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

Upgrade yt_dlp and download script

Browse Source
This commit is contained in:
itdominator
2025-05-02 16:11:08 -05:00
parent 3a2e8eeb08
commit d68d9ce4f9
1194 changed files with 60099 additions and 44436 deletions
Download Patch File Download Diff File Expand all files Collapse all files

623
plugins/youtube_download/yt_dlp/extractor/niconico.py
View File

@@ -1,48 +1,104 @@
import datetime
import datetime as dt
import functools
import itertools
import json
import re
import time
from urllib.parse import urlparse
import urllib.parse
from .common import InfoExtractor, SearchInfoExtractor
from ..dependencies import websockets
from ..networking import Request
from ..networking.exceptions import HTTPError
from ..utils import (
ExtractorError,
OnDemandPagedList,
WebSocketsWrapper,
bug_reports_message,
clean_html,
determine_ext,
float_or_none,
int_or_none,
join_nonempty,
parse_duration,
parse_filesize,
parse_iso8601,
parse_qs,
parse_resolution,
qualities,
remove_start,
str_or_none,
traverse_obj,
try_get,
unescapeHTML,
unified_timestamp,
update_url_query,
url_basename,
url_or_none,
urlencode_postdata,
urljoin,
)
from ..utils.traversal import find_element, traverse_obj
class NiconicoIE(InfoExtractor):
class NiconicoBaseIE(InfoExtractor):
_GEO_BYPASS = False
_GEO_COUNTRIES = ['JP']
_LOGIN_BASE = 'https://account.nicovideo.jp'
_NETRC_MACHINE = 'niconico'
@property
def is_logged_in(self):
return bool(self._get_cookies('https://www.nicovideo.jp').get('user_session'))
def _raise_login_error(self, message, expected=True):
raise ExtractorError(f'Unable to login: {message}', expected=expected)
def _perform_login(self, username, password):
if self.is_logged_in:
return
self._request_webpage(
f'{self._LOGIN_BASE}/login', None, 'Requesting session cookies')
webpage = self._download_webpage(
f'{self._LOGIN_BASE}/login/redirector', None,
'Logging in', 'Unable to log in', headers={
'Content-Type': 'application/x-www-form-urlencoded',
'Referer': f'{self._LOGIN_BASE}/login',
}, data=urlencode_postdata({
'mail_tel': username,
'password': password,
}))
if self.is_logged_in:
return
elif err_msg := traverse_obj(webpage, (
{find_element(cls='notice error')}, {find_element(cls='notice__text')}, {clean_html},
)):
self._raise_login_error(err_msg or 'Invalid username or password')
elif 'oneTimePw' in webpage:
post_url = self._search_regex(
r'<form[^>]+action=(["\'])(?P<url>.+?)\1', webpage, 'post url', group='url')
mfa, urlh = self._download_webpage_handle(
urljoin(self._LOGIN_BASE, post_url), None,
'Performing MFA', 'Unable to complete MFA', headers={
'Content-Type': 'application/x-www-form-urlencoded',
}, data=urlencode_postdata({
'otp': self._get_tfa_info('6 digit number shown on app'),
}))
if self.is_logged_in:
return
elif 'error-code' in parse_qs(urlh.url):
err_msg = traverse_obj(mfa, ({find_element(cls='pageMainMsg')}, {clean_html}))
self._raise_login_error(err_msg or 'MFA session expired')
elif 'formError' in mfa:
err_msg = traverse_obj(mfa, (
{find_element(cls='formError')}, {find_element(tag='div')}, {clean_html}))
self._raise_login_error(err_msg or 'MFA challenge failed')
self._raise_login_error('Unexpected login error', expected=False)
class NiconicoIE(NiconicoBaseIE):
IE_NAME = 'niconico'
IE_DESC = 'ニコニコ動画'
_TESTS = [{
'url': 'http://www.nicovideo.jp/watch/sm22312215',
'md5': 'd1a75c0823e2f629128c43e1212760f9',
'info_dict': {
'id': 'sm22312215',
'ext': 'mp4',
@@ -56,25 +112,31 @@ class NiconicoIE(InfoExtractor):
'duration': 33,
'view_count': int,
'comment_count': int,
'genres': ['未設定'],
'tags': [],
},
'skip': 'Requires an account',
'params': {'skip_download': 'm3u8'},
}, {
# File downloaded with and without credentials are different, so omit
# the md5 field
'url': 'http://www.nicovideo.jp/watch/nm14296458',
'info_dict': {
'id': 'nm14296458',
'ext': 'swf',
'title': '【鏡音リン】Dance on media【オリジナル】take2!',
'description': 'md5:689f066d74610b3b22e0f1739add0f58',
'ext': 'mp4',
'title': '【Kagamine Rin】Dance on media【Original】take2!',
'description': 'md5:9368f2b1f4178de64f2602c2f3d6cbf5',
'thumbnail': r're:https?://.*',
'uploader': 'りょうた',
'uploader_id': '18822557',
'upload_date': '20110429',
'timestamp': 1304065916,
'duration': 209,
'duration': 208.0,
'comment_count': int,
'view_count': int,
'genres': ['音楽・サウンド'],
'tags': ['Translation_Request', 'Kagamine_Rin', 'Rin_Original'],
},
'skip': 'Requires an account',
'params': {'skip_download': 'm3u8'},
}, {
# 'video exists but is marked as "deleted"
# md5 is unstable
@@ -108,60 +170,61 @@ class NiconicoIE(InfoExtractor):
}, {
# video not available via `getflv`; "old" HTML5 video
'url': 'http://www.nicovideo.jp/watch/sm1151009',
'md5': '8fa81c364eb619d4085354eab075598a',
'info_dict': {
'id': 'sm1151009',
'ext': 'mp4',
'title': 'マスターシステム本体内蔵のスペハリのメインテーマ（ＰＳＧ版）',
'description': 'md5:6ee077e0581ff5019773e2e714cdd0b7',
'description': 'md5:f95a3d259172667b293530cc2e41ebda',
'thumbnail': r're:https?://.*',
'duration': 184,
'timestamp': 1190868283,
'upload_date': '20070927',
'timestamp': 1190835883,
'upload_date': '20070926',
'uploader': 'denden2',
'uploader_id': '1392194',
'view_count': int,
'comment_count': int,
'genres': ['ゲーム'],
'tags': [],
},
'skip': 'Requires an account',
'params': {'skip_download': 'm3u8'},
}, {
# "New" HTML5 video
# md5 is unstable
'url': 'http://www.nicovideo.jp/watch/sm31464864',
'info_dict': {
'id': 'sm31464864',
'ext': 'mp4',
'title': '新作TVアニメ「戦姫絶唱シンフォギアAXZ」PV 最高画質',
'description': 'md5:e52974af9a96e739196b2c1ca72b5feb',
'timestamp': 1498514060,
'timestamp': 1498481660,
'upload_date': '20170626',
'uploader': 'ゲスト',
'uploader': 'no-namamae',
'uploader_id': '40826363',
'thumbnail': r're:https?://.*',
'duration': 198,
'view_count': int,
'comment_count': int,
'genres': ['アニメ'],
'tags': [],
},
'skip': 'Requires an account',
'params': {'skip_download': 'm3u8'},
}, {
# Video without owner
'url': 'http://www.nicovideo.jp/watch/sm18238488',
'md5': 'd265680a1f92bdcbbd2a507fc9e78a9e',
'info_dict': {
'id': 'sm18238488',
'ext': 'mp4',
'title': '【実写版】ミュータントタートルズ',
'description': 'md5:15df8988e47a86f9e978af2064bf6d8e',
'timestamp': 1341160408,
'timestamp': 1341128008,
'upload_date': '20120701',
'uploader': None,
'uploader_id': None,
'thumbnail': r're:https?://.*',
'duration': 5271,
'view_count': int,
'comment_count': int,
'genres': ['エンターテイメント'],
'tags': [],
},
'skip': 'Requires an account',
'params': {'skip_download': 'm3u8'},
}, {
'url': 'http://sp.nicovideo.jp/watch/sm28964488?ss_pos=1&cp_in=wt_tg',
'only_matching': True,
@@ -172,220 +235,53 @@ class NiconicoIE(InfoExtractor):
}]
_VALID_URL = r'https?://(?:(?:www\.|secure\.|sp\.)?nicovideo\.jp/watch|nico\.ms)/(?P<id>(?:[a-z]{2})?[0-9]+)'
_NETRC_MACHINE = 'niconico'
_COMMENT_API_ENDPOINTS = (
'https://nvcomment.nicovideo.jp/legacy/api.json',
'https://nmsg.nicovideo.jp/api.json',)
_API_HEADERS = {
'X-Frontend-ID': '6',
'X-Frontend-Version': '0',
'X-Niconico-Language': 'en-us',
'Referer': 'https://www.nicovideo.jp/',
'Origin': 'https://www.nicovideo.jp',
}
def _perform_login(self, username, password):
login_ok = True
login_form_strs = {
'mail_tel': username,
'password': password,
}
self._request_webpage(
'https://account.nicovideo.jp/login', None,
note='Acquiring Login session')
page = self._download_webpage(
'https://account.nicovideo.jp/login/redirector?show_button_twitter=1&site=niconico&show_button_facebook=1', None,
note='Logging in', errnote='Unable to log in',
data=urlencode_postdata(login_form_strs),
headers={
'Referer': 'https://account.nicovideo.jp/login',
'Content-Type': 'application/x-www-form-urlencoded',
})
if 'oneTimePw' in page:
post_url = self._search_regex(
r'<form[^>]+action=(["\'])(?P<url>.+?)\1', page, 'post url', group='url')
page = self._download_webpage(
urljoin('https://account.nicovideo.jp', post_url), None,
note='Performing MFA', errnote='Unable to complete MFA',
data=urlencode_postdata({
'otp': self._get_tfa_info('6 digits code')
}), headers={
'Content-Type': 'application/x-www-form-urlencoded',
})
if 'oneTimePw' in page or 'formError' in page:
err_msg = self._html_search_regex(
r'formError["\']+>(.*?)</div>', page, 'form_error',
default='There\'s an error but the message can\'t be parsed.',
flags=re.DOTALL)
self.report_warning(f'Unable to log in: MFA challenge failed, "{err_msg}"')
return False
login_ok = 'class="notice error"' not in page
if not login_ok:
self.report_warning('Unable to log in: bad username or password')
return login_ok
def _yield_dms_formats(self, api_data, video_id):
fmt_filter = lambda _, v: v['isAvailable'] and v['id']
videos = traverse_obj(api_data, ('media', 'domand', 'videos', fmt_filter))
audios = traverse_obj(api_data, ('media', 'domand', 'audios', fmt_filter))
access_key = traverse_obj(api_data, ('media', 'domand', 'accessRightKey', {str}))
track_id = traverse_obj(api_data, ('client', 'watchTrackId', {str}))
if not all((videos, audios, access_key, track_id)):
return
def _get_heartbeat_info(self, info_dict):
video_id, video_src_id, audio_src_id = info_dict['url'].split(':')[1].split('/')
dmc_protocol = info_dict['expected_protocol']
api_data = (
info_dict.get('_api_data')
or self._parse_json(
self._html_search_regex(
'data-api-data="([^"]+)"',
self._download_webpage('https://www.nicovideo.jp/watch/' + video_id, video_id),
'API data', default='{}'),
video_id))
session_api_data = try_get(api_data, lambda x: x['media']['delivery']['movie']['session'])
session_api_endpoint = try_get(session_api_data, lambda x: x['urls'][0])
def ping():
tracking_id = traverse_obj(api_data, ('media', 'delivery', 'trackingId'))
if tracking_id:
tracking_url = update_url_query('https://nvapi.nicovideo.jp/v1/2ab0cbaa/watch', {'t': tracking_id})
watch_request_response = self._download_json(
tracking_url, video_id,
note='Acquiring permission for downloading video', fatal=False,
headers=self._API_HEADERS)
if traverse_obj(watch_request_response, ('meta', 'status')) != 200:
self.report_warning('Failed to acquire permission for playing video. Video download may fail.')
yesno = lambda x: 'yes' if x else 'no'
if dmc_protocol == 'http':
protocol = 'http'
protocol_parameters = {
'http_output_download_parameters': {
'use_ssl': yesno(session_api_data['urls'][0]['isSsl']),
'use_well_known_port': yesno(session_api_data['urls'][0]['isWellKnownPort']),
}
}
elif dmc_protocol == 'hls':
protocol = 'm3u8'
segment_duration = try_get(self._configuration_arg('segment_duration'), lambda x: int(x[0])) or 6000
parsed_token = self._parse_json(session_api_data['token'], video_id)
encryption = traverse_obj(api_data, ('media', 'delivery', 'encryption'))
protocol_parameters = {
'hls_parameters': {
'segment_duration': segment_duration,
'transfer_preset': '',
'use_ssl': yesno(session_api_data['urls'][0]['isSsl']),
'use_well_known_port': yesno(session_api_data['urls'][0]['isWellKnownPort']),
}
}
if 'hls_encryption' in parsed_token and encryption:
protocol_parameters['hls_parameters']['encryption'] = {
parsed_token['hls_encryption']: {
'encrypted_key': encryption['encryptedKey'],
'key_uri': encryption['keyUri'],
}
}
else:
protocol = 'm3u8_native'
else:
raise ExtractorError(f'Unsupported DMC protocol: {dmc_protocol}')
session_response = self._download_json(
session_api_endpoint['url'], video_id,
query={'_format': 'json'},
headers={'Content-Type': 'application/json'},
note='Downloading JSON metadata for %s' % info_dict['format_id'],
dms_m3u8_url = self._download_json(
f'https://nvapi.nicovideo.jp/v1/watch/{video_id}/access-rights/hls', video_id,
data=json.dumps({
'session': {
'client_info': {
'player_id': session_api_data.get('playerId'),
},
'content_auth': {
'auth_type': try_get(session_api_data, lambda x: x['authTypes'][session_api_data['protocols'][0]]),
'content_key_timeout': session_api_data.get('contentKeyTimeout'),
'service_id': 'nicovideo',
'service_user_id': session_api_data.get('serviceUserId')
},
'content_id': session_api_data.get('contentId'),
'content_src_id_sets': [{
'content_src_ids': [{
'src_id_to_mux': {
'audio_src_ids': [audio_src_id],
'video_src_ids': [video_src_id],
}
}]
}],
'content_type': 'movie',
'content_uri': '',
'keep_method': {
'heartbeat': {
'lifetime': session_api_data.get('heartbeatLifetime')
}
},
'priority': session_api_data['priority'],
'protocol': {
'name': 'http',
'parameters': {
'http_parameters': {
'parameters': protocol_parameters
}
}
},
'recipe_id': session_api_data.get('recipeId'),
'session_operation_auth': {
'session_operation_auth_by_signature': {
'signature': session_api_data.get('signature'),
'token': session_api_data.get('token'),
}
},
'timing_constraint': 'unlimited'
}
}).encode())
'outputs': list(itertools.product((v['id'] for v in videos), (a['id'] for a in audios))),
}).encode(), query={'actionTrackId': track_id}, headers={
'x-access-right-key': access_key,
'x-frontend-id': 6,
'x-frontend-version': 0,
'x-request-with': 'https://www.nicovideo.jp',
})['data']['contentUrl']
# Getting all audio formats results in duplicate video formats which we filter out later
dms_fmts = self._extract_m3u8_formats(dms_m3u8_url, video_id, 'mp4')
info_dict['url'] = session_response['data']['session']['content_uri']
info_dict['protocol'] = protocol
# get heartbeat info
heartbeat_info_dict = {
'url': session_api_endpoint['url'] + '/' + session_response['data']['session']['id'] + '?_format=json&_method=PUT',
'data': json.dumps(session_response['data']),
# interval, convert milliseconds to seconds, then halve to make a buffer.
'interval': float_or_none(session_api_data.get('heartbeatLifetime'), scale=3000),
'ping': ping
}
return info_dict, heartbeat_info_dict
def _extract_format_for_quality(self, video_id, audio_quality, video_quality, dmc_protocol):
if not audio_quality.get('isAvailable') or not video_quality.get('isAvailable'):
return None
def extract_video_quality(video_quality):
return parse_filesize('%sB' % self._search_regex(
r'\| ([0-9]*\.?[0-9]*[MK])', video_quality, 'vbr', default=''))
format_id = '-'.join(
[remove_start(s['id'], 'archive_') for s in (video_quality, audio_quality)] + [dmc_protocol])
vid_qual_label = traverse_obj(video_quality, ('metadata', 'label'))
vid_quality = traverse_obj(video_quality, ('metadata', 'bitrate'))
return {
'url': 'niconico_dmc:%s/%s/%s' % (video_id, video_quality['id'], audio_quality['id']),
'format_id': format_id,
'format_note': join_nonempty('DMC', vid_qual_label, dmc_protocol.upper(), delim=' '),
'ext': 'mp4', # Session API are used in HTML5, which always serves mp4
'acodec': 'aac',
'vcodec': 'h264',
'abr': float_or_none(traverse_obj(audio_quality, ('metadata', 'bitrate')), 1000),
'vbr': float_or_none(vid_quality if vid_quality > 0 else extract_video_quality(vid_qual_label), 1000),
'height': traverse_obj(video_quality, ('metadata', 'resolution', 'height')),
'width': traverse_obj(video_quality, ('metadata', 'resolution', 'width')),
'quality': -2 if 'low' in video_quality['id'] else None,
'protocol': 'niconico_dmc',
'expected_protocol': dmc_protocol, # XXX: This is not a documented field
'http_headers': {
'Origin': 'https://www.nicovideo.jp',
'Referer': 'https://www.nicovideo.jp/watch/' + video_id,
# m3u8 extraction does not provide audio bitrates, so extract from the API data and fix
for audio_fmt in traverse_obj(dms_fmts, lambda _, v: v['vcodec'] == 'none'):
yield {
**audio_fmt,
**traverse_obj(audios, (lambda _, v: audio_fmt['format_id'].startswith(v['id']), {
'format_id': ('id', {str}),
'abr': ('bitRate', {float_or_none(scale=1000)}),
'asr': ('samplingRate', {int_or_none}),
'quality': ('qualityLevel', {int_or_none}),
}), get_all=False),
'acodec': 'aac',
}
}
# Sort before removing dupes to keep the format dicts with the lowest tbr
video_fmts = sorted((fmt for fmt in dms_fmts if fmt['vcodec'] != 'none'), key=lambda f: f['tbr'])
self._remove_duplicate_formats(video_fmts)
# Calculate the true vbr/tbr by subtracting the lowest abr
min_abr = min(traverse_obj(audios, (..., 'bitRate', {float_or_none})), default=0) / 1000
for video_fmt in video_fmts:
video_fmt['tbr'] -= min_abr
video_fmt['format_id'] = url_basename(video_fmt['url']).rpartition('.')[0]
video_fmt['quality'] = traverse_obj(videos, (
lambda _, v: v['id'] == video_fmt['format_id'], 'qualityLevel', {int_or_none}, any)) or -1
yield video_fmt
def _real_extract(self, url):
video_id = self._match_id(url)
@@ -396,13 +292,15 @@ class NiconicoIE(InfoExtractor):
if video_id.startswith('so'):
video_id = self._match_id(handle.url)
api_data = self._parse_json(self._html_search_regex(
'data-api-data="([^"]+)"', webpage,
'API data', default='{}'), video_id)
api_data = traverse_obj(
self._parse_json(self._html_search_meta('server-response', webpage) or '', video_id),
('data', 'response', {dict}))
if not api_data:
raise ExtractorError('Server response data not found')
except ExtractorError as e:
try:
api_data = self._download_json(
'https://www.nicovideo.jp/api/watch/v3/%s?_frontendId=6&_frontendVersion=0&actionTrackId=AAAAAAAAAA_%d' % (video_id, round(time.time() * 1000)), video_id,
f'https://www.nicovideo.jp/api/watch/v3/{video_id}?_frontendId=6&_frontendVersion=0&actionTrackId=AAAAAAAAAA_{round(time.time() * 1000)}', video_id,
note='Downloading API JSON', errnote='Unable to fetch data')['data']
except ExtractorError:
if not isinstance(e.cause, HTTPError):
@@ -413,19 +311,29 @@ class NiconicoIE(InfoExtractor):
webpage, 'error reason', default=None)
if not error_msg:
raise
raise ExtractorError(re.sub(r'\s+', ' ', error_msg), expected=True)
raise ExtractorError(clean_html(error_msg), expected=True)
formats = []
availability = self._availability(**(traverse_obj(api_data, ('payment', 'video', {
'needs_premium': ('isPremium', {bool}),
'needs_subscription': ('isAdmission', {bool}),
})) or {'needs_auth': True}))
def get_video_info(*items, get_first=True, **kwargs):
return traverse_obj(api_data, ('video', *items), get_all=not get_first, **kwargs)
quality_info = api_data['media']['delivery']['movie']
session_api_data = quality_info['session']
for (audio_quality, video_quality, protocol) in itertools.product(quality_info['audios'], quality_info['videos'], session_api_data['protocols']):
fmt = self._extract_format_for_quality(video_id, audio_quality, video_quality, protocol)
if fmt:
formats.append(fmt)
formats = list(self._yield_dms_formats(api_data, video_id))
if not formats:
fail_msg = clean_html(self._html_search_regex(
r'<p[^>]+\bclass="fail-message"[^>]*>(?P<msg>.+?)</p>',
webpage, 'fail message', default=None, group='msg'))
if fail_msg:
self.to_screen(f'Niconico said: {fail_msg}')
if fail_msg and 'された地域と同じ地域からのみ視聴できます。' in fail_msg:
availability = None
self.raise_geo_restricted(countries=self._GEO_COUNTRIES, metadata_available=True)
elif availability == 'premium_only':
self.raise_login_required('This video requires premium', metadata_available=True)
elif availability == 'subscriber_only':
self.raise_login_required('This video is for members only', metadata_available=True)
elif availability == 'needs_auth':
self.raise_login_required(metadata_available=False)
# Start extracting information
tags = None
@@ -444,11 +352,15 @@ class NiconicoIE(InfoExtractor):
thumb_prefs = qualities(['url', 'middleUrl', 'largeUrl', 'player', 'ogp'])
def get_video_info(*items, get_first=True, **kwargs):
return traverse_obj(api_data, ('video', *items), get_all=not get_first, **kwargs)
return {
'id': video_id,
'_api_data': api_data,
'title': get_video_info(('originalTitle', 'title')) or self._og_search_title(webpage, default=None),
'formats': formats,
'availability': availability,
'thumbnails': [{
'id': key,
'url': url,
@@ -471,93 +383,19 @@ class NiconicoIE(InfoExtractor):
parse_duration(self._html_search_meta('video:duration', webpage, 'video duration', default=None))
or get_video_info('duration')),
'webpage_url': url_or_none(url) or f'https://www.nicovideo.jp/watch/{video_id}',
'subtitles': self.extract_subtitles(video_id, api_data, session_api_data),
'subtitles': self.extract_subtitles(video_id, api_data),
}
def _get_subtitles(self, video_id, api_data, session_api_data):
comment_user_key = traverse_obj(api_data, ('comment', 'keys', 'userKey'))
user_id_str = session_api_data.get('serviceUserId')
thread_ids = traverse_obj(api_data, ('comment', 'threads', lambda _, v: v['isActive']))
legacy_danmaku = self._extract_legacy_comments(video_id, thread_ids, user_id_str, comment_user_key) or []
new_comments = traverse_obj(api_data, ('comment', 'nvComment'))
new_danmaku = self._extract_new_comments(
new_comments.get('server'), video_id,
new_comments.get('params'), new_comments.get('threadKey'))
if not legacy_danmaku and not new_danmaku:
self.report_warning(f'Failed to get comments. {bug_reports_message()}')
def _get_subtitles(self, video_id, api_data):
comments_info = traverse_obj(api_data, ('comment', 'nvComment', {dict})) or {}
if not comments_info.get('server'):
return
return {
'comments': [{
'ext': 'json',
'data': json.dumps(legacy_danmaku + new_danmaku),
}],
}
def _extract_legacy_comments(self, video_id, threads, user_id, user_key):
auth_data = {
'user_id': user_id,
'userkey': user_key,
} if user_id and user_key else {'user_id': ''}
api_url = traverse_obj(threads, (..., 'server'), get_all=False)
# Request Start
post_data = [{'ping': {'content': 'rs:0'}}]
for i, thread in enumerate(threads):
thread_id = thread['id']
thread_fork = thread['fork']
# Post Start (2N)
post_data.append({'ping': {'content': f'ps:{i * 2}'}})
post_data.append({'thread': {
'fork': thread_fork,
'language': 0,
'nicoru': 3,
'scores': 1,
'thread': thread_id,
'version': '20090904',
'with_global': 1,
**auth_data,
}})
# Post Final (2N)
post_data.append({'ping': {'content': f'pf:{i * 2}'}})
# Post Start (2N+1)
post_data.append({'ping': {'content': f'ps:{i * 2 + 1}'}})
post_data.append({'thread_leaves': {
# format is '<bottom of minute range>-<top of minute range>:<comments per minute>,<total last comments'
# unfortunately NND limits (deletes?) comment returns this way, so you're only able to grab the last 1000 per language
'content': '0-999999:999999,999999,nicoru:999999',
'fork': thread_fork,
'language': 0,
'nicoru': 3,
'scores': 1,
'thread': thread_id,
**auth_data,
}})
# Post Final (2N+1)
post_data.append({'ping': {'content': f'pf:{i * 2 + 1}'}})
# Request Final
post_data.append({'ping': {'content': 'rf:0'}})
return self._download_json(
f'{api_url}/api.json', video_id, data=json.dumps(post_data).encode(), fatal=False,
headers={
'Referer': f'https://www.nicovideo.jp/watch/{video_id}',
'Origin': 'https://www.nicovideo.jp',
'Content-Type': 'text/plain;charset=UTF-8',
},
note='Downloading comments', errnote=f'Failed to access endpoint {api_url}')
def _extract_new_comments(self, endpoint, video_id, params, thread_key):
comments = self._download_json(
f'{endpoint}/v1/threads', video_id, data=json.dumps({
danmaku = traverse_obj(self._download_json(
f'{comments_info["server"]}/v1/threads', video_id, data=json.dumps({
'additionals': {},
'params': params,
'threadKey': thread_key,
'params': comments_info.get('params'),
'threadKey': comments_info.get('threadKey'),
}).encode(), fatal=False,
headers={
'Referer': 'https://www.nicovideo.jp/',
@@ -567,8 +405,15 @@ class NiconicoIE(InfoExtractor):
'x-frontend-id': '6',
'x-frontend-version': '0',
},
note='Downloading comments (new)', errnote='Failed to download comments (new)')
return traverse_obj(comments, ('data', 'threads', ..., 'comments', ...))
note='Downloading comments', errnote='Failed to download comments'),
('data', 'threads', ..., 'comments', ...))
return {
'comments': [{
'ext': 'json',
'data': json.dumps(danmaku),
}],
}
class NiconicoPlaylistBaseIE(InfoExtractor):
@@ -577,7 +422,7 @@ class NiconicoPlaylistBaseIE(InfoExtractor):
_API_HEADERS = {
'X-Frontend-ID': '6',
'X-Frontend-Version': '0',
'X-Niconico-Language': 'en-us'
'X-Niconico-Language': 'en-us',
}
def _call_api(self, list_id, resource, query):
@@ -586,13 +431,13 @@ class NiconicoPlaylistBaseIE(InfoExtractor):
@staticmethod
def _parse_owner(item):
return {
'uploader': traverse_obj(item, ('owner', 'name')),
'uploader_id': traverse_obj(item, ('owner', 'id')),
'uploader': traverse_obj(item, ('owner', ('name', ('user', 'nickname')), {str}, any)),
'uploader_id': traverse_obj(item, ('owner', 'id', {str})),
}
def _fetch_page(self, list_id, page):
page += 1
resp = self._call_api(list_id, 'page %d' % page, {
resp = self._call_api(list_id, f'page {page}', {
'page': page,
'pageSize': self._PAGE_SIZE,
})
@@ -660,7 +505,7 @@ class NiconicoPlaylistIE(NiconicoPlaylistBaseIE):
mylist.get('name'), mylist.get('description'), **self._parse_owner(mylist))
class NiconicoSeriesIE(InfoExtractor):
class NiconicoSeriesIE(NiconicoPlaylistBaseIE):
IE_NAME = 'niconico:series'
_VALID_URL = r'https?://(?:(?:www\.|sp\.)?nicovideo\.jp(?:/user/\d+)?|nico\.ms)/series/(?P<id>\d+)'
@@ -669,6 +514,9 @@ class NiconicoSeriesIE(InfoExtractor):
'info_dict': {
'id': '110226',
'title': 'ご立派ァ！のシリーズ',
'description': '楽しそうな外人の吹き替えをさせたら終身名誉ホモガキの右に出る人はいませんね…',
'uploader': 'アルファるふぁ',
'uploader_id': '44113208',
},
'playlist_mincount': 10,
}, {
@@ -676,6 +524,9 @@ class NiconicoSeriesIE(InfoExtractor):
'info_dict': {
'id': '12312',
'title': 'バトルスピリッツ　お勧めカード紹介(調整中)',
'description': '',
'uploader': '野鳥',
'uploader_id': '2275360',
},
'playlist_mincount': 103,
}, {
@@ -683,19 +534,21 @@ class NiconicoSeriesIE(InfoExtractor):
'only_matching': True,
}]
def _call_api(self, list_id, resource, query):
return self._download_json(
f'https://nvapi.nicovideo.jp/v2/series/{list_id}', list_id,
f'Downloading {resource}', query=query,
headers=self._API_HEADERS)['data']
def _real_extract(self, url):
list_id = self._match_id(url)
webpage = self._download_webpage(url, list_id)
series = self._call_api(list_id, 'list', {
'pageSize': 1,
})['detail']
title = self._search_regex(
(r'<title>「(.+)（全',
r'<div class="TwitterShareButton"\s+data-text="(.+)\s+https:'),
webpage, 'title', fatal=False)
if title:
title = unescapeHTML(title)
json_data = next(self._yield_json_ld(webpage, None, fatal=False))
return self.playlist_from_matches(
traverse_obj(json_data, ('itemListElement', ..., 'url')), list_id, title, ie=NiconicoIE)
return self.playlist_result(
self._entries(list_id), list_id,
series.get('title'), series.get('description'), **self._parse_owner(series))
class NiconicoHistoryIE(NiconicoPlaylistBaseIE):
@@ -780,14 +633,14 @@ class NicovideoSearchURLIE(NicovideoSearchBaseIE):
'url': 'http://www.nicovideo.jp/search/sm9',
'info_dict': {
'id': 'sm9',
'title': 'sm9'
'title': 'sm9',
},
'playlist_mincount': 40,
}, {
'url': 'https://www.nicovideo.jp/search/sm9?sort=h&order=d&end=2020-12-31&start=2020-01-01',
'info_dict': {
'id': 'sm9',
'title': 'sm9'
'title': 'sm9',
},
'playlist_count': 31,
}]
@@ -805,17 +658,17 @@ class NicovideoSearchDateIE(NicovideoSearchBaseIE, SearchInfoExtractor):
'url': 'nicosearchdateall:a',
'info_dict': {
'id': 'a',
'title': 'a'
'title': 'a',
},
'playlist_mincount': 1610,
}]
_START_DATE = datetime.date(2007, 1, 1)
_START_DATE = dt.date(2007, 1, 1)
_RESULTS_PER_PAGE = 32
_MAX_PAGES = 50
def _entries(self, url, item_id, start_date=None, end_date=None):
start_date, end_date = start_date or self._START_DATE, end_date or datetime.datetime.now().date()
start_date, end_date = start_date or self._START_DATE, end_date or dt.datetime.now().date()
# If the last page has a full page of videos, we need to break down the query interval further
last_page_len = len(list(self._get_entries_for_date(
@@ -852,7 +705,7 @@ class NicovideoTagURLIE(NicovideoSearchBaseIE):
'url': 'https://www.nicovideo.jp/tag/ドキュメンタリー淫夢',
'info_dict': {
'id': 'ドキュメンタリー淫夢',
'title': 'ドキュメンタリー淫夢'
'title': 'ドキュメンタリー淫夢',
},
'playlist_mincount': 400,
}]
@@ -863,7 +716,7 @@ class NicovideoTagURLIE(NicovideoSearchBaseIE):
class NiconicoUserIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?nicovideo\.jp/user/(?P<id>\d+)/?(?:$|[#?])'
_VALID_URL = r'https?://(?:www\.)?nicovideo\.jp/user/(?P<id>\d+)(?:/video)?/?(?:$|[#?])'
_TEST = {
'url': 'https://www.nicovideo.jp/user/419948',
'info_dict': {
@@ -871,12 +724,12 @@ class NiconicoUserIE(InfoExtractor):
},
'playlist_mincount': 101,
}
_API_URL = "https://nvapi.nicovideo.jp/v1/users/%s/videos?sortKey=registeredAt&sortOrder=desc&pageSize=%s&page=%s"
_API_URL = 'https://nvapi.nicovideo.jp/v2/users/%s/videos?sortKey=registeredAt&sortOrder=desc&pageSize=%s&page=%s'
_PAGE_SIZE = 100
_API_HEADERS = {
'X-Frontend-ID': '6',
'X-Frontend-Version': '0'
'X-Frontend-Version': '0',
}
def _entries(self, list_id):
@@ -886,20 +739,21 @@ class NiconicoUserIE(InfoExtractor):
json_parsed = self._download_json(
self._API_URL % (list_id, self._PAGE_SIZE, page_num + 1), list_id,
headers=self._API_HEADERS,
note='Downloading JSON metadata%s' % (' page %d' % page_num if page_num else ''))
note='Downloading JSON metadata%s' % (f' page {page_num}' if page_num else ''))
if not page_num:
total_count = int_or_none(json_parsed['data'].get('totalCount'))
for entry in json_parsed["data"]["items"]:
for entry in json_parsed['data']['items']:
count += 1
yield self.url_result('https://www.nicovideo.jp/watch/%s' % entry['id'])
yield self.url_result(
f'https://www.nicovideo.jp/watch/{entry["essential"]["id"]}', ie=NiconicoIE)
page_num += 1
def _real_extract(self, url):
list_id = self._match_id(url)
return self.playlist_result(self._entries(list_id), list_id, ie=NiconicoIE.ie_key())
return self.playlist_result(self._entries(list_id), list_id)
class NiconicoLiveIE(InfoExtractor):
class NiconicoLiveIE(NiconicoBaseIE):
IE_NAME = 'niconico:live'
IE_DESC = 'ニコニコ生放送'
_VALID_URL = r'https?://(?:sp\.)?live2?\.nicovideo\.jp/(?:watch|gate)/(?P<id>lv\d+)'
@@ -908,7 +762,7 @@ class NiconicoLiveIE(InfoExtractor):
'url': 'https://live.nicovideo.jp/watch/lv339533123',
'info_dict': {
'id': 'lv339533123',
'title': '激辛ペヤング食べます‪( ;ᯅ; )‬（歌枠オーディション参加中）',
'title': '激辛ペヤング食べます\u202a( ;ᯅ; )\u202c（歌枠オーディション参加中）',
'view_count': 1526,
'comment_count': 1772,
'description': '初めましてもかって言います❕\nのんびり自由に適当に暮らしてます',
@@ -934,8 +788,6 @@ class NiconicoLiveIE(InfoExtractor):
_KNOWN_LATENCY = ('high', 'low')
def _real_extract(self, url):
if not websockets:
raise ExtractorError('websockets library is not available. Please install it.', expected=True)
video_id = self._match_id(url)
webpage, urlh = self._download_webpage_handle(f'https://live.nicovideo.jp/watch/{video_id}', video_id)
@@ -949,18 +801,14 @@ class NiconicoLiveIE(InfoExtractor):
'frontend_id': traverse_obj(embedded_data, ('site', 'frontendId')) or '9',
})
hostname = remove_start(urlparse(urlh.url).hostname, 'sp.')
cookies = try_get(urlh.url, self._downloader._calc_cookies)
hostname = remove_start(urllib.parse.urlparse(urlh.url).hostname, 'sp.')
latency = try_get(self._configuration_arg('latency'), lambda x: x[0])
if latency not in self._KNOWN_LATENCY:
latency = 'high'
ws = WebSocketsWrapper(ws_url, {
'Cookies': str_or_none(cookies) or '',
'Origin': f'https://{hostname}',
'Accept': '*/*',
'User-Agent': self.get_param('http_headers')['User-Agent'],
})
ws = self._request_webpage(
Request(ws_url, headers={'Origin': f'https://{hostname}'}),
video_id=video_id, note='Connecting to WebSocket server')
self.write_debug('[debug] Sending HLS server request')
ws.send(json.dumps({
@@ -970,14 +818,15 @@ class NiconicoLiveIE(InfoExtractor):
'quality': 'abr',
'protocol': 'hls+fmp4',
'latency': latency,
'chasePlay': False
'accessRightMethod': 'single_cookie',
'chasePlay': False,
},
'room': {
'protocol': 'webSocket',
'commentable': True
'commentable': True,
},
'reconnect': False,
}
},
}))
while True:
@@ -990,6 +839,7 @@ class NiconicoLiveIE(InfoExtractor):
if data.get('type') == 'stream':
m3u8_url = data['data']['uri']
qualities = data['data']['availableQualities']
cookies = data['data']['cookies']
break
elif data.get('type') == 'disconnect':
self.write_debug(recv)
@@ -1001,7 +851,7 @@ class NiconicoLiveIE(InfoExtractor):
elif self.get_param('verbose', False):
if len(recv) > 100:
recv = recv[:100] + '...'
self.write_debug('Server said: %s' % recv)
self.write_debug(f'Server said: {recv}')
title = traverse_obj(embedded_data, ('program', 'title')) or self._html_search_meta(
('og:title', 'twitter:title'), webpage, 'live title', fatal=False)
@@ -1024,9 +874,15 @@ class NiconicoLiveIE(InfoExtractor):
thumbnails.append({
'id': f'{name}_{width}x{height}',
'url': img_url,
'ext': traverse_obj(parse_qs(img_url), ('image', 0, {determine_ext(default_ext='jpg')})),
**res,
})
for cookie in cookies:
self._set_cookie(
cookie['domain'], cookie['name'], cookie['value'],
expire_time=unified_timestamp(cookie['expires']), path=cookie['path'], secure=cookie['secure'])
formats = self._extract_m3u8_formats(m3u8_url, video_id, ext='mp4', live=True)
for fmt, q in zip(formats, reversed(qualities[1:])):
fmt.update({
@@ -1034,7 +890,6 @@ class NiconicoLiveIE(InfoExtractor):
'protocol': 'niconico_live',
'ws': ws,
'video_id': video_id,
'cookies': cookies,
'live_latency': latency,
'origin': hostname,
})