': 'mcdodo usb c cable 100W 5a',
'thumbnail': r're:^https?://.*\.jpg$',
},
}]
}, {
'url': 'https://www.amazon.in/Sony-WH-1000XM4-Cancelling-Headphones-Bluetooth/dp/B0863TXGM3',
'info_dict': {
'id': 'B0863TXGM3',
'title': 'md5:b0bde4881d3cfd40d63af19f7898b8ff',
},
'playlist_mincount': 4,
}, {
'url': 'https://www.amazon.com/dp/B0845NXCXF/',
'info_dict': {
'id': 'B0845NXCXF',
'title': 'md5:2145cd4e3c7782f1ee73649a3cff1171',
},
'playlist-mincount': 1,
}]
def _real_extract(self, url):
id = self._match_id(url)
webpage = self._download_webpage(url, id)
data_json = self._parse_json(self._html_search_regex(r'var\s?obj\s?=\s?jQuery\.parseJSON\(\'(.*)\'\)', webpage, 'data'), id)
entries = [{
'id': video['marketPlaceID'],
'url': video['url'],
'title': video.get('title'),
'thumbnail': video.get('thumbUrl') or video.get('thumb'),
'duration': video.get('durationSeconds'),
'height': int_or_none(video.get('videoHeight')),
'width': int_or_none(video.get('videoWidth')),
} for video in (data_json.get('videos') or []) if video.get('isVideo') and video.get('url')]
return self.playlist_result(entries, playlist_id=id, playlist_title=data_json['title'])

150
plugins/youtube_download/yt_dlp/extractor/amcnetworks.py Normal file
View File

@ -0,0 +1,150 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .theplatform import ThePlatformIE
from ..utils import (
int_or_none,
parse_age_limit,
try_get,
update_url_query,
)
class AMCNetworksIE(ThePlatformIE):
_VALID_URL = r'https?://(?:www\.)?(?P<site>amc|bbcamerica|ifc|(?:we|sundance)tv)\.com/(?P<id>(?:movies|shows(?:/[^/]+)+)/[^/?#&]+)'
_TESTS = [{
'url': 'https://www.bbcamerica.com/shows/the-graham-norton-show/videos/tina-feys-adorable-airline-themed-family-dinner--51631',
'info_dict': {
'id': '4Lq1dzOnZGt0',
'ext': 'mp4',
'title': "The Graham Norton Show - Season 28 - Tina Fey's Adorable Airline-Themed Family Dinner",
'description': "It turns out child stewardesses are very generous with the wine! All-new episodes of 'The Graham Norton Show' premiere Fridays at 11/10c on BBC America.",
'upload_date': '20201120',
'timestamp': 1605904350,
'uploader': 'AMCN',
},
'params': {
# m3u8 download
'skip_download': True,
},
}, {
'url': 'http://www.bbcamerica.com/shows/the-hunt/full-episodes/season-1/episode-01-the-hardest-challenge',
'only_matching': True,
}, {
'url': 'http://www.amc.com/shows/preacher/full-episodes/season-01/episode-00/pilot',
'only_matching': True,
}, {
'url': 'http://www.wetv.com/shows/million-dollar-matchmaker/season-01/episode-06-the-dumped-dj-and-shallow-hal',
'only_matching': True,
}, {
'url': 'http://www.ifc.com/movies/chaos',
'only_matching': True,
}, {
'url': 'http://www.bbcamerica.com/shows/doctor-who/full-episodes/the-power-of-the-daleks/episode-01-episode-1-color-version',
'only_matching': True,
}, {
'url': 'http://www.wetv.com/shows/mama-june-from-not-to-hot/full-episode/season-01/thin-tervention',
'only_matching': True,
}, {
'url': 'http://www.wetv.com/shows/la-hair/videos/season-05/episode-09-episode-9-2/episode-9-sneak-peek-3',
'only_matching': True,
}, {
'url': 'https://www.sundancetv.com/shows/riviera/full-episodes/season-1/episode-01-episode-1',
'only_matching': True,
}]
_REQUESTOR_ID_MAP = {
'amc': 'AMC',
'bbcamerica': 'BBCA',
'ifc': 'IFC',
'sundancetv': 'SUNDANCE',
'wetv': 'WETV',
}
def _real_extract(self, url):
site, display_id = self._match_valid_url(url).groups()
requestor_id = self._REQUESTOR_ID_MAP[site]
page_data = self._download_json(
'https://content-delivery-gw.svc.ds.amcn.com/api/v2/content/amcn/%s/url/%s'
% (requestor_id.lower(), display_id), display_id)['data']
properties = page_data.get('properties') or {}
query = {
'mbr': 'true',
'manifest': 'm3u',
}
video_player_count = 0
try:
for v in page_data['children']:
if v.get('type') == 'video-player':
releasePid = v['properties']['currentVideo']['meta']['releasePid']
tp_path = 'M_UwQC/' + releasePid
media_url = 'https://link.theplatform.com/s/' + tp_path
video_player_count += 1
except KeyError:
pass
if video_player_count > 1:
self.report_warning(
'The JSON data has %d video players. Only one will be extracted' % video_player_count)
# Fall back to videoPid if releasePid not found.
# TODO: Fall back to videoPid if releasePid manifest uses DRM.
if not video_player_count:
tp_path = 'M_UwQC/media/' + properties['videoPid']
media_url = 'https://link.theplatform.com/s/' + tp_path
theplatform_metadata = self._download_theplatform_metadata(tp_path, display_id)
info = self._parse_theplatform_metadata(theplatform_metadata)
video_id = theplatform_metadata['pid']
title = theplatform_metadata['title']
rating = try_get(
theplatform_metadata, lambda x: x['ratings'][0]['rating'])
video_category = properties.get('videoCategory')
if video_category and video_category.endswith('-Auth'):
resource = self._get_mvpd_resource(
requestor_id, title, video_id, rating)
query['auth'] = self._extract_mvpd_auth(
url, video_id, requestor_id, resource)
media_url = update_url_query(media_url, query)
formats, subtitles = self._extract_theplatform_smil(
media_url, video_id)
self._sort_formats(formats)
thumbnails = []
thumbnail_urls = [properties.get('imageDesktop')]
if 'thumbnail' in info:
thumbnail_urls.append(info.pop('thumbnail'))
for thumbnail_url in thumbnail_urls:
if not thumbnail_url:
continue
mobj = re.search(r'(\d+)x(\d+)', thumbnail_url)
thumbnails.append({
'url': thumbnail_url,
'width': int(mobj.group(1)) if mobj else None,
'height': int(mobj.group(2)) if mobj else None,
})
info.update({
'age_limit': parse_age_limit(rating),
'formats': formats,
'id': video_id,
'subtitles': subtitles,
'thumbnails': thumbnails,
})
ns_keys = theplatform_metadata.get('$xmlns', {}).keys()
if ns_keys:
ns = list(ns_keys)[0]
episode = theplatform_metadata.get(ns + '$episodeTitle') or None
episode_number = int_or_none(
theplatform_metadata.get(ns + '$episode'))
season_number = int_or_none(
theplatform_metadata.get(ns + '$season'))
series = theplatform_metadata.get(ns + '$show') or None
info.update({
'episode': episode,
'episode_number': episode_number,
'season_number': season_number,
'series': series,
})
return info

158
plugins/youtube_download/yt_dlp/extractor/americastestkitchen.py Normal file
View File

@ -0,0 +1,158 @@
# coding: utf-8
from __future__ import unicode_literals
import json
from .common import InfoExtractor
from ..utils import (
clean_html,
int_or_none,
try_get,
unified_strdate,
unified_timestamp,
)
class AmericasTestKitchenIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?(?:americastestkitchen|cooks(?:country|illustrated))\.com/(?P<resource_type>episode|videos)/(?P<id>\d+)'
_TESTS = [{
'url': 'https://www.americastestkitchen.com/episode/582-weeknight-japanese-suppers',
'md5': 'b861c3e365ac38ad319cfd509c30577f',
'info_dict': {
'id': '5b400b9ee338f922cb06450c',
'title': 'Japanese Suppers',
'ext': 'mp4',
'description': 'md5:64e606bfee910627efc4b5f050de92b3',
'thumbnail': r're:^https?://',
'timestamp': 1523318400,
'upload_date': '20180410',
'release_date': '20180410',
'series': "America's Test Kitchen",
'season_number': 18,
'episode': 'Japanese Suppers',
'episode_number': 15,
},
'params': {
'skip_download': True,
},
}, {
# Metadata parsing behaves differently for newer episodes (705) as opposed to older episodes (582 above)
'url': 'https://www.americastestkitchen.com/episode/705-simple-chicken-dinner',
'md5': '06451608c57651e985a498e69cec17e5',
'info_dict': {
'id': '5fbe8c61bda2010001c6763b',
'title': 'Simple Chicken Dinner',
'ext': 'mp4',
'description': 'md5:eb68737cc2fd4c26ca7db30139d109e7',
'thumbnail': r're:^https?://',
'timestamp': 1610755200,
'upload_date': '20210116',
'release_date': '20210116',
'series': "America's Test Kitchen",
'season_number': 21,
'episode': 'Simple Chicken Dinner',
'episode_number': 3,
},
'params': {
'skip_download': True,
},
}, {
'url': 'https://www.americastestkitchen.com/videos/3420-pan-seared-salmon',
'only_matching': True,
}, {
'url': 'https://www.cookscountry.com/episode/564-when-only-chocolate-will-do',
'only_matching': True,
}, {
'url': 'https://www.cooksillustrated.com/videos/4478-beef-wellington',
'only_matching': True,
}]
def _real_extract(self, url):
resource_type, video_id = self._match_valid_url(url).groups()
is_episode = resource_type == 'episode'
if is_episode:
resource_type = 'episodes'
resource = self._download_json(
'https://www.americastestkitchen.com/api/v6/%s/%s' % (resource_type, video_id), video_id)
video = resource['video'] if is_episode else resource
episode = resource if is_episode else resource.get('episode') or {}
return {
'_type': 'url_transparent',
'url': 'https://player.zype.com/embed/%s.js?api_key=jZ9GUhRmxcPvX7M3SlfejB6Hle9jyHTdk2jVxG7wOHPLODgncEKVdPYBhuz9iWXQ' % video['zypeId'],
'ie_key': 'Zype',
'description': clean_html(video.get('description')),
'timestamp': unified_timestamp(video.get('publishDate')),
'release_date': unified_strdate(video.get('publishDate')),
'episode_number': int_or_none(episode.get('number')),
'season_number': int_or_none(episode.get('season')),
'series': try_get(episode, lambda x: x['show']['title']),
'episode': episode.get('title'),
}
class AmericasTestKitchenSeasonIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?(?P<show>americastestkitchen|cookscountry)\.com/episodes/browse/season_(?P<id>\d+)'
_TESTS = [{
# ATK Season
'url': 'https://www.americastestkitchen.com/episodes/browse/season_1',
'info_dict': {
'id': 'season_1',
'title': 'Season 1',
},
'playlist_count': 13,
}, {
# Cooks Country Season
'url': 'https://www.cookscountry.com/episodes/browse/season_12',
'info_dict': {
'id': 'season_12',
'title': 'Season 12',
},
'playlist_count': 13,
}]
def _real_extract(self, url):
show_name, season_number = self._match_valid_url(url).groups()
season_number = int(season_number)
slug = 'atk' if show_name == 'americastestkitchen' else 'cco'
season = 'Season %d' % season_number
season_search = self._download_json(
'https://y1fnzxui30-dsn.algolia.net/1/indexes/everest_search_%s_season_desc_production' % slug,
season, headers={
'Origin': 'https://www.%s.com' % show_name,
'X-Algolia-API-Key': '8d504d0099ed27c1b73708d22871d805',
'X-Algolia-Application-Id': 'Y1FNZXUI30',
}, query={
'facetFilters': json.dumps([
'search_season_list:' + season,
'search_document_klass:episode',
'search_show_slug:' + slug,
]),
'attributesToRetrieve': 'description,search_%s_episode_number,search_document_date,search_url,title' % slug,
'attributesToHighlight': '',
'hitsPerPage': 1000,
})
def entries():
for episode in (season_search.get('hits') or []):
search_url = episode.get('search_url')
if not search_url:
continue
yield {
'_type': 'url',
'url': 'https://www.%s.com%s' % (show_name, search_url),
'id': try_get(episode, lambda e: e['objectID'].split('_')[-1]),
'title': episode.get('title'),
'description': episode.get('description'),
'timestamp': unified_timestamp(episode.get('search_document_date')),
'season_number': season_number,
'episode_number': int_or_none(episode.get('search_%s_episode_number' % slug)),
'ie_key': AmericasTestKitchenIE.ie_key(),
}
return self.playlist_result(
entries(), 'season_%d' % season_number, season)

103
plugins/youtube_download/yt_dlp/extractor/amp.py Normal file
View File

@ -0,0 +1,103 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import (
determine_ext,
ExtractorError,
int_or_none,
mimetype2ext,
parse_iso8601,
unified_timestamp,
url_or_none,
)
class AMPIE(InfoExtractor):
# parse Akamai Adaptive Media Player feed
def _extract_feed_info(self, url):
feed = self._download_json(
url, None, 'Downloading Akamai AMP feed',
'Unable to download Akamai AMP feed')
item = feed.get('channel', {}).get('item')
if not item:
raise ExtractorError('%s said: %s' % (self.IE_NAME, feed['error']))
video_id = item['guid']
def get_media_node(name, default=None):
media_name = 'media-%s' % name
media_group = item.get('media-group') or item
return media_group.get(media_name) or item.get(media_name) or item.get(name, default)
thumbnails = []
media_thumbnail = get_media_node('thumbnail')
if media_thumbnail:
if isinstance(media_thumbnail, dict):
media_thumbnail = [media_thumbnail]
for thumbnail_data in media_thumbnail:
thumbnail = thumbnail_data.get('@attributes', {})
thumbnail_url = url_or_none(thumbnail.get('url'))
if not thumbnail_url:
continue
thumbnails.append({
'url': self._proto_relative_url(thumbnail_url, 'http:'),
'width': int_or_none(thumbnail.get('width')),
'height': int_or_none(thumbnail.get('height')),
})
subtitles = {}
media_subtitle = get_media_node('subTitle')
if media_subtitle:
if isinstance(media_subtitle, dict):
media_subtitle = [media_subtitle]
for subtitle_data in media_subtitle:
subtitle = subtitle_data.get('@attributes', {})
subtitle_href = url_or_none(subtitle.get('href'))
if not subtitle_href:
continue
subtitles.setdefault(subtitle.get('lang') or 'en', []).append({
'url': subtitle_href,
'ext': mimetype2ext(subtitle.get('type')) or determine_ext(subtitle_href),
})
formats = []
media_content = get_media_node('content')
if isinstance(media_content, dict):
media_content = [media_content]
for media_data in media_content:
media = media_data.get('@attributes', {})
media_url = url_or_none(media.get('url'))
if not media_url:
continue
ext = mimetype2ext(media.get('type')) or determine_ext(media_url)
if ext == 'f4m':
formats.extend(self._extract_f4m_formats(
media_url + '?hdcore=3.4.0&plugin=aasp-3.4.0.132.124',
video_id, f4m_id='hds', fatal=False))
elif ext == 'm3u8':
formats.extend(self._extract_m3u8_formats(
media_url, video_id, 'mp4', m3u8_id='hls', fatal=False))
else:
formats.append({
'format_id': media_data.get('media-category', {}).get('@attributes', {}).get('label'),
'url': media_url,
'tbr': int_or_none(media.get('bitrate')),
'filesize': int_or_none(media.get('fileSize')),
'ext': ext,
})
self._sort_formats(formats)
timestamp = unified_timestamp(item.get('pubDate'), ' ') or parse_iso8601(item.get('dc-date'))
return {
'id': video_id,
'title': get_media_node('title'),
'description': get_media_node('description'),
'thumbnails': thumbnails,
'timestamp': timestamp,
'duration': int_or_none(media_content[0].get('@attributes', {}).get('duration')),
'subtitles': subtitles,
'formats': formats,
}

285
plugins/youtube_download/yt_dlp/extractor/animelab.py Normal file
View File

@ -0,0 +1,285 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import (
ExtractorError,
urlencode_postdata,
int_or_none,
str_or_none,
determine_ext,
)
from ..compat import compat_HTTPError
class AnimeLabBaseIE(InfoExtractor):
_LOGIN_REQUIRED = True
_LOGIN_URL = 'https://www.animelab.com/login'
_NETRC_MACHINE = 'animelab'
def _login(self):
def is_logged_in(login_webpage):
return 'Sign In' not in login_webpage
login_page = self._download_webpage(
self._LOGIN_URL, None, 'Downloading login page')
# Check if already logged in
if is_logged_in(login_page):
return
(username, password) = self._get_login_info()
if username is None and self._LOGIN_REQUIRED:
self.raise_login_required('Login is required to access any AnimeLab content')
login_form = {
'email': username,
'password': password,
}
try:
response = self._download_webpage(
self._LOGIN_URL, None, 'Logging in', 'Wrong login info',
data=urlencode_postdata(login_form),
headers={'Content-Type': 'application/x-www-form-urlencoded'})
except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 400:
raise ExtractorError('Unable to log in (wrong credentials?)', expected=True)
else:
raise
# if login was successful
if is_logged_in(response):
return
raise ExtractorError('Unable to login (cannot verify if logged in)')
def _real_initialize(self):
self._login()
class AnimeLabIE(AnimeLabBaseIE):
_VALID_URL = r'https?://(?:www\.)?animelab\.com/player/(?P<id>[^/]+)'
# the following tests require authentication, but a free account will suffice
# just set 'usenetrc' to true in test/local_parameters.json if you use a .netrc file
# or you can set 'username' and 'password' there
# the tests also select a specific format so that the same video is downloaded
# regardless of whether the user is premium or not (needs testing on a premium account)
_TEST = {
'url': 'https://www.animelab.com/player/fullmetal-alchemist-brotherhood-episode-42',
'md5': '05bde4b91a5d1ff46ef5b94df05b0f7f',
'info_dict': {
'id': '383',
'ext': 'mp4',
'display_id': 'fullmetal-alchemist-brotherhood-episode-42',
'title': 'Fullmetal Alchemist: Brotherhood - Episode 42 - Signs of a Counteroffensive',
'description': 'md5:103eb61dd0a56d3dfc5dbf748e5e83f4',
'series': 'Fullmetal Alchemist: Brotherhood',
'episode': 'Signs of a Counteroffensive',
'episode_number': 42,
'duration': 1469,
'season': 'Season 1',
'season_number': 1,
'season_id': '38',
},
'params': {
'format': '[format_id=21711_yeshardsubbed_ja-JP][height=480]',
},
'skip': 'All AnimeLab content requires authentication',
}
def _real_extract(self, url):
display_id = self._match_id(url)
# unfortunately we can get different URLs for the same formats
# e.g. if we are using a "free" account so no dubs available
# (so _remove_duplicate_formats is not effective)
# so we use a dictionary as a workaround
formats = {}
for language_option_url in ('https://www.animelab.com/player/%s/subtitles',
'https://www.animelab.com/player/%s/dubbed'):
actual_url = language_option_url % display_id
webpage = self._download_webpage(actual_url, display_id, 'Downloading URL ' + actual_url)
video_collection = self._parse_json(self._search_regex(r'new\s+?AnimeLabApp\.VideoCollection\s*?\((.*?)\);', webpage, 'AnimeLab VideoCollection'), display_id)
position = int_or_none(self._search_regex(r'playlistPosition\s*?=\s*?(\d+)', webpage, 'Playlist Position'))
raw_data = video_collection[position]['videoEntry']
video_id = str_or_none(raw_data['id'])
# create a title from many sources (while grabbing other info)
# TODO use more fallback sources to get some of these
series = raw_data.get('showTitle')
video_type = raw_data.get('videoEntryType', {}).get('name')
episode_number = raw_data.get('episodeNumber')
episode_name = raw_data.get('name')
title_parts = (series, video_type, episode_number, episode_name)
if None not in title_parts:
title = '%s - %s %s - %s' % title_parts
else:
title = episode_name
description = raw_data.get('synopsis') or self._og_search_description(webpage, default=None)
duration = int_or_none(raw_data.get('duration'))
thumbnail_data = raw_data.get('images', [])
thumbnails = []
for thumbnail in thumbnail_data:
for instance in thumbnail['imageInstances']:
image_data = instance.get('imageInfo', {})
thumbnails.append({
'id': str_or_none(image_data.get('id')),
'url': image_data.get('fullPath'),
'width': image_data.get('width'),
'height': image_data.get('height'),
})
season_data = raw_data.get('season', {}) or {}
season = str_or_none(season_data.get('name'))
season_number = int_or_none(season_data.get('seasonNumber'))
season_id = str_or_none(season_data.get('id'))
for video_data in raw_data['videoList']:
current_video_list = {}
current_video_list['language'] = video_data.get('language', {}).get('languageCode')
is_hardsubbed = video_data.get('hardSubbed')
for video_instance in video_data['videoInstances']:
httpurl = video_instance.get('httpUrl')
url = httpurl if httpurl else video_instance.get('rtmpUrl')
if url is None:
# this video format is unavailable to the user (not premium etc.)
continue
current_format = current_video_list.copy()
format_id_parts = []
format_id_parts.append(str_or_none(video_instance.get('id')))
if is_hardsubbed is not None:
if is_hardsubbed:
format_id_parts.append('yeshardsubbed')
else:
format_id_parts.append('nothardsubbed')
format_id_parts.append(current_format['language'])
format_id = '_'.join([x for x in format_id_parts if x is not None])
ext = determine_ext(url)
if ext == 'm3u8':
for format_ in self._extract_m3u8_formats(
url, video_id, m3u8_id=format_id, fatal=False):
formats[format_['format_id']] = format_
continue
elif ext == 'mpd':
for format_ in self._extract_mpd_formats(
url, video_id, mpd_id=format_id, fatal=False):
formats[format_['format_id']] = format_
continue
current_format['url'] = url
quality_data = video_instance.get('videoQuality')
if quality_data:
quality = quality_data.get('name') or quality_data.get('description')
else:
quality = None
height = None
if quality:
height = int_or_none(self._search_regex(r'(\d+)p?$', quality, 'Video format height', default=None))
if height is None:
self.report_warning('Could not get height of video')
else:
current_format['height'] = height
current_format['format_id'] = format_id
formats[current_format['format_id']] = current_format
formats = list(formats.values())
self._sort_formats(formats)
return {
'id': video_id,
'display_id': display_id,
'title': title,
'description': description,
'series': series,
'episode': episode_name,
'episode_number': int_or_none(episode_number),
'thumbnails': thumbnails,
'duration': duration,
'formats': formats,
'season': season,
'season_number': season_number,
'season_id': season_id,
}
class AnimeLabShowsIE(AnimeLabBaseIE):
_VALID_URL = r'https?://(?:www\.)?animelab\.com/shows/(?P<id>[^/]+)'
_TEST = {
'url': 'https://www.animelab.com/shows/attack-on-titan',
'info_dict': {
'id': '45',
'title': 'Attack on Titan',
'description': 'md5:989d95a2677e9309368d5cf39ba91469',
},
'playlist_count': 59,
'skip': 'All AnimeLab content requires authentication',
}
def _real_extract(self, url):
_BASE_URL = 'http://www.animelab.com'
_SHOWS_API_URL = '/api/videoentries/show/videos/'
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id, 'Downloading requested URL')
show_data_str = self._search_regex(r'({"id":.*}),\svideoEntry', webpage, 'AnimeLab show data')
show_data = self._parse_json(show_data_str, display_id)
show_id = str_or_none(show_data.get('id'))
title = show_data.get('name')
description = show_data.get('shortSynopsis') or show_data.get('longSynopsis')
entries = []
for season in show_data['seasons']:
season_id = season['id']
get_data = urlencode_postdata({
'seasonId': season_id,
'limit': 1000,
})
# despite using urlencode_postdata, we are sending a GET request
target_url = _BASE_URL + _SHOWS_API_URL + show_id + "?" + get_data.decode('utf-8')
response = self._download_webpage(
target_url,
None, 'Season id %s' % season_id)
season_data = self._parse_json(response, display_id)
for video_data in season_data['list']:
entries.append(self.url_result(
_BASE_URL + '/player/' + video_data['slug'], 'AnimeLab',
str_or_none(video_data.get('id')), video_data.get('name')
))
return {
'_type': 'playlist',
'id': show_id,
'title': title,
'description': description,
'entries': entries,
}
# TODO implement myqueue

291
plugins/youtube_download/yt_dlp/extractor/animeondemand.py Normal file
View File

@ -0,0 +1,291 @@
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
determine_ext,
extract_attributes,
ExtractorError,
join_nonempty,
url_or_none,
urlencode_postdata,
urljoin,
)
class AnimeOnDemandIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?anime-on-demand\.de/anime/(?P<id>\d+)'
_LOGIN_URL = 'https://www.anime-on-demand.de/users/sign_in'
_APPLY_HTML5_URL = 'https://www.anime-on-demand.de/html5apply'
_NETRC_MACHINE = 'animeondemand'
# German-speaking countries of Europe
_GEO_COUNTRIES = ['AT', 'CH', 'DE', 'LI', 'LU']
_TESTS = [{
# jap, OmU
'url': 'https://www.anime-on-demand.de/anime/161',
'info_dict': {
'id': '161',
'title': 'Grimgar, Ashes and Illusions (OmU)',
'description': 'md5:6681ce3c07c7189d255ac6ab23812d31',
},
'playlist_mincount': 4,
}, {
# Film wording is used instead of Episode, ger/jap, Dub/OmU
'url': 'https://www.anime-on-demand.de/anime/39',
'only_matching': True,
}, {
# Episodes without titles, jap, OmU
'url': 'https://www.anime-on-demand.de/anime/162',
'only_matching': True,
}, {
# ger/jap, Dub/OmU, account required
'url': 'https://www.anime-on-demand.de/anime/169',
'only_matching': True,
}, {
# Full length film, non-series, ger/jap, Dub/OmU, account required
'url': 'https://www.anime-on-demand.de/anime/185',
'only_matching': True,
}, {
# Flash videos
'url': 'https://www.anime-on-demand.de/anime/12',
'only_matching': True,
}]
def _login(self):
username, password = self._get_login_info()
if username is None:
return
login_page = self._download_webpage(
self._LOGIN_URL, None, 'Downloading login page')
if '>Our licensing terms allow the distribution of animes only to German-speaking countries of Europe' in login_page:
self.raise_geo_restricted(
'%s is only available in German-speaking countries of Europe' % self.IE_NAME)
login_form = self._form_hidden_inputs('new_user', login_page)
login_form.update({
'user[login]': username,
'user[password]': password,
})
post_url = self._search_regex(
r'<form[^>]+action=(["\'])(?P<url>.+?)\1', login_page,
'post url', default=self._LOGIN_URL, group='url')
if not post_url.startswith('http'):
post_url = urljoin(self._LOGIN_URL, post_url)
response = self._download_webpage(
post_url, None, 'Logging in',
data=urlencode_postdata(login_form), headers={
'Referer': self._LOGIN_URL,
})
if all(p not in response for p in ('>Logout<', 'href="/users/sign_out"')):
error = self._search_regex(
r'<p[^>]+\bclass=(["\'])(?:(?!\1).)*\balert\b(?:(?!\1).)*\1[^>]*>(?P<error>.+?)</p>',
response, 'error', default=None, group='error')
if error:
raise ExtractorError('Unable to login: %s' % error, expected=True)
raise ExtractorError('Unable to log in')
def _real_initialize(self):
self._login()
def _real_extract(self, url):
anime_id = self._match_id(url)
webpage = self._download_webpage(url, anime_id)
if 'data-playlist=' not in webpage:
self._download_webpage(
self._APPLY_HTML5_URL, anime_id,
'Activating HTML5 beta', 'Unable to apply HTML5 beta')
webpage = self._download_webpage(url, anime_id)
csrf_token = self._html_search_meta(
'csrf-token', webpage, 'csrf token', fatal=True)
anime_title = self._html_search_regex(
r'(?s)<h1[^>]+itemprop="name"[^>]*>(.+?)</h1>',
webpage, 'anime name')
anime_description = self._html_search_regex(
r'(?s)<div[^>]+itemprop="description"[^>]*>(.+?)</div>',
webpage, 'anime description', default=None)
def extract_info(html, video_id, num=None):
title, description = [None] * 2
formats = []
for input_ in re.findall(
r'<input[^>]+class=["\'].*?streamstarter[^>]+>', html):
attributes = extract_attributes(input_)
title = attributes.get('data-dialog-header')
playlist_urls = []
for playlist_key in ('data-playlist', 'data-otherplaylist', 'data-stream'):
playlist_url = attributes.get(playlist_key)
if isinstance(playlist_url, compat_str) and re.match(
r'/?[\da-zA-Z]+', playlist_url):
playlist_urls.append(attributes[playlist_key])
if not playlist_urls:
continue
lang = attributes.get('data-lang')
lang_note = attributes.get('value')
for playlist_url in playlist_urls:
kind = self._search_regex(
r'videomaterialurl/\d+/([^/]+)/',
playlist_url, 'media kind', default=None)
format_id = join_nonempty(lang, kind) if lang or kind else str(num)
format_note = join_nonempty(kind, lang_note, delim=', ')
item_id_list = []
if format_id:
item_id_list.append(format_id)
item_id_list.append('videomaterial')
playlist = self._download_json(
urljoin(url, playlist_url), video_id,
'Downloading %s JSON' % ' '.join(item_id_list),
headers={
'X-Requested-With': 'XMLHttpRequest',
'X-CSRF-Token': csrf_token,
'Referer': url,
'Accept': 'application/json, text/javascript, */*; q=0.01',
}, fatal=False)
if not playlist:
continue
stream_url = url_or_none(playlist.get('streamurl'))
if stream_url:
rtmp = re.search(
r'^(?P<url>rtmpe?://(?P<host>[^/]+)/(?P<app>.+/))(?P<playpath>mp[34]:.+)',
stream_url)
if rtmp:
formats.append({
'url': rtmp.group('url'),
'app': rtmp.group('app'),
'play_path': rtmp.group('playpath'),
'page_url': url,
'player_url': 'https://www.anime-on-demand.de/assets/jwplayer.flash-55abfb34080700304d49125ce9ffb4a6.swf',
'rtmp_real_time': True,
'format_id': 'rtmp',
'ext': 'flv',
})
continue
start_video = playlist.get('startvideo', 0)
playlist = playlist.get('playlist')
if not playlist or not isinstance(playlist, list):
continue
playlist = playlist[start_video]
title = playlist.get('title')
if not title:
continue
description = playlist.get('description')
for source in playlist.get('sources', []):
file_ = source.get('file')
if not file_:
continue
ext = determine_ext(file_)
format_id = join_nonempty(
lang, kind,
'hls' if ext == 'm3u8' else None,
'dash' if source.get('type') == 'video/dash' or ext == 'mpd' else None)
if ext == 'm3u8':
file_formats = self._extract_m3u8_formats(
file_, video_id, 'mp4',
entry_protocol='m3u8_native', m3u8_id=format_id, fatal=False)
elif source.get('type') == 'video/dash' or ext == 'mpd':
continue
file_formats = self._extract_mpd_formats(
file_, video_id, mpd_id=format_id, fatal=False)
else:
continue
for f in file_formats:
f.update({
'language': lang,
'format_note': format_note,
})
formats.extend(file_formats)
return {
'title': title,
'description': description,
'formats': formats,
}
def extract_entries(html, video_id, common_info, num=None):
info = extract_info(html, video_id, num)
if info['formats']:
self._sort_formats(info['formats'])
f = common_info.copy()
f.update(info)
yield f
# Extract teaser/trailer only when full episode is not available
if not info['formats']:
m = re.search(
r'data-dialog-header=(["\'])(?P<title>.+?)\1[^>]+href=(["\'])(?P<href>.+?)\3[^>]*>(?P<kind>Teaser|Trailer)<',
html)
if m:
f = common_info.copy()
f.update({
'id': '%s-%s' % (f['id'], m.group('kind').lower()),
'title': m.group('title'),
'url': urljoin(url, m.group('href')),
})
yield f
def extract_episodes(html):
for num, episode_html in enumerate(re.findall(
r'(?s)<h3[^>]+class="episodebox-title".+?>Episodeninhalt<', html), 1):
episodebox_title = self._search_regex(
(r'class="episodebox-title"[^>]+title=(["\'])(?P<title>.+?)\1',
r'class="episodebox-title"[^>]+>(?P<title>.+?)<'),
episode_html, 'episodebox title', default=None, group='title')
if not episodebox_title:
continue
episode_number = int(self._search_regex(
r'(?:Episode|Film)\s*(\d+)',
episodebox_title, 'episode number', default=num))
episode_title = self._search_regex(
r'(?:Episode|Film)\s*\d+\s*-\s*(.+)',
episodebox_title, 'episode title', default=None)
video_id = 'episode-%d' % episode_number
common_info = {
'id': video_id,
'series': anime_title,
'episode': episode_title,
'episode_number': episode_number,
}
for e in extract_entries(episode_html, video_id, common_info):
yield e
def extract_film(html, video_id):
common_info = {
'id': anime_id,
'title': anime_title,
'description': anime_description,
}
for e in extract_entries(html, video_id, common_info):
yield e
def entries():
has_episodes = False
for e in extract_episodes(webpage):
has_episodes = True
yield e
if not has_episodes:
for e in extract_film(webpage, anime_id):
yield e
return self.playlist_result(
entries(), anime_id, anime_title, anime_description)

399
plugins/youtube_download/yt_dlp/extractor/anvato.py Normal file
View File

@ -0,0 +1,399 @@
# coding: utf-8
from __future__ import unicode_literals
import base64
import hashlib
import json
import random
import re
import time
from .common import InfoExtractor
from ..aes import aes_encrypt
from ..compat import compat_str
from ..utils import (
bytes_to_intlist,
determine_ext,
intlist_to_bytes,
int_or_none,
join_nonempty,
strip_jsonp,
unescapeHTML,
unsmuggle_url,
)
# This import causes a ModuleNotFoundError on some systems for unknown reason.
# See issues:
# https://github.com/yt-dlp/yt-dlp/issues/35
# https://github.com/ytdl-org/youtube-dl/issues/27449
# https://github.com/animelover1984/youtube-dl/issues/17
try:
from .anvato_token_generator import NFLTokenGenerator
except ImportError:
NFLTokenGenerator = None
def md5_text(s):
if not isinstance(s, compat_str):
s = compat_str(s)
return hashlib.md5(s.encode('utf-8')).hexdigest()
class AnvatoIE(InfoExtractor):
_VALID_URL = r'anvato:(?P<access_key_or_mcp>[^:]+):(?P<id>\d+)'
# Copied from anvplayer.min.js
_ANVACK_TABLE = {
'nbcu_nbcd_desktop_web_prod_93d8ead38ce2024f8f544b78306fbd15895ae5e6': 'NNemUkySjxLyPTKvZRiGntBIjEyK8uqicjMakIaQ',
'nbcu_nbcd_desktop_web_qa_1a6f01bdd0dc45a439043b694c8a031d': 'eSxJUbA2UUKBTXryyQ2d6NuM8oEqaPySvaPzfKNA',
'nbcu_nbcd_desktop_web_acc_eb2ff240a5d4ae9a63d4c297c32716b6c523a129': '89JR3RtUGbvKuuJIiKOMK0SoarLb5MUx8v89RcbP',
'nbcu_nbcd_watchvod_web_prod_e61107507180976724ec8e8319fe24ba5b4b60e1': 'Uc7dFt7MJ9GsBWB5T7iPvLaMSOt8BBxv4hAXk5vv',
'nbcu_nbcd_watchvod_web_qa_42afedba88a36203db5a4c09a5ba29d045302232': 'T12oDYVFP2IaFvxkmYMy5dKxswpLHtGZa4ZAXEi7',
'nbcu_nbcd_watchvod_web_acc_9193214448e2e636b0ffb78abacfd9c4f937c6ca': 'MmobcxUxMedUpohNWwXaOnMjlbiyTOBLL6d46ZpR',
'nbcu_local_monitor_web_acc_f998ad54eaf26acd8ee033eb36f39a7b791c6335': 'QvfIoPYrwsjUCcASiw3AIkVtQob2LtJHfidp9iWg',
'nbcu_cable_monitor_web_acc_a413759603e8bedfcd3c61b14767796e17834077': 'uwVPJLShvJWSs6sWEIuVem7MTF8A4IknMMzIlFto',
'nbcu_nbcd_mcpstage_web_qa_4c43a8f6e95a88dbb40276c0630ba9f693a63a4e': 'PxVYZVwjhgd5TeoPRxL3whssb5OUPnM3zyAzq8GY',
'nbcu_comcast_comcast_web_prod_074080762ad4ce956b26b43fb22abf153443a8c4': 'afnaRZfDyg1Z3WZHdupKfy6xrbAG2MHqe3VfuSwh',
'nbcu_comcast_comcast_web_qa_706103bb93ead3ef70b1de12a0e95e3c4481ade0': 'DcjsVbX9b3uoPlhdriIiovgFQZVxpISZwz0cx1ZK',
'nbcu_comcast_comcastcable_web_prod_669f04817536743563d7331c9293e59fbdbe3d07': '0RwMN2cWy10qhAhOscq3eK7aEe0wqnKt3vJ0WS4D',
'nbcu_comcast_comcastcable_web_qa_3d9d2d66219094127f0f6b09cc3c7bb076e3e1ca': '2r8G9DEya7PCqBceKZgrn2XkXgASjwLMuaFE1Aad',
'hearst_hearst_demo_web_stage_960726dfef3337059a01a78816e43b29ec04dfc7': 'cuZBPXTR6kSdoTCVXwk5KGA8rk3NrgGn4H6e9Dsp',
'anvato_mcpqa_demo_web_stage_18b55e00db5a13faa8d03ae6e41f6f5bcb15b922': 'IOaaLQ8ymqVyem14QuAvE5SndQynTcH5CrLkU2Ih',
'anvato_nextmedia_demo_web_stage_9787d56a02ff6b9f43e9a2b0920d8ca88beb5818': 'Pqu9zVzI1ApiIzbVA3VkGBEQHvdKSUuKpD6s2uaR',
'anvato_scripps_app_web_prod_0837996dbe373629133857ae9eb72e740424d80a': 'du1ccmn7RxzgizwbWU7hyUaGodNlJn7HtXI0WgXW',
'anvato_scripps_app_web_stage_360797e00fe2826be142155c4618cc52fce6c26c': '2PMrQ0BRoqCWl7nzphj0GouIMEh2mZYivAT0S1Su',
'fs2go_fs2go_go_all_prod_21934911ccfafc03a075894ead2260d11e2ddd24': 'RcuHlKikW2IJw6HvVoEkqq2UsuEJlbEl11pWXs4Q',
'fs2go_fs2go_go_web_prod_ead4b0eec7460c1a07783808db21b49cf1f2f9a7': '4K0HTT2u1zkQA2MaGaZmkLa1BthGSBdr7jllrhk5',
'fs2go_fs2go_go_web_stage_407585454a4400355d4391691c67f361': 'ftnc37VKRJBmHfoGGi3kT05bHyeJzilEzhKJCyl3',
'fs2go_fs2go_go_android_stage_44b714db6f8477f29afcba15a41e1d30': 'CtxpPvVpo6AbZGomYUhkKs7juHZwNml9b9J0J2gI',
'anvato_cbslocal_app_web_prod_547f3e49241ef0e5d30c79b2efbca5d92c698f67': 'Pw0XX5KBDsyRnPS0R2JrSrXftsy8Jnz5pAjaYC8s',
'anvato_cbslocal_app_web_stage_547a5f096594cd3e00620c6f825cad1096d28c80': '37OBUhX2uwNyKhhrNzSSNHSRPZpApC3trdqDBpuz',
'fs2go_att_att_web_prod_1042dddd089a05438b6a08f972941176f699ffd8': 'JLcF20JwYvpv6uAGcLWIaV12jKwaL1R8us4b6Zkg',
'fs2go_att_att_web_stage_807c5001955fc114a3331fe027ddc76e': 'gbu1oO1y0JiOFh4SUipt86P288JHpyjSqolrrT1x',
'fs2go_fs2go_tudor_web_prod_a7dd8e5a7cdc830cae55eae6f3e9fee5ee49eb9b': 'ipcp87VCEZXPPe868j3orLqzc03oTy7DXsGkAXXH',
'anvato_mhz_app_web_prod_b808218b30de7fdf60340cbd9831512bc1bf6d37': 'Stlm5Gs6BEhJLRTZHcNquyzxGqr23EuFmE5DCgjX',
'fs2go_charter_charter_web_stage_c2c6e5a68375a1bf00fff213d3ff8f61a835a54c': 'Lz4hbJp1fwL6jlcz4M2PMzghM4jp4aAmybtT5dPc',
'fs2go_charter_charter_web_prod_ebfe3b10f1af215a7321cd3d629e0b81dfa6fa8c': 'vUJsK345A1bVmyYDRhZX0lqFIgVXuqhmuyp1EtPK',
'anvato_epfox_app_web_prod_b3373168e12f423f41504f207000188daf88251b': 'GDKq1ixvX3MoBNdU5IOYmYa2DTUXYOozPjrCJnW7',
'anvato_epfox_app_web_stage_a3c2ce60f8f83ef374a88b68ee73a950f8ab87ce': '2jz2NH4BsXMaDsoJ5qkHMbcczAfIReo2eFYuVC1C',
'fs2go_verizon_verizon_web_stage_08e6df0354a4803f1b1f2428b5a9a382e8dbcd62': 'rKTVapNaAcmnUbGL4ZcuOoY4SE7VmZSQsblPFr7e',
'fs2go_verizon_verizon_web_prod_f909564cb606eff1f731b5e22e0928676732c445': 'qLSUuHerM3u9eNPzaHyUK52obai5MvE4XDJfqYe1',
'fs2go_foxcom_synd_web_stage_f7b9091f00ea25a4fdaaae77fca5b54cdc7e7043': '96VKF2vLd24fFiDfwPFpzM5llFN4TiIGAlodE0Re',
'fs2go_foxcom_synd_web_prod_0f2cdd64d87e4ab6a1d54aada0ff7a7c8387a064': 'agiPjbXEyEZUkbuhcnmVPhe9NNVbDjCFq2xkcx51',
'anvato_own_app_web_stage_1214ade5d28422c4dae9d03c1243aba0563c4dba': 'mzhamNac3swG4WsJAiUTacnGIODi6SWeVWk5D7ho',
'anvato_own_app_web_prod_944e162ed927ec3e9ed13eb68ed2f1008ee7565e': '9TSxh6G2TXOLBoYm9ro3LdNjjvnXpKb8UR8KoIP9',
'anvato_scripps_app_ftv_prod_a10a10468edd5afb16fb48171c03b956176afad1': 'COJ2i2UIPK7xZqIWswxe7FaVBOVgRkP1F6O6qGoH',
'anvato_scripps_app_ftv_stage_77d3ad2bdb021ec37ca2e35eb09acd396a974c9a': 'Q7nnopNLe2PPfGLOTYBqxSaRpl209IhqaEuDZi1F',
'anvato_univision_app_web_stage_551236ef07a0e17718c3995c35586b5ed8cb5031': 'D92PoLS6UitwxDRA191HUGT9OYcOjV6mPMa5wNyo',
'anvato_univision_app_web_prod_039a5c0a6009e637ae8ac906718a79911e0e65e1': '5mVS5u4SQjtw6NGw2uhMbKEIONIiLqRKck5RwQLR',
'nbcu_cnbc_springfield_ios_prod_670207fae43d6e9a94c351688851a2ce': 'M7fqCCIP9lW53oJbHs19OlJlpDrVyc2OL8gNeuTa',
'nbcu_cnbc_springfieldvod_ios_prod_7a5f04b1ceceb0e9c9e2264a44aa236e08e034c2': 'Yia6QbJahW0S7K1I0drksimhZb4UFq92xLBmmMvk',
'anvato_cox_app_web_prod_ce45cda237969f93e7130f50ee8bb6280c1484ab': 'cc0miZexpFtdoqZGvdhfXsLy7FXjRAOgb9V0f5fZ',
'anvato_cox_app_web_stage_c23dbe016a8e9d8c7101d10172b92434f6088bf9': 'yivU3MYHd2eDZcOfmLbINVtqxyecKTOp8OjOuoGJ',
'anvato_chnzero_app_web_stage_b1164d1352b579e792e542fddf13ee34c0eeb46b': 'A76QkXMmVH8lTCfU15xva1mZnSVcqeY4Xb22Kp7m',
'anvato_chnzero_app_web_prod_253d358928dc08ec161eda2389d53707288a730c': 'OA5QI3ZWZZkdtUEDqh28AH8GedsF6FqzJI32596b',
'anvato_discovery_vodpoc_web_stage_9fa7077b5e8af1f8355f65d4fb8d2e0e9d54e2b7': 'q3oT191tTQ5g3JCP67PkjLASI9s16DuWZ6fYmry3',
'anvato_discovery_vodpoc_web_prod_688614983167a1af6cdf6d76343fda10a65223c1': 'qRvRQCTVHd0VVOHsMvvfidyWmlYVrTbjby7WqIuK',
'nbcu_cnbc_springfieldvod_ftv_stage_826040aad1925a46ac5dfb4b3c5143e648c6a30d': 'JQaSb5a8Tz0PT4ti329DNmzDO30TnngTHmvX8Vua',
'nbcu_cnbc_springfield_ftv_stage_826040aad1925a46ac5dfb4b3c5143e648c6a30d': 'JQaSb5a8Tz0PT4ti329DNmzDO30TnngTHmvX8Vua',
'nbcu_nbcd_capture_web_stage_4dd9d585bfb984ebf856dee35db027b2465cc4ae': '0j1Ov4Vopyi2HpBZJYdL2m8ERJVGYh3nNpzPiO8F',
'nbcu_nbcd_watch3_android_prod_7712ca5fcf1c22f19ec1870a9650f9c37db22dcf': '3LN2UB3rPUAMu7ZriWkHky9vpLMXYha8JbSnxBlx',
'nbcu_nbcd_watchvod3_android_prod_0910a3a4692d57c0b5ff4316075bc5d096be45b9': 'mJagcQ2II30vUOAauOXne7ERwbf5S9nlB3IP17lQ',
'anvato_scripps_app_atv_prod_790deda22e16e71e83df58f880cd389908a45d52': 'CB6trI1mpoDIM5o54DNTsji90NDBQPZ4z4RqBNSH',
'nbcu_nbcd_watchv4_android_prod_ff67cef9cb409158c6f8c3533edddadd0b750507': 'j8CHQCUWjlYERj4NFRmUYOND85QNbHViH09UwuKm',
'nbcu_nbcd_watchvodv4_android_prod_a814d781609989dea6a629d50ae4c7ad8cc8e907': 'rkVnUXxdA9rawVLUlDQtMue9Y4Q7lFEaIotcUhjt',
'rvVKpA50qlOPLFxMjrCGf5pdkdQDm7qn': '1J7ZkY5Qz5lMLi93QOH9IveE7EYB3rLl',
'nbcu_dtv_local_web_prod_b266cf49defe255fd4426a97e27c09e513e9f82f': 'HuLnJDqzLa4saCzYMJ79zDRSQpEduw1TzjMNQu2b',
'nbcu_att_local_web_prod_4cef038b2d969a6b7d700a56a599040b6a619f67': 'Q0Em5VDc2KpydUrVwzWRXAwoNBulWUxCq2faK0AV',
'nbcu_dish_local_web_prod_c56dcaf2da2e9157a4266c82a78195f1dd570f6b': 'bC1LWmRz9ayj2AlzizeJ1HuhTfIaJGsDBnZNgoRg',
'nbcu_verizon_local_web_prod_88bebd2ce006d4ed980de8133496f9a74cb9b3e1': 'wzhDKJZpgvUSS1EQvpCQP8Q59qVzcPixqDGJefSk',
'nbcu_charter_local_web_prod_9ad90f7fc4023643bb718f0fe0fd5beea2382a50': 'PyNbxNhEWLzy1ZvWEQelRuIQY88Eub7xbSVRMdfT',
'nbcu_suddenlink_local_web_prod_20fb711725cac224baa1c1cb0b1c324d25e97178': '0Rph41lPXZbb3fqeXtHjjbxfSrNbtZp1Ygq7Jypa',
'nbcu_wow_local_web_prod_652d9ce4f552d9c2e7b5b1ed37b8cb48155174ad': 'qayIBZ70w1dItm2zS42AptXnxW15mkjRrwnBjMPv',
'nbcu_centurylink_local_web_prod_2034402b029bf3e837ad46814d9e4b1d1345ccd5': 'StePcPMkjsX51PcizLdLRMzxMEl5k2FlsMLUNV4k',
'nbcu_atlanticbrd_local_web_prod_8d5f5ecbf7f7b2f5e6d908dd75d90ae3565f682e': 'NtYLb4TFUS0pRs3XTkyO5sbVGYjVf17bVbjaGscI',
'nbcu_nbcd_watchvod_web_dev_08bc05699be47c4f31d5080263a8cfadc16d0f7c': 'hwxi2dgDoSWgfmVVXOYZm14uuvku4QfopstXckhr',
'anvato_nextmedia_app_web_prod_a4fa8c7204aa65e71044b57aaf63711980cfe5a0': 'tQN1oGPYY1nM85rJYePWGcIb92TG0gSqoVpQTWOw',
'anvato_mcp_lin_web_prod_4c36fbfd4d8d8ecae6488656e21ac6d1ac972749': 'GUXNf5ZDX2jFUpu4WT2Go4DJ5nhUCzpnwDRRUx1K',
'anvato_mcp_univision_web_prod_37fe34850c99a3b5cdb71dab10a417dd5cdecafa': 'bLDYF8JqfG42b7bwKEgQiU9E2LTIAtnKzSgYpFUH',
'anvato_mcp_fs2go_web_prod_c7b90a93e171469cdca00a931211a2f556370d0a': 'icgGoYGipQMMSEvhplZX1pwbN69srwKYWksz3xWK',
'anvato_mcp_sps_web_prod_54bdc90dd6ba21710e9f7074338365bba28da336': 'fA2iQdI7RDpynqzQYIpXALVS83NTPr8LLFK4LFsu',
'anvato_mcp_anv_web_prod_791407490f4c1ef2a4bcb21103e0cb1bcb3352b3': 'rMOUZqe9lwcGq2mNgG3EDusm6lKgsUnczoOX3mbg',
'anvato_mcp_gray_web_prod_4c10f067c393ed8fc453d3930f8ab2b159973900': 'rMOUZqe9lwcGq2mNgG3EDusm6lKgsUnczoOX3mbg',
'anvato_mcp_hearst_web_prod_5356c3de0fc7c90a3727b4863ca7fec3a4524a99': 'P3uXJ0fXXditBPCGkfvlnVScpPEfKmc64Zv7ZgbK',
'anvato_mcp_cbs_web_prod_02f26581ff80e5bda7aad28226a8d369037f2cbe': 'mGPvo5ZA5SgjOFAPEPXv7AnOpFUICX8hvFQVz69n',
'anvato_mcp_telemundo_web_prod_c5278d51ad46fda4b6ca3d0ea44a7846a054f582': 'qyT6PXXLjVNCrHaRVj0ugAhalNRS7Ee9BP7LUokD',
'nbcu_nbcd_watchvodv4_web_stage_4108362fba2d4ede21f262fea3c4162cbafd66c7': 'DhaU5lj0W2gEdcSSsnxURq8t7KIWtJfD966crVDk',
'anvato_scripps_app_ios_prod_409c41960c60b308db43c3cc1da79cab9f1c3d93': 'WPxj5GraLTkYCyj3M7RozLqIycjrXOEcDGFMIJPn',
'EZqvRyKBJLrgpClDPDF8I7Xpdp40Vx73': '4OxGd2dEakylntVKjKF0UK9PDPYB6A9W',
'M2v78QkpleXm9hPp9jUXI63x5vA6BogR': 'ka6K32k7ZALmpINkjJUGUo0OE42Md1BQ',
'nbcu_nbcd_desktop_web_prod_93d8ead38ce2024f8f544b78306fbd15895ae5e6_secure': 'NNemUkySjxLyPTKvZRiGntBIjEyK8uqicjMakIaQ',
'X8POa4zPPaKVZHqmWjuEzfP31b1QM9VN': 'Dn5vOY9ooDw7VSl9qztjZI5o0g08mA0z',
'M2v78QkBMpNJlSPp9diX5F2PBmBy6Bog': 'ka6K32kyo7nDZfNkjQCGWf1lpApXMd1B',
'bvJ0dQpav07l0hG5JgfVLF2dv1vARwpP': 'BzoQW24GrJZoJfmNodiJKSPeB9B8NOxj',
'lxQMLg2XZKuEZaWgsqubBxV9INZ6bryY': 'Vm2Mx6noKds9jB71h6urazwlTG3m9x8l',
'04EnjvXeoSmkbJ9ckPs7oY0mcxv7PlyN': 'aXERQP9LMfQVlEDsgGs6eEA1SWznAQ8P',
'mQbO2ge6BFRWVPYCYpU06YvNt80XLvAX': 'E2BV1NGmasN5v7eujECVPJgwflnLPm2A',
'g43oeBzJrCml7o6fa5fRL1ErCdeD8z4K': 'RX34mZ6zVH4Nr6whbxIGLv9WSbxEKo8V',
'VQrDJoP7mtdBzkxhXbSPwGB1coeElk4x': 'j2VejQx0VFKQepAF7dI0mJLKtOVJE18z',
'WxA5NzLRjCrmq0NUgaU5pdMDuZO7RJ4w': 'lyY5ADLKaIOLEgAsGQCveEMAcqnx3rY9',
'M4lpMXB71ie0PjMCjdFzVXq0SeRVqz49': 'n2zVkOqaLIv3GbLfBjcwW51LcveWOZ2e',
'dyDZGEqN8u8nkJZcJns0oxYmtP7KbGAn': 'VXOEqQW9BtEVLajfZQSLEqxgS5B7qn2D',
'E7QNjrVY5u5mGvgu67IoDgV1CjEND8QR': 'rz8AaDmdKIkLmPNhB5ILPJnjS5PnlL8d',
'a4zrqjoKlfzg0dwHEWtP31VqcLBpjm4g': 'LY9J16gwETdGWa3hjBu5o0RzuoQDjqXQ',
'dQP5BZroMsMVLO1hbmT5r2Enu86GjxA6': '7XR3oOdbPF6x3PRFLDCq9RkgsRjAo48V',
'M4lKNBO1NFe0PjMCj1tzVXq0SeRVqzA9': 'n2zoRqGLRUv3GbLfBmTwW51LcveWOZYe',
'nAZ7MZdpGCGg1pqFEbsoJOz2C60mv143': 'dYJgdqA9aT4yojETqGi7yNgoFADxqmXP',
'3y1MERYgOuE9NzbFgwhV6Wv2F0YKvbyz': '081xpZDQgC4VadLTavhWQxrku56DAgXV',
'bmQvmEXr5HWklBMCZOcpE2Z3HBYwqGyl': 'zxXPbVNyMiMAZldhr9FkOmA0fl4aKr2v',
'wA7oDNYldfr6050Hwxi52lPZiVlB86Ap': 'ZYK16aA7ni0d3l3c34uwpxD7CbReMm8Q',
'g43MbKMWmFml7o7sJoSRkXxZiXRvJ3QK': 'RX3oBJonvs4Nr6rUWBCGn3matRGqJPXV',
'mA9VdlqpLS0raGaSDvtoqNrBTzb8XY4q': '0XN4OjBD3fnW7r7IbmtJB4AyfOmlrE2r',
'mAajOwgkGt17oGoFmEuklMP9H0GnW54d': 'lXbBLPGyzikNGeGujAuAJGjZiwLRxyXR',
'vy8vjJ9kbUwrRqRu59Cj5dWZfzYErlAb': 'K8l7gpwaGcBpnAnCLNCmPZRdin3eaQX0',
'xQMWBpR8oHEZaWaSMGUb0avOHjLVYn4Y': 'm2MrN4vEaf9jB7BFy5Srb40jTrN67AYl',
'xyKEmVO3miRr6D6UVkt7oB8jtD6aJEAv': 'g2ddDebqDfqdgKgswyUKwGjbTWwzq923',
'7Qk0wa2D9FjKapacoJF27aLvUDKkLGA0': 'b2kgBEkephJaMkMTL7s1PLe4Ua6WyP2P',
'3QLg6nqmNTJ5VvVTo7f508LPidz1xwyY': 'g2L1GgpraipmAOAUqmIbBnPxHOmw4MYa',
'3y1B7zZjXTE9NZNSzZSVNPZaTNLjo6Qz': '081b5G6wzH4VagaURmcWbN5mT4JGEe2V',
'lAqnwvkw6SG6D8DSqmUg6DRLUp0w3G4x': 'O2pbP0xPDFNJjpjIEvcdryOJtpkVM4X5',
'awA7xd1N0Hr6050Hw2c52lPZiVlB864p': 'GZYKpn4aoT0d3l3c3PiwpxD7CbReMmXQ',
'jQVqPLl9YHL1WGWtR1HDgWBGT63qRNyV': '6X03ne6vrU4oWyWUN7tQVoajikxJR3Ye',
'GQRMR8mL7uZK797t7xH3eNzPIP5dOny1': 'm2vqPWGd4U31zWzSyasDRAoMT1PKRp8o',
'zydq9RdmRhXLkNkfNoTJlMzaF0lWekQB': '3X7LnvE7vH5nkEkSqLiey793Un7dLB8e',
'VQrDzwkB2IdBzjzu9MHPbEYkSB50gR4x': 'j2VebLzoKUKQeEesmVh0gM1eIp9jKz8z',
'mAa2wMamBs17oGoFmktklMP9H0GnW54d': 'lXbgP74xZTkNGeGujVUAJGjZiwLRxy8R',
'7yjB6ZLG6sW8R6RF2xcan1KGfJ5dNoyd': 'wXQkPorvPHZ45N5t4Jf6qwg5Tp4xvw29',
'a4zPpNeWGuzg0m0iX3tPeanGSkRKWXQg': 'LY9oa3QAyHdGW9Wu3Ri5JGeEik7l1N8Q',
'k2rneA2M38k25cXDwwSknTJlxPxQLZ6M': '61lyA2aEVDzklfdwmmh31saPxQx2VRjp',
'bK9Zk4OvPnvxduLgxvi8VUeojnjA02eV': 'o5jANYjbeMb4nfBaQvcLAt1jzLzYx6ze',
'5VD6EydM3R9orHmNMGInGCJwbxbQvGRw': 'w3zjmX7g4vnxzCxElvUEOiewkokXprkZ',
'70X35QbVYVYNPUmP9YfbzI06YqYQk2R1': 'vG4Aj2BMjMjoztB7zeFOnCVPJpJ8lMOa',
'26qYwQVG9p1Bks2GgBckjfDJOXOAMgG1': 'r4ev9X0mv5zqJc0yk5IBDcQOwZw8mnwQ',
'rvVKpA56MBXWlSxMw3cobT5pdkd4Dm7q': '1J7ZkY53pZ645c93owcLZuveE7E8B3rL',
'qN1zdy1zlYL23IWZGWtDvfV6WeWQWkJo': 'qN1zdy1zlYL23IWZGWtDvfV6WeWQWkJo',
'jdKqRGF16dKsBviMDae7IGDl7oTjEbVV': 'Q09l7vhlNxPFErIOK6BVCe7KnwUW5DVV',
'3QLkogW1OUJ5VvPsrDH56DY2u7lgZWyY': 'g2LRE1V9espmAOPhE4ubj4ZdUA57yDXa',
'wyJvWbXGBSdbkEzhv0CW8meou82aqRy8': 'M2wolPvyBIpQGkbT4juedD4ruzQGdK2y',
'7QkdZrzEkFjKap6IYDU2PB0oCNZORmA0': 'b2kN1l96qhJaMkPs9dt1lpjBfwqZoA8P',
'pvA05113MHG1w3JTYxc6DVlRCjErVz4O': 'gQXeAbblBUnDJ7vujbHvbRd1cxlz3AXO',
'mA9blJDZwT0raG1cvkuoeVjLC7ZWd54q': '0XN9jRPwMHnW7rvumgfJZOD9CJgVkWYr',
'5QwRN5qKJTvGKlDTmnf7xwNZcjRmvEy9': 'R2GP6LWBJU1QlnytwGt0B9pytWwAdDYy',
'eyn5rPPbkfw2KYxH32fG1q58CbLJzM40': 'p2gyqooZnS56JWeiDgfmOy1VugOQEBXn',
'3BABn3b5RfPJGDwilbHe7l82uBoR05Am': '7OYZG7KMVhbPdKJS3xcWEN3AuDlLNmXj',
'xA5zNGXD3HrmqMlF6OS5pdMDuZO7RJ4w': 'yY5DAm6r1IOLE3BCVMFveEMAcqnx3r29',
'g43PgW3JZfml7o6fDEURL1ErCdeD8zyK': 'RX3aQn1zrS4Nr6whDgCGLv9WSbxEKo2V',
'lAqp8WbGgiG6D8LTKJcg3O72CDdre1Qx': 'O2pnm6473HNJjpKuVosd3vVeh975yrX5',
'wyJbYEDxKSdbkJ6S6RhW8meou82aqRy8': 'M2wPm7EgRSpQGlAh70CedD4ruzQGdKYy',
'M4lgW28nLCe0PVdtaXszVXq0SeRVqzA9': 'n2zmJvg4jHv3G0ETNgiwW51LcveWOZ8e',
'5Qw3OVvp9FvGKlDTmOC7xwNZcjRmvEQ9': 'R2GzDdml9F1Qlnytw9s0B9pytWwAdD8y',
'vy8a98X7zCwrRqbHrLUjYzwDiK2b70Qb': 'K8lVwzyjZiBpnAaSGeUmnAgxuGOBxmY0',
'g4eGjJLLoiqRD3Pf9oT5O03LuNbLRDQp': '6XqD59zzpfN4EwQuaGt67qNpSyRBlnYy',
'g43OPp9boIml7o6fDOIRL1ErCdeD8z4K': 'RX33alNB4s4Nr6whDPUGLv9WSbxEKoXV',
'xA2ng9OkBcGKzDbTkKsJlx7dUK8R3dA5': 'z2aPnJvzBfObkwGC3vFaPxeBhxoMqZ8K',
'xyKEgBajZuRr6DEC0Kt7XpD1cnNW9gAv': 'g2ddlEBvRsqdgKaI4jUK9PrgfMexGZ23',
'BAogww51jIMa2JnH1BcYpXM5F658RNAL': 'rYWDmm0KptlkGv4FGJFMdZmjs9RDE6XR',
'BAokpg62VtMa2JnH1mHYpXM5F658RNAL': 'rYWryDnlNslkGv4FG4HMdZmjs9RDE62R',
'a4z1Px5e2hzg0m0iMMCPeanGSkRKWXAg': 'LY9eorNQGUdGW9WuKKf5JGeEik7l1NYQ',
'kAx69R58kF9nY5YcdecJdl2pFXP53WyX': 'gXyRxELpbfPvLeLSaRil0mp6UEzbZJ8L',
'BAoY13nwViMa2J2uo2cY6BlETgmdwryL': 'rYWwKzJmNFlkGvGtNoUM9bzwIJVzB1YR',
}
_MCP_TO_ACCESS_KEY_TABLE = {
'qa': 'anvato_mcpqa_demo_web_stage_18b55e00db5a13faa8d03ae6e41f6f5bcb15b922',
'lin': 'anvato_mcp_lin_web_prod_4c36fbfd4d8d8ecae6488656e21ac6d1ac972749',
'univison': 'anvato_mcp_univision_web_prod_37fe34850c99a3b5cdb71dab10a417dd5cdecafa',
'uni': 'anvato_mcp_univision_web_prod_37fe34850c99a3b5cdb71dab10a417dd5cdecafa',
'dev': 'anvato_mcp_fs2go_web_prod_c7b90a93e171469cdca00a931211a2f556370d0a',
'sps': 'anvato_mcp_sps_web_prod_54bdc90dd6ba21710e9f7074338365bba28da336',
'spsstg': 'anvato_mcp_sps_web_prod_54bdc90dd6ba21710e9f7074338365bba28da336',
'anv': 'anvato_mcp_anv_web_prod_791407490f4c1ef2a4bcb21103e0cb1bcb3352b3',
'gray': 'anvato_mcp_gray_web_prod_4c10f067c393ed8fc453d3930f8ab2b159973900',
'hearst': 'anvato_mcp_hearst_web_prod_5356c3de0fc7c90a3727b4863ca7fec3a4524a99',
'cbs': 'anvato_mcp_cbs_web_prod_02f26581ff80e5bda7aad28226a8d369037f2cbe',
'telemundo': 'anvato_mcp_telemundo_web_prod_c5278d51ad46fda4b6ca3d0ea44a7846a054f582'
}
_TOKEN_GENERATORS = {
'GXvEgwyJeWem8KCYXfeoHWknwP48Mboj': NFLTokenGenerator,
}
_API_KEY = '3hwbSuqqT690uxjNYBktSQpa5ZrpYYR0Iofx7NcJHyA'
_ANVP_RE = r'<script[^>]+\bdata-anvp\s*=\s*(["\'])(?P<anvp>(?:(?!\1).)+)\1'
_AUTH_KEY = b'\x31\xc2\x42\x84\x9e\x73\xa0\xce'
_TESTS = [{
# from https://www.boston25news.com/news/watch-humpback-whale-breaches-right-next-to-fishing-boat-near-nh/817484874
'url': 'anvato:8v9BEynrwx8EFLYpgfOWcG1qJqyXKlRM:4465496',
'info_dict': {
'id': '4465496',
'ext': 'mp4',
'title': 'VIDEO: Humpback whale breaches right next to NH boat',
'description': 'VIDEO: Humpback whale breaches right next to NH boat. Footage courtesy: Zach Fahey.',
'duration': 22,
'timestamp': 1534855680,
'upload_date': '20180821',
'uploader': 'ANV',
},
'params': {
'skip_download': True,
},
}, {
# from https://sanfrancisco.cbslocal.com/2016/06/17/source-oakland-cop-on-leave-for-having-girlfriend-help-with-police-reports/
'url': 'anvato:DVzl9QRzox3ZZsP9bNu5Li3X7obQOnqP:3417601',
'only_matching': True,
}]
def __init__(self, *args, **kwargs):
super(AnvatoIE, self).__init__(*args, **kwargs)
self.__server_time = None
def _server_time(self, access_key, video_id):
if self.__server_time is not None:
return self.__server_time
self.__server_time = int(self._download_json(
self._api_prefix(access_key) + 'server_time?anvack=' + access_key, video_id,
note='Fetching server time')['server_time'])
return self.__server_time
def _api_prefix(self, access_key):
return 'https://tkx2-%s.anvato.net/rest/v2/' % ('prod' if 'prod' in access_key else 'stage')
def _get_video_json(self, access_key, video_id):
# See et() in anvplayer.min.js, which is an alias of getVideoJSON()
video_data_url = self._api_prefix(access_key) + 'mcp/video/%s?anvack=%s' % (video_id, access_key)
server_time = self._server_time(access_key, video_id)
input_data = '%d~%s~%s' % (server_time, md5_text(video_data_url), md5_text(server_time))
auth_secret = intlist_to_bytes(aes_encrypt(
bytes_to_intlist(input_data[:64]), bytes_to_intlist(self._AUTH_KEY)))
video_data_url += '&X-Anvato-Adst-Auth=' + base64.b64encode(auth_secret).decode('ascii')
anvrid = md5_text(time.time() * 1000 * random.random())[:30]
api = {
'anvrid': anvrid,
'anvts': server_time,
}
if self._TOKEN_GENERATORS.get(access_key) is not None:
api['anvstk2'] = self._TOKEN_GENERATORS[access_key].generate(self, access_key, video_id)
else:
api['anvstk'] = md5_text('%s|%s|%d|%s' % (
access_key, anvrid, server_time,
self._ANVACK_TABLE.get(access_key, self._API_KEY)))
return self._download_json(
video_data_url, video_id, transform_source=strip_jsonp,
data=json.dumps({'api': api}).encode('utf-8'))
def _get_anvato_videos(self, access_key, video_id):
video_data = self._get_video_json(access_key, video_id)
formats = []
for published_url in video_data['published_urls']:
video_url = published_url['embed_url']
media_format = published_url.get('format')
ext = determine_ext(video_url)
if ext == 'smil' or media_format == 'smil':
formats.extend(self._extract_smil_formats(video_url, video_id))
continue
tbr = int_or_none(published_url.get('kbps'))
a_format = {
'url': video_url,
'format_id': join_nonempty('http', published_url.get('cdn_name')).lower(),
'tbr': tbr or None,
}
if media_format == 'm3u8' and tbr is not None:
a_format.update({
'format_id': join_nonempty('hls', tbr),
'ext': 'mp4',
})
elif media_format == 'm3u8-variant' or ext == 'm3u8':
formats.extend(self._extract_m3u8_formats(
video_url, video_id, 'mp4', entry_protocol='m3u8_native',
m3u8_id='hls', fatal=False))
continue
elif ext == 'mp3' or media_format == 'mp3':
a_format['vcodec'] = 'none'
else:
a_format.update({
'width': int_or_none(published_url.get('width')),
'height': int_or_none(published_url.get('height')),
})
formats.append(a_format)
self._sort_formats(formats)
subtitles = {}
for caption in video_data.get('captions', []):
a_caption = {
'url': caption['url'],
'ext': 'tt' if caption.get('format') == 'SMPTE-TT' else None
}
subtitles.setdefault(caption['language'], []).append(a_caption)
return {
'id': video_id,
'formats': formats,
'title': video_data.get('def_title'),
'description': video_data.get('def_description'),
'tags': video_data.get('def_tags', '').split(','),
'categories': video_data.get('categories'),
'thumbnail': video_data.get('src_image_url') or video_data.get('thumbnail'),
'timestamp': int_or_none(video_data.get(
'ts_published') or video_data.get('ts_added')),
'uploader': video_data.get('mcp_id'),
'duration': int_or_none(video_data.get('duration')),
'subtitles': subtitles,
}
@staticmethod
def _extract_urls(ie, webpage, video_id):
entries = []
for mobj in re.finditer(AnvatoIE._ANVP_RE, webpage):
anvplayer_data = ie._parse_json(
mobj.group('anvp'), video_id, transform_source=unescapeHTML,
fatal=False)
if not anvplayer_data:
continue
video = anvplayer_data.get('video')
if not isinstance(video, compat_str) or not video.isdigit():
continue
access_key = anvplayer_data.get('accessKey')
if not access_key:
mcp = anvplayer_data.get('mcp')
if mcp:
access_key = AnvatoIE._MCP_TO_ACCESS_KEY_TABLE.get(
mcp.lower())
if not access_key:
continue
entries.append(ie.url_result(
'anvato:%s:%s' % (access_key, video), ie=AnvatoIE.ie_key(),
video_id=video))
return entries
def _extract_anvato_videos(self, webpage, video_id):
anvplayer_data = self._parse_json(
self._html_search_regex(
self._ANVP_RE, webpage, 'Anvato player data', group='anvp'),
video_id)
return self._get_anvato_videos(
anvplayer_data['accessKey'], anvplayer_data['video'])
def _real_extract(self, url):
url, smuggled_data = unsmuggle_url(url, {})
self._initialize_geo_bypass({
'countries': smuggled_data.get('geo_countries'),
})
mobj = self._match_valid_url(url)
access_key, video_id = mobj.group('access_key_or_mcp', 'id')
if access_key not in self._ANVACK_TABLE:
access_key = self._MCP_TO_ACCESS_KEY_TABLE.get(
access_key) or access_key
return self._get_anvato_videos(access_key, video_id)

7
plugins/youtube_download/yt_dlp/extractor/anvato_token_generator/__init__.py Normal file
View File

@ -0,0 +1,7 @@
from __future__ import unicode_literals
from .nfl import NFLTokenGenerator
__all__ = [
'NFLTokenGenerator',
]

6
plugins/youtube_download/yt_dlp/extractor/anvato_token_generator/common.py Normal file
View File

@ -0,0 +1,6 @@
from __future__ import unicode_literals
class TokenGenerator:
def generate(self, anvack, mcp_id):
raise NotImplementedError('This method must be implemented by subclasses')

30
plugins/youtube_download/yt_dlp/extractor/anvato_token_generator/nfl.py Normal file
View File

@ -0,0 +1,30 @@
from __future__ import unicode_literals
import json
from .common import TokenGenerator
class NFLTokenGenerator(TokenGenerator):
_AUTHORIZATION = None
def generate(ie, anvack, mcp_id):
if not NFLTokenGenerator._AUTHORIZATION:
reroute = ie._download_json(
'https://api.nfl.com/v1/reroute', mcp_id,
data=b'grant_type=client_credentials',
headers={'X-Domain-Id': 100})
NFLTokenGenerator._AUTHORIZATION = '%s %s' % (reroute.get('token_type') or 'Bearer', reroute['access_token'])
return ie._download_json(
'https://api.nfl.com/v3/shield/', mcp_id, data=json.dumps({
'query': '''{
viewer {
mediaToken(anvack: "%s", id: %s) {
token
}
}
}''' % (anvack, mcp_id),
}).encode(), headers={
'Authorization': NFLTokenGenerator._AUTHORIZATION,
'Content-Type': 'application/json',
})['data']['viewer']['mediaToken']['token']

136
plugins/youtube_download/yt_dlp/extractor/aol.py Normal file
View File

@ -0,0 +1,136 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .yahoo import YahooIE
from ..utils import (
ExtractorError,
int_or_none,
parse_qs,
url_or_none,
)
class AolIE(YahooIE):
IE_NAME = 'aol.com'
_VALID_URL = r'(?:aol-video:|https?://(?:www\.)?aol\.(?:com|ca|co\.uk|de|jp)/video/(?:[^/]+/)*)(?P<id>\d{9}|[0-9a-f]{24}|[0-9a-f]{8}-(?:[0-9a-f]{4}-){3}[0-9a-f]{12})'
_TESTS = [{
# video with 5min ID
'url': 'https://www.aol.com/video/view/u-s--official-warns-of-largest-ever-irs-phone-scam/518167793/',
'md5': '18ef68f48740e86ae94b98da815eec42',
'info_dict': {
'id': '518167793',
'ext': 'mp4',
'title': 'U.S. Official Warns Of \'Largest Ever\' IRS Phone Scam',
'description': 'A major phone scam has cost thousands of taxpayers more than $1 million, with less than a month until income tax returns are due to the IRS.',
'timestamp': 1395405060,
'upload_date': '20140321',
'uploader': 'Newsy Studio',
},
'params': {
# m3u8 download
'skip_download': True,
}
}, {
# video with vidible ID
'url': 'https://www.aol.com/video/view/netflix-is-raising-rates/5707d6b8e4b090497b04f706/',
'info_dict': {
'id': '5707d6b8e4b090497b04f706',
'ext': 'mp4',
'title': 'Netflix is Raising Rates',
'description': 'Netflix is rewarding millions of it’s long-standing members with an increase in cost. Veuer’s Carly Figueroa has more.',
'upload_date': '20160408',
'timestamp': 1460123280,
'uploader': 'Veuer',
},
'params': {
# m3u8 download
'skip_download': True,
}
}, {
'url': 'https://www.aol.com/video/view/park-bench-season-2-trailer/559a1b9be4b0c3bfad3357a7/',
'only_matching': True,
}, {
'url': 'https://www.aol.com/video/view/donald-trump-spokeswoman-tones-down-megyn-kelly-attacks/519442220/',
'only_matching': True,
}, {
'url': 'aol-video:5707d6b8e4b090497b04f706',
'only_matching': True,
}, {
'url': 'https://www.aol.com/video/playlist/PL8245/5ca79d19d21f1a04035db606/',
'only_matching': True,
}, {
'url': 'https://www.aol.ca/video/view/u-s-woman-s-family-arrested-for-murder-first-pinned-on-panhandler-police/5c7ccf45bc03931fa04b2fe1/',
'only_matching': True,
}, {
'url': 'https://www.aol.co.uk/video/view/-one-dead-and-22-hurt-in-bus-crash-/5cb3a6f3d21f1a072b457347/',
'only_matching': True,
}, {
'url': 'https://www.aol.de/video/view/eva-braun-privataufnahmen-von-hitlers-geliebter-werden-digitalisiert/5cb2d49de98ab54c113d3d5d/',
'only_matching': True,
}, {
'url': 'https://www.aol.jp/video/playlist/5a28e936a1334d000137da0c/5a28f3151e642219fde19831/',
'only_matching': True,
}, {
# Yahoo video
'url': 'https://www.aol.com/video/play/991e6700-ac02-11ea-99ff-357400036f61/24bbc846-3e30-3c46-915e-fe8ccd7fcc46/',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
if '-' in video_id:
return self._extract_yahoo_video(video_id, 'us')
response = self._download_json(
'https://feedapi.b2c.on.aol.com/v1.0/app/videos/aolon/%s/details' % video_id,
video_id)['response']
if response['statusText'] != 'Ok':
raise ExtractorError('%s said: %s' % (self.IE_NAME, response['statusText']), expected=True)
video_data = response['data']
formats = []
m3u8_url = url_or_none(video_data.get('videoMasterPlaylist'))
if m3u8_url:
formats.extend(self._extract_m3u8_formats(
m3u8_url, video_id, 'mp4', m3u8_id='hls', fatal=False))
for rendition in video_data.get('renditions', []):
video_url = url_or_none(rendition.get('url'))
if not video_url:
continue
ext = rendition.get('format')
if ext == 'm3u8':
formats.extend(self._extract_m3u8_formats(
video_url, video_id, 'mp4', m3u8_id='hls', fatal=False))
else:
f = {
'url': video_url,
'format_id': rendition.get('quality'),
}
mobj = re.search(r'(\d+)x(\d+)', video_url)
if mobj:
f.update({
'width': int(mobj.group(1)),
'height': int(mobj.group(2)),
})
else:
qs = parse_qs(video_url)
f.update({
'width': int_or_none(qs.get('w', [None])[0]),
'height': int_or_none(qs.get('h', [None])[0]),
})
formats.append(f)
self._sort_formats(formats)
return {
'id': video_id,
'title': video_data['title'],
'duration': int_or_none(video_data.get('duration')),
'timestamp': int_or_none(video_data.get('publishDate')),
'view_count': int_or_none(video_data.get('views')),
'description': video_data.get('description'),
'uploader': video_data.get('videoOwner'),
'formats': formats,
}

95
plugins/youtube_download/yt_dlp/extractor/apa.py Normal file
View File

@ -0,0 +1,95 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
determine_ext,
int_or_none,
url_or_none,
)
class APAIE(InfoExtractor):
_VALID_URL = r'(?P<base_url>https?://[^/]+\.apa\.at)/embed/(?P<id>[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})'
_TESTS = [{
'url': 'http://uvp.apa.at/embed/293f6d17-692a-44e3-9fd5-7b178f3a1029',
'md5': '2b12292faeb0a7d930c778c7a5b4759b',
'info_dict': {
'id': '293f6d17-692a-44e3-9fd5-7b178f3a1029',
'ext': 'mp4',
'title': '293f6d17-692a-44e3-9fd5-7b178f3a1029',
'thumbnail': r're:^https?://.*\.jpg$',
},
}, {
'url': 'https://uvp-apapublisher.sf.apa.at/embed/2f94e9e6-d945-4db2-9548-f9a41ebf7b78',
'only_matching': True,
}, {
'url': 'http://uvp-rma.sf.apa.at/embed/70404cca-2f47-4855-bbb8-20b1fae58f76',
'only_matching': True,
}, {
'url': 'http://uvp-kleinezeitung.sf.apa.at/embed/f1c44979-dba2-4ebf-b021-e4cf2cac3c81',
'only_matching': True,
}]
@staticmethod
def _extract_urls(webpage):
return [
mobj.group('url')
for mobj in re.finditer(
r'<iframe[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//[^/]+\.apa\.at/embed/[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12}.*?)\1',
webpage)]
def _real_extract(self, url):
mobj = self._match_valid_url(url)
video_id, base_url = mobj.group('id', 'base_url')
webpage = self._download_webpage(
'%s/player/%s' % (base_url, video_id), video_id)
jwplatform_id = self._search_regex(
r'media[iI]d\s*:\s*["\'](?P<id>[a-zA-Z0-9]{8})', webpage,
'jwplatform id', default=None)
if jwplatform_id:
return self.url_result(
'jwplatform:' + jwplatform_id, ie='JWPlatform',
video_id=video_id)
def extract(field, name=None):
return self._search_regex(
r'\b%s["\']\s*:\s*(["\'])(?P<value>(?:(?!\1).)+)\1' % field,
webpage, name or field, default=None, group='value')
title = extract('title') or video_id
description = extract('description')
thumbnail = extract('poster', 'thumbnail')
formats = []
for format_id in ('hls', 'progressive'):
source_url = url_or_none(extract(format_id))
if not source_url:
continue
ext = determine_ext(source_url)
if ext == 'm3u8':
formats.extend(self._extract_m3u8_formats(
source_url, video_id, 'mp4', entry_protocol='m3u8_native',
m3u8_id='hls', fatal=False))
else:
height = int_or_none(self._search_regex(
r'(\d+)\.mp4', source_url, 'height', default=None))
formats.append({
'url': source_url,
'format_id': format_id,
'height': height,
})
self._sort_formats(formats)
return {
'id': video_id,
'title': title,
'description': description,
'thumbnail': thumbnail,
'formats': formats,
}

91
plugins/youtube_download/yt_dlp/extractor/aparat.py Normal file
View File

@ -0,0 +1,91 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import (
get_element_by_id,
int_or_none,
merge_dicts,
mimetype2ext,
url_or_none,
)
class AparatIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?aparat\.com/(?:v/|video/video/embed/videohash/)(?P<id>[a-zA-Z0-9]+)'
_TESTS = [{
'url': 'http://www.aparat.com/v/wP8On',
'md5': '131aca2e14fe7c4dcb3c4877ba300c89',
'info_dict': {
'id': 'wP8On',
'ext': 'mp4',
'title': 'تیم گلکسی 11 - زومیت',
'description': 'md5:096bdabcdcc4569f2b8a5e903a3b3028',
'duration': 231,
'timestamp': 1387394859,
'upload_date': '20131218',
'view_count': int,
},
}, {
# multiple formats
'url': 'https://www.aparat.com/v/8dflw/',
'only_matching': True,
}]
def _parse_options(self, webpage, video_id, fatal=True):
return self._parse_json(self._search_regex(
r'options\s*=\s*({.+?})\s*;', webpage, 'options', default='{}'), video_id)
def _real_extract(self, url):
video_id = self._match_id(url)
# If available, provides more metadata
webpage = self._download_webpage(url, video_id, fatal=False)
options = self._parse_options(webpage, video_id, fatal=False)
if not options:
webpage = self._download_webpage(
'http://www.aparat.com/video/video/embed/vt/frame/showvideo/yes/videohash/' + video_id,
video_id, 'Downloading embed webpage')
options = self._parse_options(webpage, video_id)
formats = []
for sources in (options.get('multiSRC') or []):
for item in sources:
if not isinstance(item, dict):
continue
file_url = url_or_none(item.get('src'))
if not file_url:
continue
item_type = item.get('type')
if item_type == 'application/vnd.apple.mpegurl':
formats.extend(self._extract_m3u8_formats(
file_url, video_id, 'mp4',
entry_protocol='m3u8_native', m3u8_id='hls',
fatal=False))
else:
ext = mimetype2ext(item.get('type'))
label = item.get('label')
formats.append({
'url': file_url,
'ext': ext,
'format_id': 'http-%s' % (label or ext),
'height': int_or_none(self._search_regex(
r'(\d+)[pP]', label or '', 'height',
default=None)),
})
self._sort_formats(formats)
info = self._search_json_ld(webpage, video_id, default={})
if not info.get('title'):
info['title'] = get_element_by_id('videoTitle', webpage) or \
self._html_search_meta(['og:title', 'twitter:title', 'DC.Title', 'title'], webpage, fatal=True)
return merge_dicts(info, {
'id': video_id,
'thumbnail': url_or_none(options.get('poster')),
'duration': int_or_none(options.get('duration')),
'formats': formats,
})

53
plugins/youtube_download/yt_dlp/extractor/appleconnect.py Normal file
View File

@ -0,0 +1,53 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import (
str_to_int,
ExtractorError
)
class AppleConnectIE(InfoExtractor):
_VALID_URL = r'https?://itunes\.apple\.com/\w{0,2}/?post/(?:id)?sa\.(?P<id>[\w-]+)'
_TESTS = [{
'url': 'https://itunes.apple.com/us/post/idsa.4ab17a39-2720-11e5-96c5-a5b38f6c42d3',
'md5': 'c1d41f72c8bcaf222e089434619316e4',
'info_dict': {
'id': '4ab17a39-2720-11e5-96c5-a5b38f6c42d3',
'ext': 'm4v',
'title': 'Energy',
'uploader': 'Drake',
'thumbnail': r're:^https?://.*\.jpg$',
'upload_date': '20150710',
'timestamp': 1436545535,
},
}, {
'url': 'https://itunes.apple.com/us/post/sa.0fe0229f-2457-11e5-9f40-1bb645f2d5d9',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
try:
video_json = self._html_search_regex(
r'class="auc-video-data">(\{.*?\})', webpage, 'json')
except ExtractorError:
raise ExtractorError('This post doesn\'t contain a video', expected=True)
video_data = self._parse_json(video_json, video_id)
timestamp = str_to_int(self._html_search_regex(r'data-timestamp="(\d+)"', webpage, 'timestamp'))
like_count = str_to_int(self._html_search_regex(r'(\d+) Loves', webpage, 'like count', default=None))
return {
'id': video_id,
'url': video_data['sslSrc'],
'title': video_data['title'],
'description': video_data['description'],
'uploader': video_data['artistName'],
'thumbnail': video_data['artworkUrl'],
'timestamp': timestamp,
'like_count': like_count,
}

62
plugins/youtube_download/yt_dlp/extractor/applepodcasts.py Normal file
View File

@ -0,0 +1,62 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import (
clean_podcast_url,
int_or_none,
parse_iso8601,
try_get,
)
class ApplePodcastsIE(InfoExtractor):
_VALID_URL = r'https?://podcasts\.apple\.com/(?:[^/]+/)?podcast(?:/[^/]+){1,2}.*?\bi=(?P<id>\d+)'
_TESTS = [{
'url': 'https://podcasts.apple.com/us/podcast/207-whitney-webb-returns/id1135137367?i=1000482637777',
'md5': 'df02e6acb11c10e844946a39e7222b08',
'info_dict': {
'id': '1000482637777',
'ext': 'mp3',
'title': '207 - Whitney Webb Returns',
'description': 'md5:13a73bade02d2e43737751e3987e1399',
'upload_date': '20200705',
'timestamp': 1593921600,
'duration': 6425,
'series': 'The Tim Dillon Show',
}
}, {
'url': 'https://podcasts.apple.com/podcast/207-whitney-webb-returns/id1135137367?i=1000482637777',
'only_matching': True,
}, {
'url': 'https://podcasts.apple.com/podcast/207-whitney-webb-returns?i=1000482637777',
'only_matching': True,
}, {
'url': 'https://podcasts.apple.com/podcast/id1135137367?i=1000482637777',
'only_matching': True,
}]
def _real_extract(self, url):
episode_id = self._match_id(url)
webpage = self._download_webpage(url, episode_id)
ember_data = self._parse_json(self._search_regex(
r'id="shoebox-ember-data-store"[^>]*>\s*({.+?})\s*<',
webpage, 'ember data'), episode_id)
ember_data = ember_data.get(episode_id) or ember_data
episode = ember_data['data']['attributes']
description = episode.get('description') or {}
series = None
for inc in (ember_data.get('included') or []):
if inc.get('type') == 'media/podcast':
series = try_get(inc, lambda x: x['attributes']['name'])
return {
'id': episode_id,
'title': episode['name'],
'url': clean_podcast_url(episode['assetUrl']),
'description': description.get('standard') or description.get('short'),
'timestamp': parse_iso8601(episode.get('releaseDateTime')),
'duration': int_or_none(episode.get('durationInMilliseconds'), 1000),
'series': series,
}

283
plugins/youtube_download/yt_dlp/extractor/appletrailers.py Normal file
View File

@ -0,0 +1,283 @@
from __future__ import unicode_literals
import re
import json
from .common import InfoExtractor
from ..compat import compat_urlparse
from ..utils import (
int_or_none,
parse_duration,
unified_strdate,
)
class AppleTrailersIE(InfoExtractor):
IE_NAME = 'appletrailers'
_VALID_URL = r'https?://(?:www\.|movie)?trailers\.apple\.com/(?:trailers|ca)/(?P<company>[^/]+)/(?P<movie>[^/]+)'
_TESTS = [{
'url': 'http://trailers.apple.com/trailers/wb/manofsteel/',
'info_dict': {
'id': '5111',
'title': 'Man of Steel',
},
'playlist': [
{
'md5': 'd97a8e575432dbcb81b7c3acb741f8a8',
'info_dict': {
'id': 'manofsteel-trailer4',
'ext': 'mov',
'duration': 111,
'title': 'Trailer 4',
'upload_date': '20130523',
'uploader_id': 'wb',
},
},
{
'md5': 'b8017b7131b721fb4e8d6f49e1df908c',
'info_dict': {
'id': 'manofsteel-trailer3',
'ext': 'mov',
'duration': 182,
'title': 'Trailer 3',
'upload_date': '20130417',
'uploader_id': 'wb',
},
},
{
'md5': 'd0f1e1150989b9924679b441f3404d48',
'info_dict': {
'id': 'manofsteel-trailer',
'ext': 'mov',
'duration': 148,
'title': 'Trailer',
'upload_date': '20121212',
'uploader_id': 'wb',
},
},
{
'md5': '5fe08795b943eb2e757fa95cb6def1cb',
'info_dict': {
'id': 'manofsteel-teaser',
'ext': 'mov',
'duration': 93,
'title': 'Teaser',
'upload_date': '20120721',
'uploader_id': 'wb',
},
},
]
}, {
'url': 'http://trailers.apple.com/trailers/magnolia/blackthorn/',
'info_dict': {
'id': '4489',
'title': 'Blackthorn',
},
'playlist_mincount': 2,
'expected_warnings': ['Unable to download JSON metadata'],
}, {
# json data only available from http://trailers.apple.com/trailers/feeds/data/15881.json
'url': 'http://trailers.apple.com/trailers/fox/kungfupanda3/',
'info_dict': {
'id': '15881',
'title': 'Kung Fu Panda 3',
},
'playlist_mincount': 4,
}, {
'url': 'http://trailers.apple.com/ca/metropole/autrui/',
'only_matching': True,
}, {
'url': 'http://movietrailers.apple.com/trailers/focus_features/kuboandthetwostrings/',
'only_matching': True,
}]
_JSON_RE = r'iTunes.playURL\((.*?)\);'
def _real_extract(self, url):
mobj = self._match_valid_url(url)
movie = mobj.group('movie')
uploader_id = mobj.group('company')
webpage = self._download_webpage(url, movie)
film_id = self._search_regex(r"FilmId\s*=\s*'(\d+)'", webpage, 'film id')
film_data = self._download_json(
'http://trailers.apple.com/trailers/feeds/data/%s.json' % film_id,
film_id, fatal=False)
if film_data:
entries = []
for clip in film_data.get('clips', []):
clip_title = clip['title']
formats = []
for version, version_data in clip.get('versions', {}).items():
for size, size_data in version_data.get('sizes', {}).items():
src = size_data.get('src')
if not src:
continue
formats.append({
'format_id': '%s-%s' % (version, size),
'url': re.sub(r'_(\d+p\.mov)', r'_h\1', src),
'width': int_or_none(size_data.get('width')),
'height': int_or_none(size_data.get('height')),
'language': version[:2],
})
self._sort_formats(formats)
entries.append({
'id': movie + '-' + re.sub(r'[^a-zA-Z0-9]', '', clip_title).lower(),
'formats': formats,
'title': clip_title,
'thumbnail': clip.get('screen') or clip.get('thumb'),
'duration': parse_duration(clip.get('runtime') or clip.get('faded')),
'upload_date': unified_strdate(clip.get('posted')),
'uploader_id': uploader_id,
})
page_data = film_data.get('page', {})
return self.playlist_result(entries, film_id, page_data.get('movie_title'))
playlist_url = compat_urlparse.urljoin(url, 'includes/playlists/itunes.inc')
def fix_html(s):
s = re.sub(r'(?s)<script[^<]*?>.*?</script>', '', s)
s = re.sub(r'<img ([^<]*?)/?>', r'<img \1/>', s)
# The ' in the onClick attributes are not escaped, it couldn't be parsed
# like: http://trailers.apple.com/trailers/wb/gravity/
def _clean_json(m):
return 'iTunes.playURL(%s);' % m.group(1).replace('\'', '&#39;')
s = re.sub(self._JSON_RE, _clean_json, s)
s = '<html>%s</html>' % s
return s
doc = self._download_xml(playlist_url, movie, transform_source=fix_html)
playlist = []
for li in doc.findall('./div/ul/li'):
on_click = li.find('.//a').attrib['onClick']
trailer_info_json = self._search_regex(self._JSON_RE,
on_click, 'trailer info')
trailer_info = json.loads(trailer_info_json)
first_url = trailer_info.get('url')
if not first_url:
continue
title = trailer_info['title']
video_id = movie + '-' + re.sub(r'[^a-zA-Z0-9]', '', title).lower()
thumbnail = li.find('.//img').attrib['src']
upload_date = trailer_info['posted'].replace('-', '')
runtime = trailer_info['runtime']
m = re.search(r'(?P<minutes>[0-9]+):(?P<seconds>[0-9]{1,2})', runtime)
duration = None
if m:
duration = 60 * int(m.group('minutes')) + int(m.group('seconds'))
trailer_id = first_url.split('/')[-1].rpartition('_')[0].lower()
settings_json_url = compat_urlparse.urljoin(url, 'includes/settings/%s.json' % trailer_id)
settings = self._download_json(settings_json_url, trailer_id, 'Downloading settings json')
formats = []
for format in settings['metadata']['sizes']:
# The src is a file pointing to the real video file
format_url = re.sub(r'_(\d*p\.mov)', r'_h\1', format['src'])
formats.append({
'url': format_url,
'format': format['type'],
'width': int_or_none(format['width']),
'height': int_or_none(format['height']),
})
self._sort_formats(formats)
playlist.append({
'_type': 'video',
'id': video_id,
'formats': formats,
'title': title,
'duration': duration,
'thumbnail': thumbnail,
'upload_date': upload_date,
'uploader_id': uploader_id,
'http_headers': {
'User-Agent': 'QuickTime compatible (yt-dlp)',
},
})
return {
'_type': 'playlist',
'id': movie,
'entries': playlist,
}
class AppleTrailersSectionIE(InfoExtractor):
IE_NAME = 'appletrailers:section'
_SECTIONS = {
'justadded': {
'feed_path': 'just_added',
'title': 'Just Added',
},
'exclusive': {
'feed_path': 'exclusive',
'title': 'Exclusive',
},
'justhd': {
'feed_path': 'just_hd',
'title': 'Just HD',
},
'mostpopular': {
'feed_path': 'most_pop',
'title': 'Most Popular',
},
'moviestudios': {
'feed_path': 'studios',
'title': 'Movie Studios',
},
}
_VALID_URL = r'https?://(?:www\.)?trailers\.apple\.com/#section=(?P<id>%s)' % '|'.join(_SECTIONS)
_TESTS = [{
'url': 'http://trailers.apple.com/#section=justadded',
'info_dict': {
'title': 'Just Added',
'id': 'justadded',
},
'playlist_mincount': 80,
}, {
'url': 'http://trailers.apple.com/#section=exclusive',
'info_dict': {
'title': 'Exclusive',
'id': 'exclusive',
},
'playlist_mincount': 80,
}, {
'url': 'http://trailers.apple.com/#section=justhd',
'info_dict': {
'title': 'Just HD',
'id': 'justhd',
},
'playlist_mincount': 80,
}, {
'url': 'http://trailers.apple.com/#section=mostpopular',
'info_dict': {
'title': 'Most Popular',
'id': 'mostpopular',
},
'playlist_mincount': 30,
}, {
'url': 'http://trailers.apple.com/#section=moviestudios',
'info_dict': {
'title': 'Movie Studios',
'id': 'moviestudios',
},
'playlist_mincount': 80,
}]
def _real_extract(self, url):
section = self._match_id(url)
section_data = self._download_json(
'http://trailers.apple.com/trailers/home/feeds/%s.json' % self._SECTIONS[section]['feed_path'],
section)
entries = [
self.url_result('http://trailers.apple.com' + e['location'])
for e in section_data]
return self.playlist_result(entries, section, self._SECTIONS[section]['title'])

673
plugins/youtube_download/yt_dlp/extractor/archiveorg.py Normal file
View File

@ -0,0 +1,673 @@
# coding: utf-8
from __future__ import unicode_literals
import re
import json
from .common import InfoExtractor
from .youtube import YoutubeIE, YoutubeBaseInfoExtractor
from ..compat import (
compat_urllib_parse_unquote,
compat_urllib_parse_unquote_plus,
compat_HTTPError
)
from ..utils import (
bug_reports_message,
clean_html,
dict_get,
extract_attributes,
ExtractorError,
get_element_by_id,
HEADRequest,
int_or_none,
join_nonempty,
KNOWN_EXTENSIONS,
merge_dicts,
mimetype2ext,
orderedSet,
parse_duration,
parse_qs,
str_to_int,
str_or_none,
traverse_obj,
try_get,
unified_strdate,
unified_timestamp,
urlhandle_detect_ext,
url_or_none
)
class ArchiveOrgIE(InfoExtractor):
IE_NAME = 'archive.org'
IE_DESC = 'archive.org video and audio'
_VALID_URL = r'https?://(?:www\.)?archive\.org/(?:details|embed)/(?P<id>[^?#]+)(?:[?].*)?$'
_TESTS = [{
'url': 'http://archive.org/details/XD300-23_68HighlightsAResearchCntAugHumanIntellect',
'md5': '8af1d4cf447933ed3c7f4871162602db',
'info_dict': {
'id': 'XD300-23_68HighlightsAResearchCntAugHumanIntellect',
'ext': 'ogv',
'title': '1968 Demo - FJCC Conference Presentation Reel #1',
'description': 'md5:da45c349df039f1cc8075268eb1b5c25',
'release_date': '19681210',
'timestamp': 1268695290,
'upload_date': '20100315',
'creator': 'SRI International',
'uploader': 'laura@archive.org',
},
}, {
'url': 'https://archive.org/details/Cops1922',
'md5': '0869000b4ce265e8ca62738b336b268a',
'info_dict': {
'id': 'Cops1922',
'ext': 'mp4',
'title': 'Buster Keaton\'s "Cops" (1922)',
'description': 'md5:43a603fd6c5b4b90d12a96b921212b9c',
'uploader': 'yorkmba99@hotmail.com',
'timestamp': 1387699629,
'upload_date': '20131222',
},
}, {
'url': 'http://archive.org/embed/XD300-23_68HighlightsAResearchCntAugHumanIntellect',
'only_matching': True,
}, {
'url': 'https://archive.org/details/Election_Ads',
'md5': '284180e857160cf866358700bab668a3',
'info_dict': {
'id': 'Election_Ads/Commercial-JFK1960ElectionAdCampaignJingle.mpg',
'title': 'Commercial-JFK1960ElectionAdCampaignJingle.mpg',
'ext': 'mp4',
},
}, {
'url': 'https://archive.org/details/Election_Ads/Commercial-Nixon1960ElectionAdToughonDefense.mpg',
'md5': '7915213ef02559b5501fe630e1a53f59',
'info_dict': {
'id': 'Election_Ads/Commercial-Nixon1960ElectionAdToughonDefense.mpg',
'title': 'Commercial-Nixon1960ElectionAdToughonDefense.mpg',
'ext': 'mp4',
'timestamp': 1205588045,
'uploader': 'mikedavisstripmaster@yahoo.com',
'description': '1960 Presidential Campaign Election Commercials John F Kennedy, Richard M Nixon',
'upload_date': '20080315',
},
}, {
'url': 'https://archive.org/details/gd1977-05-08.shure57.stevenson.29303.flac16',
'md5': '7d07ffb42aba6537c28e053efa4b54c9',
'info_dict': {
'id': 'gd1977-05-08.shure57.stevenson.29303.flac16/gd1977-05-08d01t01.flac',
'title': 'Turning',
'ext': 'flac',
},
}, {
'url': 'https://archive.org/details/gd1977-05-08.shure57.stevenson.29303.flac16/gd1977-05-08d01t07.flac',
'md5': 'a07cd8c6ab4ee1560f8a0021717130f3',
'info_dict': {
'id': 'gd1977-05-08.shure57.stevenson.29303.flac16/gd1977-05-08d01t07.flac',
'title': 'Deal',
'ext': 'flac',
'timestamp': 1205895624,
'uploader': 'mvernon54@yahoo.com',
'description': 'md5:6a31f1996db0aa0fc9da6d6e708a1bb0',
'upload_date': '20080319',
'location': 'Barton Hall - Cornell University',
},
}, {
'url': 'https://archive.org/details/lp_the-music-of-russia_various-artists-a-askaryan-alexander-melik',
'md5': '7cb019baa9b332e82ea7c10403acd180',
'info_dict': {
'id': 'lp_the-music-of-russia_various-artists-a-askaryan-alexander-melik/disc1/01.01. Bells Of Rostov.mp3',
'title': 'Bells Of Rostov',
'ext': 'mp3',
},
}, {
'url': 'https://archive.org/details/lp_the-music-of-russia_various-artists-a-askaryan-alexander-melik/disc1/02.02.+Song+And+Chorus+In+The+Polovetsian+Camp+From+%22Prince+Igor%22+(Act+2%2C+Scene+1).mp3',
'md5': '1d0aabe03edca83ca58d9ed3b493a3c3',
'info_dict': {
'id': 'lp_the-music-of-russia_various-artists-a-askaryan-alexander-melik/disc1/02.02. Song And Chorus In The Polovetsian Camp From "Prince Igor" (Act 2, Scene 1).mp3',
'title': 'Song And Chorus In The Polovetsian Camp From "Prince Igor" (Act 2, Scene 1)',
'ext': 'mp3',
'timestamp': 1569662587,
'uploader': 'associate-joygen-odiongan@archive.org',
'description': 'md5:012b2d668ae753be36896f343d12a236',
'upload_date': '20190928',
},
}]
@staticmethod
def _playlist_data(webpage):
element = re.findall(r'''(?xs)
<input
(?:\s+[a-zA-Z0-9:._-]+(?:=[a-zA-Z0-9:._-]*|="[^"]*"|='[^']*'|))*?
\s+class=['"]?js-play8-playlist['"]?
(?:\s+[a-zA-Z0-9:._-]+(?:=[a-zA-Z0-9:._-]*|="[^"]*"|='[^']*'|))*?
\s*/>
''', webpage)[0]
return json.loads(extract_attributes(element)['value'])
def _real_extract(self, url):
video_id = compat_urllib_parse_unquote_plus(self._match_id(url))
identifier, entry_id = (video_id.split('/', 1) + [None])[:2]
# Archive.org metadata API doesn't clearly demarcate playlist entries
# or subtitle tracks, so we get them from the embeddable player.
embed_page = self._download_webpage(f'https://archive.org/embed/{identifier}', identifier)
playlist = self._playlist_data(embed_page)
entries = {}
for p in playlist:
# If the user specified a playlist entry in the URL, ignore the
# rest of the playlist.
if entry_id and p['orig'] != entry_id:
continue
entries[p['orig']] = {
'formats': [],
'thumbnails': [],
'artist': p.get('artist'),
'track': p.get('title'),
'subtitles': {},
}
for track in p.get('tracks', []):
if track['kind'] != 'subtitles':
continue
entries[p['orig']][track['label']] = {
'url': 'https://archive.org/' + track['file'].lstrip('/')
}
metadata = self._download_json('http://archive.org/metadata/' + identifier, identifier)
m = metadata['metadata']
identifier = m['identifier']
info = {
'id': identifier,
'title': m['title'],
'description': clean_html(m.get('description')),
'uploader': dict_get(m, ['uploader', 'adder']),
'creator': m.get('creator'),
'license': m.get('licenseurl'),
'release_date': unified_strdate(m.get('date')),
'timestamp': unified_timestamp(dict_get(m, ['publicdate', 'addeddate'])),
'webpage_url': f'https://archive.org/details/{identifier}',
'location': m.get('venue'),
'release_year': int_or_none(m.get('year'))}
for f in metadata['files']:
if f['name'] in entries:
entries[f['name']] = merge_dicts(entries[f['name']], {
'id': identifier + '/' + f['name'],
'title': f.get('title') or f['name'],
'display_id': f['name'],
'description': clean_html(f.get('description')),
'creator': f.get('creator'),
'duration': parse_duration(f.get('length')),
'track_number': int_or_none(f.get('track')),
'album': f.get('album'),
'discnumber': int_or_none(f.get('disc')),
'release_year': int_or_none(f.get('year'))})
entry = entries[f['name']]
elif traverse_obj(f, 'original', expected_type=str) in entries:
entry = entries[f['original']]
else:
continue
if f.get('format') == 'Thumbnail':
entry['thumbnails'].append({
'id': f['name'],
'url': 'https://archive.org/download/' + identifier + '/' + f['name'],
'width': int_or_none(f.get('width')),
'height': int_or_none(f.get('width')),
'filesize': int_or_none(f.get('size'))})
extension = (f['name'].rsplit('.', 1) + [None])[1]
if extension in KNOWN_EXTENSIONS:
entry['formats'].append({
'url': 'https://archive.org/download/' + identifier + '/' + f['name'],
'format': f.get('format'),
'width': int_or_none(f.get('width')),
'height': int_or_none(f.get('height')),
'filesize': int_or_none(f.get('size')),
'protocol': 'https'})
for entry in entries.values():
self._sort_formats(entry['formats'])
if len(entries) == 1:
# If there's only one item, use it as the main info dict
only_video = next(iter(entries.values()))
if entry_id:
info = merge_dicts(only_video, info)
else:
info = merge_dicts(info, only_video)
else:
# Otherwise, we have a playlist.
info['_type'] = 'playlist'
info['entries'] = list(entries.values())
if metadata.get('reviews'):
info['comments'] = []
for review in metadata['reviews']:
info['comments'].append({
'id': review.get('review_id'),
'author': review.get('reviewer'),
'text': str_or_none(review.get('reviewtitle'), '') + '\n\n' + review.get('reviewbody'),
'timestamp': unified_timestamp(review.get('createdate')),
'parent': 'root'})
return info
class YoutubeWebArchiveIE(InfoExtractor):
IE_NAME = 'web.archive:youtube'
IE_DESC = 'web.archive.org saved youtube videos, "ytarchive:" prefix'
_VALID_URL = r'''(?x)(?:(?P<prefix>ytarchive:)|
(?:https?://)?web\.archive\.org/
(?:web/)?(?:(?P<date>[0-9]{14})?[0-9A-Za-z_*]*/)? # /web and the version index is optional
(?:https?(?::|%3[Aa])//)?(?:
(?:\w+\.)?youtube\.com(?::(?:80|443))?/watch(?:\.php)?(?:\?|%3[fF])(?:[^\#]+(?:&|%26))?v(?:=|%3[dD]) # Youtube URL
|(?:wayback-fakeurl\.archive\.org/yt/) # Or the internal fake url
)
)(?P<id>[0-9A-Za-z_-]{11})
(?(prefix)
(?::(?P<date2>[0-9]{14}))?$|
(?:%26|[#&]|$)
)'''
_TESTS = [
{
'url': 'https://web.archive.org/web/20150415002341/https://www.youtube.com/watch?v=aYAGB11YrSs',
'info_dict': {
'id': 'aYAGB11YrSs',
'ext': 'webm',
'title': 'Team Fortress 2 - Sandviches!',
'description': 'md5:4984c0f9a07f349fc5d8e82ab7af4eaf',
'upload_date': '20110926',
'uploader': 'Zeurel',
'channel_id': 'UCukCyHaD-bK3in_pKpfH9Eg',
'duration': 32,
'uploader_id': 'Zeurel',
'uploader_url': 'http://www.youtube.com/user/Zeurel'
}
}, {
# Internal link
'url': 'https://web.archive.org/web/2oe/http://wayback-fakeurl.archive.org/yt/97t7Xj_iBv0',
'info_dict': {
'id': '97t7Xj_iBv0',
'ext': 'mp4',
'title': 'Why Machines That Bend Are Better',
'description': 'md5:00404df2c632d16a674ff8df1ecfbb6c',
'upload_date': '20190312',
'uploader': 'Veritasium',
'channel_id': 'UCHnyfMqiRRG1u-2MsSQLbXA',
'duration': 771,
'uploader_id': '1veritasium',
'uploader_url': 'http://www.youtube.com/user/1veritasium'
}
}, {
# Video from 2012, webm format itag 45. Newest capture is deleted video, with an invalid description.
# Should use the date in the link. Title ends with '- Youtube'. Capture has description in eow-description
'url': 'https://web.archive.org/web/20120712231619/http://www.youtube.com/watch?v=AkhihxRKcrs&gl=US&hl=en',
'info_dict': {
'id': 'AkhihxRKcrs',
'ext': 'webm',
'title': 'Limited Run: Mondo\'s Modern Classic 1 of 3 (SDCC 2012)',
'upload_date': '20120712',
'duration': 398,
'description': 'md5:ff4de6a7980cb65d951c2f6966a4f2f3',
'uploader_id': 'machinima',
'uploader_url': 'http://www.youtube.com/user/machinima'
}
}, {
# FLV video. Video file URL does not provide itag information
'url': 'https://web.archive.org/web/20081211103536/http://www.youtube.com/watch?v=jNQXAC9IVRw',
'info_dict': {
'id': 'jNQXAC9IVRw',
'ext': 'flv',
'title': 'Me at the zoo',
'upload_date': '20050423',
'channel_id': 'UC4QobU6STFB0P71PMvOGN5A',
'duration': 19,
'description': 'md5:10436b12e07ac43ff8df65287a56efb4',
'uploader_id': 'jawed',
'uploader_url': 'http://www.youtube.com/user/jawed'
}
}, {
'url': 'https://web.archive.org/web/20110712231407/http://www.youtube.com/watch?v=lTx3G6h2xyA',
'info_dict': {
'id': 'lTx3G6h2xyA',
'ext': 'flv',
'title': 'Madeon - Pop Culture (live mashup)',
'upload_date': '20110711',
'uploader': 'Madeon',
'channel_id': 'UCqMDNf3Pn5L7pcNkuSEeO3w',
'duration': 204,
'description': 'md5:f7535343b6eda34a314eff8b85444680',
'uploader_id': 'itsmadeon',
'uploader_url': 'http://www.youtube.com/user/itsmadeon'
}
}, {
# First capture is of dead video, second is the oldest from CDX response.
'url': 'https://web.archive.org/https://www.youtube.com/watch?v=1JYutPM8O6E',
'info_dict': {
'id': '1JYutPM8O6E',
'ext': 'mp4',
'title': 'Fake Teen Doctor Strikes AGAIN! - Weekly Weird News',
'upload_date': '20160218',
'channel_id': 'UCdIaNUarhzLSXGoItz7BHVA',
'duration': 1236,
'description': 'md5:21032bae736421e89c2edf36d1936947',
'uploader_id': 'MachinimaETC',
'uploader_url': 'http://www.youtube.com/user/MachinimaETC'
}
}, {
# First capture of dead video, capture date in link links to dead capture.
'url': 'https://web.archive.org/web/20180803221945/https://www.youtube.com/watch?v=6FPhZJGvf4E',
'info_dict': {
'id': '6FPhZJGvf4E',
'ext': 'mp4',
'title': 'WTF: Video Games Still Launch BROKEN?! - T.U.G.S.',
'upload_date': '20160219',
'channel_id': 'UCdIaNUarhzLSXGoItz7BHVA',
'duration': 798,
'description': 'md5:a1dbf12d9a3bd7cb4c5e33b27d77ffe7',
'uploader_id': 'MachinimaETC',
'uploader_url': 'http://www.youtube.com/user/MachinimaETC'
},
'expected_warnings': [
r'unable to download capture webpage \(it may not be archived\)'
]
}, { # Very old YouTube page, has - YouTube in title.
'url': 'http://web.archive.org/web/20070302011044/http://youtube.com/watch?v=-06-KB9XTzg',
'info_dict': {
'id': '-06-KB9XTzg',
'ext': 'flv',
'title': 'New Coin Hack!! 100% Safe!!'
}
}, {
'url': 'web.archive.org/https://www.youtube.com/watch?v=dWW7qP423y8',
'info_dict': {
'id': 'dWW7qP423y8',
'ext': 'mp4',
'title': 'It\'s Bootleg AirPods Time.',
'upload_date': '20211021',
'channel_id': 'UC7Jwj9fkrf1adN4fMmTkpug',
'channel_url': 'http://www.youtube.com/channel/UC7Jwj9fkrf1adN4fMmTkpug',
'duration': 810,
'description': 'md5:7b567f898d8237b256f36c1a07d6d7bc',
'uploader': 'DankPods',
'uploader_id': 'UC7Jwj9fkrf1adN4fMmTkpug',
'uploader_url': 'http://www.youtube.com/channel/UC7Jwj9fkrf1adN4fMmTkpug'
}
}, {
# player response contains '};' See: https://github.com/ytdl-org/youtube-dl/issues/27093
'url': 'https://web.archive.org/web/20200827003909if_/http://www.youtube.com/watch?v=6Dh-RL__uN4',
'info_dict': {
'id': '6Dh-RL__uN4',
'ext': 'mp4',
'title': 'bitch lasagna',
'upload_date': '20181005',
'channel_id': 'UC-lHJZR3Gqxm24_Vd_AJ5Yw',
'channel_url': 'http://www.youtube.com/channel/UC-lHJZR3Gqxm24_Vd_AJ5Yw',
'duration': 135,
'description': 'md5:2dbe4051feeff2dab5f41f82bb6d11d0',
'uploader': 'PewDiePie',
'uploader_id': 'PewDiePie',
'uploader_url': 'http://www.youtube.com/user/PewDiePie'
}
}, {
'url': 'https://web.archive.org/web/http://www.youtube.com/watch?v=kH-G_aIBlFw',
'only_matching': True
}, {
'url': 'https://web.archive.org/web/20050214000000_if/http://www.youtube.com/watch?v=0altSZ96U4M',
'only_matching': True
}, {
# Video not archived, only capture is unavailable video page
'url': 'https://web.archive.org/web/20210530071008/https://www.youtube.com/watch?v=lHJTf93HL1s&spfreload=10',
'only_matching': True
}, { # Encoded url
'url': 'https://web.archive.org/web/20120712231619/http%3A//www.youtube.com/watch%3Fgl%3DUS%26v%3DAkhihxRKcrs%26hl%3Den',
'only_matching': True
}, {
'url': 'https://web.archive.org/web/20120712231619/http%3A//www.youtube.com/watch%3Fv%3DAkhihxRKcrs%26gl%3DUS%26hl%3Den',
'only_matching': True
}, {
'url': 'https://web.archive.org/web/20060527081937/http://www.youtube.com:80/watch.php?v=ELTFsLT73fA&amp;search=soccer',
'only_matching': True
}, {
'url': 'https://web.archive.org/http://www.youtube.com:80/watch?v=-05VVye-ffg',
'only_matching': True
}, {
'url': 'ytarchive:BaW_jenozKc:20050214000000',
'only_matching': True
}, {
'url': 'ytarchive:BaW_jenozKc',
'only_matching': True
},
]
_YT_INITIAL_DATA_RE = r'(?:(?:(?:window\s*\[\s*["\']ytInitialData["\']\s*\]|ytInitialData)\s*=\s*({.+?})\s*;)|%s)' % YoutubeBaseInfoExtractor._YT_INITIAL_DATA_RE
_YT_INITIAL_PLAYER_RESPONSE_RE = r'(?:(?:(?:window\s*\[\s*["\']ytInitialPlayerResponse["\']\s*\]|ytInitialPlayerResponse)\s*=[(\s]*({.+?})[)\s]*;)|%s)' % YoutubeBaseInfoExtractor._YT_INITIAL_PLAYER_RESPONSE_RE
_YT_INITIAL_BOUNDARY_RE = r'(?:(?:var\s+meta|</script|\n)|%s)' % YoutubeBaseInfoExtractor._YT_INITIAL_BOUNDARY_RE
_YT_DEFAULT_THUMB_SERVERS = ['i.ytimg.com'] # thumbnails most likely archived on these servers
_YT_ALL_THUMB_SERVERS = orderedSet(
_YT_DEFAULT_THUMB_SERVERS + ['img.youtube.com', *[f'{c}{n or ""}.ytimg.com' for c in ('i', 's') for n in (*range(0, 5), 9)]])
_WAYBACK_BASE_URL = 'https://web.archive.org/web/%sif_/'
_OLDEST_CAPTURE_DATE = 20050214000000
_NEWEST_CAPTURE_DATE = 20500101000000
def _call_cdx_api(self, item_id, url, filters: list = None, collapse: list = None, query: dict = None, note='Downloading CDX API JSON'):
# CDX docs: https://github.com/internetarchive/wayback/blob/master/wayback-cdx-server/README.md
query = {
'url': url,
'output': 'json',
'fl': 'original,mimetype,length,timestamp',
'limit': 500,
'filter': ['statuscode:200'] + (filters or []),
'collapse': collapse or [],
**(query or {})
}
res = self._download_json('https://web.archive.org/cdx/search/cdx', item_id, note, query=query)
if isinstance(res, list) and len(res) >= 2:
# format response to make it easier to use
return list(dict(zip(res[0], v)) for v in res[1:])
elif not isinstance(res, list) or len(res) != 0:
self.report_warning('Error while parsing CDX API response' + bug_reports_message())
def _extract_yt_initial_variable(self, webpage, regex, video_id, name):
return self._parse_json(self._search_regex(
(r'%s\s*%s' % (regex, self._YT_INITIAL_BOUNDARY_RE),
regex), webpage, name, default='{}'), video_id, fatal=False)
def _extract_webpage_title(self, webpage):
page_title = self._html_search_regex(
r'<title>([^<]*)</title>', webpage, 'title', default='')
# YouTube video pages appear to always have either 'YouTube -' as prefix or '- YouTube' as suffix.
return self._html_search_regex(
r'(?:YouTube\s*-\s*(.*)$)|(?:(.*)\s*-\s*YouTube$)',
page_title, 'title', default='')
def _extract_metadata(self, video_id, webpage):
search_meta = ((lambda x: self._html_search_meta(x, webpage, default=None)) if webpage else (lambda x: None))
player_response = self._extract_yt_initial_variable(
webpage, self._YT_INITIAL_PLAYER_RESPONSE_RE, video_id, 'initial player response') or {}
initial_data = self._extract_yt_initial_variable(
webpage, self._YT_INITIAL_DATA_RE, video_id, 'initial player response') or {}
initial_data_video = traverse_obj(
initial_data, ('contents', 'twoColumnWatchNextResults', 'results', 'results', 'contents', ..., 'videoPrimaryInfoRenderer'),
expected_type=dict, get_all=False, default={})
video_details = traverse_obj(
player_response, 'videoDetails', expected_type=dict, get_all=False, default={})
microformats = traverse_obj(
player_response, ('microformat', 'playerMicroformatRenderer'), expected_type=dict, get_all=False, default={})
video_title = (
video_details.get('title')
or YoutubeBaseInfoExtractor._get_text(microformats, 'title')
or YoutubeBaseInfoExtractor._get_text(initial_data_video, 'title')
or self._extract_webpage_title(webpage)
or search_meta(['og:title', 'twitter:title', 'title']))
channel_id = str_or_none(
video_details.get('channelId')
or microformats.get('externalChannelId')
or search_meta('channelId')
or self._search_regex(
r'data-channel-external-id=(["\'])(?P<id>(?:(?!\1).)+)\1', # @b45a9e6
webpage, 'channel id', default=None, group='id'))
channel_url = f'http://www.youtube.com/channel/{channel_id}' if channel_id else None
duration = int_or_none(
video_details.get('lengthSeconds')
or microformats.get('lengthSeconds')
or parse_duration(search_meta('duration')))
description = (
video_details.get('shortDescription')
or YoutubeBaseInfoExtractor._get_text(microformats, 'description')
or clean_html(get_element_by_id('eow-description', webpage)) # @9e6dd23
or search_meta(['description', 'og:description', 'twitter:description']))
uploader = video_details.get('author')
# Uploader ID and URL
uploader_mobj = re.search(
r'<link itemprop="url" href="(?P<uploader_url>https?://www\.youtube\.com/(?:user|channel)/(?P<uploader_id>[^"]+))">', # @fd05024
webpage)
if uploader_mobj is not None:
uploader_id, uploader_url = uploader_mobj.group('uploader_id'), uploader_mobj.group('uploader_url')
else:
# @a6211d2
uploader_url = url_or_none(microformats.get('ownerProfileUrl'))
uploader_id = self._search_regex(
r'(?:user|channel)/([^/]+)', uploader_url or '', 'uploader id', default=None)
upload_date = unified_strdate(
dict_get(microformats, ('uploadDate', 'publishDate'))
or search_meta(['uploadDate', 'datePublished'])
or self._search_regex(
[r'(?s)id="eow-date.*?>(.*?)</span>',
r'(?:id="watch-uploader-info".*?>.*?|["\']simpleText["\']\s*:\s*["\'])(?:Published|Uploaded|Streamed live|Started) on (.+?)[<"\']'], # @7998520
webpage, 'upload date', default=None))
return {
'title': video_title,
'description': description,
'upload_date': upload_date,
'uploader': uploader,
'channel_id': channel_id,
'channel_url': channel_url,
'duration': duration,
'uploader_url': uploader_url,
'uploader_id': uploader_id,
}
def _extract_thumbnails(self, video_id):
try_all = 'thumbnails' in self._configuration_arg('check_all')
thumbnail_base_urls = ['http://{server}/vi{webp}/{video_id}'.format(
webp='_webp' if ext == 'webp' else '', video_id=video_id, server=server)
for server in (self._YT_ALL_THUMB_SERVERS if try_all else self._YT_DEFAULT_THUMB_SERVERS) for ext in (('jpg', 'webp') if try_all else ('jpg',))]
thumbnails = []
for url in thumbnail_base_urls:
response = self._call_cdx_api(
video_id, url, filters=['mimetype:image/(?:webp|jpeg)'],
collapse=['urlkey'], query={'matchType': 'prefix'})
if not response:
continue
thumbnails.extend(
{
'url': (self._WAYBACK_BASE_URL % (int_or_none(thumbnail_dict.get('timestamp')) or self._OLDEST_CAPTURE_DATE)) + thumbnail_dict.get('original'),
'filesize': int_or_none(thumbnail_dict.get('length')),
'preference': int_or_none(thumbnail_dict.get('length'))
} for thumbnail_dict in response)
if not try_all:
break
self._remove_duplicate_formats(thumbnails)
return thumbnails
def _get_capture_dates(self, video_id, url_date):
capture_dates = []
# Note: CDX API will not find watch pages with extra params in the url.
response = self._call_cdx_api(
video_id, f'https://www.youtube.com/watch?v={video_id}',
filters=['mimetype:text/html'], collapse=['timestamp:6', 'digest'], query={'matchType': 'prefix'}) or []
all_captures = sorted([int_or_none(r['timestamp']) for r in response if int_or_none(r['timestamp']) is not None])
# Prefer the new polymer UI captures as we support extracting more metadata from them
# WBM captures seem to all switch to this layout ~July 2020
modern_captures = [x for x in all_captures if x >= 20200701000000]
if modern_captures:
capture_dates.append(modern_captures[0])
capture_dates.append(url_date)
if all_captures:
capture_dates.append(all_captures[0])
if 'captures' in self._configuration_arg('check_all'):
capture_dates.extend(modern_captures + all_captures)
# Fallbacks if any of the above fail
capture_dates.extend([self._OLDEST_CAPTURE_DATE, self._NEWEST_CAPTURE_DATE])
return orderedSet(filter(None, capture_dates))
def _real_extract(self, url):
video_id, url_date, url_date_2 = self._match_valid_url(url).group('id', 'date', 'date2')
url_date = url_date or url_date_2
urlh = None
try:
urlh = self._request_webpage(
HEADRequest('https://web.archive.org/web/2oe_/http://wayback-fakeurl.archive.org/yt/%s' % video_id),
video_id, note='Fetching archived video file url', expected_status=True)
except ExtractorError as e:
# HTTP Error 404 is expected if the video is not saved.
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 404:
self.raise_no_formats(
'The requested video is not archived, indexed, or there is an issue with web.archive.org',
expected=True)
else:
raise
capture_dates = self._get_capture_dates(video_id, int_or_none(url_date))
self.write_debug('Captures to try: ' + join_nonempty(*capture_dates, delim=', '))
info = {'id': video_id}
for capture in capture_dates:
webpage = self._download_webpage(
(self._WAYBACK_BASE_URL + 'http://www.youtube.com/watch?v=%s') % (capture, video_id),
video_id=video_id, fatal=False, errnote='unable to download capture webpage (it may not be archived)',
note='Downloading capture webpage')
current_info = self._extract_metadata(video_id, webpage or '')
# Try avoid getting deleted video metadata
if current_info.get('title'):
info = merge_dicts(info, current_info)
if 'captures' not in self._configuration_arg('check_all'):
break
info['thumbnails'] = self._extract_thumbnails(video_id)
if urlh:
url = compat_urllib_parse_unquote(urlh.geturl())
video_file_url_qs = parse_qs(url)
# Attempt to recover any ext & format info from playback url & response headers
format = {'url': url, 'filesize': int_or_none(urlh.headers.get('x-archive-orig-content-length'))}
itag = try_get(video_file_url_qs, lambda x: x['itag'][0])
if itag and itag in YoutubeIE._formats:
format.update(YoutubeIE._formats[itag])
format.update({'format_id': itag})
else:
mime = try_get(video_file_url_qs, lambda x: x['mime'][0])
ext = (mimetype2ext(mime)
or urlhandle_detect_ext(urlh)
or mimetype2ext(urlh.headers.get('x-archive-guessed-content-type')))
format.update({'ext': ext})
info['formats'] = [format]
if not info.get('duration'):
info['duration'] = str_to_int(try_get(video_file_url_qs, lambda x: x['dur'][0]))
if not info.get('title'):
info['title'] = video_id
return info

169
plugins/youtube_download/yt_dlp/extractor/arcpublishing.py Normal file
View File

@ -0,0 +1,169 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
extract_attributes,
int_or_none,
parse_iso8601,
try_get,
)
class ArcPublishingIE(InfoExtractor):
_UUID_REGEX = r'[\da-f]{8}-(?:[\da-f]{4}-){3}[\da-f]{12}'
_VALID_URL = r'arcpublishing:(?P<org>[a-z]+):(?P<id>%s)' % _UUID_REGEX
_TESTS = [{
# https://www.adn.com/politics/2020/11/02/video-senate-candidates-campaign-in-anchorage-on-eve-of-election-day/
'url': 'arcpublishing:adn:8c99cb6e-b29c-4bc9-9173-7bf9979225ab',
'only_matching': True,
}, {
# https://www.bostonglobe.com/video/2020/12/30/metro/footage-released-showing-officer-talking-about-striking-protesters-with-car/
'url': 'arcpublishing:bostonglobe:232b7ae6-7d73-432d-bc0a-85dbf0119ab1',
'only_matching': True,
}, {
# https://www.actionnewsjax.com/video/live-stream/
'url': 'arcpublishing:cmg:cfb1cf1b-3ab5-4d1b-86c5-a5515d311f2a',
'only_matching': True,
}, {
# https://elcomercio.pe/videos/deportes/deporte-total-futbol-peruano-seleccion-peruana-la-valorizacion-de-los-peruanos-en-el-exterior-tras-un-2020-atipico-nnav-vr-video-noticia/
'url': 'arcpublishing:elcomercio:27a7e1f8-2ec7-4177-874f-a4feed2885b3',
'only_matching': True,
}, {
# https://www.clickondetroit.com/video/community/2020/05/15/events-surrounding-woodward-dream-cruise-being-canceled/
'url': 'arcpublishing:gmg:c8793fb2-8d44-4242-881e-2db31da2d9fe',
'only_matching': True,
}, {
# https://www.wabi.tv/video/2020/12/30/trenton-company-making-equipment-pfizer-covid-vaccine/
'url': 'arcpublishing:gray:0b0ba30e-032a-4598-8810-901d70e6033e',
'only_matching': True,
}, {
# https://www.lateja.cr/el-mundo/video-china-aprueba-con-condiciones-su-primera/dfcbfa57-527f-45ff-a69b-35fe71054143/video/
'url': 'arcpublishing:gruponacion:dfcbfa57-527f-45ff-a69b-35fe71054143',
'only_matching': True,
}, {
# https://www.fifthdomain.com/video/2018/03/09/is-america-vulnerable-to-a-cyber-attack/
'url': 'arcpublishing:mco:aa0ca6fe-1127-46d4-b32c-be0d6fdb8055',
'only_matching': True,
}, {
# https://www.vl.no/kultur/2020/12/09/en-melding-fra-en-lytter-endret-julelista-til-lewi-bergrud/
'url': 'arcpublishing:mentormedier:47a12084-650b-4011-bfd0-3699b6947b2d',
'only_matching': True,
}, {
# https://www.14news.com/2020/12/30/whiskey-theft-caught-camera-henderson-liquor-store/
'url': 'arcpublishing:raycom:b89f61f8-79fa-4c09-8255-e64237119bf7',
'only_matching': True,
}, {
# https://www.theglobeandmail.com/world/video-ethiopian-woman-who-became-symbol-of-integration-in-italy-killed-on/
'url': 'arcpublishing:tgam:411b34c1-8701-4036-9831-26964711664b',
'only_matching': True,
}, {
# https://www.pilotonline.com/460f2931-8130-4719-8ea1-ffcb2d7cb685-132.html
'url': 'arcpublishing:tronc:460f2931-8130-4719-8ea1-ffcb2d7cb685',
'only_matching': True,
}]
_POWA_DEFAULTS = [
(['cmg', 'prisa'], '%s-config-prod.api.cdn.arcpublishing.com/video'),
([
'adn', 'advancelocal', 'answers', 'bonnier', 'bostonglobe', 'demo',
'gmg', 'gruponacion', 'infobae', 'mco', 'nzme', 'pmn', 'raycom',
'spectator', 'tbt', 'tgam', 'tronc', 'wapo', 'wweek',
], 'video-api-cdn.%s.arcpublishing.com/api'),
]
@staticmethod
def _extract_urls(webpage):
entries = []
# https://arcpublishing.atlassian.net/wiki/spaces/POWA/overview
for powa_el in re.findall(r'(<div[^>]+class="[^"]*\bpowa\b[^"]*"[^>]+data-uuid="%s"[^>]*>)' % ArcPublishingIE._UUID_REGEX, webpage):
powa = extract_attributes(powa_el) or {}
org = powa.get('data-org')
uuid = powa.get('data-uuid')
if org and uuid:
entries.append('arcpublishing:%s:%s' % (org, uuid))
return entries
def _real_extract(self, url):
org, uuid = self._match_valid_url(url).groups()
for orgs, tmpl in self._POWA_DEFAULTS:
if org in orgs:
base_api_tmpl = tmpl
break
else:
base_api_tmpl = '%s-prod-cdn.video-api.arcpublishing.com/api'
if org == 'wapo':
org = 'washpost'
video = self._download_json(
'https://%s/v1/ansvideos/findByUuid' % (base_api_tmpl % org),
uuid, query={'uuid': uuid})[0]
title = video['headlines']['basic']
is_live = video.get('status') == 'live'
urls = []
formats = []
for s in video.get('streams', []):
s_url = s.get('url')
if not s_url or s_url in urls:
continue
urls.append(s_url)
stream_type = s.get('stream_type')
if stream_type == 'smil':
smil_formats = self._extract_smil_formats(
s_url, uuid, fatal=False)
for f in smil_formats:
if f['url'].endswith('/cfx/st'):
f['app'] = 'cfx/st'
if not f['play_path'].startswith('mp4:'):
f['play_path'] = 'mp4:' + f['play_path']
if isinstance(f['tbr'], float):
f['vbr'] = f['tbr'] * 1000
del f['tbr']
f['format_id'] = 'rtmp-%d' % f['vbr']
formats.extend(smil_formats)
elif stream_type in ('ts', 'hls'):
m3u8_formats = self._extract_m3u8_formats(
s_url, uuid, 'mp4', 'm3u8' if is_live else 'm3u8_native',
m3u8_id='hls', fatal=False)
if all([f.get('acodec') == 'none' for f in m3u8_formats]):
continue
for f in m3u8_formats:
height = f.get('height')
if not height:
continue
vbr = self._search_regex(
r'[_x]%d[_-](\d+)' % height, f['url'], 'vbr', default=None)
if vbr:
f['vbr'] = int(vbr)
formats.extend(m3u8_formats)
else:
vbr = int_or_none(s.get('bitrate'))
formats.append({
'format_id': '%s-%d' % (stream_type, vbr) if vbr else stream_type,
'vbr': vbr,
'width': int_or_none(s.get('width')),
'height': int_or_none(s.get('height')),
'filesize': int_or_none(s.get('filesize')),
'url': s_url,
'quality': -10,
})
self._sort_formats(formats)
subtitles = {}
for subtitle in (try_get(video, lambda x: x['subtitles']['urls'], list) or []):
subtitle_url = subtitle.get('url')
if subtitle_url:
subtitles.setdefault('en', []).append({'url': subtitle_url})
return {
'id': uuid,
'title': title,
'thumbnail': try_get(video, lambda x: x['promo_image']['url']),
'description': try_get(video, lambda x: x['subheadlines']['basic']),
'formats': formats,
'duration': int_or_none(video.get('duration'), 100),
'timestamp': parse_iso8601(video.get('created_date')),
'subtitles': subtitles,
'is_live': is_live,
}

640
plugins/youtube_download/yt_dlp/extractor/ard.py Normal file
View File

@ -0,0 +1,640 @@
# coding: utf-8
from __future__ import unicode_literals
import json
import re
from .common import InfoExtractor
from .generic import GenericIE
from ..utils import (
determine_ext,
ExtractorError,
int_or_none,
parse_duration,
qualities,
str_or_none,
try_get,
unified_strdate,
unified_timestamp,
update_url_query,
url_or_none,
xpath_text,
)
from ..compat import compat_etree_fromstring
class ARDMediathekBaseIE(InfoExtractor):
_GEO_COUNTRIES = ['DE']
def _extract_media_info(self, media_info_url, webpage, video_id):
media_info = self._download_json(
media_info_url, video_id, 'Downloading media JSON')
return self._parse_media_info(media_info, video_id, '"fsk"' in webpage)
def _parse_media_info(self, media_info, video_id, fsk):
formats = self._extract_formats(media_info, video_id)
if not formats:
if fsk:
self.raise_no_formats(
'This video is only available after 20:00', expected=True)
elif media_info.get('_geoblocked'):
self.raise_geo_restricted(
'This video is not available due to geoblocking',
countries=self._GEO_COUNTRIES, metadata_available=True)
self._sort_formats(formats)
subtitles = {}
subtitle_url = media_info.get('_subtitleUrl')
if subtitle_url:
subtitles['de'] = [{
'ext': 'ttml',
'url': subtitle_url,
}]
return {
'id': video_id,
'duration': int_or_none(media_info.get('_duration')),
'thumbnail': media_info.get('_previewImage'),
'is_live': media_info.get('_isLive') is True,
'formats': formats,
'subtitles': subtitles,
}
def _ARD_extract_episode_info(self, title):
"""Try to extract season/episode data from the title."""
res = {}
if not title:
return res
for pattern in [
# Pattern for title like "Homo sapiens (S06/E07) - Originalversion"
# from: https://www.ardmediathek.de/one/sendung/doctor-who/Y3JpZDovL3dkci5kZS9vbmUvZG9jdG9yIHdobw
r'.*(?P<ep_info> \(S(?P<season_number>\d+)/E(?P<episode_number>\d+)\)).*',
# E.g.: title="Fritjof aus Norwegen (2) (AD)"
# from: https://www.ardmediathek.de/ard/sammlung/der-krieg-und-ich/68cMkqJdllm639Skj4c7sS/
r'.*(?P<ep_info> \((?:Folge |Teil )?(?P<episode_number>\d+)(?:/\d+)?\)).*',
r'.*(?P<ep_info>Folge (?P<episode_number>\d+)(?:\:| -|) )\"(?P<episode>.+)\".*',
# E.g.: title="Folge 25/42: Symmetrie"
# from: https://www.ardmediathek.de/ard/video/grips-mathe/folge-25-42-symmetrie/ard-alpha/Y3JpZDovL2JyLmRlL3ZpZGVvLzMyYzI0ZjczLWQ1N2MtNDAxNC05ZmZhLTFjYzRkZDA5NDU5OQ/
# E.g.: title="Folge 1063 - Vertrauen"
# from: https://www.ardmediathek.de/ard/sendung/die-fallers/Y3JpZDovL3N3ci5kZS8yMzAyMDQ4/
r'.*(?P<ep_info>Folge (?P<episode_number>\d+)(?:/\d+)?(?:\:| -|) ).*',
]:
m = re.match(pattern, title)
if m:
groupdict = m.groupdict()
res['season_number'] = int_or_none(groupdict.get('season_number'))
res['episode_number'] = int_or_none(groupdict.get('episode_number'))
res['episode'] = str_or_none(groupdict.get('episode'))
# Build the episode title by removing numeric episode information:
if groupdict.get('ep_info') and not res['episode']:
res['episode'] = str_or_none(
title.replace(groupdict.get('ep_info'), ''))
if res['episode']:
res['episode'] = res['episode'].strip()
break
# As a fallback use the whole title as the episode name:
if not res.get('episode'):
res['episode'] = title.strip()
return res
def _extract_formats(self, media_info, video_id):
type_ = media_info.get('_type')
media_array = media_info.get('_mediaArray', [])
formats = []
for num, media in enumerate(media_array):
for stream in media.get('_mediaStreamArray', []):
stream_urls = stream.get('_stream')
if not stream_urls:
continue
if not isinstance(stream_urls, list):
stream_urls = [stream_urls]
quality = stream.get('_quality')
server = stream.get('_server')
for stream_url in stream_urls:
if not url_or_none(stream_url):
continue
ext = determine_ext(stream_url)
if quality != 'auto' and ext in ('f4m', 'm3u8'):
continue
if ext == 'f4m':
formats.extend(self._extract_f4m_formats(
update_url_query(stream_url, {
'hdcore': '3.1.1',
'plugin': 'aasp-3.1.1.69.124'
}), video_id, f4m_id='hds', fatal=False))
elif ext == 'm3u8':
formats.extend(self._extract_m3u8_formats(
stream_url, video_id, 'mp4', 'm3u8_native',
m3u8_id='hls', fatal=False))
else:
if server and server.startswith('rtmp'):
f = {
'url': server,
'play_path': stream_url,
'format_id': 'a%s-rtmp-%s' % (num, quality),
}
else:
f = {
'url': stream_url,
'format_id': 'a%s-%s-%s' % (num, ext, quality)
}
m = re.search(
r'_(?P<width>\d+)x(?P<height>\d+)\.mp4$',
stream_url)
if m:
f.update({
'width': int(m.group('width')),
'height': int(m.group('height')),
})
if type_ == 'audio':
f['vcodec'] = 'none'
formats.append(f)
return formats
class ARDMediathekIE(ARDMediathekBaseIE):
IE_NAME = 'ARD:mediathek'
_VALID_URL = r'^https?://(?:(?:(?:www|classic)\.)?ardmediathek\.de|mediathek\.(?:daserste|rbb-online)\.de|one\.ard\.de)/(?:.*/)(?P<video_id>[0-9]+|[^0-9][^/\?]+)[^/\?]*(?:\?.*)?'
_TESTS = [{
# available till 26.07.2022
'url': 'http://www.ardmediathek.de/tv/S%C3%9CDLICHT/Was-ist-die-Kunst-der-Zukunft-liebe-Ann/BR-Fernsehen/Video?bcastId=34633636&documentId=44726822',
'info_dict': {
'id': '44726822',
'ext': 'mp4',
'title': 'Was ist die Kunst der Zukunft, liebe Anna McCarthy?',
'description': 'md5:4ada28b3e3b5df01647310e41f3a62f5',
'duration': 1740,
},
'params': {
# m3u8 download
'skip_download': True,
}
}, {
'url': 'https://one.ard.de/tv/Mord-mit-Aussicht/Mord-mit-Aussicht-6-39-T%C3%B6dliche-Nach/ONE/Video?bcastId=46384294&documentId=55586872',
'only_matching': True,
}, {
# audio
'url': 'http://www.ardmediathek.de/tv/WDR-H%C3%B6rspiel-Speicher/Tod-eines-Fu%C3%9Fballers/WDR-3/Audio-Podcast?documentId=28488308&bcastId=23074086',
'only_matching': True,
}, {
'url': 'http://mediathek.daserste.de/sendungen_a-z/328454_anne-will/22429276_vertrauen-ist-gut-spionieren-ist-besser-geht',
'only_matching': True,
}, {
# audio
'url': 'http://mediathek.rbb-online.de/radio/Hörspiel/Vor-dem-Fest/kulturradio/Audio?documentId=30796318&topRessort=radio&bcastId=9839158',
'only_matching': True,
}, {
'url': 'https://classic.ardmediathek.de/tv/Panda-Gorilla-Co/Panda-Gorilla-Co-Folge-274/Das-Erste/Video?bcastId=16355486&documentId=58234698',
'only_matching': True,
}]
@classmethod
def suitable(cls, url):
return False if ARDBetaMediathekIE.suitable(url) else super(ARDMediathekIE, cls).suitable(url)
def _real_extract(self, url):
# determine video id from url
m = self._match_valid_url(url)
document_id = None
numid = re.search(r'documentId=([0-9]+)', url)
if numid:
document_id = video_id = numid.group(1)
else:
video_id = m.group('video_id')
webpage = self._download_webpage(url, video_id)
ERRORS = (
('>Leider liegt eine Störung vor.', 'Video %s is unavailable'),
('>Der gewünschte Beitrag ist nicht mehr verfügbar.<',
'Video %s is no longer available'),
)
for pattern, message in ERRORS:
if pattern in webpage:
raise ExtractorError(message % video_id, expected=True)
if re.search(r'[\?&]rss($|[=&])', url):
doc = compat_etree_fromstring(webpage.encode('utf-8'))
if doc.tag == 'rss':
return GenericIE()._extract_rss(url, video_id, doc)
title = self._og_search_title(webpage, default=None) or self._html_search_regex(
[r'<h1(?:\s+class="boxTopHeadline")?>(.*?)</h1>',
r'<meta name="dcterms\.title" content="(.*?)"/>',
r'<h4 class="headline">(.*?)</h4>',
r'<title[^>]*>(.*?)</title>'],
webpage, 'title')
description = self._og_search_description(webpage, default=None) or self._html_search_meta(
'dcterms.abstract', webpage, 'description', default=None)
if description is None:
description = self._html_search_meta(
'description', webpage, 'meta description', default=None)
if description is None:
description = self._html_search_regex(
r'<p\s+class="teasertext">(.+?)</p>',
webpage, 'teaser text', default=None)
# Thumbnail is sometimes not present.
# It is in the mobile version, but that seems to use a different URL
# structure altogether.
thumbnail = self._og_search_thumbnail(webpage, default=None)
media_streams = re.findall(r'''(?x)
mediaCollection\.addMediaStream\([0-9]+,\s*[0-9]+,\s*"[^"]*",\s*
"([^"]+)"''', webpage)
if media_streams:
QUALITIES = qualities(['lo', 'hi', 'hq'])
formats = []
for furl in set(media_streams):
if furl.endswith('.f4m'):
fid = 'f4m'
else:
fid_m = re.match(r'.*\.([^.]+)\.[^.]+$', furl)
fid = fid_m.group(1) if fid_m else None
formats.append({
'quality': QUALITIES(fid),
'format_id': fid,
'url': furl,
})
self._sort_formats(formats)
info = {
'formats': formats,
}
else: # request JSON file
if not document_id:
video_id = self._search_regex(
(r'/play/(?:config|media|sola)/(\d+)', r'contentId["\']\s*:\s*(\d+)'),
webpage, 'media id', default=None)
info = self._extract_media_info(
'http://www.ardmediathek.de/play/media/%s' % video_id,
webpage, video_id)
info.update({
'id': video_id,
'title': title,
'description': description,
'thumbnail': thumbnail,
})
info.update(self._ARD_extract_episode_info(info['title']))
return info
class ARDIE(InfoExtractor):
_VALID_URL = r'(?P<mainurl>https?://(?:www\.)?daserste\.de/(?:[^/?#&]+/)+(?P<id>[^/?#&]+))\.html'
_TESTS = [{
# available till 7.01.2022
'url': 'https://www.daserste.de/information/talk/maischberger/videos/maischberger-die-woche-video100.html',
'md5': '867d8aa39eeaf6d76407c5ad1bb0d4c1',
'info_dict': {
'id': 'maischberger-die-woche-video100',
'display_id': 'maischberger-die-woche-video100',
'ext': 'mp4',
'duration': 3687.0,
'title': 'maischberger. die woche vom 7. Januar 2021',
'upload_date': '20210107',
'thumbnail': r're:^https?://.*\.jpg$',
},
}, {
'url': 'https://www.daserste.de/information/politik-weltgeschehen/morgenmagazin/videosextern/dominik-kahun-aus-der-nhl-direkt-zur-weltmeisterschaft-100.html',
'only_matching': True,
}, {
'url': 'https://www.daserste.de/information/nachrichten-wetter/tagesthemen/videosextern/tagesthemen-17736.html',
'only_matching': True,
}, {
'url': 'https://www.daserste.de/unterhaltung/serie/in-aller-freundschaft-die-jungen-aerzte/videos/diversity-tag-sanam-afrashteh100.html',
'only_matching': True,
}, {
'url': 'http://www.daserste.de/information/reportage-dokumentation/dokus/videos/die-story-im-ersten-mission-unter-falscher-flagge-100.html',
'only_matching': True,
}, {
'url': 'https://www.daserste.de/unterhaltung/serie/in-aller-freundschaft-die-jungen-aerzte/Drehpause-100.html',
'only_matching': True,
}, {
'url': 'https://www.daserste.de/unterhaltung/film/filmmittwoch-im-ersten/videos/making-ofwendezeit-video-100.html',
'only_matching': True,
}]
def _real_extract(self, url):
mobj = self._match_valid_url(url)
display_id = mobj.group('id')
player_url = mobj.group('mainurl') + '~playerXml.xml'
doc = self._download_xml(player_url, display_id)
video_node = doc.find('./video')
upload_date = unified_strdate(xpath_text(
video_node, './broadcastDate'))
thumbnail = xpath_text(video_node, './/teaserImage//variant/url')
formats = []
for a in video_node.findall('.//asset'):
file_name = xpath_text(a, './fileName', default=None)
if not file_name:
continue
format_type = a.attrib.get('type')
format_url = url_or_none(file_name)
if format_url:
ext = determine_ext(file_name)
if ext == 'm3u8':
formats.extend(self._extract_m3u8_formats(
format_url, display_id, 'mp4', entry_protocol='m3u8_native',
m3u8_id=format_type or 'hls', fatal=False))
continue
elif ext == 'f4m':
formats.extend(self._extract_f4m_formats(
update_url_query(format_url, {'hdcore': '3.7.0'}),
display_id, f4m_id=format_type or 'hds', fatal=False))
continue
f = {
'format_id': format_type,
'width': int_or_none(xpath_text(a, './frameWidth')),
'height': int_or_none(xpath_text(a, './frameHeight')),
'vbr': int_or_none(xpath_text(a, './bitrateVideo')),
'abr': int_or_none(xpath_text(a, './bitrateAudio')),
'vcodec': xpath_text(a, './codecVideo'),
'tbr': int_or_none(xpath_text(a, './totalBitrate')),
}
server_prefix = xpath_text(a, './serverPrefix', default=None)
if server_prefix:
f.update({
'url': server_prefix,
'playpath': file_name,
})
else:
if not format_url:
continue
f['url'] = format_url
formats.append(f)
self._sort_formats(formats)
_SUB_FORMATS = (
('./dataTimedText', 'ttml'),
('./dataTimedTextNoOffset', 'ttml'),
('./dataTimedTextVtt', 'vtt'),
)
subtitles = {}
for subsel, subext in _SUB_FORMATS:
for node in video_node.findall(subsel):
subtitles.setdefault('de', []).append({
'url': node.attrib['url'],
'ext': subext,
})
return {
'id': xpath_text(video_node, './videoId', default=display_id),
'formats': formats,
'subtitles': subtitles,
'display_id': display_id,
'title': video_node.find('./title').text,
'duration': parse_duration(video_node.find('./duration').text),
'upload_date': upload_date,
'thumbnail': thumbnail,
}
class ARDBetaMediathekIE(ARDMediathekBaseIE):
_VALID_URL = r'''(?x)https://
(?:(?:beta|www)\.)?ardmediathek\.de/
(?:(?P<client>[^/]+)/)?
(?:player|live|video|(?P<playlist>sendung|sammlung))/
(?:(?P<display_id>[^?#]+)/)?
(?P<id>(?(playlist)|Y3JpZDovL)[a-zA-Z0-9]+)'''
_TESTS = [{
'url': 'https://www.ardmediathek.de/mdr/video/die-robuste-roswita/Y3JpZDovL21kci5kZS9iZWl0cmFnL2Ntcy84MWMxN2MzZC0wMjkxLTRmMzUtODk4ZS0wYzhlOWQxODE2NGI/',
'md5': 'a1dc75a39c61601b980648f7c9f9f71d',
'info_dict': {
'display_id': 'die-robuste-roswita',
'id': '78566716',
'title': 'Die robuste Roswita',
'description': r're:^Der Mord.*totgeglaubte Ehefrau Roswita',
'duration': 5316,
'thumbnail': 'https://img.ardmediathek.de/standard/00/78/56/67/84/575672121/16x9/960?mandant=ard',
'timestamp': 1596658200,
'upload_date': '20200805',
'ext': 'mp4',
},
'skip': 'Error',
}, {
'url': 'https://www.ardmediathek.de/video/tagesschau-oder-tagesschau-20-00-uhr/das-erste/Y3JpZDovL2Rhc2Vyc3RlLmRlL3RhZ2Vzc2NoYXUvZmM4ZDUxMjgtOTE0ZC00Y2MzLTgzNzAtNDZkNGNiZWJkOTll',
'md5': 'f1837e563323b8a642a8ddeff0131f51',
'info_dict': {
'id': '10049223',
'ext': 'mp4',
'title': 'tagesschau, 20:00 Uhr',
'timestamp': 1636398000,
'description': 'md5:39578c7b96c9fe50afdf5674ad985e6b',
'upload_date': '20211108',
},
}, {
'url': 'https://beta.ardmediathek.de/ard/video/Y3JpZDovL2Rhc2Vyc3RlLmRlL3RhdG9ydC9mYmM4NGM1NC0xNzU4LTRmZGYtYWFhZS0wYzcyZTIxNGEyMDE',
'only_matching': True,
}, {
'url': 'https://ardmediathek.de/ard/video/saartalk/saartalk-gesellschaftsgift-haltung-gegen-hass/sr-fernsehen/Y3JpZDovL3NyLW9ubGluZS5kZS9TVF84MTY4MA/',
'only_matching': True,
}, {
'url': 'https://www.ardmediathek.de/ard/video/trailer/private-eyes-s01-e01/one/Y3JpZDovL3dkci5kZS9CZWl0cmFnLTE1MTgwYzczLWNiMTEtNGNkMS1iMjUyLTg5MGYzOWQxZmQ1YQ/',
'only_matching': True,
}, {
'url': 'https://www.ardmediathek.de/ard/player/Y3JpZDovL3N3ci5kZS9hZXgvbzEwNzE5MTU/',
'only_matching': True,
}, {
'url': 'https://www.ardmediathek.de/swr/live/Y3JpZDovL3N3ci5kZS8xMzQ4MTA0Mg',
'only_matching': True,
}, {
# playlist of type 'sendung'
'url': 'https://www.ardmediathek.de/ard/sendung/doctor-who/Y3JpZDovL3dkci5kZS9vbmUvZG9jdG9yIHdobw/',
'only_matching': True,
}, {
# playlist of type 'sammlung'
'url': 'https://www.ardmediathek.de/ard/sammlung/team-muenster/5JpTzLSbWUAK8184IOvEir/',
'only_matching': True,
}, {
'url': 'https://www.ardmediathek.de/video/coronavirus-update-ndr-info/astrazeneca-kurz-lockdown-und-pims-syndrom-81/ndr/Y3JpZDovL25kci5kZS84NzE0M2FjNi0wMWEwLTQ5ODEtOTE5NS1mOGZhNzdhOTFmOTI/',
'only_matching': True,
}, {
'url': 'https://www.ardmediathek.de/ard/player/Y3JpZDovL3dkci5kZS9CZWl0cmFnLWQ2NDJjYWEzLTMwZWYtNGI4NS1iMTI2LTU1N2UxYTcxOGIzOQ/tatort-duo-koeln-leipzig-ihr-kinderlein-kommet',
'only_matching': True,
}]
def _ARD_load_playlist_snipped(self, playlist_id, display_id, client, mode, pageNumber):
""" Query the ARD server for playlist information
and returns the data in "raw" format """
if mode == 'sendung':
graphQL = json.dumps({
'query': '''{
showPage(
client: "%s"
showId: "%s"
pageNumber: %d
) {
pagination {
pageSize
totalElements
}
teasers { # Array
mediumTitle
links { target { id href title } }
type
}
}}''' % (client, playlist_id, pageNumber),
}).encode()
else: # mode == 'sammlung'
graphQL = json.dumps({
'query': '''{
morePage(
client: "%s"
compilationId: "%s"
pageNumber: %d
) {
widget {
pagination {
pageSize
totalElements
}
teasers { # Array
mediumTitle
links { target { id href title } }
type
}
}
}}''' % (client, playlist_id, pageNumber),
}).encode()
# Ressources for ARD graphQL debugging:
# https://api-test.ardmediathek.de/public-gateway
show_page = self._download_json(
'https://api.ardmediathek.de/public-gateway',
'[Playlist] %s' % display_id,
data=graphQL,
headers={'Content-Type': 'application/json'})['data']
# align the structure of the returned data:
if mode == 'sendung':
show_page = show_page['showPage']
else: # mode == 'sammlung'
show_page = show_page['morePage']['widget']
return show_page
def _ARD_extract_playlist(self, url, playlist_id, display_id, client, mode):
""" Collects all playlist entries and returns them as info dict.
Supports playlists of mode 'sendung' and 'sammlung', and also nested
playlists. """
entries = []
pageNumber = 0
while True: # iterate by pageNumber
show_page = self._ARD_load_playlist_snipped(
playlist_id, display_id, client, mode, pageNumber)
for teaser in show_page['teasers']: # process playlist items
if '/compilation/' in teaser['links']['target']['href']:
# alternativ cond.: teaser['type'] == "compilation"
# => This is an nested compilation, e.g. like:
# https://www.ardmediathek.de/ard/sammlung/die-kirche-bleibt-im-dorf/5eOHzt8XB2sqeFXbIoJlg2/
link_mode = 'sammlung'
else:
link_mode = 'video'
item_url = 'https://www.ardmediathek.de/%s/%s/%s/%s/%s' % (
client, link_mode, display_id,
# perform HTLM quoting of episode title similar to ARD:
re.sub('^-|-$', '', # remove '-' from begin/end
re.sub('[^a-zA-Z0-9]+', '-', # replace special chars by -
teaser['links']['target']['title'].lower()
.replace('ä', 'ae').replace('ö', 'oe')
.replace('ü', 'ue').replace('ß', 'ss'))),
teaser['links']['target']['id'])
entries.append(self.url_result(
item_url,
ie=ARDBetaMediathekIE.ie_key()))
if (show_page['pagination']['pageSize'] * (pageNumber + 1)
>= show_page['pagination']['totalElements']):
# we've processed enough pages to get all playlist entries
break
pageNumber = pageNumber + 1
return self.playlist_result(entries, playlist_title=display_id)
def _real_extract(self, url):
video_id, display_id, playlist_type, client = self._match_valid_url(url).group(
'id', 'display_id', 'playlist', 'client')
display_id, client = display_id or video_id, client or 'ard'
if playlist_type:
return self._ARD_extract_playlist(url, video_id, display_id, client, playlist_type)
player_page = self._download_json(
'https://api.ardmediathek.de/public-gateway',
display_id, data=json.dumps({
'query': '''{
playerPage(client:"%s", clipId: "%s") {
blockedByFsk
broadcastedOn
maturityContentRating
mediaCollection {
_duration
_geoblocked
_isLive
_mediaArray {
_mediaStreamArray {
_quality
_server
_stream
}
}
_previewImage
_subtitleUrl
_type
}
show {
title
}
synopsis
title
tracking {
atiCustomVars {
contentId
}
}
}
}''' % (client, video_id),
}).encode(), headers={
'Content-Type': 'application/json'
})['data']['playerPage']
title = player_page['title']
content_id = str_or_none(try_get(
player_page, lambda x: x['tracking']['atiCustomVars']['contentId']))
media_collection = player_page.get('mediaCollection') or {}
if not media_collection and content_id:
media_collection = self._download_json(
'https://www.ardmediathek.de/play/media/' + content_id,
content_id, fatal=False) or {}
info = self._parse_media_info(
media_collection, content_id or video_id,
player_page.get('blockedByFsk'))
age_limit = None
description = player_page.get('synopsis')
maturity_content_rating = player_page.get('maturityContentRating')
if maturity_content_rating:
age_limit = int_or_none(maturity_content_rating.lstrip('FSK'))
if not age_limit and description:
age_limit = int_or_none(self._search_regex(
r'\(FSK\s*(\d+)\)\s*$', description, 'age limit', default=None))
info.update({
'age_limit': age_limit,
'display_id': display_id,
'title': title,
'description': description,
'timestamp': unified_timestamp(player_page.get('broadcastedOn')),
'series': try_get(player_page, lambda x: x['show']['title']),
})
info.update(self._ARD_extract_episode_info(info['title']))
return info

163
plugins/youtube_download/yt_dlp/extractor/arkena.py Normal file
View File

@ -0,0 +1,163 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
ExtractorError,
float_or_none,
int_or_none,
parse_iso8601,
parse_qs,
try_get,
)
class ArkenaIE(InfoExtractor):
_VALID_URL = r'''(?x)
https?://
(?:
video\.(?:arkena|qbrick)\.com/play2/embed/player\?|
play\.arkena\.com/(?:config|embed)/avp/v\d/player/media/(?P<id>[^/]+)/[^/]+/(?P<account_id>\d+)
)
'''
_TESTS = [{
'url': 'https://video.qbrick.com/play2/embed/player?accountId=1034090&mediaId=d8ab4607-00090107-aab86310',
'md5': '97f117754e5f3c020f5f26da4a44ebaf',
'info_dict': {
'id': 'd8ab4607-00090107-aab86310',
'ext': 'mp4',
'title': 'EM_HT20_117_roslund_v2.mp4',
'timestamp': 1608285912,
'upload_date': '20201218',
'duration': 1429.162667,
'subtitles': {
'sv': 'count:3',
},
},
}, {
'url': 'https://play.arkena.com/embed/avp/v2/player/media/b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe/1/129411',
'only_matching': True,
}, {
'url': 'https://play.arkena.com/config/avp/v2/player/media/b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe/1/129411/?callbackMethod=jQuery1111023664739129262213_1469227693893',
'only_matching': True,
}, {
'url': 'http://play.arkena.com/config/avp/v1/player/media/327336/darkmatter/131064/?callbackMethod=jQuery1111002221189684892677_1469227595972',
'only_matching': True,
}, {
'url': 'http://play.arkena.com/embed/avp/v1/player/media/327336/darkmatter/131064/',
'only_matching': True,
}, {
'url': 'http://video.arkena.com/play2/embed/player?accountId=472718&mediaId=35763b3b-00090078-bf604299&pageStyling=styled',
'only_matching': True,
}]
@staticmethod
def _extract_url(webpage):
# See https://support.arkena.com/display/PLAY/Ways+to+embed+your+video
mobj = re.search(
r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//play\.arkena\.com/embed/avp/.+?)\1',
webpage)
if mobj:
return mobj.group('url')
def _real_extract(self, url):
mobj = self._match_valid_url(url)
video_id = mobj.group('id')
account_id = mobj.group('account_id')
# Handle http://video.arkena.com/play2/embed/player URL
if not video_id:
qs = parse_qs(url)
video_id = qs.get('mediaId', [None])[0]
account_id = qs.get('accountId', [None])[0]
if not video_id or not account_id:
raise ExtractorError('Invalid URL', expected=True)
media = self._download_json(
'https://video.qbrick.com/api/v1/public/accounts/%s/medias/%s' % (account_id, video_id),
video_id, query={
# https://video.qbrick.com/docs/api/examples/library-api.html
'fields': 'asset/resources/*/renditions/*(height,id,language,links/*(href,mimeType),type,size,videos/*(audios/*(codec,sampleRate),bitrate,codec,duration,height,width),width),created,metadata/*(title,description),tags',
})
metadata = media.get('metadata') or {}
title = metadata['title']
duration = None
formats = []
thumbnails = []
subtitles = {}
for resource in media['asset']['resources']:
for rendition in (resource.get('renditions') or []):
rendition_type = rendition.get('type')
for i, link in enumerate(rendition.get('links') or []):
href = link.get('href')
if not href:
continue
if rendition_type == 'image':
thumbnails.append({
'filesize': int_or_none(rendition.get('size')),
'height': int_or_none(rendition.get('height')),
'id': rendition.get('id'),
'url': href,
'width': int_or_none(rendition.get('width')),
})
elif rendition_type == 'subtitle':
subtitles.setdefault(rendition.get('language') or 'en', []).append({
'url': href,
})
elif rendition_type == 'video':
f = {
'filesize': int_or_none(rendition.get('size')),
'format_id': rendition.get('id'),
'url': href,
}
video = try_get(rendition, lambda x: x['videos'][i], dict)
if video:
if not duration:
duration = float_or_none(video.get('duration'))
f.update({
'height': int_or_none(video.get('height')),
'tbr': int_or_none(video.get('bitrate'), 1000),
'vcodec': video.get('codec'),
'width': int_or_none(video.get('width')),
})
audio = try_get(video, lambda x: x['audios'][0], dict)
if audio:
f.update({
'acodec': audio.get('codec'),
'asr': int_or_none(audio.get('sampleRate')),
})
formats.append(f)
elif rendition_type == 'index':
mime_type = link.get('mimeType')
if mime_type == 'application/smil+xml':
formats.extend(self._extract_smil_formats(
href, video_id, fatal=False))
elif mime_type == 'application/x-mpegURL':
formats.extend(self._extract_m3u8_formats(
href, video_id, 'mp4', 'm3u8_native',
m3u8_id='hls', fatal=False))
elif mime_type == 'application/hds+xml':
formats.extend(self._extract_f4m_formats(
href, video_id, f4m_id='hds', fatal=False))
elif mime_type == 'application/dash+xml':
formats.extend(self._extract_f4m_formats(
href, video_id, f4m_id='hds', fatal=False))
elif mime_type == 'application/vnd.ms-sstr+xml':
formats.extend(self._extract_ism_formats(
href, video_id, ism_id='mss', fatal=False))
self._sort_formats(formats)
return {
'id': video_id,
'title': title,
'description': metadata.get('description'),
'timestamp': parse_iso8601(media.get('created')),
'thumbnails': thumbnails,
'subtitles': subtitles,
'duration': duration,
'tags': media.get('tags'),
'formats': formats,
}

102
plugins/youtube_download/yt_dlp/extractor/arnes.py Normal file
View File

@ -0,0 +1,102 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..compat import (
compat_parse_qs,
compat_urllib_parse_urlparse,
)
from ..utils import (
format_field,
float_or_none,
int_or_none,
parse_iso8601,
remove_start,
)
class ArnesIE(InfoExtractor):
IE_NAME = 'video.arnes.si'
IE_DESC = 'Arnes Video'
_VALID_URL = r'https?://video\.arnes\.si/(?:[a-z]{2}/)?(?:watch|embed|api/(?:asset|public/video))/(?P<id>[0-9a-zA-Z]{12})'
_TESTS = [{
'url': 'https://video.arnes.si/watch/a1qrWTOQfVoU?t=10',
'md5': '4d0f4d0a03571b33e1efac25fd4a065d',
'info_dict': {
'id': 'a1qrWTOQfVoU',
'ext': 'mp4',
'title': 'Linearna neodvisnost, definicija',
'description': 'Linearna neodvisnost, definicija',
'license': 'PRIVATE',
'creator': 'Polona Oblak',
'timestamp': 1585063725,
'upload_date': '20200324',
'channel': 'Polona Oblak',
'channel_id': 'q6pc04hw24cj',
'channel_url': 'https://video.arnes.si/?channel=q6pc04hw24cj',
'duration': 596.75,
'view_count': int,
'tags': ['linearna_algebra'],
'start_time': 10,
}
}, {
'url': 'https://video.arnes.si/api/asset/s1YjnV7hadlC/play.mp4',
'only_matching': True,
}, {
'url': 'https://video.arnes.si/embed/s1YjnV7hadlC',
'only_matching': True,
}, {
'url': 'https://video.arnes.si/en/watch/s1YjnV7hadlC',
'only_matching': True,
}, {
'url': 'https://video.arnes.si/embed/s1YjnV7hadlC?t=123&hideRelated=1',
'only_matching': True,
}, {
'url': 'https://video.arnes.si/api/public/video/s1YjnV7hadlC',
'only_matching': True,
}]
_BASE_URL = 'https://video.arnes.si'
def _real_extract(self, url):
video_id = self._match_id(url)
video = self._download_json(
self._BASE_URL + '/api/public/video/' + video_id, video_id)['data']
title = video['title']
formats = []
for media in (video.get('media') or []):
media_url = media.get('url')
if not media_url:
continue
formats.append({
'url': self._BASE_URL + media_url,
'format_id': remove_start(media.get('format'), 'FORMAT_'),
'format_note': media.get('formatTranslation'),
'width': int_or_none(media.get('width')),
'height': int_or_none(media.get('height')),
})
self._sort_formats(formats)
channel = video.get('channel') or {}
channel_id = channel.get('url')
thumbnail = video.get('thumbnailUrl')
return {
'id': video_id,
'title': title,
'formats': formats,
'thumbnail': self._BASE_URL + thumbnail,
'description': video.get('description'),
'license': video.get('license'),
'creator': video.get('author'),
'timestamp': parse_iso8601(video.get('creationTime')),
'channel': channel.get('name'),
'channel_id': channel_id,
'channel_url': format_field(channel_id, template=f'{self._BASE_URL}/?channel=%s'),
'duration': float_or_none(video.get('duration'), 1000),
'view_count': int_or_none(video.get('views')),
'tags': video.get('hashtags'),
'start_time': int_or_none(compat_parse_qs(
compat_urllib_parse_urlparse(url).query).get('t', [None])[0]),
}

255
plugins/youtube_download/yt_dlp/extractor/arte.py Normal file
View File

@ -0,0 +1,255 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import (
compat_str,
)
from ..utils import (
ExtractorError,
int_or_none,
parse_qs,
qualities,
try_get,
unified_strdate,
url_or_none,
)
class ArteTVBaseIE(InfoExtractor):
_ARTE_LANGUAGES = 'fr|de|en|es|it|pl'
_API_BASE = 'https://api.arte.tv/api/player/v1'
class ArteTVIE(ArteTVBaseIE):
_VALID_URL = r'''(?x)
https?://
(?:
(?:www\.)?arte\.tv/(?P<lang>%(langs)s)/videos|
api\.arte\.tv/api/player/v\d+/config/(?P<lang_2>%(langs)s)
)
/(?P<id>\d{6}-\d{3}-[AF])
''' % {'langs': ArteTVBaseIE._ARTE_LANGUAGES}
_TESTS = [{
'url': 'https://www.arte.tv/en/videos/088501-000-A/mexico-stealing-petrol-to-survive/',
'info_dict': {
'id': '088501-000-A',
'ext': 'mp4',
'title': 'Mexico: Stealing Petrol to Survive',
'upload_date': '20190628',
},
}, {
'url': 'https://www.arte.tv/pl/videos/100103-000-A/usa-dyskryminacja-na-porodowce/',
'only_matching': True,
}, {
'url': 'https://api.arte.tv/api/player/v2/config/de/100605-013-A',
'only_matching': True,
}]
def _real_extract(self, url):
mobj = self._match_valid_url(url)
video_id = mobj.group('id')
lang = mobj.group('lang') or mobj.group('lang_2')
info = self._download_json(
'%s/config/%s/%s' % (self._API_BASE, lang, video_id), video_id)
player_info = info['videoJsonPlayer']
vsr = try_get(player_info, lambda x: x['VSR'], dict)
if not vsr:
error = None
if try_get(player_info, lambda x: x['custom_msg']['type']) == 'error':
error = try_get(
player_info, lambda x: x['custom_msg']['msg'], compat_str)
if not error:
error = 'Video %s is not available' % player_info.get('VID') or video_id
raise ExtractorError(error, expected=True)
upload_date_str = player_info.get('shootingDate')
if not upload_date_str:
upload_date_str = (player_info.get('VRA') or player_info.get('VDA') or '').split(' ')[0]
title = (player_info.get('VTI') or player_info['VID']).strip()
subtitle = player_info.get('VSU', '').strip()
if subtitle:
title += ' - %s' % subtitle
qfunc = qualities(['MQ', 'HQ', 'EQ', 'SQ'])
LANGS = {
'fr': 'F',
'de': 'A',
'en': 'E[ANG]',
'es': 'E[ESP]',
'it': 'E[ITA]',
'pl': 'E[POL]',
}
langcode = LANGS.get(lang, lang)
formats = []
for format_id, format_dict in vsr.items():
f = dict(format_dict)
format_url = url_or_none(f.get('url'))
streamer = f.get('streamer')
if not format_url and not streamer:
continue
versionCode = f.get('versionCode')
l = re.escape(langcode)
# Language preference from most to least priority
# Reference: section 6.8 of
# https://www.arte.tv/sites/en/corporate/files/complete-technical-guidelines-arte-geie-v1-07-1.pdf
PREFERENCES = (
# original version in requested language, without subtitles
r'VO{0}$'.format(l),
# original version in requested language, with partial subtitles in requested language
r'VO{0}-ST{0}$'.format(l),
# original version in requested language, with subtitles for the deaf and hard-of-hearing in requested language
r'VO{0}-STM{0}$'.format(l),
# non-original (dubbed) version in requested language, without subtitles
r'V{0}$'.format(l),
# non-original (dubbed) version in requested language, with subtitles partial subtitles in requested language
r'V{0}-ST{0}$'.format(l),
# non-original (dubbed) version in requested language, with subtitles for the deaf and hard-of-hearing in requested language
r'V{0}-STM{0}$'.format(l),
# original version in requested language, with partial subtitles in different language
r'VO{0}-ST(?!{0}).+?$'.format(l),
# original version in requested language, with subtitles for the deaf and hard-of-hearing in different language
r'VO{0}-STM(?!{0}).+?$'.format(l),
# original version in different language, with partial subtitles in requested language
r'VO(?:(?!{0}).+?)?-ST{0}$'.format(l),
# original version in different language, with subtitles for the deaf and hard-of-hearing in requested language
r'VO(?:(?!{0}).+?)?-STM{0}$'.format(l),
# original version in different language, without subtitles
r'VO(?:(?!{0}))?$'.format(l),
# original version in different language, with partial subtitles in different language
r'VO(?:(?!{0}).+?)?-ST(?!{0}).+?$'.format(l),
# original version in different language, with subtitles for the deaf and hard-of-hearing in different language
r'VO(?:(?!{0}).+?)?-STM(?!{0}).+?$'.format(l),
)
for pref, p in enumerate(PREFERENCES):
if re.match(p, versionCode):
lang_pref = len(PREFERENCES) - pref
break
else:
lang_pref = -1
media_type = f.get('mediaType')
if media_type == 'hls':
m3u8_formats = self._extract_m3u8_formats(
format_url, video_id, 'mp4', entry_protocol='m3u8_native',
m3u8_id=format_id, fatal=False)
for m3u8_format in m3u8_formats:
m3u8_format['language_preference'] = lang_pref
formats.extend(m3u8_formats)
continue
format = {
'format_id': format_id,
'language_preference': lang_pref,
'format_note': '%s, %s' % (f.get('versionCode'), f.get('versionLibelle')),
'width': int_or_none(f.get('width')),
'height': int_or_none(f.get('height')),
'tbr': int_or_none(f.get('bitrate')),
'quality': qfunc(f.get('quality')),
}
if media_type == 'rtmp':
format['url'] = f['streamer']
format['play_path'] = 'mp4:' + f['url']
format['ext'] = 'flv'
else:
format['url'] = f['url']
formats.append(format)
# For this extractor, quality only represents the relative quality
# with respect to other formats with the same resolution
self._sort_formats(formats, ('res', 'quality'))
return {
'id': player_info.get('VID') or video_id,
'title': title,
'description': player_info.get('VDE') or player_info.get('V7T'),
'upload_date': unified_strdate(upload_date_str),
'thumbnail': player_info.get('programImage') or player_info.get('VTU', {}).get('IUR'),
'formats': formats,
}
class ArteTVEmbedIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?arte\.tv/player/v\d+/index\.php\?.*?\bjson_url=.+'
_TESTS = [{
'url': 'https://www.arte.tv/player/v5/index.php?json_url=https%3A%2F%2Fapi.arte.tv%2Fapi%2Fplayer%2Fv2%2Fconfig%2Fde%2F100605-013-A&lang=de&autoplay=true&mute=0100605-013-A',
'info_dict': {
'id': '100605-013-A',
'ext': 'mp4',
'title': 'United we Stream November Lockdown Edition #13',
'description': 'md5:be40b667f45189632b78c1425c7c2ce1',
'upload_date': '20201116',
},
}, {
'url': 'https://www.arte.tv/player/v3/index.php?json_url=https://api.arte.tv/api/player/v2/config/de/100605-013-A',
'only_matching': True,
}]
@staticmethod
def _extract_urls(webpage):
return [url for _, url in re.findall(
r'<(?:iframe|script)[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?arte\.tv/player/v\d+/index\.php\?.*?\bjson_url=.+?)\1',
webpage)]
def _real_extract(self, url):
qs = parse_qs(url)
json_url = qs['json_url'][0]
video_id = ArteTVIE._match_id(json_url)
return self.url_result(
json_url, ie=ArteTVIE.ie_key(), video_id=video_id)
class ArteTVPlaylistIE(ArteTVBaseIE):
_VALID_URL = r'https?://(?:www\.)?arte\.tv/(?P<lang>%s)/videos/(?P<id>RC-\d{6})' % ArteTVBaseIE._ARTE_LANGUAGES
_TESTS = [{
'url': 'https://www.arte.tv/en/videos/RC-016954/earn-a-living/',
'info_dict': {
'id': 'RC-016954',
'title': 'Earn a Living',
'description': 'md5:d322c55011514b3a7241f7fb80d494c2',
},
'playlist_mincount': 6,
}, {
'url': 'https://www.arte.tv/pl/videos/RC-014123/arte-reportage/',
'only_matching': True,
}]
def _real_extract(self, url):
lang, playlist_id = self._match_valid_url(url).groups()
collection = self._download_json(
'%s/collectionData/%s/%s?source=videos'
% (self._API_BASE, lang, playlist_id), playlist_id)
entries = []
for video in collection['videos']:
if not isinstance(video, dict):
continue
video_url = url_or_none(video.get('url')) or url_or_none(video.get('jsonUrl'))
if not video_url:
continue
video_id = video.get('programId')
entries.append({
'_type': 'url_transparent',
'url': video_url,
'id': video_id,
'title': video.get('title'),
'alt_title': video.get('subtitle'),
'thumbnail': url_or_none(try_get(video, lambda x: x['mainImage']['url'], compat_str)),
'duration': int_or_none(video.get('durationSeconds')),
'view_count': int_or_none(video.get('views')),
'ie_key': ArteTVIE.ie_key(),
})
title = collection.get('title')
description = collection.get('shortDescription') or collection.get('teaserText')
return self.playlist_result(entries, playlist_id, title, description)

200
plugins/youtube_download/yt_dlp/extractor/asiancrush.py Normal file
View File

@ -0,0 +1,200 @@
# coding: utf-8
from __future__ import unicode_literals
import functools
import re
from .common import InfoExtractor
from .kaltura import KalturaIE
from ..utils import (
extract_attributes,
int_or_none,
OnDemandPagedList,
parse_age_limit,
strip_or_none,
try_get,
)
class AsianCrushBaseIE(InfoExtractor):
_VALID_URL_BASE = r'https?://(?:www\.)?(?P<host>(?:(?:asiancrush|yuyutv|midnightpulp)\.com|(?:cocoro|retrocrush)\.tv))'
_KALTURA_KEYS = [
'video_url', 'progressive_url', 'download_url', 'thumbnail_url',
'widescreen_thumbnail_url', 'screencap_widescreen',
]
_API_SUFFIX = {'retrocrush.tv': '-ott'}
def _call_api(self, host, endpoint, video_id, query, resource):
return self._download_json(
'https://api%s.%s/%s' % (self._API_SUFFIX.get(host, ''), host, endpoint), video_id,
'Downloading %s JSON metadata' % resource, query=query,
headers=self.geo_verification_headers())['objects']
def _download_object_data(self, host, object_id, resource):
return self._call_api(
host, 'search', object_id, {'id': object_id}, resource)[0]
def _get_object_description(self, obj):
return strip_or_none(obj.get('long_description') or obj.get('short_description'))
def _parse_video_data(self, video):
title = video['name']
entry_id, partner_id = [None] * 2
for k in self._KALTURA_KEYS:
k_url = video.get(k)
if k_url:
mobj = re.search(r'/p/(\d+)/.+?/entryId/([^/]+)/', k_url)
if mobj:
partner_id, entry_id = mobj.groups()
break
meta_categories = try_get(video, lambda x: x['meta']['categories'], list) or []
categories = list(filter(None, [c.get('name') for c in meta_categories]))
show_info = video.get('show_info') or {}
return {
'_type': 'url_transparent',
'url': 'kaltura:%s:%s' % (partner_id, entry_id),
'ie_key': KalturaIE.ie_key(),
'id': entry_id,
'title': title,
'description': self._get_object_description(video),
'age_limit': parse_age_limit(video.get('mpaa_rating') or video.get('tv_rating')),
'categories': categories,
'series': show_info.get('show_name'),
'season_number': int_or_none(show_info.get('season_num')),
'season_id': show_info.get('season_id'),
'episode_number': int_or_none(show_info.get('episode_num')),
}
class AsianCrushIE(AsianCrushBaseIE):
_VALID_URL = r'%s/video/(?:[^/]+/)?0+(?P<id>\d+)v\b' % AsianCrushBaseIE._VALID_URL_BASE
_TESTS = [{
'url': 'https://www.asiancrush.com/video/004289v/women-who-flirt',
'md5': 'c3b740e48d0ba002a42c0b72857beae6',
'info_dict': {
'id': '1_y4tmjm5r',
'ext': 'mp4',
'title': 'Women Who Flirt',
'description': 'md5:b65c7e0ae03a85585476a62a186f924c',
'timestamp': 1496936429,
'upload_date': '20170608',
'uploader_id': 'craig@crifkin.com',
'age_limit': 13,
'categories': 'count:5',
'duration': 5812,
},
}, {
'url': 'https://www.asiancrush.com/video/she-was-pretty/011886v-pretty-episode-3/',
'only_matching': True,
}, {
'url': 'https://www.yuyutv.com/video/013886v/the-act-of-killing/',
'only_matching': True,
}, {
'url': 'https://www.yuyutv.com/video/peep-show/013922v-warring-factions/',
'only_matching': True,
}, {
'url': 'https://www.midnightpulp.com/video/010400v/drifters/',
'only_matching': True,
}, {
'url': 'https://www.midnightpulp.com/video/mononoke/016378v-zashikiwarashi-part-1/',
'only_matching': True,
}, {
'url': 'https://www.cocoro.tv/video/the-wonderful-wizard-of-oz/008878v-the-wonderful-wizard-of-oz-ep01/',
'only_matching': True,
}, {
'url': 'https://www.retrocrush.tv/video/true-tears/012328v-i...gave-away-my-tears',
'only_matching': True,
}]
def _real_extract(self, url):
host, video_id = self._match_valid_url(url).groups()
if host == 'cocoro.tv':
webpage = self._download_webpage(url, video_id)
embed_vars = self._parse_json(self._search_regex(
r'iEmbedVars\s*=\s*({.+?})', webpage, 'embed vars',
default='{}'), video_id, fatal=False) or {}
video_id = embed_vars.get('entry_id') or video_id
video = self._download_object_data(host, video_id, 'video')
return self._parse_video_data(video)
class AsianCrushPlaylistIE(AsianCrushBaseIE):
_VALID_URL = r'%s/series/0+(?P<id>\d+)s\b' % AsianCrushBaseIE._VALID_URL_BASE
_TESTS = [{
'url': 'https://www.asiancrush.com/series/006447s/fruity-samurai',
'info_dict': {
'id': '6447',
'title': 'Fruity Samurai',
'description': 'md5:7535174487e4a202d3872a7fc8f2f154',
},
'playlist_count': 13,
}, {
'url': 'https://www.yuyutv.com/series/013920s/peep-show/',
'only_matching': True,
}, {
'url': 'https://www.midnightpulp.com/series/016375s/mononoke/',
'only_matching': True,
}, {
'url': 'https://www.cocoro.tv/series/008549s/the-wonderful-wizard-of-oz/',
'only_matching': True,
}, {
'url': 'https://www.retrocrush.tv/series/012355s/true-tears',
'only_matching': True,
}]
_PAGE_SIZE = 1000000000
def _fetch_page(self, domain, parent_id, page):
videos = self._call_api(
domain, 'getreferencedobjects', parent_id, {
'max': self._PAGE_SIZE,
'object_type': 'video',
'parent_id': parent_id,
'start': page * self._PAGE_SIZE,
}, 'page %d' % (page + 1))
for video in videos:
yield self._parse_video_data(video)
def _real_extract(self, url):
host, playlist_id = self._match_valid_url(url).groups()
if host == 'cocoro.tv':
webpage = self._download_webpage(url, playlist_id)
entries = []
for mobj in re.finditer(
r'<a[^>]+href=(["\'])(?P<url>%s.*?)\1[^>]*>' % AsianCrushIE._VALID_URL,
webpage):
attrs = extract_attributes(mobj.group(0))
if attrs.get('class') == 'clearfix':
entries.append(self.url_result(
mobj.group('url'), ie=AsianCrushIE.ie_key()))
title = self._html_search_regex(
r'(?s)<h1\b[^>]\bid=["\']movieTitle[^>]+>(.+?)</h1>', webpage,
'title', default=None) or self._og_search_title(
webpage, default=None) or self._html_search_meta(
'twitter:title', webpage, 'title',
default=None) or self._search_regex(
r'<title>([^<]+)</title>', webpage, 'title', fatal=False)
if title:
title = re.sub(r'\s*\|\s*.+?$', '', title)
description = self._og_search_description(
webpage, default=None) or self._html_search_meta(
'twitter:description', webpage, 'description', fatal=False)
else:
show = self._download_object_data(host, playlist_id, 'show')
title = show.get('name')
description = self._get_object_description(show)
entries = OnDemandPagedList(
functools.partial(self._fetch_page, host, playlist_id),
self._PAGE_SIZE)
return self.playlist_result(entries, playlist_id, title, description)

116
plugins/youtube_download/yt_dlp/extractor/atresplayer.py Normal file
View File

@ -0,0 +1,116 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..compat import compat_HTTPError
from ..utils import (
ExtractorError,
int_or_none,
urlencode_postdata,
)
class AtresPlayerIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?atresplayer\.com/[^/]+/[^/]+/[^/]+/[^/]+/(?P<display_id>.+?)_(?P<id>[0-9a-f]{24})'
_NETRC_MACHINE = 'atresplayer'
_TESTS = [
{
'url': 'https://www.atresplayer.com/antena3/series/pequenas-coincidencias/temporada-1/capitulo-7-asuntos-pendientes_5d4aa2c57ed1a88fc715a615/',
'info_dict': {
'id': '5d4aa2c57ed1a88fc715a615',
'ext': 'mp4',
'title': 'Capítulo 7: Asuntos pendientes',
'description': 'md5:7634cdcb4d50d5381bedf93efb537fbc',
'duration': 3413,
},
'skip': 'This video is only available for registered users'
},
{
'url': 'https://www.atresplayer.com/lasexta/programas/el-club-de-la-comedia/temporada-4/capitulo-10-especial-solidario-nochebuena_5ad08edf986b2855ed47adc4/',
'only_matching': True,
},
{
'url': 'https://www.atresplayer.com/antena3/series/el-secreto-de-puente-viejo/el-chico-de-los-tres-lunares/capitulo-977-29-12-14_5ad51046986b2886722ccdea/',
'only_matching': True,
},
]
_API_BASE = 'https://api.atresplayer.com/'
def _real_initialize(self):
self._login()
def _handle_error(self, e, code):
if isinstance(e.cause, compat_HTTPError) and e.cause.code == code:
error = self._parse_json(e.cause.read(), None)
if error.get('error') == 'required_registered':
self.raise_login_required()
raise ExtractorError(error['error_description'], expected=True)
raise
def _login(self):
username, password = self._get_login_info()
if username is None:
return
self._request_webpage(
self._API_BASE + 'login', None, 'Downloading login page')
try:
target_url = self._download_json(
'https://account.atresmedia.com/api/login', None,
'Logging in', headers={
'Content-Type': 'application/x-www-form-urlencoded'
}, data=urlencode_postdata({
'username': username,
'password': password,
}))['targetUrl']
except ExtractorError as e:
self._handle_error(e, 400)
self._request_webpage(target_url, None, 'Following Target URL')
def _real_extract(self, url):
display_id, video_id = self._match_valid_url(url).groups()
try:
episode = self._download_json(
self._API_BASE + 'client/v1/player/episode/' + video_id, video_id)
except ExtractorError as e:
self._handle_error(e, 403)
title = episode['titulo']
formats = []
subtitles = {}
for source in episode.get('sources', []):
src = source.get('src')
if not src:
continue
src_type = source.get('type')
if src_type == 'application/vnd.apple.mpegurl':
formats, subtitles = self._extract_m3u8_formats(
src, video_id, 'mp4', 'm3u8_native',
m3u8_id='hls', fatal=False)
elif src_type == 'application/dash+xml':
formats, subtitles = self._extract_mpd_formats(
src, video_id, mpd_id='dash', fatal=False)
self._sort_formats(formats)
heartbeat = episode.get('heartbeat') or {}
omniture = episode.get('omniture') or {}
get_meta = lambda x: heartbeat.get(x) or omniture.get(x)
return {
'display_id': display_id,
'id': video_id,
'title': title,
'description': episode.get('descripcion'),
'thumbnail': episode.get('imgPoster'),
'duration': int_or_none(episode.get('duration')),
'formats': formats,
'channel': get_meta('channel'),
'season': get_meta('season'),
'episode_number': int_or_none(get_meta('episodeNumber')),
'subtitles': subtitles,
}

55
plugins/youtube_download/yt_dlp/extractor/atttechchannel.py Normal file
View File

@ -0,0 +1,55 @@
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import unified_strdate
class ATTTechChannelIE(InfoExtractor):
_VALID_URL = r'https?://techchannel\.att\.com/play-video\.cfm/([^/]+/)*(?P<id>.+)'
_TEST = {
'url': 'http://techchannel.att.com/play-video.cfm/2014/1/27/ATT-Archives-The-UNIX-System-Making-Computers-Easier-to-Use',
'info_dict': {
'id': '11316',
'display_id': 'ATT-Archives-The-UNIX-System-Making-Computers-Easier-to-Use',
'ext': 'flv',
'title': 'AT&T Archives : The UNIX System: Making Computers Easier to Use',
'description': 'A 1982 film about UNIX is the foundation for software in use around Bell Labs and AT&T.',
'thumbnail': r're:^https?://.*\.jpg$',
'upload_date': '20140127',
},
'params': {
# rtmp download
'skip_download': True,
},
}
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
video_url = self._search_regex(
r"url\s*:\s*'(rtmp://[^']+)'",
webpage, 'video URL')
video_id = self._search_regex(
r'mediaid\s*=\s*(\d+)',
webpage, 'video id', fatal=False)
title = self._og_search_title(webpage)
description = self._og_search_description(webpage)
thumbnail = self._og_search_thumbnail(webpage)
upload_date = unified_strdate(self._search_regex(
r'[Rr]elease\s+date:\s*(\d{1,2}/\d{1,2}/\d{4})',
webpage, 'upload date', fatal=False), False)
return {
'id': video_id,
'display_id': display_id,
'url': video_url,
'ext': 'flv',
'title': title,
'description': description,
'thumbnail': thumbnail,
'upload_date': upload_date,
}

106
plugins/youtube_download/yt_dlp/extractor/atvat.py Normal file
View File

@ -0,0 +1,106 @@
# coding: utf-8
from __future__ import unicode_literals
import datetime
from .common import InfoExtractor
from ..utils import (
float_or_none,
jwt_encode_hs256,
try_get,
)
class ATVAtIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?atv\.at/tv/(?:[^/]+/){2,3}(?P<id>.*)'
_TESTS = [{
'url': 'https://www.atv.at/tv/bauer-sucht-frau/staffel-18/bauer-sucht-frau/bauer-sucht-frau-staffel-18-folge-3-die-hofwochen',
'md5': '3c3b4aaca9f63e32b35e04a9c2515903',
'info_dict': {
'id': 'v-ce9cgn1e70n5-1',
'ext': 'mp4',
'title': 'Bauer sucht Frau - Staffel 18 Folge 3 - Die Hofwochen',
}
}, {
'url': 'https://www.atv.at/tv/bauer-sucht-frau/staffel-18/episode-01/bauer-sucht-frau-staffel-18-vorstellungsfolge-1',
'only_matching': True,
}]
# extracted from bootstrap.js function (search for e.encryption_key and use your browser's debugger)
_ACCESS_ID = 'x_atv'
_ENCRYPTION_KEY = 'Hohnaekeishoogh2omaeghooquooshia'
def _extract_video_info(self, url, content, video):
clip_id = content.get('splitId', content['id'])
formats = []
clip_urls = video['urls']
for protocol, variant in clip_urls.items():
source_url = try_get(variant, lambda x: x['clear']['url'])
if not source_url:
continue
if protocol == 'dash':
formats.extend(self._extract_mpd_formats(
source_url, clip_id, mpd_id=protocol, fatal=False))
elif protocol == 'hls':
formats.extend(self._extract_m3u8_formats(
source_url, clip_id, 'mp4', 'm3u8_native',
m3u8_id=protocol, fatal=False))
else:
formats.append({
'url': source_url,
'format_id': protocol,
})
self._sort_formats(formats)
return {
'id': clip_id,
'title': content.get('title'),
'duration': float_or_none(content.get('duration')),
'series': content.get('tvShowTitle'),
'formats': formats,
}
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
json_data = self._parse_json(
self._search_regex(r'<script id="state" type="text/plain">(.*)</script>', webpage, 'json_data'),
video_id=video_id)
video_title = json_data['views']['default']['page']['title']
contentResource = json_data['views']['default']['page']['contentResource']
content_id = contentResource[0]['id']
content_ids = [{'id': id, 'subclip_start': content['start'], 'subclip_end': content['end']}
for id, content in enumerate(contentResource)]
time_of_request = datetime.datetime.now()
not_before = time_of_request - datetime.timedelta(minutes=5)
expire = time_of_request + datetime.timedelta(minutes=5)
payload = {
'content_ids': {
content_id: content_ids,
},
'secure_delivery': True,
'iat': int(time_of_request.timestamp()),
'nbf': int(not_before.timestamp()),
'exp': int(expire.timestamp()),
}
jwt_token = jwt_encode_hs256(payload, self._ENCRYPTION_KEY, headers={'kid': self._ACCESS_ID})
videos = self._download_json(
'https://vas-v4.p7s1video.net/4.0/getsources',
content_id, 'Downloading videos JSON', query={
'token': jwt_token.decode('utf-8')
})
video_id, videos_data = list(videos['data'].items())[0]
entries = [
self._extract_video_info(url, contentResource[video['id']], video)
for video in videos_data]
return {
'_type': 'multi_video',
'id': video_id,
'title': video_title,
'entries': entries,
}

93
plugins/youtube_download/yt_dlp/extractor/audimedia.py Normal file
View File

@ -0,0 +1,93 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import (
int_or_none,
parse_iso8601,
)
class AudiMediaIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?audi-mediacenter\.com/(?:en|de)/audimediatv/(?:video/)?(?P<id>[^/?#]+)'
_TESTS = [{
'url': 'https://www.audi-mediacenter.com/en/audimediatv/60-seconds-of-audi-sport-104-2015-wec-bahrain-rookie-test-1467',
'md5': '79a8b71c46d49042609795ab59779b66',
'info_dict': {
'id': '1565',
'ext': 'mp4',
'title': '60 Seconds of Audi Sport 104/2015 - WEC Bahrain, Rookie Test',
'description': 'md5:60e5d30a78ced725f7b8d34370762941',
'upload_date': '20151124',
'timestamp': 1448354940,
'duration': 74022,
'view_count': int,
}
}, {
'url': 'https://www.audi-mediacenter.com/en/audimediatv/video/60-seconds-of-audi-sport-104-2015-wec-bahrain-rookie-test-2991',
'only_matching': True,
}]
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
raw_payload = self._search_regex([
r'class="amtv-embed"[^>]+id="([0-9a-z-]+)"',
r'id="([0-9a-z-]+)"[^>]+class="amtv-embed"',
r'class=\\"amtv-embed\\"[^>]+id=\\"([0-9a-z-]+)\\"',
r'id=\\"([0-9a-z-]+)\\"[^>]+class=\\"amtv-embed\\"',
r'id=(?:\\)?"(amtve-[a-z]-\d+-[a-z]{2})',
], webpage, 'raw payload')
_, stage_mode, video_id, _ = raw_payload.split('-')
# TODO: handle s and e stage_mode (live streams and ended live streams)
if stage_mode not in ('s', 'e'):
video_data = self._download_json(
'https://www.audimedia.tv/api/video/v1/videos/' + video_id,
video_id, query={
'embed[]': ['video_versions', 'thumbnail_image'],
})['results']
formats = []
stream_url_hls = video_data.get('stream_url_hls')
if stream_url_hls:
formats.extend(self._extract_m3u8_formats(
stream_url_hls, video_id, 'mp4',
entry_protocol='m3u8_native', m3u8_id='hls', fatal=False))
stream_url_hds = video_data.get('stream_url_hds')
if stream_url_hds:
formats.extend(self._extract_f4m_formats(
stream_url_hds + '?hdcore=3.4.0',
video_id, f4m_id='hds', fatal=False))
for video_version in video_data.get('video_versions', []):
video_version_url = video_version.get('download_url') or video_version.get('stream_url')
if not video_version_url:
continue
f = {
'url': video_version_url,
'width': int_or_none(video_version.get('width')),
'height': int_or_none(video_version.get('height')),
'abr': int_or_none(video_version.get('audio_bitrate')),
'vbr': int_or_none(video_version.get('video_bitrate')),
}
bitrate = self._search_regex(r'(\d+)k', video_version_url, 'bitrate', default=None)
if bitrate:
f.update({
'format_id': 'http-%s' % bitrate,
})
formats.append(f)
self._sort_formats(formats)
return {
'id': video_id,
'title': video_data['title'],
'description': video_data.get('subtitle'),
'thumbnail': video_data.get('thumbnail_image', {}).get('file'),
'timestamp': parse_iso8601(video_data.get('publication_date')),
'duration': int_or_none(video_data.get('duration')),
'view_count': int_or_none(video_data.get('view_count')),
'formats': formats,
}

73
plugins/youtube_download/yt_dlp/extractor/audioboom.py Normal file
View File

@ -0,0 +1,73 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import (
clean_html,
float_or_none,
)
class AudioBoomIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?audioboom\.com/(?:boos|posts)/(?P<id>[0-9]+)'
_TESTS = [{
'url': 'https://audioboom.com/posts/7398103-asim-chaudhry',
'md5': '7b00192e593ff227e6a315486979a42d',
'info_dict': {
'id': '7398103',
'ext': 'mp3',
'title': 'Asim Chaudhry',
'description': 'md5:2f3fef17dacc2595b5362e1d7d3602fc',
'duration': 4000.99,
'uploader': 'Sue Perkins: An hour or so with...',
'uploader_url': r're:https?://(?:www\.)?audioboom\.com/channel/perkins',
}
}, {
'url': 'https://audioboom.com/posts/4279833-3-09-2016-czaban-hour-3?t=0',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
clip = None
clip_store = self._parse_json(
self._html_search_regex(
r'data-new-clip-store=(["\'])(?P<json>{.+?})\1',
webpage, 'clip store', default='{}', group='json'),
video_id, fatal=False)
if clip_store:
clips = clip_store.get('clips')
if clips and isinstance(clips, list) and isinstance(clips[0], dict):
clip = clips[0]
def from_clip(field):
if clip:
return clip.get(field)
audio_url = from_clip('clipURLPriorToLoading') or self._og_search_property(
'audio', webpage, 'audio url')
title = from_clip('title') or self._html_search_meta(
['og:title', 'og:audio:title', 'audio_title'], webpage)
description = from_clip('description') or clean_html(from_clip('formattedDescription')) or self._og_search_description(webpage)
duration = float_or_none(from_clip('duration') or self._html_search_meta(
'weibo:audio:duration', webpage))
uploader = from_clip('author') or self._html_search_meta(
['og:audio:artist', 'twitter:audio:artist_name', 'audio_artist'], webpage, 'uploader')
uploader_url = from_clip('author_url') or self._html_search_meta(
'audioboo:channel', webpage, 'uploader url')
return {
'id': video_id,
'url': audio_url,
'title': title,
'description': description,
'duration': duration,
'uploader': uploader,
'uploader_url': uploader_url,
}

149
plugins/youtube_download/yt_dlp/extractor/audiomack.py Normal file
View File

@ -0,0 +1,149 @@
# coding: utf-8
from __future__ import unicode_literals
import itertools
import time
from .common import InfoExtractor
from .soundcloud import SoundcloudIE
from ..compat import compat_str
from ..utils import (
ExtractorError,
url_basename,
)
class AudiomackIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?audiomack\.com/(?:song/|(?=.+/song/))(?P<id>[\w/-]+)'
IE_NAME = 'audiomack'
_TESTS = [
# hosted on audiomack
{
'url': 'http://www.audiomack.com/song/roosh-williams/extraordinary',
'info_dict':
{
'id': '310086',
'ext': 'mp3',
'uploader': 'Roosh Williams',
'title': 'Extraordinary'
}
},
# audiomack wrapper around soundcloud song
{
'add_ie': ['Soundcloud'],
'url': 'http://www.audiomack.com/song/hip-hop-daily/black-mamba-freestyle',
'info_dict': {
'id': '258901379',
'ext': 'mp3',
'description': 'mamba day freestyle for the legend Kobe Bryant ',
'title': 'Black Mamba Freestyle [Prod. By Danny Wolf]',
'uploader': 'ILOVEMAKONNEN',
'upload_date': '20160414',
},
'skip': 'Song has been removed from the site',
},
]
def _real_extract(self, url):
# URLs end with [uploader name]/song/[uploader title]
# this title is whatever the user types in, and is rarely
# the proper song title. Real metadata is in the api response
album_url_tag = self._match_id(url).replace('/song/', '/')
# Request the extended version of the api for extra fields like artist and title
api_response = self._download_json(
'http://www.audiomack.com/api/music/url/song/%s?extended=1&_=%d' % (
album_url_tag, time.time()),
album_url_tag)
# API is inconsistent with errors
if 'url' not in api_response or not api_response['url'] or 'error' in api_response:
raise ExtractorError('Invalid url %s' % url)
# Audiomack wraps a lot of soundcloud tracks in their branded wrapper
# if so, pass the work off to the soundcloud extractor
if SoundcloudIE.suitable(api_response['url']):
return self.url_result(api_response['url'], SoundcloudIE.ie_key())
return {
'id': compat_str(api_response.get('id', album_url_tag)),
'uploader': api_response.get('artist'),
'title': api_response.get('title'),
'url': api_response['url'],
}
class AudiomackAlbumIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?audiomack\.com/(?:album/|(?=.+/album/))(?P<id>[\w/-]+)'
IE_NAME = 'audiomack:album'
_TESTS = [
# Standard album playlist
{
'url': 'http://www.audiomack.com/album/flytunezcom/tha-tour-part-2-mixtape',
'playlist_count': 11,
'info_dict':
{
'id': '812251',
'title': 'Tha Tour: Part 2 (Official Mixtape)'
}
},
# Album playlist ripped from fakeshoredrive with no metadata
{
'url': 'http://www.audiomack.com/album/fakeshoredrive/ppp-pistol-p-project',
'info_dict': {
'title': 'PPP (Pistol P Project)',
'id': '837572',
},
'playlist': [{
'info_dict': {
'title': 'PPP (Pistol P Project) - 8. Real (prod by SYK SENSE )',
'id': '837576',
'ext': 'mp3',
'uploader': 'Lil Herb a.k.a. G Herbo',
}
}, {
'info_dict': {
'title': 'PPP (Pistol P Project) - 10. 4 Minutes Of Hell Part 4 (prod by DY OF 808 MAFIA)',
'id': '837580',
'ext': 'mp3',
'uploader': 'Lil Herb a.k.a. G Herbo',
}
}],
}
]
def _real_extract(self, url):
# URLs end with [uploader name]/album/[uploader title]
# this title is whatever the user types in, and is rarely
# the proper song title. Real metadata is in the api response
album_url_tag = self._match_id(url).replace('/album/', '/')
result = {'_type': 'playlist', 'entries': []}
# There is no one endpoint for album metadata - instead it is included/repeated in each song's metadata
# Therefore we don't know how many songs the album has and must infi-loop until failure
for track_no in itertools.count():
# Get song's metadata
api_response = self._download_json(
'http://www.audiomack.com/api/music/url/album/%s/%d?extended=1&_=%d'
% (album_url_tag, track_no, time.time()), album_url_tag,
note='Querying song information (%d)' % (track_no + 1))
# Total failure, only occurs when url is totally wrong
# Won't happen in middle of valid playlist (next case)
if 'url' not in api_response or 'error' in api_response:
raise ExtractorError('Invalid url for track %d of album url %s' % (track_no, url))
# URL is good but song id doesn't exist - usually means end of playlist
elif not api_response['url']:
break
else:
# Pull out the album metadata and add to result (if it exists)
for resultkey, apikey in [('id', 'album_id'), ('title', 'album_title')]:
if apikey in api_response and resultkey not in result:
result[resultkey] = compat_str(api_response[apikey])
song_id = url_basename(api_response['url']).rpartition('.')[0]
result['entries'].append({
'id': compat_str(api_response.get('id', song_id)),
'uploader': api_response.get('artist'),
'title': api_response.get('title', song_id),
'url': api_response['url'],
})
return result

274
plugins/youtube_download/yt_dlp/extractor/audius.py Normal file
View File

@ -0,0 +1,274 @@
# coding: utf-8
from __future__ import unicode_literals
import random
from .common import InfoExtractor
from ..utils import ExtractorError, try_get, compat_str, str_or_none
from ..compat import compat_urllib_parse_unquote
class AudiusBaseIE(InfoExtractor):
_API_BASE = None
_API_V = '/v1'
def _get_response_data(self, response):
if isinstance(response, dict):
response_data = response.get('data')
if response_data is not None:
return response_data
if len(response) == 1 and 'message' in response:
raise ExtractorError('API error: %s' % response['message'],
expected=True)
raise ExtractorError('Unexpected API response')
def _select_api_base(self):
"""Selecting one of the currently available API hosts"""
response = super(AudiusBaseIE, self)._download_json(
'https://api.audius.co/', None,
note='Requesting available API hosts',
errnote='Unable to request available API hosts')
hosts = self._get_response_data(response)
if isinstance(hosts, list):
self._API_BASE = random.choice(hosts)
return
raise ExtractorError('Unable to get available API hosts')
@staticmethod
def _prepare_url(url, title):
"""
Audius removes forward slashes from the uri, but leaves backslashes.
The problem is that the current version of Chrome replaces backslashes
in the address bar with a forward slashes, so if you copy the link from
there and paste it into youtube-dl, you won't be able to download
anything from this link, since the Audius API won't be able to resolve
this url
"""
url = compat_urllib_parse_unquote(url)
title = compat_urllib_parse_unquote(title)
if '/' in title or '%2F' in title:
fixed_title = title.replace('/', '%5C').replace('%2F', '%5C')
return url.replace(title, fixed_title)
return url
def _api_request(self, path, item_id=None, note='Downloading JSON metadata',
errnote='Unable to download JSON metadata',
expected_status=None):
if self._API_BASE is None:
self._select_api_base()
try:
response = super(AudiusBaseIE, self)._download_json(
'%s%s%s' % (self._API_BASE, self._API_V, path), item_id, note=note,
errnote=errnote, expected_status=expected_status)
except ExtractorError as exc:
# some of Audius API hosts may not work as expected and return HTML
if 'Failed to parse JSON' in compat_str(exc):
raise ExtractorError('An error occurred while receiving data. Try again',
expected=True)
raise exc
return self._get_response_data(response)
def _resolve_url(self, url, item_id):
return self._api_request('/resolve?url=%s' % url, item_id,
expected_status=404)
class AudiusIE(AudiusBaseIE):
_VALID_URL = r'''(?x)https?://(?:www\.)?(?:audius\.co/(?P<uploader>[\w\d-]+)(?!/album|/playlist)/(?P<title>\S+))'''
IE_DESC = 'Audius.co'
_TESTS = [
{
# URL from Chrome address bar which replace backslash to forward slash
'url': 'https://audius.co/test_acc/t%D0%B5%D0%B5%D0%B5est-1.%5E_%7B%7D/%22%3C%3E.%E2%84%96~%60-198631',
'md5': '92c35d3e754d5a0f17eef396b0d33582',
'info_dict': {
'id': 'xd8gY',
'title': '''Tеееest/ 1.!@#$%^&*()_+=[]{};'\\\":<>,.?/№~`''',
'ext': 'mp3',
'description': 'Description',
'duration': 30,
'track': '''Tеееest/ 1.!@#$%^&*()_+=[]{};'\\\":<>,.?/№~`''',
'artist': 'test',
'genre': 'Electronic',
'thumbnail': r're:https?://.*\.jpg',
'view_count': int,
'like_count': int,
'repost_count': int,
}
},
{
# Regular track
'url': 'https://audius.co/voltra/radar-103692',
'md5': '491898a0a8de39f20c5d6a8a80ab5132',
'info_dict': {
'id': 'KKdy2',
'title': 'RADAR',
'ext': 'mp3',
'duration': 318,
'track': 'RADAR',
'artist': 'voltra',
'genre': 'Trance',
'thumbnail': r're:https?://.*\.jpg',
'view_count': int,
'like_count': int,
'repost_count': int,
}
},
]
_ARTWORK_MAP = {
"150x150": 150,
"480x480": 480,
"1000x1000": 1000
}
def _real_extract(self, url):
mobj = self._match_valid_url(url)
track_id = try_get(mobj, lambda x: x.group('track_id'))
if track_id is None:
title = mobj.group('title')
# uploader = mobj.group('uploader')
url = self._prepare_url(url, title)
track_data = self._resolve_url(url, title)
else: # API link
title = None
# uploader = None
track_data = self._api_request('/tracks/%s' % track_id, track_id)
if not isinstance(track_data, dict):
raise ExtractorError('Unexpected API response')
track_id = track_data.get('id')
if track_id is None:
raise ExtractorError('Unable to get ID of the track')
artworks_data = track_data.get('artwork')
thumbnails = []
if isinstance(artworks_data, dict):
for quality_key, thumbnail_url in artworks_data.items():
thumbnail = {
"url": thumbnail_url
}
quality_code = self._ARTWORK_MAP.get(quality_key)
if quality_code is not None:
thumbnail['preference'] = quality_code
thumbnails.append(thumbnail)
return {
'id': track_id,
'title': track_data.get('title', title),
'url': '%s/v1/tracks/%s/stream' % (self._API_BASE, track_id),
'ext': 'mp3',
'description': track_data.get('description'),
'duration': track_data.get('duration'),
'track': track_data.get('title'),
'artist': try_get(track_data, lambda x: x['user']['name'], compat_str),
'genre': track_data.get('genre'),
'thumbnails': thumbnails,
'view_count': track_data.get('play_count'),
'like_count': track_data.get('favorite_count'),
'repost_count': track_data.get('repost_count'),
}
class AudiusTrackIE(AudiusIE):
_VALID_URL = r'''(?x)(?:audius:)(?:https?://(?:www\.)?.+/v1/tracks/)?(?P<track_id>\w+)'''
IE_NAME = 'audius:track'
IE_DESC = 'Audius track ID or API link. Prepend with "audius:"'
_TESTS = [
{
'url': 'audius:9RWlo',
'only_matching': True
},
{
'url': 'audius:http://discoveryprovider.audius.prod-us-west-2.staked.cloud/v1/tracks/9RWlo',
'only_matching': True
},
]
class AudiusPlaylistIE(AudiusBaseIE):
_VALID_URL = r'https?://(?:www\.)?audius\.co/(?P<uploader>[\w\d-]+)/(?:album|playlist)/(?P<title>\S+)'
IE_NAME = 'audius:playlist'
IE_DESC = 'Audius.co playlists'
_TEST = {
'url': 'https://audius.co/test_acc/playlist/test-playlist-22910',
'info_dict': {
'id': 'DNvjN',
'title': 'test playlist',
'description': 'Test description\n\nlol',
},
'playlist_count': 175,
}
def _build_playlist(self, tracks):
entries = []
for track in tracks:
if not isinstance(track, dict):
raise ExtractorError('Unexpected API response')
track_id = str_or_none(track.get('id'))
if not track_id:
raise ExtractorError('Unable to get track ID from playlist')
entries.append(self.url_result(
'audius:%s' % track_id,
ie=AudiusTrackIE.ie_key(), video_id=track_id))
return entries
def _real_extract(self, url):
self._select_api_base()
mobj = self._match_valid_url(url)
title = mobj.group('title')
# uploader = mobj.group('uploader')
url = self._prepare_url(url, title)
playlist_response = self._resolve_url(url, title)
if not isinstance(playlist_response, list) or len(playlist_response) != 1:
raise ExtractorError('Unexpected API response')
playlist_data = playlist_response[0]
if not isinstance(playlist_data, dict):
raise ExtractorError('Unexpected API response')
playlist_id = playlist_data.get('id')
if playlist_id is None:
raise ExtractorError('Unable to get playlist ID')
playlist_tracks = self._api_request(
'/playlists/%s/tracks' % playlist_id,
title, note='Downloading playlist tracks metadata',
errnote='Unable to download playlist tracks metadata')
if not isinstance(playlist_tracks, list):
raise ExtractorError('Unexpected API response')
entries = self._build_playlist(playlist_tracks)
return self.playlist_result(entries, playlist_id,
playlist_data.get('playlist_name', title),
playlist_data.get('description'))
class AudiusProfileIE(AudiusPlaylistIE):
IE_NAME = 'audius:artist'
IE_DESC = 'Audius.co profile/artist pages'
_VALID_URL = r'https?://(?:www)?audius\.co/(?P<id>[^\/]+)/?(?:[?#]|$)'
_TEST = {
'url': 'https://audius.co/pzl/',
'info_dict': {
'id': 'ezRo7',
'description': 'TAMALE\n\nContact: officialpzl@gmail.com',
'title': 'pzl',
},
'playlist_count': 24,
}
def _real_extract(self, url):
self._select_api_base()
profile_id = self._match_id(url)
try:
_profile_data = self._api_request('/full/users/handle/' + profile_id, profile_id)
except ExtractorError as e:
raise ExtractorError('Could not download profile info; ' + str(e))
profile_audius_id = _profile_data[0]['id']
profile_bio = _profile_data[0].get('bio')
api_call = self._api_request('/full/users/handle/%s/tracks' % profile_id, profile_id)
return self.playlist_result(self._build_playlist(api_call), profile_audius_id, profile_id, profile_bio)

187
plugins/youtube_download/yt_dlp/extractor/awaan.py Normal file
View File

@ -0,0 +1,187 @@
# coding: utf-8
from __future__ import unicode_literals
import base64
from .common import InfoExtractor
from ..compat import (
compat_urllib_parse_urlencode,
compat_str,
)
from ..utils import (
format_field,
int_or_none,
parse_iso8601,
smuggle_url,
unsmuggle_url,
urlencode_postdata,
)
class AWAANIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?(?:awaan|dcndigital)\.ae/(?:#/)?show/(?P<show_id>\d+)/[^/]+(?:/(?P<id>\d+)/(?P<season_id>\d+))?'
def _real_extract(self, url):
show_id, video_id, season_id = self._match_valid_url(url).groups()
if video_id and int(video_id) > 0:
return self.url_result(
'http://awaan.ae/media/%s' % video_id, 'AWAANVideo')
elif season_id and int(season_id) > 0:
return self.url_result(smuggle_url(
'http://awaan.ae/program/season/%s' % season_id,
{'show_id': show_id}), 'AWAANSeason')
else:
return self.url_result(
'http://awaan.ae/program/%s' % show_id, 'AWAANSeason')
class AWAANBaseIE(InfoExtractor):
def _parse_video_data(self, video_data, video_id, is_live):
title = video_data.get('title_en') or video_data['title_ar']
img = video_data.get('img')
return {
'id': video_id,
'title': title,
'description': video_data.get('description_en') or video_data.get('description_ar'),
'thumbnail': format_field(img, template='http://admin.mangomolo.com/analytics/%s'),
'duration': int_or_none(video_data.get('duration')),
'timestamp': parse_iso8601(video_data.get('create_time'), ' '),
'is_live': is_live,
'uploader_id': video_data.get('user_id'),
}
class AWAANVideoIE(AWAANBaseIE):
IE_NAME = 'awaan:video'
_VALID_URL = r'https?://(?:www\.)?(?:awaan|dcndigital)\.ae/(?:#/)?(?:video(?:/[^/]+)?|media|catchup/[^/]+/[^/]+)/(?P<id>\d+)'
_TESTS = [{
'url': 'http://www.dcndigital.ae/#/video/%D8%B1%D8%AD%D9%84%D8%A9-%D8%A7%D9%84%D8%B9%D9%85%D8%B1-%D8%A7%D9%84%D8%AD%D9%84%D9%82%D8%A9-1/17375',
'md5': '5f61c33bfc7794315c671a62d43116aa',
'info_dict':
{
'id': '17375',
'ext': 'mp4',
'title': 'رحلة العمر : الحلقة 1',
'description': 'md5:0156e935d870acb8ef0a66d24070c6d6',
'duration': 2041,
'timestamp': 1227504126,
'upload_date': '20081124',
'uploader_id': '71',
},
}, {
'url': 'http://awaan.ae/video/26723981/%D8%AF%D8%A7%D8%B1-%D8%A7%D9%84%D8%B3%D9%84%D8%A7%D9%85:-%D8%AE%D9%8A%D8%B1-%D8%AF%D9%88%D8%B1-%D8%A7%D9%84%D8%A3%D9%86%D8%B5%D8%A7%D8%B1',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
video_data = self._download_json(
'http://admin.mangomolo.com/analytics/index.php/plus/video?id=%s' % video_id,
video_id, headers={'Origin': 'http://awaan.ae'})
info = self._parse_video_data(video_data, video_id, False)
embed_url = 'http://admin.mangomolo.com/analytics/index.php/customers/embed/video?' + compat_urllib_parse_urlencode({
'id': video_data['id'],
'user_id': video_data['user_id'],
'signature': video_data['signature'],
'countries': 'Q0M=',
'filter': 'DENY',
})
info.update({
'_type': 'url_transparent',
'url': embed_url,
'ie_key': 'MangomoloVideo',
})
return info
class AWAANLiveIE(AWAANBaseIE):
IE_NAME = 'awaan:live'
_VALID_URL = r'https?://(?:www\.)?(?:awaan|dcndigital)\.ae/(?:#/)?live/(?P<id>\d+)'
_TEST = {
'url': 'http://awaan.ae/live/6/dubai-tv',
'info_dict': {
'id': '6',
'ext': 'mp4',
'title': 're:Dubai Al Oula [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
'upload_date': '20150107',
'timestamp': 1420588800,
'uploader_id': '71',
},
'params': {
# m3u8 download
'skip_download': True,
},
}
def _real_extract(self, url):
channel_id = self._match_id(url)
channel_data = self._download_json(
'http://admin.mangomolo.com/analytics/index.php/plus/getchanneldetails?channel_id=%s' % channel_id,
channel_id, headers={'Origin': 'http://awaan.ae'})
info = self._parse_video_data(channel_data, channel_id, True)
embed_url = 'http://admin.mangomolo.com/analytics/index.php/customers/embed/index?' + compat_urllib_parse_urlencode({
'id': base64.b64encode(channel_data['user_id'].encode()).decode(),
'channelid': base64.b64encode(channel_data['id'].encode()).decode(),
'signature': channel_data['signature'],
'countries': 'Q0M=',
'filter': 'DENY',
})
info.update({
'_type': 'url_transparent',
'url': embed_url,
'ie_key': 'MangomoloLive',
})
return info
class AWAANSeasonIE(InfoExtractor):
IE_NAME = 'awaan:season'
_VALID_URL = r'https?://(?:www\.)?(?:awaan|dcndigital)\.ae/(?:#/)?program/(?:(?P<show_id>\d+)|season/(?P<season_id>\d+))'
_TEST = {
'url': 'http://dcndigital.ae/#/program/205024/%D9%85%D8%AD%D8%A7%D8%B6%D8%B1%D8%A7%D8%AA-%D8%A7%D9%84%D8%B4%D9%8A%D8%AE-%D8%A7%D9%84%D8%B4%D8%B9%D8%B1%D8%A7%D9%88%D9%8A',
'info_dict':
{
'id': '7910',
'title': 'محاضرات الشيخ الشعراوي',
},
'playlist_mincount': 27,
}
def _real_extract(self, url):
url, smuggled_data = unsmuggle_url(url, {})
show_id, season_id = self._match_valid_url(url).groups()
data = {}
if season_id:
data['season'] = season_id
show_id = smuggled_data.get('show_id')
if show_id is None:
season = self._download_json(
'http://admin.mangomolo.com/analytics/index.php/plus/season_info?id=%s' % season_id,
season_id, headers={'Origin': 'http://awaan.ae'})
show_id = season['id']
data['show_id'] = show_id
show = self._download_json(
'http://admin.mangomolo.com/analytics/index.php/plus/show',
show_id, data=urlencode_postdata(data), headers={
'Origin': 'http://awaan.ae',
'Content-Type': 'application/x-www-form-urlencoded'
})
if not season_id:
season_id = show['default_season']
for season in show['seasons']:
if season['id'] == season_id:
title = season.get('title_en') or season['title_ar']
entries = []
for video in show['videos']:
video_id = compat_str(video['id'])
entries.append(self.url_result(
'http://awaan.ae/media/%s' % video_id, 'AWAANVideo', video_id))
return self.playlist_result(entries, season_id, title)

78
plugins/youtube_download/yt_dlp/extractor/aws.py Normal file
View File

@ -0,0 +1,78 @@
# coding: utf-8
from __future__ import unicode_literals
import datetime
import hashlib
import hmac
from .common import InfoExtractor
from ..compat import compat_urllib_parse_urlencode
class AWSIE(InfoExtractor):
_AWS_ALGORITHM = 'AWS4-HMAC-SHA256'
_AWS_REGION = 'us-east-1'
def _aws_execute_api(self, aws_dict, video_id, query=None):
query = query or {}
amz_date = datetime.datetime.utcnow().strftime('%Y%m%dT%H%M%SZ')
date = amz_date[:8]
headers = {
'Accept': 'application/json',
'Host': self._AWS_PROXY_HOST,
'X-Amz-Date': amz_date,
'X-Api-Key': self._AWS_API_KEY
}
session_token = aws_dict.get('session_token')
if session_token:
headers['X-Amz-Security-Token'] = session_token
def aws_hash(s):
return hashlib.sha256(s.encode('utf-8')).hexdigest()
# Task 1: http://docs.aws.amazon.com/general/latest/gr/sigv4-create-canonical-request.html
canonical_querystring = compat_urllib_parse_urlencode(query)
canonical_headers = ''
for header_name, header_value in sorted(headers.items()):
canonical_headers += '%s:%s\n' % (header_name.lower(), header_value)
signed_headers = ';'.join([header.lower() for header in sorted(headers.keys())])
canonical_request = '\n'.join([
'GET',
aws_dict['uri'],
canonical_querystring,
canonical_headers,
signed_headers,
aws_hash('')
])
# Task 2: http://docs.aws.amazon.com/general/latest/gr/sigv4-create-string-to-sign.html
credential_scope_list = [date, self._AWS_REGION, 'execute-api', 'aws4_request']
credential_scope = '/'.join(credential_scope_list)
string_to_sign = '\n'.join([self._AWS_ALGORITHM, amz_date, credential_scope, aws_hash(canonical_request)])
# Task 3: http://docs.aws.amazon.com/general/latest/gr/sigv4-calculate-signature.html
def aws_hmac(key, msg):
return hmac.new(key, msg.encode('utf-8'), hashlib.sha256)
def aws_hmac_digest(key, msg):
return aws_hmac(key, msg).digest()
def aws_hmac_hexdigest(key, msg):
return aws_hmac(key, msg).hexdigest()
k_signing = ('AWS4' + aws_dict['secret_key']).encode('utf-8')
for value in credential_scope_list:
k_signing = aws_hmac_digest(k_signing, value)
signature = aws_hmac_hexdigest(k_signing, string_to_sign)
# Task 4: http://docs.aws.amazon.com/general/latest/gr/sigv4-add-signature-to-request.html
headers['Authorization'] = ', '.join([
'%s Credential=%s/%s' % (self._AWS_ALGORITHM, aws_dict['access_key'], credential_scope),
'SignedHeaders=%s' % signed_headers,
'Signature=%s' % signature,
])
return self._download_json(
'https://%s%s%s' % (self._AWS_PROXY_HOST, aws_dict['uri'], '?' + canonical_querystring if canonical_querystring else ''),
video_id, headers=headers)

65
plugins/youtube_download/yt_dlp/extractor/azmedien.py Normal file
View File

@ -0,0 +1,65 @@
# coding: utf-8
from __future__ import unicode_literals
import json
from .common import InfoExtractor
from .kaltura import KalturaIE
class AZMedienIE(InfoExtractor):
IE_DESC = 'AZ Medien videos'
_VALID_URL = r'''(?x)
https?://
(?:www\.)?
(?P<host>
telezueri\.ch|
telebaern\.tv|
telem1\.ch
)/
[^/]+/
(?P<id>
[^/]+-(?P<article_id>\d+)
)
(?:
\#video=
(?P<kaltura_id>
[_0-9a-z]+
)
)?
'''
_TESTS = [{
'url': 'https://www.telezueri.ch/sonntalk/bundesrats-vakanzen-eu-rahmenabkommen-133214569',
'info_dict': {
'id': '1_anruz3wy',
'ext': 'mp4',
'title': 'Bundesrats-Vakanzen / EU-Rahmenabkommen',
'uploader_id': 'TVOnline',
'upload_date': '20180930',
'timestamp': 1538328802,
},
'params': {
'skip_download': True,
},
}, {
'url': 'https://www.telebaern.tv/telebaern-news/montag-1-oktober-2018-ganze-sendung-133531189#video=0_7xjo9lf1',
'only_matching': True
}]
_API_TEMPL = 'https://www.%s/api/pub/gql/%s/NewsArticleTeaser/a4016f65fe62b81dc6664dd9f4910e4ab40383be'
_PARTNER_ID = '1719221'
def _real_extract(self, url):
host, display_id, article_id, entry_id = self._match_valid_url(url).groups()
if not entry_id:
entry_id = self._download_json(
self._API_TEMPL % (host, host.split('.')[0]), display_id, query={
'variables': json.dumps({
'contextId': 'NewsArticle:' + article_id,
}),
})['data']['context']['mainAsset']['video']['kaltura']['kalturaId']
return self.url_result(
'kaltura:%s:%s' % (self._PARTNER_ID, entry_id),
ie=KalturaIE.ie_key(), video_id=entry_id)

55
plugins/youtube_download/yt_dlp/extractor/baidu.py Normal file
View File

@ -0,0 +1,55 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import unescapeHTML
class BaiduVideoIE(InfoExtractor):
IE_DESC = '百度视频'
_VALID_URL = r'https?://v\.baidu\.com/(?P<type>[a-z]+)/(?P<id>\d+)\.htm'
_TESTS = [{
'url': 'http://v.baidu.com/comic/1069.htm?frp=bdbrand&q=%E4%B8%AD%E5%8D%8E%E5%B0%8F%E5%BD%93%E5%AE%B6',
'info_dict': {
'id': '1069',
'title': '中华小当家 TV版国语',
'description': 'md5:51be07afe461cf99fa61231421b5397c',
},
'playlist_count': 52,
}, {
'url': 'http://v.baidu.com/show/11595.htm?frp=bdbrand',
'info_dict': {
'id': '11595',
'title': 're:^奔跑吧兄弟',
'description': 'md5:1bf88bad6d850930f542d51547c089b8',
},
'playlist_mincount': 12,
}]
def _call_api(self, path, category, playlist_id, note):
return self._download_json('http://app.video.baidu.com/%s/?worktype=adnative%s&id=%s' % (
path, category, playlist_id), playlist_id, note)
def _real_extract(self, url):
category, playlist_id = self._match_valid_url(url).groups()
if category == 'show':
category = 'tvshow'
if category == 'tv':
category = 'tvplay'
playlist_detail = self._call_api(
'xqinfo', category, playlist_id, 'Download playlist JSON metadata')
playlist_title = playlist_detail['title']
playlist_description = unescapeHTML(playlist_detail.get('intro'))
episodes_detail = self._call_api(
'xqsingle', category, playlist_id, 'Download episodes JSON metadata')
entries = [self.url_result(
episode['url'], video_title=episode['title']
) for episode in episodes_detail['videos']]
return self.playlist_result(
entries, playlist_id, playlist_title, playlist_description)

36
plugins/youtube_download/yt_dlp/extractor/bandaichannel.py Normal file
View File

@ -0,0 +1,36 @@
# coding: utf-8
from __future__ import unicode_literals
from .brightcove import BrightcoveNewIE
from ..utils import extract_attributes
class BandaiChannelIE(BrightcoveNewIE):
IE_NAME = 'bandaichannel'
_VALID_URL = r'https?://(?:www\.)?b-ch\.com/titles/(?P<id>\d+/\d+)'
_TESTS = [{
'url': 'https://www.b-ch.com/titles/514/001',
'md5': 'a0f2d787baa5729bed71108257f613a4',
'info_dict': {
'id': '6128044564001',
'ext': 'mp4',
'title': 'メタルファイターMIKU 第1話',
'timestamp': 1580354056,
'uploader_id': '5797077852001',
'upload_date': '20200130',
'duration': 1387.733,
},
'params': {
'skip_download': True,
},
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
attrs = extract_attributes(self._search_regex(
r'(<video-js[^>]+\bid="bcplayer"[^>]*>)', webpage, 'player'))
bc = self._download_json(
'https://pbifcd.b-ch.com/v1/playbackinfo/ST/70/' + attrs['data-info'],
video_id, headers={'X-API-KEY': attrs['data-auth'].strip()})['bc']
return self._parse_brightcove_metadata(bc, bc['id'])

431
plugins/youtube_download/yt_dlp/extractor/bandcamp.py Normal file
View File

@ -0,0 +1,431 @@
# coding: utf-8
from __future__ import unicode_literals
import random
import re
import time
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
ExtractorError,
float_or_none,
int_or_none,
KNOWN_EXTENSIONS,
parse_filesize,
str_or_none,
try_get,
update_url_query,
unified_strdate,
unified_timestamp,
url_or_none,
urljoin,
)
class BandcampIE(InfoExtractor):
_VALID_URL = r'https?://[^/]+\.bandcamp\.com/track/(?P<id>[^/?#&]+)'
_TESTS = [{
'url': 'http://youtube-dl.bandcamp.com/track/youtube-dl-test-song',
'md5': 'c557841d5e50261777a6585648adf439',
'info_dict': {
'id': '1812978515',
'ext': 'mp3',
'title': "youtube-dl \"'/\\ä↭ - youtube-dl \"'/\\ä↭ - youtube-dl test song \"'/\\ä↭",
'duration': 9.8485,
'uploader': 'youtube-dl "\'/\\ä↭',
'upload_date': '20121129',
'timestamp': 1354224127,
},
'_skip': 'There is a limit of 200 free downloads / month for the test song'
}, {
# free download
'url': 'http://benprunty.bandcamp.com/track/lanius-battle',
'info_dict': {
'id': '2650410135',
'ext': 'aiff',
'title': 'Ben Prunty - Lanius (Battle)',
'thumbnail': r're:^https?://.*\.jpg$',
'uploader': 'Ben Prunty',
'timestamp': 1396508491,
'upload_date': '20140403',
'release_timestamp': 1396483200,
'release_date': '20140403',
'duration': 260.877,
'track': 'Lanius (Battle)',
'track_number': 1,
'track_id': '2650410135',
'artist': 'Ben Prunty',
'album': 'FTL: Advanced Edition Soundtrack',
},
}, {
# no free download, mp3 128
'url': 'https://relapsealumni.bandcamp.com/track/hail-to-fire',
'md5': 'fec12ff55e804bb7f7ebeb77a800c8b7',
'info_dict': {
'id': '2584466013',
'ext': 'mp3',
'title': 'Mastodon - Hail to Fire',
'thumbnail': r're:^https?://.*\.jpg$',
'uploader': 'Mastodon',
'timestamp': 1322005399,
'upload_date': '20111122',
'release_timestamp': 1076112000,
'release_date': '20040207',
'duration': 120.79,
'track': 'Hail to Fire',
'track_number': 5,
'track_id': '2584466013',
'artist': 'Mastodon',
'album': 'Call of the Mastodon',
},
}]
def _extract_data_attr(self, webpage, video_id, attr='tralbum', fatal=True):
return self._parse_json(self._html_search_regex(
r'data-%s=(["\'])({.+?})\1' % attr, webpage,
attr + ' data', group=2), video_id, fatal=fatal)
def _real_extract(self, url):
title = self._match_id(url)
webpage = self._download_webpage(url, title)
tralbum = self._extract_data_attr(webpage, title)
thumbnail = self._og_search_thumbnail(webpage)
track_id = None
track = None
track_number = None
duration = None
formats = []
track_info = try_get(tralbum, lambda x: x['trackinfo'][0], dict)
if track_info:
file_ = track_info.get('file')
if isinstance(file_, dict):
for format_id, format_url in file_.items():
if not url_or_none(format_url):
continue
ext, abr_str = format_id.split('-', 1)
formats.append({
'format_id': format_id,
'url': self._proto_relative_url(format_url, 'http:'),
'ext': ext,
'vcodec': 'none',
'acodec': ext,
'abr': int_or_none(abr_str),
})
track = track_info.get('title')
track_id = str_or_none(
track_info.get('track_id') or track_info.get('id'))
track_number = int_or_none(track_info.get('track_num'))
duration = float_or_none(track_info.get('duration'))
embed = self._extract_data_attr(webpage, title, 'embed', False)
current = tralbum.get('current') or {}
artist = embed.get('artist') or current.get('artist') or tralbum.get('artist')
timestamp = unified_timestamp(
current.get('publish_date') or tralbum.get('album_publish_date'))
download_link = tralbum.get('freeDownloadPage')
if download_link:
track_id = compat_str(tralbum['id'])
download_webpage = self._download_webpage(
download_link, track_id, 'Downloading free downloads page')
blob = self._extract_data_attr(download_webpage, track_id, 'blob')
info = try_get(
blob, (lambda x: x['digital_items'][0],
lambda x: x['download_items'][0]), dict)
if info:
downloads = info.get('downloads')
if isinstance(downloads, dict):
if not track:
track = info.get('title')
if not artist:
artist = info.get('artist')
if not thumbnail:
thumbnail = info.get('thumb_url')
download_formats = {}
download_formats_list = blob.get('download_formats')
if isinstance(download_formats_list, list):
for f in blob['download_formats']:
name, ext = f.get('name'), f.get('file_extension')
if all(isinstance(x, compat_str) for x in (name, ext)):
download_formats[name] = ext.strip('.')
for format_id, f in downloads.items():
format_url = f.get('url')
if not format_url:
continue
# Stat URL generation algorithm is reverse engineered from
# download_*_bundle_*.js
stat_url = update_url_query(
format_url.replace('/download/', '/statdownload/'), {
'.rand': int(time.time() * 1000 * random.random()),
})
format_id = f.get('encoding_name') or format_id
stat = self._download_json(
stat_url, track_id, 'Downloading %s JSON' % format_id,
transform_source=lambda s: s[s.index('{'):s.rindex('}') + 1],
fatal=False)
if not stat:
continue
retry_url = url_or_none(stat.get('retry_url'))
if not retry_url:
continue
formats.append({
'url': self._proto_relative_url(retry_url, 'http:'),
'ext': download_formats.get(format_id),
'format_id': format_id,
'format_note': f.get('description'),
'filesize': parse_filesize(f.get('size_mb')),
'vcodec': 'none',
})
self._sort_formats(formats)
title = '%s - %s' % (artist, track) if artist else track
if not duration:
duration = float_or_none(self._html_search_meta(
'duration', webpage, default=None))
return {
'id': track_id,
'title': title,
'thumbnail': thumbnail,
'uploader': artist,
'timestamp': timestamp,
'release_timestamp': unified_timestamp(tralbum.get('album_release_date')),
'duration': duration,
'track': track,
'track_number': track_number,
'track_id': track_id,
'artist': artist,
'album': embed.get('album_title'),
'formats': formats,
}
class BandcampAlbumIE(BandcampIE):
IE_NAME = 'Bandcamp:album'
_VALID_URL = r'https?://(?:(?P<subdomain>[^.]+)\.)?bandcamp\.com(?!/music)(?:/album/(?P<id>[^/?#&]+))?'
_TESTS = [{
'url': 'http://blazo.bandcamp.com/album/jazz-format-mixtape-vol-1',
'playlist': [
{
'md5': '39bc1eded3476e927c724321ddf116cf',
'info_dict': {
'id': '1353101989',
'ext': 'mp3',
'title': 'Blazo - Intro',
'timestamp': 1311756226,
'upload_date': '20110727',
'uploader': 'Blazo',
}
},
{
'md5': '1a2c32e2691474643e912cc6cd4bffaa',
'info_dict': {
'id': '38097443',
'ext': 'mp3',
'title': 'Blazo - Kero One - Keep It Alive (Blazo remix)',
'timestamp': 1311757238,
'upload_date': '20110727',
'uploader': 'Blazo',
}
},
],
'info_dict': {
'title': 'Jazz Format Mixtape vol.1',
'id': 'jazz-format-mixtape-vol-1',
'uploader_id': 'blazo',
},
'params': {
'playlistend': 2
},
'skip': 'Bandcamp imposes download limits.'
}, {
'url': 'http://nightbringer.bandcamp.com/album/hierophany-of-the-open-grave',
'info_dict': {
'title': 'Hierophany of the Open Grave',
'uploader_id': 'nightbringer',
'id': 'hierophany-of-the-open-grave',
},
'playlist_mincount': 9,
}, {
'url': 'http://dotscale.bandcamp.com',
'info_dict': {
'title': 'Loom',
'id': 'dotscale',
'uploader_id': 'dotscale',
},
'playlist_mincount': 7,
}, {
# with escaped quote in title
'url': 'https://jstrecords.bandcamp.com/album/entropy-ep',
'info_dict': {
'title': '"Entropy" EP',
'uploader_id': 'jstrecords',
'id': 'entropy-ep',
'description': 'md5:0ff22959c943622972596062f2f366a5',
},
'playlist_mincount': 3,
}, {
# not all tracks have songs
'url': 'https://insulters.bandcamp.com/album/we-are-the-plague',
'info_dict': {
'id': 'we-are-the-plague',
'title': 'WE ARE THE PLAGUE',
'uploader_id': 'insulters',
'description': 'md5:b3cf845ee41b2b1141dc7bde9237255f',
},
'playlist_count': 2,
}]
@classmethod
def suitable(cls, url):
return (False
if BandcampWeeklyIE.suitable(url) or BandcampIE.suitable(url)
else super(BandcampAlbumIE, cls).suitable(url))
def _real_extract(self, url):
uploader_id, album_id = self._match_valid_url(url).groups()
playlist_id = album_id or uploader_id
webpage = self._download_webpage(url, playlist_id)
tralbum = self._extract_data_attr(webpage, playlist_id)
track_info = tralbum.get('trackinfo')
if not track_info:
raise ExtractorError('The page doesn\'t contain any tracks')
# Only tracks with duration info have songs
entries = [
self.url_result(
urljoin(url, t['title_link']), BandcampIE.ie_key(),
str_or_none(t.get('track_id') or t.get('id')), t.get('title'))
for t in track_info
if t.get('duration')]
current = tralbum.get('current') or {}
return {
'_type': 'playlist',
'uploader_id': uploader_id,
'id': playlist_id,
'title': current.get('title'),
'description': current.get('about'),
'entries': entries,
}
class BandcampWeeklyIE(BandcampIE):
IE_NAME = 'Bandcamp:weekly'
_VALID_URL = r'https?://(?:www\.)?bandcamp\.com/?\?(?:.*?&)?show=(?P<id>\d+)'
_TESTS = [{
'url': 'https://bandcamp.com/?show=224',
'md5': 'b00df799c733cf7e0c567ed187dea0fd',
'info_dict': {
'id': '224',
'ext': 'opus',
'title': 'BC Weekly April 4th 2017 - Magic Moments',
'description': 'md5:5d48150916e8e02d030623a48512c874',
'duration': 5829.77,
'release_date': '20170404',
'series': 'Bandcamp Weekly',
'episode': 'Magic Moments',
'episode_id': '224',
},
'params': {
'format': 'opus-lo',
},
}, {
'url': 'https://bandcamp.com/?blah/blah@&show=228',
'only_matching': True
}]
def _real_extract(self, url):
show_id = self._match_id(url)
webpage = self._download_webpage(url, show_id)
blob = self._extract_data_attr(webpage, show_id, 'blob')
show = blob['bcw_data'][show_id]
formats = []
for format_id, format_url in show['audio_stream'].items():
if not url_or_none(format_url):
continue
for known_ext in KNOWN_EXTENSIONS:
if known_ext in format_id:
ext = known_ext
break
else:
ext = None
formats.append({
'format_id': format_id,
'url': format_url,
'ext': ext,
'vcodec': 'none',
})
self._sort_formats(formats)
title = show.get('audio_title') or 'Bandcamp Weekly'
subtitle = show.get('subtitle')
if subtitle:
title += ' - %s' % subtitle
return {
'id': show_id,
'title': title,
'description': show.get('desc') or show.get('short_desc'),
'duration': float_or_none(show.get('audio_duration')),
'is_live': False,
'release_date': unified_strdate(show.get('published_date')),
'series': 'Bandcamp Weekly',
'episode': show.get('subtitle'),
'episode_id': show_id,
'formats': formats
}
class BandcampMusicIE(InfoExtractor):
_VALID_URL = r'https?://(?P<id>[^/]+)\.bandcamp\.com/music'
_TESTS = [{
'url': 'https://steviasphere.bandcamp.com/music',
'playlist_mincount': 47,
'info_dict': {
'id': 'steviasphere',
},
}, {
'url': 'https://coldworldofficial.bandcamp.com/music',
'playlist_mincount': 10,
'info_dict': {
'id': 'coldworldofficial',
},
}, {
'url': 'https://nuclearwarnowproductions.bandcamp.com/music',
'playlist_mincount': 399,
'info_dict': {
'id': 'nuclearwarnowproductions',
},
}
]
_TYPE_IE_DICT = {
'album': BandcampAlbumIE.ie_key(),
'track': BandcampIE.ie_key()
}
def _real_extract(self, url):
id = self._match_id(url)
webpage = self._download_webpage(url, id)
items = re.findall(r'href\=\"\/(?P<path>(?P<type>album|track)+/[^\"]+)', webpage)
entries = [
self.url_result(
f'https://{id}.bandcamp.com/{item[0]}',
ie=self._TYPE_IE_DICT[item[1]])
for item in items]
return self.playlist_result(entries, id)

158
plugins/youtube_download/yt_dlp/extractor/bannedvideo.py Normal file
View File

@ -0,0 +1,158 @@
from __future__ import unicode_literals
import json
from .common import InfoExtractor
from ..utils import (
try_get,
int_or_none,
url_or_none,
float_or_none,
unified_timestamp,
)
class BannedVideoIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?banned\.video/watch\?id=(?P<id>[0-f]{24})'
_TESTS = [{
'url': 'https://banned.video/watch?id=5e7a859644e02200c6ef5f11',
'md5': '14b6e81d41beaaee2215cd75c6ed56e4',
'info_dict': {
'id': '5e7a859644e02200c6ef5f11',
'ext': 'mp4',
'title': 'China Discovers Origin of Corona Virus: Issues Emergency Statement',
'thumbnail': r're:^https?://(?:www\.)?assets\.infowarsmedia.com/images/',
'description': 'md5:560d96f02abbebe6c6b78b47465f6b28',
'upload_date': '20200324',
'timestamp': 1585087895,
}
}]
_GRAPHQL_GETMETADATA_QUERY = '''
query GetVideoAndComments($id: String!) {
getVideo(id: $id) {
streamUrl
directUrl
unlisted
live
tags {
name
}
title
summary
playCount
largeImage
videoDuration
channel {
_id
title
}
createdAt
}
getVideoComments(id: $id, limit: 999999, offset: 0) {
_id
content
user {
_id
username
}
voteCount {
positive
}
createdAt
replyCount
}
}'''
_GRAPHQL_GETCOMMENTSREPLIES_QUERY = '''
query GetCommentReplies($id: String!) {
getCommentReplies(id: $id, limit: 999999, offset: 0) {
_id
content
user {
_id
username
}
voteCount {
positive
}
createdAt
replyCount
}
}'''
_GRAPHQL_QUERIES = {
'GetVideoAndComments': _GRAPHQL_GETMETADATA_QUERY,
'GetCommentReplies': _GRAPHQL_GETCOMMENTSREPLIES_QUERY,
}
def _call_api(self, video_id, id, operation, note):
return self._download_json(
'https://api.infowarsmedia.com/graphql', video_id, note=note,
headers={
'Content-Type': 'application/json; charset=utf-8'
}, data=json.dumps({
'variables': {'id': id},
'operationName': operation,
'query': self._GRAPHQL_QUERIES[operation]
}).encode('utf8')).get('data')
def _get_comments(self, video_id, comments, comment_data):
yield from comments
for comment in comment_data.copy():
comment_id = comment.get('_id')
if comment.get('replyCount') > 0:
reply_json = self._call_api(
video_id, comment_id, 'GetCommentReplies',
f'Downloading replies for comment {comment_id}')
for reply in reply_json.get('getCommentReplies'):
yield self._parse_comment(reply, comment_id)
@staticmethod
def _parse_comment(comment_data, parent):
return {
'id': comment_data.get('_id'),
'text': comment_data.get('content'),
'author': try_get(comment_data, lambda x: x['user']['username']),
'author_id': try_get(comment_data, lambda x: x['user']['_id']),
'timestamp': unified_timestamp(comment_data.get('createdAt')),
'parent': parent,
'like_count': try_get(comment_data, lambda x: x['voteCount']['positive']),
}
def _real_extract(self, url):
video_id = self._match_id(url)
video_json = self._call_api(video_id, video_id, 'GetVideoAndComments', 'Downloading video metadata')
video_info = video_json['getVideo']
is_live = video_info.get('live')
comments = [self._parse_comment(comment, 'root') for comment in video_json.get('getVideoComments')]
formats = [{
'format_id': 'direct',
'quality': 1,
'url': video_info.get('directUrl'),
'ext': 'mp4',
}] if url_or_none(video_info.get('directUrl')) else []
if video_info.get('streamUrl'):
formats.extend(self._extract_m3u8_formats(
video_info.get('streamUrl'), video_id, 'mp4',
entry_protocol='m3u8_native', m3u8_id='hls', live=True))
self._sort_formats(formats)
return {
'id': video_id,
'title': video_info.get('title')[:-1],
'formats': formats,
'is_live': is_live,
'description': video_info.get('summary'),
'channel': try_get(video_info, lambda x: x['channel']['title']),
'channel_id': try_get(video_info, lambda x: x['channel']['_id']),
'view_count': int_or_none(video_info.get('playCount')),
'thumbnail': url_or_none(video_info.get('largeImage')),
'duration': float_or_none(video_info.get('videoDuration')),
'timestamp': unified_timestamp(video_info.get('createdAt')),
'tags': [tag.get('name') for tag in video_info.get('tags')],
'availability': self._availability(is_unlisted=video_info.get('unlisted')),
'comments': comments,
'__post_extractor': self.extract_comments(video_id, comments, video_json.get('getVideoComments'))
}

1632
plugins/youtube_download/yt_dlp/extractor/bbc.py Normal file
View File

File diff suppressed because it is too large Load Diff

101
plugins/youtube_download/yt_dlp/extractor/beatport.py Normal file
View File

@ -0,0 +1,101 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import int_or_none
class BeatportIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.|pro\.)?beatport\.com/track/(?P<display_id>[^/]+)/(?P<id>[0-9]+)'
_TESTS = [{
'url': 'https://beatport.com/track/synesthesia-original-mix/5379371',
'md5': 'b3c34d8639a2f6a7f734382358478887',
'info_dict': {
'id': '5379371',
'display_id': 'synesthesia-original-mix',
'ext': 'mp4',
'title': 'Froxic - Synesthesia (Original Mix)',
},
}, {
'url': 'https://beatport.com/track/love-and-war-original-mix/3756896',
'md5': 'e44c3025dfa38c6577fbaeb43da43514',
'info_dict': {
'id': '3756896',
'display_id': 'love-and-war-original-mix',
'ext': 'mp3',
'title': 'Wolfgang Gartner - Love & War (Original Mix)',
},
}, {
'url': 'https://beatport.com/track/birds-original-mix/4991738',
'md5': 'a1fd8e8046de3950fd039304c186c05f',
'info_dict': {
'id': '4991738',
'display_id': 'birds-original-mix',
'ext': 'mp4',
'title': "Tos, Middle Milk, Mumblin' Johnsson - Birds (Original Mix)",
}
}]
def _real_extract(self, url):
mobj = self._match_valid_url(url)
track_id = mobj.group('id')
display_id = mobj.group('display_id')
webpage = self._download_webpage(url, display_id)
playables = self._parse_json(
self._search_regex(
r'window\.Playables\s*=\s*({.+?});', webpage,
'playables info', flags=re.DOTALL),
track_id)
track = next(t for t in playables['tracks'] if t['id'] == int(track_id))
title = ', '.join((a['name'] for a in track['artists'])) + ' - ' + track['name']
if track['mix']:
title += ' (' + track['mix'] + ')'
formats = []
for ext, info in track['preview'].items():
if not info['url']:
continue
fmt = {
'url': info['url'],
'ext': ext,
'format_id': ext,
'vcodec': 'none',
}
if ext == 'mp3':
fmt['acodec'] = 'mp3'
fmt['abr'] = 96
fmt['asr'] = 44100
elif ext == 'mp4':
fmt['acodec'] = 'aac'
fmt['abr'] = 96
fmt['asr'] = 44100
formats.append(fmt)
self._sort_formats(formats)
images = []
for name, info in track['images'].items():
image_url = info.get('url')
if name == 'dynamic' or not image_url:
continue
image = {
'id': name,
'url': image_url,
'height': int_or_none(info.get('height')),
'width': int_or_none(info.get('width')),
}
images.append(image)
return {
'id': compat_str(track.get('id')) or track_id,
'display_id': track.get('slug') or display_id,
'title': title,
'formats': formats,
'thumbnails': images,
}

116
plugins/youtube_download/yt_dlp/extractor/beeg.py Normal file
View File

@ -0,0 +1,116 @@
from __future__ import unicode_literals
from .common import InfoExtractor
from ..compat import (
compat_str,
)
from ..utils import (
int_or_none,
parse_qs,
unified_timestamp,
)
class BeegIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?beeg\.(?:com|porn(?:/video)?)/(?P<id>\d+)'
_TESTS = [{
# api/v6 v1
'url': 'http://beeg.com/5416503',
'md5': 'a1a1b1a8bc70a89e49ccfd113aed0820',
'info_dict': {
'id': '5416503',
'ext': 'mp4',
'title': 'Sultry Striptease',
'description': 'md5:d22219c09da287c14bed3d6c37ce4bc2',
'timestamp': 1391813355,
'upload_date': '20140207',
'duration': 383,
'tags': list,
'age_limit': 18,
}
}, {
# api/v6 v2
'url': 'https://beeg.com/1941093077?t=911-1391',
'only_matching': True,
}, {
# api/v6 v2 w/o t
'url': 'https://beeg.com/1277207756',
'only_matching': True,
}, {
'url': 'https://beeg.porn/video/5416503',
'only_matching': True,
}, {
'url': 'https://beeg.porn/5416503',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
beeg_version = self._search_regex(
r'beeg_version\s*=\s*([\da-zA-Z_-]+)', webpage, 'beeg version',
default='1546225636701')
if len(video_id) >= 10:
query = {
'v': 2,
}
qs = parse_qs(url)
t = qs.get('t', [''])[0].split('-')
if len(t) > 1:
query.update({
's': t[0],
'e': t[1],
})
else:
query = {'v': 1}
for api_path in ('', 'api.'):
video = self._download_json(
'https://%sbeeg.com/api/v6/%s/video/%s'
% (api_path, beeg_version, video_id), video_id,
fatal=api_path == 'api.', query=query)
if video:
break
formats = []
for format_id, video_url in video.items():
if not video_url:
continue
height = self._search_regex(
r'^(\d+)[pP]$', format_id, 'height', default=None)
if not height:
continue
formats.append({
'url': self._proto_relative_url(
video_url.replace('{DATA_MARKERS}', 'data=pc_XX__%s_0' % beeg_version), 'https:'),
'format_id': format_id,
'height': int(height),
})
self._sort_formats(formats)
title = video['title']
video_id = compat_str(video.get('id') or video_id)
display_id = video.get('code')
description = video.get('desc')
series = video.get('ps_name')
timestamp = unified_timestamp(video.get('date'))
duration = int_or_none(video.get('duration'))
tags = [tag.strip() for tag in video['tags'].split(',')] if video.get('tags') else None
return {
'id': video_id,
'display_id': display_id,
'title': title,
'description': description,
'series': series,
'timestamp': timestamp,
'duration': duration,
'tags': tags,
'formats': formats,
'age_limit': self._rta_search(webpage),
}

45
plugins/youtube_download/yt_dlp/extractor/behindkink.py Normal file
View File

@ -0,0 +1,45 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import url_basename
class BehindKinkIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?behindkink\.com/(?P<year>[0-9]{4})/(?P<month>[0-9]{2})/(?P<day>[0-9]{2})/(?P<id>[^/#?_]+)'
_TEST = {
'url': 'http://www.behindkink.com/2014/12/05/what-are-you-passionate-about-marley-blaze/',
'md5': '507b57d8fdcd75a41a9a7bdb7989c762',
'info_dict': {
'id': '37127',
'ext': 'mp4',
'title': 'What are you passionate about – Marley Blaze',
'description': 'md5:aee8e9611b4ff70186f752975d9b94b4',
'upload_date': '20141205',
'thumbnail': 'http://www.behindkink.com/wp-content/uploads/2014/12/blaze-1.jpg',
'age_limit': 18,
}
}
def _real_extract(self, url):
mobj = self._match_valid_url(url)
display_id = mobj.group('id')
webpage = self._download_webpage(url, display_id)
video_url = self._search_regex(
r'<source src="([^"]+)"', webpage, 'video URL')
video_id = url_basename(video_url).split('_')[0]
upload_date = mobj.group('year') + mobj.group('month') + mobj.group('day')
return {
'id': video_id,
'display_id': display_id,
'url': video_url,
'title': self._og_search_title(webpage),
'thumbnail': self._og_search_thumbnail(webpage),
'description': self._og_search_description(webpage),
'upload_date': upload_date,
'age_limit': 18,
}

Some files were not shown because too many files have changed in this diff Show More