Upgrade yt_dlp and download script
This commit is contained in:
@@ -1,142 +1,26 @@
|
||||
import datetime as dt
|
||||
import functools
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..networking import Request
|
||||
from ..utils import (
|
||||
ExtractorError,
|
||||
OnDemandPagedList,
|
||||
date_from_str,
|
||||
UserNotLive,
|
||||
determine_ext,
|
||||
filter_dict,
|
||||
int_or_none,
|
||||
qualities,
|
||||
traverse_obj,
|
||||
unified_strdate,
|
||||
unified_timestamp,
|
||||
update_url_query,
|
||||
orderedSet,
|
||||
parse_iso8601,
|
||||
url_or_none,
|
||||
urlencode_postdata,
|
||||
xpath_text,
|
||||
urljoin,
|
||||
)
|
||||
from ..utils.traversal import traverse_obj
|
||||
|
||||
|
||||
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|player)/
|
||||
)
|
||||
(?P<id>\d+)
|
||||
'''
|
||||
class AfreecaTVBaseIE(InfoExtractor):
|
||||
_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',
|
||||
}, {
|
||||
# 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/.*$',
|
||||
'uploader': '♥이슬이',
|
||||
'uploader_id': 'dasl8121',
|
||||
'upload_date': '20170411',
|
||||
'duration': 213,
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
},
|
||||
}, {
|
||||
# adult content
|
||||
'url': 'https://vod.afreecatv.com/player/97267690',
|
||||
'info_dict': {
|
||||
'id': '20180327_27901457_202289533_1',
|
||||
'ext': 'mp4',
|
||||
'title': '[생]빨개요♥ (part 1)',
|
||||
'thumbnail': 're:^https?://(?:video|st)img.afreecatv.com/.*$',
|
||||
'uploader': '[SA]서아',
|
||||
'uploader_id': 'bjdyrksu',
|
||||
'upload_date': '20180327',
|
||||
'duration': 3601,
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
},
|
||||
'skip': 'The VOD does not exist',
|
||||
}, {
|
||||
'url': 'http://www.afreecatv.com/player/Player.swf?szType=szBjId=djleegoon&nStationNo=11273158&nBbsNo=13161095&nTitleNo=36327652',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://vod.afreecatv.com/player/96753363',
|
||||
'info_dict': {
|
||||
'id': '20230108_9FF5BEE1_244432674_1',
|
||||
'ext': 'mp4',
|
||||
'uploader_id': 'rlantnghks',
|
||||
'uploader': '페이즈으',
|
||||
'duration': 10840,
|
||||
'thumbnail': 'http://videoimg.afreecatv.com/php/SnapshotLoad.php?rowKey=20230108_9FF5BEE1_244432674_1_r',
|
||||
'upload_date': '20230108',
|
||||
'title': '젠지 페이즈',
|
||||
},
|
||||
'params': {
|
||||
'skip_download': 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 _perform_login(self, username, password):
|
||||
login_form = {
|
||||
@@ -150,21 +34,21 @@ class AfreecaTVIE(InfoExtractor):
|
||||
}
|
||||
|
||||
response = self._download_json(
|
||||
'https://login.afreecatv.com/app/LoginAction.php', None,
|
||||
'https://login.sooplive.co.kr/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',
|
||||
-5: 'https://member.sooplive.co.kr/app/user_delete_progress.php',
|
||||
-6: 'https://login.sooplive.co.kr/membership/changeMember.php',
|
||||
-8: "Hello! Soop 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.sooplive.co.kr/app/pop_login_block.php',
|
||||
-11: 'https://login.sooplive.co.kr/afreeca/second_login.php',
|
||||
-12: 'https://member.sooplive.co.kr/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.',
|
||||
-7: 'You cannot use your Global Soop account to access Korean Soop.',
|
||||
-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.',
|
||||
}
|
||||
@@ -173,169 +57,206 @@ class AfreecaTVIE(InfoExtractor):
|
||||
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),
|
||||
f'Unable to login: {self.IE_NAME} said: {error}',
|
||||
expected=True)
|
||||
|
||||
def _call_api(self, endpoint, display_id, data=None, headers=None, query=None):
|
||||
return self._download_json(Request(
|
||||
f'https://api.m.sooplive.co.kr/{endpoint}',
|
||||
data=data, headers=headers, query=query,
|
||||
extensions={'legacy_ssl': True}), display_id,
|
||||
'Downloading API JSON', 'Unable to download API JSON')
|
||||
|
||||
@staticmethod
|
||||
def _fixup_thumb(thumb_url):
|
||||
if not url_or_none(thumb_url):
|
||||
return None
|
||||
# Core would determine_ext as 'php' from the url, so we need to provide the real ext
|
||||
# See: https://github.com/yt-dlp/yt-dlp/issues/11537
|
||||
return [{'url': thumb_url, 'ext': 'jpg'}]
|
||||
|
||||
|
||||
class AfreecaTVIE(AfreecaTVBaseIE):
|
||||
IE_NAME = 'soop'
|
||||
IE_DESC = 'sooplive.co.kr'
|
||||
_VALID_URL = r'https?://vod\.(?:sooplive\.co\.kr|afreecatv\.com)/(?:PLAYER/STATION|player)/(?P<id>\d+)/?(?:$|[?#&])'
|
||||
_TESTS = [{
|
||||
'url': 'https://vod.sooplive.co.kr/player/96753363',
|
||||
'info_dict': {
|
||||
'id': '20230108_9FF5BEE1_244432674_1',
|
||||
'ext': 'mp4',
|
||||
'uploader_id': 'rlantnghks',
|
||||
'uploader': '페이즈으',
|
||||
'duration': 10840,
|
||||
'thumbnail': r're:https?://videoimg\.(?:sooplive\.co\.kr|afreecatv\.com)/.+',
|
||||
'upload_date': '20230108',
|
||||
'timestamp': 1673186405,
|
||||
'title': '젠지 페이즈',
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
},
|
||||
}, {
|
||||
# non standard key
|
||||
'url': 'http://vod.sooplive.co.kr/PLAYER/STATION/20515605',
|
||||
'info_dict': {
|
||||
'id': '20170411_BE689A0E_190960999_1_2_h',
|
||||
'ext': 'mp4',
|
||||
'title': '혼자사는여자집',
|
||||
'thumbnail': r're:https?://(?:video|st)img\.(?:sooplive\.co\.kr|afreecatv\.com)/.+',
|
||||
'uploader': '♥이슬이',
|
||||
'uploader_id': 'dasl8121',
|
||||
'upload_date': '20170411',
|
||||
'timestamp': 1491929865,
|
||||
'duration': 213,
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
},
|
||||
}, {
|
||||
# adult content
|
||||
'url': 'https://vod.sooplive.co.kr/player/97267690',
|
||||
'info_dict': {
|
||||
'id': '20180327_27901457_202289533_1',
|
||||
'ext': 'mp4',
|
||||
'title': '[생]빨개요♥ (part 1)',
|
||||
'thumbnail': r're:https?://(?:video|st)img\.(?:sooplive\.co\.kr|afreecatv\.com)/.+',
|
||||
'uploader': '[SA]서아',
|
||||
'uploader_id': 'bjdyrksu',
|
||||
'upload_date': '20180327',
|
||||
'duration': 3601,
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
},
|
||||
'skip': 'The VOD does not exist',
|
||||
}, {
|
||||
# adult content
|
||||
'url': 'https://vod.sooplive.co.kr/player/70395877',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
# subscribers only
|
||||
'url': 'https://vod.sooplive.co.kr/player/104647403',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
# private
|
||||
'url': 'https://vod.sooplive.co.kr/player/81669846',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
|
||||
partial_view = False
|
||||
adult_view = False
|
||||
for _ in range(2):
|
||||
data = self._download_json(
|
||||
'https://api.m.afreecatv.com/station/video/a/view',
|
||||
video_id, headers={'Referer': url}, data=urlencode_postdata({
|
||||
'nTitleNo': video_id,
|
||||
'nApiLevel': 10,
|
||||
}))['data']
|
||||
if traverse_obj(data, ('code', {int})) == -6221:
|
||||
raise ExtractorError('The VOD does not exist', expected=True)
|
||||
query = {
|
||||
data = self._call_api(
|
||||
'station/video/a/view', video_id, headers={'Referer': url},
|
||||
data=urlencode_postdata({
|
||||
'nTitleNo': video_id,
|
||||
'nStationNo': data['station_no'],
|
||||
'nBbsNo': data['bbs_no'],
|
||||
}
|
||||
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)
|
||||
'nApiLevel': 10,
|
||||
}))['data']
|
||||
|
||||
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')
|
||||
error_code = traverse_obj(data, ('code', {int}))
|
||||
if error_code == -6221:
|
||||
raise ExtractorError('The VOD does not exist', expected=True)
|
||||
elif error_code == -6205:
|
||||
raise ExtractorError('This VOD is private', expected=True)
|
||||
|
||||
video_element = video_xml.findall('./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,
|
||||
common_info = traverse_obj(data, {
|
||||
'title': ('title', {str}),
|
||||
'uploader': ('writer_nick', {str}),
|
||||
'uploader_id': ('bj_id', {str}),
|
||||
'duration': ('total_file_duration', {int_or_none(scale=1000)}),
|
||||
'thumbnails': ('thumb', {self._fixup_thumb}),
|
||||
})
|
||||
|
||||
if not video_url:
|
||||
entries = []
|
||||
file_elements = video_element.findall('./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
|
||||
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
|
||||
entries = []
|
||||
for file_num, file_element in enumerate(
|
||||
traverse_obj(data, ('files', lambda _, v: url_or_none(v['file']))), start=1):
|
||||
file_url = file_element['file']
|
||||
if determine_ext(file_url) == 'm3u8':
|
||||
formats = self._extract_m3u8_formats(
|
||||
file_url, video_id, 'mp4', m3u8_id='hls',
|
||||
note=f'Downloading part {file_num} m3u8 information')
|
||||
else:
|
||||
formats = [{
|
||||
'url': file_url,
|
||||
'format_id': 'http',
|
||||
}]
|
||||
|
||||
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
|
||||
entries.append({
|
||||
**common_info,
|
||||
'id': file_element.get('file_info_key') or f'{video_id}_{file_num}',
|
||||
'title': f'{common_info.get("title") or "Untitled"} (part {file_num})',
|
||||
'formats': formats,
|
||||
**traverse_obj(file_element, {
|
||||
'duration': ('duration', {int_or_none(scale=1000)}),
|
||||
'timestamp': ('file_start', {parse_iso8601(delimiter=' ', timezone=dt.timedelta(hours=9))}),
|
||||
}),
|
||||
})
|
||||
|
||||
return info
|
||||
if traverse_obj(data, ('adult_status', {str})) == 'notLogin':
|
||||
if not entries:
|
||||
self.raise_login_required(
|
||||
'Only users older than 19 are able to watch this video', method='password')
|
||||
self.report_warning(
|
||||
'In accordance with local laws and regulations, underage users are '
|
||||
'restricted from watching adult content. Only content suitable for all '
|
||||
f'ages will be downloaded. {self._login_hint("password")}')
|
||||
|
||||
if not entries and traverse_obj(data, ('sub_upload_type', {str})):
|
||||
self.raise_login_required('This VOD is for subscribers only', method='password')
|
||||
|
||||
if len(entries) == 1:
|
||||
return {
|
||||
**entries[0],
|
||||
'title': common_info.get('title'),
|
||||
}
|
||||
|
||||
common_info['timestamp'] = traverse_obj(entries, (..., 'timestamp'), get_all=False)
|
||||
|
||||
return self.playlist_result(entries, video_id, multi_video=True, **common_info)
|
||||
|
||||
|
||||
class AfreecaTVLiveIE(AfreecaTVIE): # XXX: Do not subclass from concrete IE
|
||||
|
||||
IE_NAME = 'afreecatv:live'
|
||||
_VALID_URL = r'https?://play\.afreeca(?:tv)?\.com/(?P<id>[^/]+)(?:/(?P<bno>\d+))?'
|
||||
class AfreecaTVCatchStoryIE(AfreecaTVBaseIE):
|
||||
IE_NAME = 'soop:catchstory'
|
||||
IE_DESC = 'sooplive.co.kr catch story'
|
||||
_VALID_URL = r'https?://vod\.(?:sooplive\.co\.kr|afreecatv\.com)/player/(?P<id>\d+)/catchstory'
|
||||
_TESTS = [{
|
||||
'url': 'https://play.afreecatv.com/pyh3646/237852185',
|
||||
'url': 'https://vod.sooplive.co.kr/player/103247/catchstory',
|
||||
'info_dict': {
|
||||
'id': '103247',
|
||||
},
|
||||
'playlist_count': 2,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
data = self._call_api(
|
||||
'catchstory/a/view', video_id, headers={'Referer': url},
|
||||
query={'aStoryListIdx': '', 'nStoryIdx': video_id})
|
||||
|
||||
return self.playlist_result(self._entries(data), video_id)
|
||||
|
||||
def _entries(self, data):
|
||||
# 'files' is always a list with 1 element
|
||||
yield from traverse_obj(data, (
|
||||
'data', lambda _, v: v['story_type'] == 'catch',
|
||||
'catch_list', lambda _, v: v['files'][0]['file'], {
|
||||
'id': ('files', 0, 'file_info_key', {str}),
|
||||
'url': ('files', 0, 'file', {url_or_none}),
|
||||
'duration': ('files', 0, 'duration', {int_or_none(scale=1000)}),
|
||||
'title': ('title', {str}),
|
||||
'uploader': ('writer_nick', {str}),
|
||||
'uploader_id': ('writer_id', {str}),
|
||||
'thumbnails': ('thumb', {self._fixup_thumb}),
|
||||
'timestamp': ('write_timestamp', {int_or_none}),
|
||||
}))
|
||||
|
||||
|
||||
class AfreecaTVLiveIE(AfreecaTVBaseIE):
|
||||
IE_NAME = 'soop:live'
|
||||
IE_DESC = 'sooplive.co.kr livestreams'
|
||||
_VALID_URL = r'https?://play\.(?:sooplive\.co\.kr|afreecatv\.com)/(?P<id>[^/?#]+)(?:/(?P<bno>\d+))?'
|
||||
_TESTS = [{
|
||||
'url': 'https://play.sooplive.co.kr/pyh3646/237852185',
|
||||
'info_dict': {
|
||||
'id': '237852185',
|
||||
'ext': 'mp4',
|
||||
@@ -347,94 +268,121 @@ class AfreecaTVLiveIE(AfreecaTVIE): # XXX: Do not subclass from concrete IE
|
||||
},
|
||||
'skip': 'Livestream has ended',
|
||||
}, {
|
||||
'url': 'http://play.afreeca.com/pyh3646/237852185',
|
||||
'url': 'https://play.sooplive.co.kr/pyh3646/237852185',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'http://play.afreeca.com/pyh3646',
|
||||
'url': 'https://play.sooplive.co.kr/pyh3646',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
_LIVE_API_URL = 'https://live.afreecatv.com/afreeca/player_live_api.php'
|
||||
_LIVE_API_URL = 'https://live.sooplive.co.kr/afreeca/player_live_api.php'
|
||||
_WORKING_CDNS = [
|
||||
'gcp_cdn', # live-global-cdn-v02.sooplive.co.kr
|
||||
'gs_cdn_pc_app', # pc-app.stream.sooplive.co.kr
|
||||
'gs_cdn_mobile_web', # mobile-web.stream.sooplive.co.kr
|
||||
'gs_cdn_pc_web', # pc-web.stream.sooplive.co.kr
|
||||
]
|
||||
_BAD_CDNS = [
|
||||
'gs_cdn', # chromecast.afreeca.gscdn.com (cannot resolve)
|
||||
'gs_cdn_chromecast', # chromecast.stream.sooplive.co.kr (HTTP Error 400)
|
||||
'azure_cdn', # live-global-cdn-v01.sooplive.co.kr (cannot resolve)
|
||||
'aws_cf', # live-global-cdn-v03.sooplive.co.kr (cannot resolve)
|
||||
'kt_cdn', # kt.stream.sooplive.co.kr (HTTP Error 400)
|
||||
]
|
||||
|
||||
_QUALITIES = ('sd', 'hd', 'hd2k', 'original')
|
||||
def _extract_formats(self, channel_info, broadcast_no, aid):
|
||||
stream_base_url = channel_info.get('RMD') or 'https://livestream-manager.sooplive.co.kr'
|
||||
|
||||
# If user has not passed CDN IDs, try API-provided CDN ID followed by other working CDN IDs
|
||||
default_cdn_ids = orderedSet([
|
||||
*traverse_obj(channel_info, ('CDN', {str}, all, lambda _, v: v not in self._BAD_CDNS)),
|
||||
*self._WORKING_CDNS,
|
||||
])
|
||||
cdn_ids = self._configuration_arg('cdn', default_cdn_ids)
|
||||
|
||||
for attempt, cdn_id in enumerate(cdn_ids, start=1):
|
||||
m3u8_url = traverse_obj(self._download_json(
|
||||
urljoin(stream_base_url, 'broad_stream_assign.html'), broadcast_no,
|
||||
f'Downloading {cdn_id} stream info', f'Unable to download {cdn_id} stream info',
|
||||
fatal=False, query={
|
||||
'return_type': cdn_id,
|
||||
'broad_key': f'{broadcast_no}-common-master-hls',
|
||||
}), ('view_url', {url_or_none}))
|
||||
try:
|
||||
return self._extract_m3u8_formats(
|
||||
m3u8_url, broadcast_no, 'mp4', m3u8_id='hls', query={'aid': aid},
|
||||
headers={'Referer': 'https://play.sooplive.co.kr/'})
|
||||
except ExtractorError as e:
|
||||
if attempt == len(cdn_ids):
|
||||
raise
|
||||
self.report_warning(
|
||||
f'{e.cause or e.msg}. Retrying... (attempt {attempt} of {len(cdn_ids)})')
|
||||
|
||||
def _real_extract(self, url):
|
||||
broadcaster_id, broadcast_no = self._match_valid_url(url).group('id', 'bno')
|
||||
password = self.get_param('videopassword')
|
||||
channel_info = traverse_obj(self._download_json(
|
||||
self._LIVE_API_URL, broadcaster_id, data=urlencode_postdata({'bid': broadcaster_id})),
|
||||
('CHANNEL', {dict})) or {}
|
||||
|
||||
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
|
||||
password_protected = channel_info.get('BPWD')
|
||||
if not broadcast_no:
|
||||
raise ExtractorError(f'Unable to extract broadcast number ({broadcaster_id} may not be live)', expected=True)
|
||||
if password_protected == 'Y' and password is None:
|
||||
result = channel_info.get('RESULT')
|
||||
if result == 0:
|
||||
raise UserNotLive(video_id=broadcaster_id)
|
||||
elif result == -6:
|
||||
self.raise_login_required(
|
||||
'This channel is streaming for subscribers only', method='password')
|
||||
raise ExtractorError('Unable to extract broadcast number')
|
||||
|
||||
password = self.get_param('videopassword')
|
||||
if channel_info.get('BPWD') == 'Y' and password is None:
|
||||
raise ExtractorError(
|
||||
'This livestream is protected by a password, use the --video-password option',
|
||||
expected=True)
|
||||
|
||||
formats = []
|
||||
quality_key = qualities(self._QUALITIES)
|
||||
for quality_str in self._QUALITIES:
|
||||
params = {
|
||||
token_info = traverse_obj(self._download_json(
|
||||
self._LIVE_API_URL, broadcast_no, 'Downloading access token for stream',
|
||||
'Unable to download access token for stream', data=urlencode_postdata(filter_dict({
|
||||
'bno': broadcast_no,
|
||||
'stream_type': 'common',
|
||||
'type': 'aid',
|
||||
'quality': quality_str,
|
||||
}
|
||||
if password is not None:
|
||||
params['pwd'] = password
|
||||
aid_response = self._download_json(
|
||||
self._LIVE_API_URL, broadcast_no, fatal=False,
|
||||
data=urlencode_postdata(params),
|
||||
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
|
||||
'quality': 'master',
|
||||
'pwd': password,
|
||||
}))), ('CHANNEL', {dict})) or {}
|
||||
aid = token_info.get('AID')
|
||||
if not aid:
|
||||
result = token_info.get('RESULT')
|
||||
if result == 0:
|
||||
raise ExtractorError('This livestream has ended', expected=True)
|
||||
elif result == -6:
|
||||
self.raise_login_required('This livestream is for subscribers only', method='password')
|
||||
raise ExtractorError('Unable to extract access token')
|
||||
|
||||
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 {}
|
||||
formats = self._extract_formats(channel_info, broadcast_no, aid)
|
||||
|
||||
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),
|
||||
})
|
||||
|
||||
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 {}
|
||||
station_info = traverse_obj(self._download_json(
|
||||
'https://st.sooplive.co.kr/api/get_station_status.php', broadcast_no,
|
||||
'Downloading channel metadata', 'Unable to download channel metadata',
|
||||
query={'szBjId': broadcaster_id}, fatal=False), {dict}) 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')),
|
||||
'timestamp': parse_iso8601(station_info.get('broad_start'), delimiter=' ', timezone=dt.timedelta(hours=9)),
|
||||
'formats': formats,
|
||||
'is_live': True,
|
||||
'http_headers': {'Referer': url},
|
||||
}
|
||||
|
||||
|
||||
class AfreecaTVUserIE(InfoExtractor):
|
||||
IE_NAME = 'afreecatv:user'
|
||||
_VALID_URL = r'https?://bj\.afreeca(?:tv)?\.com/(?P<id>[^/]+)/vods/?(?P<slug_type>[^/]+)?'
|
||||
class AfreecaTVUserIE(AfreecaTVBaseIE):
|
||||
IE_NAME = 'soop:user'
|
||||
_VALID_URL = r'https?://ch\.(?:sooplive\.co\.kr|afreecatv\.com)/(?P<id>[^/?#]+)/vods/?(?P<slug_type>[^/?#]+)?'
|
||||
_TESTS = [{
|
||||
'url': 'https://bj.afreecatv.com/ryuryu24/vods/review',
|
||||
'url': 'https://ch.sooplive.co.kr/ryuryu24/vods/review',
|
||||
'info_dict': {
|
||||
'_type': 'playlist',
|
||||
'id': 'ryuryu24',
|
||||
@@ -442,7 +390,7 @@ class AfreecaTVUserIE(InfoExtractor):
|
||||
},
|
||||
'playlist_count': 218,
|
||||
}, {
|
||||
'url': 'https://bj.afreecatv.com/parang1995/vods/highlight',
|
||||
'url': 'https://ch.sooplive.co.kr/parang1995/vods/highlight',
|
||||
'info_dict': {
|
||||
'_type': 'playlist',
|
||||
'id': 'parang1995',
|
||||
@@ -450,7 +398,7 @@ class AfreecaTVUserIE(InfoExtractor):
|
||||
},
|
||||
'playlist_count': 997,
|
||||
}, {
|
||||
'url': 'https://bj.afreecatv.com/ryuryu24/vods',
|
||||
'url': 'https://ch.sooplive.co.kr/ryuryu24/vods',
|
||||
'info_dict': {
|
||||
'_type': 'playlist',
|
||||
'id': 'ryuryu24',
|
||||
@@ -458,7 +406,7 @@ class AfreecaTVUserIE(InfoExtractor):
|
||||
},
|
||||
'playlist_count': 221,
|
||||
}, {
|
||||
'url': 'https://bj.afreecatv.com/ryuryu24/vods/balloonclip',
|
||||
'url': 'https://ch.sooplive.co.kr/ryuryu24/vods/balloonclip',
|
||||
'info_dict': {
|
||||
'_type': 'playlist',
|
||||
'id': 'ryuryu24',
|
||||
@@ -470,12 +418,12 @@ class AfreecaTVUserIE(InfoExtractor):
|
||||
|
||||
def _fetch_page(self, user_id, user_type, page):
|
||||
page += 1
|
||||
info = self._download_json(f'https://bjapi.afreecatv.com/api/{user_id}/vods/{user_type}', user_id,
|
||||
info = self._download_json(f'https://chapi.sooplive.co.kr/api/{user_id}/vods/{user_type}', user_id,
|
||||
query={'page': page, 'per_page': self._PER_PAGE, 'orderby': 'reg_date'},
|
||||
note=f'Downloading {user_type} video page {page}')
|
||||
for item in info['data']:
|
||||
yield self.url_result(
|
||||
f'https://vod.afreecatv.com/player/{item["title_no"]}/', AfreecaTVIE, item['title_no'])
|
||||
f'https://vod.sooplive.co.kr/player/{item["title_no"]}/', AfreecaTVIE, item['title_no'])
|
||||
|
||||
def _real_extract(self, url):
|
||||
user_id, user_type = self._match_valid_url(url).group('id', 'slug_type')
|
||||
|
Reference in New Issue
Block a user