mirrors/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2026-01-01 04:21:25 +00:00
Code Issues Projects Releases Wiki Activity

Merge branch 'extractor-cablecasttv' of github.com:EGA-SUPREMO/yt-dlp into extractor-cablecasttv

Browse Source
This commit is contained in:
EGA-SUPREMO
2024-05-19 16:38:14 -04:00
parent c640231330 c61f86c641
commit b93cee03ee
57 changed files with 1879 additions and 1425 deletions
Download Patch File Download Diff File Expand all files Collapse all files

15
yt_dlp/extractor/_extractors.py
View File

@@ -387,7 +387,11 @@ from .comedycentral import (
ComedyCentralIE,
ComedyCentralTVIE,
)
from .commonmistakes import CommonMistakesIE, UnicodeBOMIE
from .commonmistakes import (
BlobIE,
CommonMistakesIE,
UnicodeBOMIE,
)
from .commonprotocols import (
MmsIE,
RtmpIE,
@@ -544,7 +548,6 @@ from .egghead import (
EggheadLessonIE,
)
from .eighttracks import EightTracksIE
from .einthusan import EinthusanIE
from .eitb import EitbIE
from .elementorembed import ElementorEmbedIE
from .elonet import ElonetIE
@@ -857,10 +860,6 @@ from .iwara import (
)
from .ixigua import IxiguaIE
from .izlesene import IzleseneIE
from .jable import (
JableIE,
JablePlaylistIE,
)
from .jamendo import (
JamendoIE,
JamendoAlbumIE,
@@ -1495,7 +1494,6 @@ from .polskieradio import (
)
from .popcorntimes import PopcorntimesIE
from .popcorntv import PopcornTVIE
from .porn91 import Porn91IE
from .pornbox import PornboxIE
from .pornflip import PornFlipIE
from .pornhub import (
@@ -2373,7 +2371,6 @@ from .wykop import (
)
from .xanimu import XanimuIE
from .xboxclips import XboxClipsIE
from .xfileshare import XFileShareIE
from .xhamster import (
XHamsterIE,
XHamsterEmbedIE,
@@ -2428,8 +2425,6 @@ from .younow import (
YouNowMomentIE,
)
from .youporn import YouPornIE
from .yourporn import YourPornIE
from .yourupload import YourUploadIE
from .zaiko import (
ZaikoIE,
ZaikoETicketIE,

4
yt_dlp/extractor/alura.py
View File

@@ -39,7 +39,7 @@ class AluraIE(InfoExtractor):
def _real_extract(self, url):
course, video_id = self._match_valid_url(url)
course, video_id = self._match_valid_url(url).group('course_name', 'id')
video_url = self._VIDEO_URL % (course, video_id)
video_dict = self._download_json(video_url, video_id, 'Searching for videos')
@@ -52,7 +52,7 @@ class AluraIE(InfoExtractor):
formats = []
for video_obj in video_dict:
video_url_m3u8 = video_obj.get('link')
video_url_m3u8 = video_obj.get('mp4')
video_format = self._extract_m3u8_formats(
video_url_m3u8, None, 'mp4', entry_protocol='m3u8_native',
m3u8_id='hls', fatal=False)

438
yt_dlp/extractor/bbc.py
View File

@@ -602,7 +602,7 @@ class BBCIE(BBCCoUkIE): # XXX: Do not subclass from concrete IE
'url': 'http://www.bbc.com/news/world-europe-32668511',
'info_dict': {
'id': 'world-europe-32668511',
'title': 'Russia stages massive WW2 parade',
'title': 'Russia stages massive WW2 parade despite Western boycott',
'description': 'md5:00ff61976f6081841f759a08bf78cc9c',
},
'playlist_count': 2,
@@ -623,6 +623,7 @@ class BBCIE(BBCCoUkIE): # XXX: Do not subclass from concrete IE
'info_dict': {
'id': '3662a707-0af9-3149-963f-47bea720b460',
'title': 'BUGGER',
'description': r're:BUGGER The recent revelations by the whistleblower Edward Snowden were fascinating. .{211}\.{3}$',
},
'playlist_count': 18,
}, {
@@ -631,14 +632,14 @@ class BBCIE(BBCCoUkIE): # XXX: Do not subclass from concrete IE
'info_dict': {
'id': 'p02mprgb',
'ext': 'mp4',
'title': 'Aerial footage showed the site of the crash in the Alps - courtesy BFM TV',
'description': 'md5:2868290467291b37feda7863f7a83f54',
'title': 'Germanwings crash site aerial video',
'description': r're:(?s)Aerial video showed the site where the Germanwings flight 4U 9525, .{156} BFM TV\.$',
'duration': 47,
'timestamp': 1427219242,
'upload_date': '20150324',
'thumbnail': 'https://ichef.bbci.co.uk/news/1024/media/images/81879000/jpg/_81879090_81879089.jpg',
},
'params': {
# rtmp download
'skip_download': True,
}
}, {
@@ -656,21 +657,24 @@ class BBCIE(BBCCoUkIE): # XXX: Do not subclass from concrete IE
},
'params': {
'skip_download': True,
}
},
'skip': 'now SIMORGH_DATA with no video',
}, {
# single video embedded with data-playable containing XML playlists (regional section)
'url': 'http://www.bbc.com/mundo/video_fotos/2015/06/150619_video_honduras_militares_hospitales_corrupcion_aw',
'info_dict': {
'id': '150619_video_honduras_militares_hospitales_corrupcion_aw',
'id': '39275083',
'display_id': '150619_video_honduras_militares_hospitales_corrupcion_aw',
'ext': 'mp4',
'title': 'Honduras militariza sus hospitales por nuevo escándalo de corrupción',
'description': 'md5:1525f17448c4ee262b64b8f0c9ce66c8',
'description': 'Honduras militariza sus hospitales por nuevo escándalo de corrupción',
'timestamp': 1434713142,
'upload_date': '20150619',
'thumbnail': 'https://a.files.bbci.co.uk/worldservice/live/assets/images/2015/06/19/150619132146_honduras_hsopitales_militares_640x360_aptn_nocredit.jpg',
},
'params': {
'skip_download': True,
}
},
}, {
# single video from video playlist embedded with vxp-playlist-data JSON
'url': 'http://www.bbc.com/news/video_and_audio/must_see/33376376',
@@ -683,22 +687,21 @@ class BBCIE(BBCCoUkIE): # XXX: Do not subclass from concrete IE
},
'params': {
'skip_download': True,
}
},
'skip': '404 Not Found',
}, {
# single video story with digitalData
# single video story with __PWA_PRELOADED_STATE__
'url': 'http://www.bbc.com/travel/story/20150625-sri-lankas-spicy-secret',
'info_dict': {
'id': 'p02q6gc4',
'ext': 'flv',
'title': 'Sri Lanka’s spicy secret',
'description': 'As a new train line to Jaffna opens up the country’s north, travellers can experience a truly distinct slice of Tamil culture.',
'timestamp': 1437674293,
'upload_date': '20150723',
'ext': 'mp4',
'title': 'Tasting the spice of life in Jaffna',
'description': r're:(?s)BBC Travel Show’s Henry Golding explores the city of Jaffna .{151} aftertaste\.$',
'timestamp': 1646058397,
'upload_date': '20220228',
'duration': 255,
'thumbnail': 'https://ichef.bbci.co.uk/images/ic/1920xn/p02vxvkn.jpg',
},
'params': {
# rtmp download
'skip_download': True,
}
}, {
# single video story without digitalData
'url': 'http://www.bbc.com/autos/story/20130513-hyundais-rock-star',
@@ -710,12 +713,10 @@ class BBCIE(BBCCoUkIE): # XXX: Do not subclass from concrete IE
'timestamp': 1415867444,
'upload_date': '20141113',
},
'params': {
# rtmp download
'skip_download': True,
}
'skip': 'redirects to TopGear home page',
}, {
# single video embedded with Morph
# TODO: replacement test page
'url': 'http://www.bbc.co.uk/sport/live/olympics/36895975',
'info_dict': {
'id': 'p041vhd0',
@@ -726,27 +727,22 @@ class BBCIE(BBCCoUkIE): # XXX: Do not subclass from concrete IE
'uploader': 'BBC Sport',
'uploader_id': 'bbc_sport',
},
'params': {
# m3u8 download
'skip_download': True,
},
'skip': 'Georestricted to UK',
'skip': 'Video no longer in page',
}, {
# single video with playlist.sxml URL in playlist param
# single video in __INITIAL_DATA__
'url': 'http://www.bbc.com/sport/0/football/33653409',
'info_dict': {
'id': 'p02xycnp',
'ext': 'mp4',
'title': 'Transfers: Cristiano Ronaldo to Man Utd, Arsenal to spend?',
'description': 'BBC Sport\'s David Ornstein has the latest transfer gossip, including rumours of a Manchester United return for Cristiano Ronaldo.',
'title': 'Ronaldo to Man Utd, Arsenal to spend?',
'description': r're:(?s)BBC Sport\'s David Ornstein rounds up the latest transfer reports, .{359} here\.$',
'timestamp': 1437750175,
'upload_date': '20150724',
'thumbnail': r're:https?://.+/.+media/images/69320000/png/_69320754_mmgossipcolumnextraaugust18.png',
'duration': 140,
},
'params': {
# rtmp download
'skip_download': True,
}
}, {
# article with multiple videos embedded with playlist.sxml in playlist param
# article with multiple videos embedded with Morph.setPayload
'url': 'http://www.bbc.com/sport/0/football/34475836',
'info_dict': {
'id': '34475836',
@@ -754,6 +750,21 @@ class BBCIE(BBCCoUkIE): # XXX: Do not subclass from concrete IE
'description': 'Fast-paced football, wit, wisdom and a ready smile - why Liverpool fans should come to love new boss Jurgen Klopp.',
},
'playlist_count': 3,
}, {
# Testing noplaylist
'url': 'http://www.bbc.com/sport/0/football/34475836',
'info_dict': {
'id': 'p034ppnv',
'ext': 'mp4',
'title': 'All you need to know about Jurgen Klopp',
'timestamp': 1444335081,
'upload_date': '20151008',
'duration': 122.0,
'thumbnail': 'https://ichef.bbci.co.uk/onesport/cps/976/cpsprodpb/7542/production/_85981003_klopp.jpg',
},
'params': {
'noplaylist': True,
},
}, {
# school report article with single video
'url': 'http://www.bbc.co.uk/schoolreport/35744779',
@@ -762,6 +773,7 @@ class BBCIE(BBCCoUkIE): # XXX: Do not subclass from concrete IE
'title': 'School which breaks down barriers in Jerusalem',
},
'playlist_count': 1,
'skip': 'redirects to Young Reporter home page https://www.bbc.co.uk/news/topics/cg41ylwv43pt',
}, {
# single video with playlist URL from weather section
'url': 'http://www.bbc.com/weather/features/33601775',
@@ -778,18 +790,33 @@ class BBCIE(BBCCoUkIE): # XXX: Do not subclass from concrete IE
'thumbnail': r're:https?://.+/.+\.jpg',
'timestamp': 1437785037,
'upload_date': '20150725',
'duration': 105,
},
}, {
# video with window.__INITIAL_DATA__ and value as JSON string
'url': 'https://www.bbc.com/news/av/world-europe-59468682',
'info_dict': {
'id': 'p0b71qth',
'id': 'p0b779gc',
'ext': 'mp4',
'title': 'Why France is making this woman a national hero',
'description': 'md5:7affdfab80e9c3a1f976230a1ff4d5e4',
'description': r're:(?s)France is honouring the US-born 20th Century singer and activist Josephine .{208} Second World War.',
'thumbnail': r're:https?://.+/.+\.jpg',
'timestamp': 1638230731,
'upload_date': '20211130',
'timestamp': 1638215626,
'upload_date': '20211129',
'duration': 125,
},
}, {
# video with script id __NEXT_DATA__ and value as JSON string
'url': 'https://www.bbc.com/news/uk-68546268',
'info_dict': {
'id': 'p0hj0lq7',
'ext': 'mp4',
'title': 'Nasser Hospital doctor describes his treatment by IDF',
'description': r're:(?s)Doctor Abu Sabha said he was detained by Israeli forces after .{276} hostages\."$',
'thumbnail': r're:https?://.+/.+\.jpg',
'timestamp': 1710188248,
'upload_date': '20240311',
'duration': 104,
},
}, {
# single video article embedded with data-media-vpid
@@ -817,6 +844,7 @@ class BBCIE(BBCCoUkIE): # XXX: Do not subclass from concrete IE
'uploader': 'Radio 3',
'uploader_id': 'bbc_radio_three',
},
'skip': '404 Not Found',
}, {
'url': 'http://www.bbc.co.uk/learningenglish/chinese/features/lingohack/ep-181227',
'info_dict': {
@@ -824,6 +852,7 @@ class BBCIE(BBCCoUkIE): # XXX: Do not subclass from concrete IE
'ext': 'mp4',
'title': 'md5:2fabf12a726603193a2879a055f72514',
'description': 'Learn English words and phrases from this story',
'thumbnail': 'https://ichef.bbci.co.uk/images/ic/1200x675/p06pq9gk.jpg',
},
'add_ie': [BBCCoUkIE.ie_key()],
}, {
@@ -832,28 +861,30 @@ class BBCIE(BBCCoUkIE): # XXX: Do not subclass from concrete IE
'info_dict': {
'id': 'p07c6sb9',
'ext': 'mp4',
'title': 'How positive thinking is harming your happiness',
'alt_title': 'The downsides of positive thinking',
'description': 'md5:fad74b31da60d83b8265954ee42d85b4',
'title': 'The downsides of positive thinking',
'description': 'The downsides of positive thinking',
'duration': 235,
'thumbnail': r're:https?://.+/p07c9dsr.jpg',
'upload_date': '20190604',
'categories': ['Psychology'],
'thumbnail': r're:https?://.+/p07c9dsr\.(?:jpg|webp|png)',
'upload_date': '20220223',
'timestamp': 1645632746,
},
}, {
# BBC Sounds
'url': 'https://www.bbc.co.uk/sounds/play/m001q78b',
'url': 'https://www.bbc.co.uk/sounds/play/w3ct5rgx',
'info_dict': {
'id': 'm001q789',
'id': 'p0hrw4nr',
'ext': 'mp4',
'title': 'The Night Tracks Mix - Music for the darkling hour',
'thumbnail': 'https://ichef.bbci.co.uk/images/ic/raw/p0c00hym.jpg',
'chapters': 'count:8',
'description': 'md5:815fb51cbdaa270040aab8145b3f1d67',
'uploader': 'Radio 3',
'duration': 1800,
'uploader_id': 'bbc_radio_three',
},
'title': 'Are our coastlines being washed away?',
'description': r're:(?s)Around the world, coastlines are constantly changing .{2000,} Images\)$',
'timestamp': 1713556800,
'upload_date': '20240419',
'duration': 1588,
'thumbnail': 'https://ichef.bbci.co.uk/images/ic/raw/p0hrnxbl.jpg',
'uploader': 'World Service',
'uploader_id': 'bbc_world_service',
'series': 'CrowdScience',
'chapters': [],
}
}, { # onion routes
'url': 'https://www.bbcnewsd73hkzno2ini43t4gblxvycyac5aw4gnv7t2rccijh7745uqd.onion/news/av/world-europe-63208576',
'only_matching': True,
@@ -1008,8 +1039,7 @@ class BBCIE(BBCCoUkIE): # XXX: Do not subclass from concrete IE
webpage, 'group id', default=None)
if group_id:
return self.url_result(
'https://www.bbc.co.uk/programmes/%s' % group_id,
ie=BBCCoUkIE.ie_key())
f'https://www.bbc.co.uk/programmes/{group_id}', BBCCoUkIE)
# single video story (e.g. http://www.bbc.com/travel/story/20150625-sri-lankas-spicy-secret)
programme_id = self._search_regex(
@@ -1069,83 +1099,133 @@ class BBCIE(BBCCoUkIE): # XXX: Do not subclass from concrete IE
}
# Morph based embed (e.g. http://www.bbc.co.uk/sport/live/olympics/36895975)
# There are several setPayload calls may be present but the video
# seems to be always related to the first one
morph_payload = self._parse_json(
self._search_regex(
r'Morph\.setPayload\([^,]+,\s*({.+?})\);',
webpage, 'morph payload', default='{}'),
playlist_id, fatal=False)
# Several setPayload calls may be present but the video(s)
# should be in one that mentions leadMedia or videoData
morph_payload = self._search_json(
r'\bMorph\s*\.\s*setPayload\s*\([^,]+,', webpage, 'morph payload', playlist_id,
contains_pattern=r'{(?s:(?:(?!</script>).)+(?:"leadMedia"|\\"videoData\\")\s*:.+)}',
default={})
if morph_payload:
components = try_get(morph_payload, lambda x: x['body']['components'], list) or []
for component in components:
if not isinstance(component, dict):
continue
lead_media = try_get(component, lambda x: x['props']['leadMedia'], dict)
if not lead_media:
continue
identifiers = lead_media.get('identifiers')
if not identifiers or not isinstance(identifiers, dict):
continue
programme_id = identifiers.get('vpid') or identifiers.get('playablePid')
for lead_media in traverse_obj(morph_payload, (
'body', 'components', ..., 'props', 'leadMedia', {dict})):
programme_id = traverse_obj(lead_media, ('identifiers', ('vpid', 'playablePid'), {str}, any))
if not programme_id:
continue
title = lead_media.get('title') or self._og_search_title(webpage)
formats, subtitles = self._download_media_selector(programme_id)
description = lead_media.get('summary')
uploader = lead_media.get('masterBrand')
uploader_id = lead_media.get('mid')
duration = None
duration_d = lead_media.get('duration')
if isinstance(duration_d, dict):
duration = parse_duration(dict_get(
duration_d, ('rawDuration', 'formattedDuration', 'spokenDuration')))
return {
'id': programme_id,
'title': title,
'description': description,
'duration': duration,
'uploader': uploader,
'uploader_id': uploader_id,
'title': lead_media.get('title') or self._og_search_title(webpage),
**traverse_obj(lead_media, {
'description': ('summary', {str}),
'duration': ('duration', ('rawDuration', 'formattedDuration', 'spokenDuration'), {parse_duration}),
'uploader': ('masterBrand', {str}),
'uploader_id': ('mid', {str}),
}),
'formats': formats,
'subtitles': subtitles,
}
body = self._parse_json(traverse_obj(morph_payload, (
'body', 'content', 'article', 'body')), playlist_id, fatal=False)
for video_data in traverse_obj(body, (lambda _, v: v['videoData']['pid'], 'videoData')):
if video_data.get('vpid'):
video_id = video_data['vpid']
formats, subtitles = self._download_media_selector(video_id)
entry = {
'id': video_id,
'formats': formats,
'subtitles': subtitles,
}
else:
video_id = video_data['pid']
entry = self.url_result(
f'https://www.bbc.co.uk/programmes/{video_id}', BBCCoUkIE,
video_id, url_transparent=True)
entry.update({
'timestamp': traverse_obj(morph_payload, (
'body', 'content', 'article', 'dateTimeInfo', 'dateTime', {parse_iso8601})
),
**traverse_obj(video_data, {
'thumbnail': (('iChefImage', 'image'), {url_or_none}, any),
'title': (('title', 'caption'), {str}, any),
'duration': ('duration', {parse_duration}),
}),
})
if video_data.get('isLead') and not self._yes_playlist(playlist_id, video_id):
return entry
entries.append(entry)
if entries:
playlist_title = traverse_obj(morph_payload, (
'body', 'content', 'article', 'headline', {str})) or playlist_title
return self.playlist_result(
entries, playlist_id, playlist_title, playlist_description)
preload_state = self._parse_json(self._search_regex(
r'window\.__PRELOADED_STATE__\s*=\s*({.+?});', webpage,
'preload state', default='{}'), playlist_id, fatal=False)
if preload_state:
current_programme = preload_state.get('programmes', {}).get('current') or {}
programme_id = current_programme.get('id')
if current_programme and programme_id and current_programme.get('type') == 'playable_item':
title = current_programme.get('titles', {}).get('tertiary') or playlist_title
formats, subtitles = self._download_media_selector(programme_id)
synopses = current_programme.get('synopses') or {}
network = current_programme.get('network') or {}
duration = int_or_none(
current_programme.get('duration', {}).get('value'))
thumbnail = None
image_url = current_programme.get('image_url')
if image_url:
thumbnail = image_url.replace('{recipe}', 'raw')
# various PRELOADED_STATE JSON
preload_state = self._search_json(
r'window\.__(?:PWA_)?PRELOADED_STATE__\s*=', webpage,
'preload state', playlist_id, transform_source=js_to_json, default={})
# PRELOADED_STATE with current programmme
current_programme = traverse_obj(preload_state, ('programmes', 'current', {dict}))
programme_id = traverse_obj(current_programme, ('id', {str}))
if programme_id and current_programme.get('type') == 'playable_item':
title = traverse_obj(current_programme, ('titles', ('tertiary', 'secondary'), {str}, any)) or playlist_title
formats, subtitles = self._download_media_selector(programme_id)
return {
'id': programme_id,
'title': title,
'formats': formats,
**traverse_obj(current_programme, {
'description': ('synopses', ('long', 'medium', 'short'), {str}, any),
'thumbnail': ('image_url', {lambda u: url_or_none(u.replace('{recipe}', 'raw'))}),
'duration': ('duration', 'value', {int_or_none}),
'uploader': ('network', 'short_title', {str}),
'uploader_id': ('network', 'id', {str}),
'timestamp': ((('availability', 'from'), ('release', 'date')), {parse_iso8601}, any),
'series': ('titles', 'primary', {str}),
}),
'subtitles': subtitles,
'chapters': traverse_obj(preload_state, (
'tracklist', 'tracks', lambda _, v: float(v['offset']['start']), {
'title': ('titles', {lambda x: join_nonempty(
'primary', 'secondary', 'tertiary', delim=' - ', from_dict=x)}),
'start_time': ('offset', 'start', {float_or_none}),
'end_time': ('offset', 'end', {float_or_none}),
})
),
}
# PWA_PRELOADED_STATE with article video asset
asset_id = traverse_obj(preload_state, (
'entities', 'articles', lambda k, _: k.rsplit('/', 1)[-1] == playlist_id,
'assetVideo', 0, {str}, any))
if asset_id:
video_id = traverse_obj(preload_state, ('entities', 'videos', asset_id, 'vpid', {str}))
if video_id:
article = traverse_obj(preload_state, (
'entities', 'articles', lambda _, v: v['assetVideo'][0] == asset_id, any))
def image_url(image_id):
return traverse_obj(preload_state, (
'entities', 'images', image_id, 'url',
{lambda u: url_or_none(u.replace('$recipe', 'raw'))}))
formats, subtitles = self._download_media_selector(video_id)
return {
'id': programme_id,
'title': title,
'description': dict_get(synopses, ('long', 'medium', 'short')),
'thumbnail': thumbnail,
'duration': duration,
'uploader': network.get('short_title'),
'uploader_id': network.get('id'),
'id': video_id,
**traverse_obj(preload_state, ('entities', 'videos', asset_id, {
'title': ('title', {str}),
'description': (('synopsisLong', 'synopsisMedium', 'synopsisShort'), {str}, any),
'thumbnail': (0, {image_url}),
'duration': ('duration', {int_or_none}),
})),
'formats': formats,
'subtitles': subtitles,
'chapters': traverse_obj(preload_state, (
'tracklist', 'tracks', lambda _, v: float_or_none(v['offset']['start']), {
'title': ('titles', {lambda x: join_nonempty(
'primary', 'secondary', 'tertiary', delim=' - ', from_dict=x)}),
'start_time': ('offset', 'start', {float_or_none}),
'end_time': ('offset', 'end', {float_or_none}),
})) or None,
'timestamp': traverse_obj(article, ('displayDate', {parse_iso8601})),
}
else:
return self.url_result(
f'https://www.bbc.co.uk/programmes/{asset_id}', BBCCoUkIE,
asset_id, playlist_title, display_id=playlist_id,
description=playlist_description)
bbc3_config = self._parse_json(
self._search_regex(
@@ -1191,6 +1271,28 @@ class BBCIE(BBCCoUkIE): # XXX: Do not subclass from concrete IE
return self.playlist_result(
entries, playlist_id, playlist_title, playlist_description)
def parse_model(model):
"""Extract single video from model structure"""
item_id = traverse_obj(model, ('versions', 0, 'versionId', {str}))
if not item_id:
return
formats, subtitles = self._download_media_selector(item_id)
return {
'id': item_id,
'formats': formats,
'subtitles': subtitles,
**traverse_obj(model, {
'title': ('title', {str}),
'thumbnail': ('imageUrl', {lambda u: urljoin(url, u.replace('$recipe', 'raw'))}),
'description': ('synopses', ('long', 'medium', 'short'), {str}, {lambda x: x or None}, any),
'duration': ('versions', 0, 'duration', {int}),
'timestamp': ('versions', 0, 'availableFrom', {functools.partial(int_or_none, scale=1000)}),
})
}
def is_type(*types):
return lambda _, v: v['type'] in types
initial_data = self._search_regex(
r'window\.__INITIAL_DATA__\s*=\s*("{.+?}")\s*;', webpage,
'quoted preload state', default=None)
@@ -1202,6 +1304,19 @@ class BBCIE(BBCCoUkIE): # XXX: Do not subclass from concrete IE
initial_data = self._parse_json(initial_data or '"{}"', playlist_id, fatal=False)
initial_data = self._parse_json(initial_data, playlist_id, fatal=False)
if initial_data:
for video_data in traverse_obj(initial_data, (
'stores', 'article', 'articleBodyContent', is_type('video'))):
model = traverse_obj(video_data, (
'model', 'blocks', is_type('aresMedia'),
'model', 'blocks', is_type('aresMediaMetadata'),
'model', {dict}, any))
entry = parse_model(model)
if entry:
entries.append(entry)
if entries:
return self.playlist_result(
entries, playlist_id, playlist_title, playlist_description)
def parse_media(media):
if not media:
return
@@ -1234,27 +1349,90 @@ class BBCIE(BBCCoUkIE): # XXX: Do not subclass from concrete IE
'subtitles': subtitles,
'timestamp': item_time,
'description': strip_or_none(item_desc),
'duration': int_or_none(item.get('duration')),
})
for resp in (initial_data.get('data') or {}).values():
name = resp.get('name')
for resp in traverse_obj(initial_data, ('data', lambda _, v: v['name'])):
name = resp['name']
if name == 'media-experience':
parse_media(try_get(resp, lambda x: x['data']['initialItem']['mediaItem'], dict))
elif name == 'article':
for block in (try_get(resp,
(lambda x: x['data']['blocks'],
lambda x: x['data']['content']['model']['blocks'],),
list) or []):
if block.get('type') not in ['media', 'video']:
continue
parse_media(block.get('model'))
for block in traverse_obj(resp, (
'data', (None, ('content', 'model')), 'blocks',
is_type('media', 'video'), 'model', {dict})):
parse_media(block)
return self.playlist_result(
entries, playlist_id, playlist_title, playlist_description)
# extract from SIMORGH_DATA hydration JSON
simorgh_data = self._search_json(
r'window\s*\.\s*SIMORGH_DATA\s*=', webpage,
'simorgh data', playlist_id, default={})
if simorgh_data:
done = False
for video_data in traverse_obj(simorgh_data, (
'pageData', 'content', 'model', 'blocks', is_type('video', 'legacyMedia'))):
model = traverse_obj(video_data, (
'model', 'blocks', is_type('aresMedia'),
'model', 'blocks', is_type('aresMediaMetadata'),
'model', {dict}, any))
if video_data['type'] == 'video':
entry = parse_model(model)
else: # legacyMedia: no duration, subtitles
block_id, entry = traverse_obj(model, ('blockId', {str})), None
media_data = traverse_obj(simorgh_data, (
'pageData', 'promo', 'media',
{lambda x: x if x['id'] == block_id else None}))
formats = traverse_obj(media_data, ('playlist', lambda _, v: url_or_none(v['url']), {
'url': ('url', {url_or_none}),
'ext': ('format', {str}),
'tbr': ('bitrate', {functools.partial(int_or_none, scale=1000)}),
}))
if formats:
entry = {
'id': block_id,
'display_id': playlist_id,
'formats': formats,
'description': traverse_obj(simorgh_data, ('pageData', 'promo', 'summary', {str})),
**traverse_obj(model, {
'title': ('title', {str}),
'thumbnail': ('imageUrl', {lambda u: urljoin(url, u.replace('$recipe', 'raw'))}),
'description': ('synopses', ('long', 'medium', 'short'), {str}, any),
'timestamp': ('firstPublished', {functools.partial(int_or_none, scale=1000)}),
}),
}
done = True
if entry:
entries.append(entry)
if done:
break
if entries:
return self.playlist_result(
entries, playlist_id, playlist_title, playlist_description)
def extract_all(pattern):
return list(filter(None, map(
lambda s: self._parse_json(s, playlist_id, fatal=False),
re.findall(pattern, webpage))))
# US accessed article with single embedded video (e.g.
# https://www.bbc.com/news/uk-68546268)
next_data = traverse_obj(self._search_nextjs_data(webpage, playlist_id, default={}),
('props', 'pageProps', 'page'))
model = traverse_obj(next_data, (
..., 'contents', is_type('video'),
'model', 'blocks', is_type('media'),
'model', 'blocks', is_type('mediaMetadata'),
'model', {dict}, any))
if model and (entry := parse_model(model)):
if not entry.get('timestamp'):
entry['timestamp'] = traverse_obj(next_data, (
..., 'contents', is_type('timestamp'), 'model',
'timestamp', {functools.partial(int_or_none, scale=1000)}, any))
entries.append(entry)
return self.playlist_result(
entries, playlist_id, playlist_title, playlist_description)
# Multiple video article (e.g.
# http://www.bbc.co.uk/blogs/adamcurtis/entries/3662a707-0af9-3149-963f-47bea720b460)
EMBED_URL = r'https?://(?:www\.)?bbc\.co\.uk/(?:[^/]+/)+%s(?:\b[^"]+)?' % self._ID_REGEX

26
yt_dlp/extractor/bilibili.py
View File

@@ -93,11 +93,11 @@ class BilibiliBaseIE(InfoExtractor):
return formats
def _download_playinfo(self, video_id, cid):
def _download_playinfo(self, video_id, cid, headers=None):
return self._download_json(
'https://api.bilibili.com/x/player/playurl', video_id,
query={'bvid': video_id, 'cid': cid, 'fnval': 4048},
note=f'Downloading video formats for cid {cid}')['data']
note=f'Downloading video formats for cid {cid}', headers=headers)['data']
def json2srt(self, json_data):
srt_data = ''
@@ -493,7 +493,8 @@ class BiliBiliIE(BilibiliBaseIE):
def _real_extract(self, url):
video_id = self._match_id(url)
webpage, urlh = self._download_webpage_handle(url, video_id)
headers = self.geo_verification_headers()
webpage, urlh = self._download_webpage_handle(url, video_id, headers=headers)
if not self._match_valid_url(urlh.url):
return self.url_result(urlh.url)
@@ -531,7 +532,7 @@ class BiliBiliIE(BilibiliBaseIE):
self._download_json(
'https://api.bilibili.com/x/player/pagelist', video_id,
fatal=False, query={'bvid': video_id, 'jsonp': 'jsonp'},
note='Extracting videos in anthology'),
note='Extracting videos in anthology', headers=headers),
'data', expected_type=list) or []
is_anthology = len(page_list_json) > 1
@@ -552,7 +553,7 @@ class BiliBiliIE(BilibiliBaseIE):
festival_info = {}
if is_festival:
play_info = self._download_playinfo(video_id, cid)
play_info = self._download_playinfo(video_id, cid, headers=headers)
festival_info = traverse_obj(initial_state, {
'uploader': ('videoInfo', 'upName'),
@@ -666,14 +667,15 @@ class BiliBiliBangumiIE(BilibiliBaseIE):
def _real_extract(self, url):
episode_id = self._match_id(url)
webpage = self._download_webpage(url, episode_id)
headers = self.geo_verification_headers()
webpage = self._download_webpage(url, episode_id, headers=headers)
if '您所在的地区无法观看本片' in webpage:
raise GeoRestrictedError('This video is restricted')
elif '正在观看预览，大会员免费看全片' in webpage:
self.raise_login_required('This video is for premium members only')
headers = {'Referer': url, **self.geo_verification_headers()}
headers['Referer'] = url
play_info = self._download_json(
'https://api.bilibili.com/pgc/player/web/v2/playurl', episode_id,
'Extracting episode', query={'fnval': '4048', 'ep_id': episode_id},
@@ -724,7 +726,7 @@ class BiliBiliBangumiIE(BilibiliBaseIE):
'duration': float_or_none(play_info.get('timelength'), scale=1000),
'subtitles': self.extract_subtitles(episode_id, episode_info.get('cid'), aid=aid),
'__post_extractor': self.extract_comments(aid),
'http_headers': headers,
'http_headers': {'Referer': url},
}
@@ -1043,15 +1045,17 @@ class BilibiliSpaceVideoIE(BilibiliSpaceBaseIE):
try:
response = self._download_json('https://api.bilibili.com/x/space/wbi/arc/search',
playlist_id, note=f'Downloading page {page_idx}', query=query)
playlist_id, note=f'Downloading page {page_idx}', query=query,
headers={'referer': url})
except ExtractorError as e:
if isinstance(e.cause, HTTPError) and e.cause.status == 412:
raise ExtractorError(
'Request is blocked by server (412), please add cookies, wait and try later.', expected=True)
raise
if response['code'] == -401:
if response['code'] in (-352, -401):
raise ExtractorError(
'Request is blocked by server (401), please add cookies, wait and try later.', expected=True)
f'Request is blocked by server ({-response["code"]}), '
'please add cookies, wait and try later.', expected=True)
return response['data']
def get_metadata(page_data):

20
yt_dlp/extractor/boosty.py
View File

@@ -1,7 +1,11 @@
import json
import urllib.parse
from .common import InfoExtractor
from .youtube import YoutubeIE
from ..utils import (
ExtractorError,
bug_reports_message,
int_or_none,
qualities,
str_or_none,
@@ -162,9 +166,19 @@ class BoostyIE(InfoExtractor):
def _real_extract(self, url):
user, post_id = self._match_valid_url(url).group('user', 'post_id')
auth_headers = {}
auth_cookie = self._get_cookies('https://boosty.to/').get('auth')
if auth_cookie is not None:
try:
auth_data = json.loads(urllib.parse.unquote(auth_cookie.value))
auth_headers['Authorization'] = f'Bearer {auth_data["accessToken"]}'
except (json.JSONDecodeError, KeyError):
self.report_warning(f'Failed to extract token from auth cookie{bug_reports_message()}')
post = self._download_json(
f'https://api.boosty.to/v1/blog/{user}/post/{post_id}', post_id,
note='Downloading post data', errnote='Unable to download post data')
note='Downloading post data', errnote='Unable to download post data', headers=auth_headers)
post_title = post.get('title')
if not post_title:
@@ -202,7 +216,9 @@ class BoostyIE(InfoExtractor):
'thumbnail': (('previewUrl', 'defaultPreview'), {url_or_none}),
}, get_all=False)})
if not entries:
if not entries and not post.get('hasAccess'):
self.raise_login_required('This post requires a subscription', metadata_available=True)
elif not entries:
raise ExtractorError('No videos found', expected=True)
if len(entries) == 1:
return entries[0]

32
yt_dlp/extractor/cableav.py
View File

@@ -1,32 +0,0 @@
from .common import InfoExtractor
class CableAVIE(InfoExtractor):
_VALID_URL = r'https?://cableav\.tv/(?P<id>[a-zA-Z0-9]+)'
_TESTS = [{
'url': 'https://cableav.tv/lS4iR9lWjN8/',
'md5': '7e3fe5e49d61c4233b7f5b0f69b15e18',
'info_dict': {
'id': 'lS4iR9lWjN8',
'ext': 'mp4',
'title': '國產麻豆AV 叮叮映畫 DDF001 情欲小說家 - CableAV',
'description': '國產AV 480p, 720p 国产麻豆AV 叮叮映画 DDF001 情欲小说家',
'thumbnail': r're:^https?://.*\.jpg$',
}
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
video_url = self._og_search_video_url(webpage, secure=False)
formats = self._extract_m3u8_formats(video_url, video_id, 'mp4')
return {
'id': video_id,
'title': self._og_search_title(webpage),
'description': self._og_search_description(webpage),
'thumbnail': self._og_search_thumbnail(webpage),
'formats': formats,
}

35
yt_dlp/extractor/canalalpha.py
View File

@@ -40,7 +40,7 @@ class CanalAlphaIE(InfoExtractor):
'id': '24484',
'ext': 'mp4',
'title': 'Ces innovations qui veulent rendre l’agriculture plus durable',
'description': 'md5:3de3f151180684621e85be7c10e4e613',
'description': 'md5:85d594a3b5dc6ccfc4a85aba6e73b129',
'thumbnail': 'https://static.canalalpha.ch/poster/magazine/magazine_10236.jpg',
'upload_date': '20211026',
'duration': 360,
@@ -58,14 +58,25 @@ class CanalAlphaIE(InfoExtractor):
'duration': 360,
},
'params': {'skip_download': True}
}, {
'url': 'https://www.canalalpha.ch/play/le-journal/topic/33500/encore-des-mesures-deconomie-dans-le-jura',
'info_dict': {
'id': '33500',
'ext': 'mp4',
'title': 'Encore des mesures d\'économie dans le Jura',
'description': 'md5:938b5b556592f2d1b9ab150268082a80',
'thumbnail': 'https://static.canalalpha.ch/poster/news/news_46665.jpg',
'upload_date': '20240411',
'duration': 105,
},
}]
def _real_extract(self, url):
id = self._match_id(url)
webpage = self._download_webpage(url, id)
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
data_json = self._parse_json(self._search_regex(
r'window\.__SERVER_STATE__\s?=\s?({(?:(?!};)[^"]|"([^"]|\\")*")+})\s?;',
webpage, 'data_json'), id)['1']['data']['data']
webpage, 'data_json'), video_id)['1']['data']['data']
manifests = try_get(data_json, lambda x: x['video']['manifests'], expected_type=dict) or {}
subtitles = {}
formats = [{
@@ -75,15 +86,17 @@ class CanalAlphaIE(InfoExtractor):
'height': try_get(video, lambda x: x['res']['height'], expected_type=int),
} for video in try_get(data_json, lambda x: x['video']['mp4'], expected_type=list) or [] if video.get('$url')]
if manifests.get('hls'):
m3u8_frmts, m3u8_subs = self._parse_m3u8_formats_and_subtitles(manifests['hls'], video_id=id)
formats.extend(m3u8_frmts)
subtitles = self._merge_subtitles(subtitles, m3u8_subs)
fmts, subs = self._extract_m3u8_formats_and_subtitles(
manifests['hls'], video_id, m3u8_id='hls', fatal=False)
formats.extend(fmts)
self._merge_subtitles(subs, target=subtitles)
if manifests.get('dash'):
dash_frmts, dash_subs = self._parse_mpd_formats_and_subtitles(manifests['dash'])
formats.extend(dash_frmts)
subtitles = self._merge_subtitles(subtitles, dash_subs)
fmts, subs = self._extract_mpd_formats_and_subtitles(
manifests['dash'], video_id, mpd_id='dash', fatal=False)
formats.extend(fmts)
self._merge_subtitles(subs, target=subtitles)
return {
'id': id,
'id': video_id,
'title': data_json.get('title').strip(),
'description': clean_html(dict_get(data_json, ('longDesc', 'shortDesc'))),
'thumbnail': data_json.get('poster'),

24
yt_dlp/extractor/cbc.py
View File

@@ -151,7 +151,7 @@ class CBCIE(InfoExtractor):
class CBCPlayerIE(InfoExtractor):
IE_NAME = 'cbc.ca:player'
_VALID_URL = r'(?:cbcplayer:|https?://(?:www\.)?cbc\.ca/(?:player/play/|i/caffeine/syndicate/\?mediaId=))(?P<id>(?:\d\.)?\d+)'
_VALID_URL = r'(?:cbcplayer:|https?://(?:www\.)?cbc\.ca/(?:player/play/(?:video/)?|i/caffeine/syndicate/\?mediaId=))(?P<id>(?:\d\.)?\d+)'
_TESTS = [{
'url': 'http://www.cbc.ca/player/play/2683190193',
'md5': '64d25f841ddf4ddb28a235338af32e2c',
@@ -277,6 +277,28 @@ class CBCPlayerIE(InfoExtractor):
'location': 'Canada',
'media_type': 'Full Program',
},
}, {
'url': 'https://www.cbc.ca/player/play/video/1.7194274',
'md5': '188b96cf6bdcb2540e178a6caa957128',
'info_dict': {
'id': '2334524995812',
'ext': 'mp4',
'title': '#TheMoment a rare white spirit moose was spotted in Alberta',
'description': 'md5:18ae269a2d0265c5b0bbe4b2e1ac61a3',
'timestamp': 1714788791,
'duration': 77.678,
'subtitles': {'eng': [{'ext': 'vtt', 'protocol': 'm3u8_native'}]},
'thumbnail': 'https://thumbnails.cbc.ca/maven_legacy/thumbnails/201/543/THE_MOMENT.jpg',
'uploader': 'CBCC-NEW',
'chapters': 'count:0',
'upload_date': '20240504',
'categories': 'count:3',
'series': 'The National',
'tags': 'count:15',
'creators': ['encoder'],
'location': 'Canada',
'media_type': 'Excerpt',
},
}, {
'url': 'cbcplayer:1.7159484',
'only_matching': True,

62
yt_dlp/extractor/cda.py
View File

@@ -16,7 +16,6 @@ from ..utils import (
merge_dicts,
multipart_encode,
parse_duration,
random_birthday,
traverse_obj,
try_call,
try_get,
@@ -63,38 +62,57 @@ class CDAIE(InfoExtractor):
'description': 'md5:60d76b71186dcce4e0ba6d4bbdb13e1a',
'thumbnail': r're:^https?://.*\.jpg$',
'uploader': 'crash404',
'view_count': int,
'average_rating': float,
'duration': 137,
'age_limit': 0,
'upload_date': '20160220',
'timestamp': 1455968218,
}
}, {
# Age-restricted
'url': 'http://www.cda.pl/video/1273454c4',
# Age-restricted with vfilm redirection
'url': 'https://www.cda.pl/video/8753244c4',
'md5': 'd8eeb83d63611289507010d3df3bb8b3',
'info_dict': {
'id': '1273454c4',
'id': '8753244c4',
'ext': 'mp4',
'title': 'Bronson (2008) napisy HD 1080p',
'description': 'md5:1b6cb18508daf2dc4e0fa4db77fec24c',
'title': '[18+] Bez Filtra: Rezerwowe Psy czyli... najwulgarniejsza polska gra?',
'description': 'md5:ae80bac31bd6a9f077a6cce03c7c077e',
'height': 1080,
'uploader': 'boniek61',
'uploader': 'arhn eu',
'thumbnail': r're:^https?://.*\.jpg$',
'duration': 5554,
'duration': 991,
'age_limit': 18,
'view_count': int,
'average_rating': float,
},
'timestamp': 1633888264,
'upload_date': '20211010',
}
}, {
# Age-restricted without vfilm redirection
'url': 'https://www.cda.pl/video/17028157b8',
'md5': 'c1fe5ff4582bace95d4f0ce0fbd0f992',
'info_dict': {
'id': '17028157b8',
'ext': 'mp4',
'title': 'STENDUPY MICHAŁ OGIŃSKI',
'description': 'md5:5851f3272bfc31f762d616040a1d609a',
'height': 480,
'uploader': 'oginski',
'thumbnail': r're:^https?://.*\.jpg$',
'duration': 18855,
'age_limit': 18,
'average_rating': float,
'timestamp': 1699705901,
'upload_date': '20231111',
}
}, {
'url': 'http://ebd.cda.pl/0x0/5749950c',
'only_matching': True,
}]
def _download_age_confirm_page(self, url, video_id, *args, **kwargs):
form_data = random_birthday('rok', 'miesiac', 'dzien')
form_data.update({'return': url, 'module': 'video', 'module_id': video_id})
data, content_type = multipart_encode(form_data)
data, content_type = multipart_encode({'age_confirm': ''})
return self._download_webpage(
urljoin(url, '/a/validatebirth'), video_id, *args,
url, video_id, *args,
data=data, headers={
'Referer': url,
'Content-Type': content_type,
@@ -164,7 +182,7 @@ class CDAIE(InfoExtractor):
if 'Authorization' in self._API_HEADERS:
return self._api_extract(video_id)
else:
return self._web_extract(video_id, url)
return self._web_extract(video_id)
def _api_extract(self, video_id):
meta = self._download_json(
@@ -197,9 +215,9 @@ class CDAIE(InfoExtractor):
'view_count': meta.get('views'),
}
def _web_extract(self, video_id, url):
def _web_extract(self, video_id):
self._set_cookie('cda.pl', 'cda.player', 'html5')
webpage = self._download_webpage(
webpage, urlh = self._download_webpage_handle(
f'{self._BASE_URL}/video/{video_id}/vfilm', video_id)
if 'Ten film jest dostępny dla użytkowników premium' in webpage:
@@ -209,10 +227,10 @@ class CDAIE(InfoExtractor):
self.raise_geo_restricted()
need_confirm_age = False
if self._html_search_regex(r'(<form[^>]+action="[^"]*/a/validatebirth[^"]*")',
if self._html_search_regex(r'(<button[^>]+name="[^"]*age_confirm[^"]*")',
webpage, 'birthday validate form', default=None):
webpage = self._download_age_confirm_page(
url, video_id, note='Confirming age')
urlh.url, video_id, note='Confirming age')
need_confirm_age = True
formats = []
@@ -222,9 +240,6 @@ class CDAIE(InfoExtractor):
(?:<\1[^>]*>[^<]*</\1>|(?!</\1>)(?:.|\n))*?
<(span|meta)[^>]+itemprop=(["\'])name\4[^>]*>(?P<uploader>[^<]+)</\3>
''', webpage, 'uploader', default=None, group='uploader')
view_count = self._search_regex(
r'Odsłony:(?:\s|&nbsp;)*([0-9]+)', webpage,
'view_count', default=None)
average_rating = self._search_regex(
(r'<(?:span|meta)[^>]+itemprop=(["\'])ratingValue\1[^>]*>(?P<rating_value>[0-9.]+)',
r'<span[^>]+\bclass=["\']rating["\'][^>]*>(?P<rating_value>[0-9.]+)'), webpage, 'rating', fatal=False,
@@ -235,7 +250,6 @@ class CDAIE(InfoExtractor):
'title': self._og_search_title(webpage),
'description': self._og_search_description(webpage),
'uploader': uploader,
'view_count': int_or_none(view_count),
'average_rating': float_or_none(average_rating),
'thumbnail': self._og_search_thumbnail(webpage),
'formats': formats,

18
yt_dlp/extractor/common.py
View File

@@ -957,7 +957,8 @@ class InfoExtractor:
if urlh is False:
assert not fatal
return False
content = self._webpage_read_content(urlh, url_or_request, video_id, note, errnote, fatal, encoding=encoding)
content = self._webpage_read_content(urlh, url_or_request, video_id, note, errnote, fatal,
encoding=encoding, data=data)
return (content, urlh)
@staticmethod
@@ -1005,8 +1006,10 @@ class InfoExtractor:
'Visit http://blocklist.rkn.gov.ru/ for a block reason.',
expected=True)
def _request_dump_filename(self, url, video_id):
basen = f'{video_id}_{url}'
def _request_dump_filename(self, url, video_id, data=None):
if data is not None:
data = hashlib.md5(data).hexdigest()
basen = join_nonempty(video_id, data, url, delim='_')
trim_length = self.get_param('trim_file_name') or 240
if len(basen) > trim_length:
h = '___' + hashlib.md5(basen.encode('utf-8')).hexdigest()
@@ -1028,7 +1031,8 @@ class InfoExtractor:
except LookupError:
return webpage_bytes.decode('utf-8', 'replace')
def _webpage_read_content(self, urlh, url_or_request, video_id, note=None, errnote=None, fatal=True, prefix=None, encoding=None):
def _webpage_read_content(self, urlh, url_or_request, video_id, note=None, errnote=None, fatal=True,
prefix=None, encoding=None, data=None):
webpage_bytes = urlh.read()
if prefix is not None:
webpage_bytes = prefix + webpage_bytes
@@ -1037,7 +1041,9 @@ class InfoExtractor:
dump = base64.b64encode(webpage_bytes).decode('ascii')
self._downloader.to_screen(dump)
if self.get_param('write_pages'):
filename = self._request_dump_filename(urlh.url, video_id)
if isinstance(url_or_request, Request):
data = self._create_request(url_or_request, data).data
filename = self._request_dump_filename(urlh.url, video_id, data)
self.to_screen(f'Saving request to {filename}')
with open(filename, 'wb') as outf:
outf.write(webpage_bytes)
@@ -1098,7 +1104,7 @@ class InfoExtractor:
impersonate=None, require_impersonation=False):
if self.get_param('load_pages'):
url_or_request = self._create_request(url_or_request, data, headers, query)
filename = self._request_dump_filename(url_or_request.url, video_id)
filename = self._request_dump_filename(url_or_request.url, video_id, url_or_request.data)
self.to_screen(f'Loading request from {filename}')
try:
with open(filename, 'rb') as dumpf:

16
yt_dlp/extractor/commonmistakes.py
View File

@@ -40,3 +40,19 @@ class UnicodeBOMIE(InfoExtractor):
'Your URL starts with a Byte Order Mark (BOM). '
'Removing the BOM and looking for "%s" ...' % real_url)
return self.url_result(real_url)
class BlobIE(InfoExtractor):
IE_DESC = False
_VALID_URL = r'blob:'
_TESTS = [{
'url': 'blob:https://www.youtube.com/4eb3d090-a761-46e6-8083-c32016a36e3b',
'only_matching': True,
}]
def _real_extract(self, url):
raise ExtractorError(
'You\'ve asked yt-dlp to download a blob URL. '
'A blob URL exists only locally in your browser. '
'It is not possible for yt-dlp to access it.', expected=True)

31
yt_dlp/extractor/crunchyroll.py
View File

@@ -53,15 +53,19 @@ class CrunchyrollBaseIE(InfoExtractor):
CrunchyrollBaseIE._AUTH_EXPIRY = time_seconds(seconds=traverse_obj(response, ('expires_in', {float_or_none}), default=300) - 10)
def _request_token(self, headers, data, note='Requesting token', errnote='Failed to request token'):
try: # TODO: Add impersonation support here
try:
return self._download_json(
f'{self._BASE_URL}/auth/v1/token', None, note=note, errnote=errnote,
headers=headers, data=urlencode_postdata(data))
headers=headers, data=urlencode_postdata(data), impersonate=True)
except ExtractorError as error:
if not isinstance(error.cause, HTTPError) or error.cause.status != 403:
raise
if target := error.cause.response.extensions.get('impersonate'):
raise ExtractorError(f'Got HTTP Error 403 when using impersonate target "{target}"')
raise ExtractorError(
'Request blocked by Cloudflare; navigate to Crunchyroll in your browser, '
'Request blocked by Cloudflare. '
'Install the required impersonation dependency if possible, '
'or else navigate to Crunchyroll in your browser, '
'then pass the fresh cookies (with --cookies-from-browser or --cookies) '
'and your browser\'s User-Agent (with --user-agent)', expected=True)
@@ -394,10 +398,11 @@ class CrunchyrollBetaIE(CrunchyrollCmsBaseIE):
if not self._IS_PREMIUM and traverse_obj(response, (f'{object_type}_metadata', 'is_premium_only')):
message = f'This {object_type} is for premium members only'
if CrunchyrollBaseIE._REFRESH_TOKEN:
raise ExtractorError(message, expected=True)
self.raise_login_required(message, method='password')
result['formats'], result['subtitles'] = self._extract_stream(internal_id)
self.raise_no_formats(message, expected=True, video_id=internal_id)
else:
self.raise_login_required(message, method='password', metadata_available=True)
else:
result['formats'], result['subtitles'] = self._extract_stream(internal_id)
result['chapters'] = self._extract_chapters(internal_id)
@@ -583,14 +588,16 @@ class CrunchyrollMusicIE(CrunchyrollBaseIE):
if not response:
raise ExtractorError(f'No video with id {internal_id} could be found (possibly region locked?)', expected=True)
result = self._transform_music_response(response)
if not self._IS_PREMIUM and response.get('isPremiumOnly'):
message = f'This {response.get("type") or "media"} is for premium members only'
if CrunchyrollBaseIE._REFRESH_TOKEN:
raise ExtractorError(message, expected=True)
self.raise_login_required(message, method='password')
result = self._transform_music_response(response)
result['formats'], _ = self._extract_stream(f'music/{internal_id}', internal_id)
self.raise_no_formats(message, expected=True, video_id=internal_id)
else:
self.raise_login_required(message, method='password', metadata_available=True)
else:
result['formats'], _ = self._extract_stream(f'music/{internal_id}', internal_id)
return result

105
yt_dlp/extractor/einthusan.py
View File

@@ -1,105 +0,0 @@
import json
from .common import InfoExtractor
from ..compat import (
compat_b64decode,
compat_str,
compat_urlparse,
)
from ..utils import (
extract_attributes,
ExtractorError,
get_elements_by_class,
urlencode_postdata,
)
class EinthusanIE(InfoExtractor):
_VALID_URL = r'https?://(?P<host>einthusan\.(?:tv|com|ca))/movie/watch/(?P<id>[^/?#&]+)'
_TESTS = [{
'url': 'https://einthusan.tv/movie/watch/9097/',
'md5': 'ff0f7f2065031b8a2cf13a933731c035',
'info_dict': {
'id': '9097',
'ext': 'mp4',
'title': 'Ae Dil Hai Mushkil',
'description': 'md5:33ef934c82a671a94652a9b4e54d931b',
'thumbnail': r're:^https?://.*\.jpg$',
}
}, {
'url': 'https://einthusan.tv/movie/watch/51MZ/?lang=hindi',
'only_matching': True,
}, {
'url': 'https://einthusan.com/movie/watch/9097/',
'only_matching': True,
}, {
'url': 'https://einthusan.ca/movie/watch/4E9n/?lang=hindi',
'only_matching': True,
}]
# reversed from jsoncrypto.prototype.decrypt() in einthusan-PGMovieWatcher.js
def _decrypt(self, encrypted_data, video_id):
return self._parse_json(compat_b64decode((
encrypted_data[:10] + encrypted_data[-1] + encrypted_data[12:-1]
)).decode('utf-8'), video_id)
def _real_extract(self, url):
mobj = self._match_valid_url(url)
host = mobj.group('host')
video_id = mobj.group('id')
webpage = self._download_webpage(url, video_id)
title = self._html_search_regex(r'<h3>([^<]+)</h3>', webpage, 'title')
player_params = extract_attributes(self._search_regex(
r'(<section[^>]+id="UIVideoPlayer"[^>]+>)', webpage, 'player parameters'))
page_id = self._html_search_regex(
'<html[^>]+data-pageid="([^"]+)"', webpage, 'page ID')
video_data = self._download_json(
'https://%s/ajax/movie/watch/%s/' % (host, video_id), video_id,
data=urlencode_postdata({
'xEvent': 'UIVideoPlayer.PingOutcome',
'xJson': json.dumps({
'EJOutcomes': player_params['data-ejpingables'],
'NativeHLS': False
}),
'arcVersion': 3,
'appVersion': 59,
'gorilla.csrf.Token': page_id,
}))['Data']
if isinstance(video_data, compat_str) and video_data.startswith('/ratelimited/'):
raise ExtractorError(
'Download rate reached. Please try again later.', expected=True)
ej_links = self._decrypt(video_data['EJLinks'], video_id)
formats = []
m3u8_url = ej_links.get('HLSLink')
if m3u8_url:
formats.extend(self._extract_m3u8_formats(
m3u8_url, video_id, ext='mp4', entry_protocol='m3u8_native'))
mp4_url = ej_links.get('MP4Link')
if mp4_url:
formats.append({
'url': mp4_url,
})
description = get_elements_by_class('synopsis', webpage)[0]
thumbnail = self._html_search_regex(
r'''<img[^>]+src=(["'])(?P<url>(?!\1).+?/moviecovers/(?!\1).+?)\1''',
webpage, 'thumbnail url', fatal=False, group='url')
if thumbnail is not None:
thumbnail = compat_urlparse.urljoin(url, thumbnail)
return {
'id': video_id,
'title': title,
'formats': formats,
'thumbnail': thumbnail,
'description': description,
}

32
yt_dlp/extractor/eplus.py
View File

@@ -16,13 +16,31 @@ class EplusIbIE(InfoExtractor):
_VALID_URL = [r'https?://live\.eplus\.jp/ex/player\?ib=(?P<id>(?:\w|%2B|%2F){86}%3D%3D)',
r'https?://live\.eplus\.jp/(?P<id>sample|\d+)']
_TESTS = [{
'url': 'https://live.eplus.jp/ex/player?ib=YEFxb3Vyc2Dombnjg7blkrLlrablnJLjgrnjgq%2Fjg7zjg6vjgqLjgqTjg4njg6vlkIzlpb3kvJpgTGllbGxhIQ%3D%3D',
'url': 'https://live.eplus.jp/ex/player?ib=41K6Wzbr3PlcMD%2FOKHFlC%2FcZCe2Eaw7FK%2BpJS1ooUHki8d0vGSy2mYqxillQBe1dSnOxU%2B8%2FzXKls4XPBSb3vw%3D%3D',
'info_dict': {
'id': '354502-0001-002',
'title': 'LoveLive!Series Presents COUNTDOWN LoveLive! 2021→2022～LIVE with a smile!～【Streaming+(配信)】',
'id': '335699-0001-006',
'title': '少女☆歌劇 レヴュースタァライト -The LIVE 青嵐- BLUE GLITTER <定点映像配信>【Streaming+(配信)】',
'live_status': 'was_live',
'release_date': '20211231',
'release_timestamp': 1640952000,
'release_date': '20201221',
'release_timestamp': 1608544800,
},
'params': {
'skip_download': True,
'ignore_no_formats_error': True,
},
'expected_warnings': [
'This event may not be accessible',
'No video formats found',
'Requested format is not available',
],
}, {
'url': 'https://live.eplus.jp/ex/player?ib=6QSsQdyRAwOFZrEHWlhRm7vocgV%2FO0YzBZ%2BaBEBg1XR%2FmbLn0R%2F048dUoAY038%2F%2F92MJ73BsoAtvUpbV6RLtDQ%3D%3D&show_id=2371511',
'info_dict': {
'id': '348021-0054-001',
'title': 'ラブライブ!スーパースター!! Liella! First LoveLive! Tour ～Starlines～【東京/DAY.1】',
'live_status': 'was_live',
'release_date': '20220115',
'release_timestamp': 1642233600,
'description': str,
},
'params': {
@@ -124,6 +142,10 @@ class EplusIbIE(InfoExtractor):
if data_json.get('drm_mode') == 'ON':
self.report_drm(video_id)
if data_json.get('is_pass_ticket') == 'YES':
raise ExtractorError(
'This URL is for a pass ticket instead of a player page', expected=True)
delivery_status = data_json.get('delivery_status')
archive_mode = data_json.get('archive_mode')
release_timestamp = try_call(lambda: unified_timestamp(data_json['event_datetime']) - 32400)

20
yt_dlp/extractor/europa.py
View File

@@ -94,13 +94,14 @@ class EuropaIE(InfoExtractor):
class EuroParlWebstreamIE(InfoExtractor):
_VALID_URL = r'''(?x)
https?://multimedia\.europarl\.europa\.eu/[^/#?]+/
(?:(?!video)[^/#?]+/[\w-]+_)(?P<id>[\w-]+)
https?://multimedia\.europarl\.europa\.eu/
(?:\w+/)?webstreaming/(?:[\w-]+_)?(?P<id>[\w-]+)
'''
_TESTS = [{
'url': 'https://multimedia.europarl.europa.eu/pl/webstreaming/plenary-session_20220914-0900-PLENARY',
'info_dict': {
'id': '62388b15-d85b-4add-99aa-ba12ccf64f0d',
'display_id': '20220914-0900-PLENARY',
'ext': 'mp4',
'title': 'Plenary session',
'release_timestamp': 1663139069,
@@ -125,6 +126,7 @@ class EuroParlWebstreamIE(InfoExtractor):
'url': 'https://multimedia.europarl.europa.eu/en/webstreaming/committee-on-culture-and-education_20230301-1130-COMMITTEE-CULT',
'info_dict': {
'id': '7355662c-8eac-445e-4bb9-08db14b0ddd7',
'display_id': '20230301-1130-COMMITTEE-CULT',
'ext': 'mp4',
'release_date': '20230301',
'title': 'Committee on Culture and Education',
@@ -142,6 +144,19 @@ class EuroParlWebstreamIE(InfoExtractor):
'live_status': 'is_live',
},
'skip': 'Not live anymore'
}, {
'url': 'https://multimedia.europarl.europa.eu/en/webstreaming/20240320-1345-SPECIAL-PRESSER',
'info_dict': {
'id': 'c1f11567-5b52-470a-f3e1-08dc3c216ace',
'display_id': '20240320-1345-SPECIAL-PRESSER',
'ext': 'mp4',
'release_date': '20240320',
'title': 'md5:7c6c814cac55dea5e2d87bf8d3db2234',
'release_timestamp': 1710939767,
}
}, {
'url': 'https://multimedia.europarl.europa.eu/webstreaming/briefing-for-media-on-2024-european-elections_20240429-1000-SPECIAL-OTHER',
'only_matching': True,
}]
def _real_extract(self, url):
@@ -166,6 +181,7 @@ class EuroParlWebstreamIE(InfoExtractor):
return {
'id': json_info['id'],
'display_id': display_id,
'title': traverse_obj(webpage_nextjs, (('mediaItem', 'title'), ('title', )), get_all=False),
'formats': formats,
'subtitles': subtitles,

36
yt_dlp/extractor/googledrive.py
View File

@@ -1,9 +1,11 @@
import re
from .common import InfoExtractor
from .youtube import YoutubeIE
from ..compat import compat_parse_qs
from ..utils import (
ExtractorError,
bug_reports_message,
determine_ext,
extract_attributes,
get_element_by_class,
@@ -38,6 +40,17 @@ class GoogleDriveIE(InfoExtractor):
'duration': 45,
'thumbnail': 'https://drive.google.com/thumbnail?id=0ByeS4oOUV-49Zzh4R1J6R09zazQ',
}
}, {
# has itag 50 which is not in YoutubeIE._formats (royalty Free music from 1922)
'url': 'https://drive.google.com/uc?id=1IP0o8dHcQrIHGgVyp0Ofvx2cGfLzyO1x',
'md5': '322db8d63dd19788c04050a4bba67073',
'info_dict': {
'id': '1IP0o8dHcQrIHGgVyp0Ofvx2cGfLzyO1x',
'ext': 'mp3',
'title': 'My Buddy - Henry Burr - Gus Kahn - Walter Donaldson.mp3',
'duration': 184,
'thumbnail': 'https://drive.google.com/thumbnail?id=1IP0o8dHcQrIHGgVyp0Ofvx2cGfLzyO1x',
},
}, {
# video can't be watched anonymously due to view count limit reached,
# but can be downloaded (see https://github.com/ytdl-org/youtube-dl/issues/14046)
@@ -58,22 +71,8 @@ class GoogleDriveIE(InfoExtractor):
'only_matching': True,
}]
_FORMATS_EXT = {
'5': 'flv',
'6': 'flv',
'13': '3gp',
'17': '3gp',
'18': 'mp4',
'22': 'mp4',
'34': 'flv',
'35': 'flv',
'36': '3gp',
'37': 'mp4',
'38': 'mp4',
'43': 'webm',
'44': 'webm',
'45': 'webm',
'46': 'webm',
'59': 'mp4',
**{k: v['ext'] for k, v in YoutubeIE._formats.items() if v.get('ext')},
'50': 'm4a',
}
_BASE_URL_CAPTIONS = 'https://drive.google.com/timedtext'
_CAPTIONS_ENTRY_TAG = {
@@ -194,10 +193,13 @@ class GoogleDriveIE(InfoExtractor):
if len(fmt_stream_split) < 2:
continue
format_id, format_url = fmt_stream_split[:2]
ext = self._FORMATS_EXT.get(format_id)
if not ext:
self.report_warning(f'Unknown format {format_id}{bug_reports_message()}')
f = {
'url': lowercase_escape(format_url),
'format_id': format_id,
'ext': self._FORMATS_EXT[format_id],
'ext': ext,
}
resolution = resolutions.get(format_id)
if resolution:

5
yt_dlp/extractor/hytale.py
View File

@@ -1,7 +1,8 @@
import re
from .cloudflarestream import CloudflareStreamIE
from .common import InfoExtractor
from ..utils import traverse_obj
from ..utils.traversal import traverse_obj
class HytaleIE(InfoExtractor):
@@ -49,7 +50,7 @@ class HytaleIE(InfoExtractor):
entries = [
self.url_result(
f'https://cloudflarestream.com/{video_hash}/manifest/video.mpd?parentOrigin=https%3A%2F%2Fhytale.com',
title=self._titles.get(video_hash), url_transparent=True)
CloudflareStreamIE, title=self._titles.get(video_hash), url_transparent=True)
for video_hash in re.findall(
r'<stream\s+class\s*=\s*"ql-video\s+cf-stream"\s+src\s*=\s*"([a-f0-9]{32})"',
webpage)

103
yt_dlp/extractor/jable.py
View File

@@ -1,103 +0,0 @@
import re
from .common import InfoExtractor
from ..utils import (
InAdvancePagedList,
int_or_none,
orderedSet,
unified_strdate,
)
class JableIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?jable\.tv/videos/(?P<id>[\w-]+)'
_TESTS = [{
'url': 'https://jable.tv/videos/pppd-812/',
'md5': 'f1537283a9bc073c31ff86ca35d9b2a6',
'info_dict': {
'id': 'pppd-812',
'ext': 'mp4',
'title': 'PPPD-812 只要表現好巨乳女教師吉根柚莉愛就獎勵學生們在白虎穴內射出精液',
'description': 'md5:5b6d4199a854f62c5e56e26ccad19967',
'thumbnail': r're:^https?://.*\.jpg$',
'age_limit': 18,
'like_count': int,
'view_count': int,
},
}, {
'url': 'https://jable.tv/videos/apak-220/',
'md5': '71f9239d69ced58ab74a816908847cc1',
'info_dict': {
'id': 'apak-220',
'ext': 'mp4',
'title': 'md5:5c3861b7cf80112a6e2b70bccf170824',
'description': '',
'thumbnail': r're:^https?://.*\.jpg$',
'age_limit': 18,
'like_count': int,
'view_count': int,
'upload_date': '20220319',
},
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
formats = self._extract_m3u8_formats(
self._search_regex(r'var\s+hlsUrl\s*=\s*\'([^\']+)', webpage, 'hls_url'), video_id, 'mp4', m3u8_id='hls')
return {
'id': video_id,
'title': self._og_search_title(webpage),
'description': self._og_search_description(webpage, default=''),
'thumbnail': self._og_search_thumbnail(webpage, default=None),
'formats': formats,
'age_limit': 18,
'upload_date': unified_strdate(self._search_regex(
r'class="inactive-color">\D+\s+(\d{4}-\d+-\d+)', webpage, 'upload_date', default=None)),
'view_count': int_or_none(self._search_regex(
r'#icon-eye"></use></svg>\n*<span class="mr-3">([\d ]+)',
webpage, 'view_count', default='').replace(' ', '')),
'like_count': int_or_none(self._search_regex(
r'#icon-heart"></use></svg><span class="count">(\d+)', webpage, 'link_count', default=None)),
}
class JablePlaylistIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?jable\.tv/(?:categories|models|tags)/(?P<id>[\w-]+)'
_TESTS = [{
'url': 'https://jable.tv/models/kaede-karen/',
'info_dict': {
'id': 'kaede-karen',
'title': '楓カレン',
},
'playlist_count': 34,
}, {
'url': 'https://jable.tv/categories/roleplay/',
'only_matching': True,
}, {
'url': 'https://jable.tv/tags/girl/',
'only_matching': True,
}]
def _real_extract(self, url):
playlist_id = self._match_id(url)
webpage = self._download_webpage(url, playlist_id)
def page_func(page_num):
return [
self.url_result(player_url, JableIE)
for player_url in orderedSet(re.findall(
r'href="(https://jable.tv/videos/[\w-]+/?)"',
self._download_webpage(url, playlist_id, query={
'mode': 'async',
'from': page_num + 1,
'function': 'get_block',
'block_id': 'list_videos_common_videos_list',
}, note=f'Downloading page {page_num + 1}')))]
return self.playlist_result(
InAdvancePagedList(page_func, int_or_none(self._search_regex(
r'from:(\d+)">[^<]+\s*&raquo;', webpage, 'last page number', default=1)), 24),
playlist_id, self._search_regex(
r'<h2 class="h3-md mb-1">([^<]+)', webpage, 'playlist title', default=None))

41
yt_dlp/extractor/mixch.py
View File

@@ -1,6 +1,12 @@
from .common import InfoExtractor
from ..networking.exceptions import HTTPError
from ..utils import ExtractorError, UserNotLive, int_or_none, url_or_none
from ..utils import (
ExtractorError,
UserNotLive,
int_or_none,
str_or_none,
url_or_none,
)
from ..utils.traversal import traverse_obj
@@ -9,17 +15,20 @@ class MixchIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?mixch\.tv/u/(?P<id>\d+)'
_TESTS = [{
'url': 'https://mixch.tv/u/16236849/live',
'url': 'https://mixch.tv/u/16943797/live',
'skip': 'don\'t know if this live persists',
'info_dict': {
'id': '16236849',
'title': '24配信シェア⭕️投票🙏💦',
'comment_count': 13145,
'view_count': 28348,
'timestamp': 1636189377,
'uploader': '🦥伊咲👶🏻#フレアワ',
'uploader_id': '16236849',
}
'id': '16943797',
'ext': 'mp4',
'title': '#EntView #カリナ #セブチ 2024-05-05 06:58',
'comment_count': int,
'view_count': int,
'timestamp': 1714726805,
'uploader': 'Ent.View K-news🎶💕',
'uploader_id': '16943797',
'live_status': 'is_live',
'upload_date': '20240503',
},
}, {
'url': 'https://mixch.tv/u/16137876/live',
'only_matching': True,
@@ -48,8 +57,20 @@ class MixchIE(InfoExtractor):
'protocol': 'm3u8',
}],
'is_live': True,
'__post_extractor': self.extract_comments(video_id),
}
def _get_comments(self, video_id):
yield from traverse_obj(self._download_json(
f'https://mixch.tv/api-web/lives/{video_id}/messages', video_id,
note='Downloading comments', errnote='Failed to download comments'), (..., {
'author': ('name', {str}),
'author_id': ('user_id', {str_or_none}),
'id': ('message_id', {str}, {lambda x: x or None}),
'text': ('body', {str}),
'timestamp': ('created', {int}),
}))
class MixchArchiveIE(InfoExtractor):
IE_NAME = 'mixch:archive'

3
yt_dlp/extractor/neteasemusic.py
View File

@@ -561,7 +561,8 @@ class NetEaseMusicProgramIE(NetEaseMusicBaseIE):
'timestamp': ('createTime', {self.kilo_or_none}),
})
if not self._yes_playlist(info['songs'] and program_id, info['mainSong']['id']):
if not self._yes_playlist(
info['songs'] and program_id, info['mainSong']['id'], playlist_label='program', video_label='song'):
formats = self.extract_formats(info['mainSong'])
return {

27
yt_dlp/extractor/nfb.py
View File

@@ -5,7 +5,6 @@ from ..utils import (
merge_dicts,
parse_count,
url_or_none,
urljoin,
)
from ..utils.traversal import traverse_obj
@@ -16,8 +15,7 @@ class NFBBaseIE(InfoExtractor):
def _extract_ep_data(self, webpage, video_id, fatal=False):
return self._search_json(
r'const\s+episodesData\s*=', webpage, 'episode data', video_id,
contains_pattern=r'\[\s*{(?s:.+)}\s*\]', fatal=fatal) or []
r'episodesData\s*:', webpage, 'episode data', video_id, fatal=fatal) or {}
def _extract_ep_info(self, data, video_id, slug=None):
info = traverse_obj(data, (lambda _, v: video_id in v['embed_url'], {
@@ -224,18 +222,14 @@ class NFBIE(NFBBaseIE):
# type_ can change from film to serie(s) after redirect; new slug may have episode number
type_, slug = self._match_valid_url(urlh.url).group('type', 'id')
embed_url = urljoin(f'https://www.{site}.ca', self._html_search_regex(
r'<[^>]+\bid=["\']player-iframe["\'][^>]*\bsrc=["\']([^"\']+)', webpage, 'embed url'))
video_id = self._match_id(embed_url) # embed url has unique slug
player = self._download_webpage(embed_url, video_id, 'Downloading player page')
if 'MESSAGE_GEOBLOCKED' in player:
self.raise_geo_restricted(countries=self._GEO_COUNTRIES)
player_data = self._search_json(
r'window\.PLAYER_OPTIONS\[[^\]]+\]\s*=', webpage, 'player data', slug)
video_id = self._match_id(player_data['overlay']['url']) # overlay url always has unique slug
formats, subtitles = self._extract_m3u8_formats_and_subtitles(
self._html_search_regex(r'source:\s*\'([^\']+)', player, 'm3u8 url'),
video_id, 'mp4', m3u8_id='hls')
player_data['source'], video_id, 'mp4', m3u8_id='hls')
if dv_source := self._html_search_regex(r'dvSource:\s*\'([^\']+)', player, 'dv', default=None):
if dv_source := url_or_none(player_data.get('dvSource')):
fmts, subs = self._extract_m3u8_formats_and_subtitles(
dv_source, video_id, 'mp4', m3u8_id='dv', preference=-2, fatal=False)
for fmt in fmts:
@@ -246,17 +240,16 @@ class NFBIE(NFBBaseIE):
info = {
'id': video_id,
'title': self._html_search_regex(
r'<[^>]+\bid=["\']titleHeader["\'][^>]*>\s*<h1[^>]*>\s*([^<]+?)\s*</h1>',
r'["\']nfb_version_title["\']\s*:\s*["\']([^"\']+)',
webpage, 'title', default=None),
'description': self._html_search_regex(
r'<[^>]+\bid=["\']tabSynopsis["\'][^>]*>\s*<p[^>]*>\s*([^<]+)',
webpage, 'description', default=None),
'thumbnail': self._html_search_regex(
r'poster:\s*\'([^\']+)', player, 'thumbnail', default=None),
'thumbnail': url_or_none(player_data.get('poster')),
'uploader': self._html_search_regex(
r'<[^>]+\bitemprop=["\']name["\'][^>]*>([^<]+)', webpage, 'uploader', default=None),
r'<[^>]+\bitemprop=["\']director["\'][^>]*>([^<]+)', webpage, 'uploader', default=None),
'release_year': int_or_none(self._html_search_regex(
r'<[^>]+\bitemprop=["\']datePublished["\'][^>]*>([^<]+)',
r'["\']nfb_version_year["\']\s*:\s*["\']([^"\']+)',
webpage, 'release_year', default=None)),
} if type_ == 'film' else self._extract_ep_info(self._extract_ep_data(webpage, video_id, slug), video_id)

134
yt_dlp/extractor/patreon.py
View File

@@ -219,7 +219,29 @@ class PatreonIE(PatreonBaseIE):
'thumbnail': r're:^https?://.+',
},
'params': {'skip_download': 'm3u8'},
}, {
# multiple attachments/embeds
'url': 'https://www.patreon.com/posts/holy-wars-solos-100601977',
'playlist_count': 3,
'info_dict': {
'id': '100601977',
'title': '"Holy Wars" (Megadeth) Solos Transcription & Lesson/Analysis',
'description': 'md5:d099ab976edfce6de2a65c2b169a88d3',
'uploader': 'Bradley Hall',
'uploader_id': '24401883',
'uploader_url': 'https://www.patreon.com/bradleyhallguitar',
'channel_id': '3193932',
'channel_url': 'https://www.patreon.com/bradleyhallguitar',
'channel_follower_count': int,
'timestamp': 1710777855,
'upload_date': '20240318',
'like_count': int,
'comment_count': int,
'thumbnail': r're:^https?://.+',
},
'skip': 'Patron-only content',
}]
_RETURN_TYPE = 'video'
def _real_extract(self, url):
video_id = self._match_id(url)
@@ -234,58 +256,54 @@ class PatreonIE(PatreonBaseIE):
'include': 'audio,user,user_defined_tags,campaign,attachments_media',
})
attributes = post['data']['attributes']
title = attributes['title'].strip()
image = attributes.get('image') or {}
info = {
'id': video_id,
'title': title,
'description': clean_html(attributes.get('content')),
'thumbnail': image.get('large_url') or image.get('url'),
'timestamp': parse_iso8601(attributes.get('published_at')),
'like_count': int_or_none(attributes.get('like_count')),
'comment_count': int_or_none(attributes.get('comment_count')),
}
can_view_post = traverse_obj(attributes, 'current_user_can_view')
if can_view_post and info['comment_count']:
info['__post_extractor'] = self.extract_comments(video_id)
info = traverse_obj(attributes, {
'title': ('title', {str.strip}),
'description': ('content', {clean_html}),
'thumbnail': ('image', ('large_url', 'url'), {url_or_none}, any),
'timestamp': ('published_at', {parse_iso8601}),
'like_count': ('like_count', {int_or_none}),
'comment_count': ('comment_count', {int_or_none}),
})
for i in post.get('included', []):
i_type = i.get('type')
if i_type == 'media':
media_attributes = i.get('attributes') or {}
download_url = media_attributes.get('download_url')
entries = []
idx = 0
for include in traverse_obj(post, ('included', lambda _, v: v['type'])):
include_type = include['type']
if include_type == 'media':
media_attributes = traverse_obj(include, ('attributes', {dict})) or {}
download_url = url_or_none(media_attributes.get('download_url'))
ext = mimetype2ext(media_attributes.get('mimetype'))
# if size_bytes is None, this media file is likely unavailable
# See: https://github.com/yt-dlp/yt-dlp/issues/4608
size_bytes = int_or_none(media_attributes.get('size_bytes'))
if download_url and ext in KNOWN_EXTENSIONS and size_bytes is not None:
# XXX: what happens if there are multiple attachments?
return {
**info,
idx += 1
entries.append({
'id': f'{video_id}-{idx}',
'ext': ext,
'filesize': size_bytes,
'url': download_url,
}
elif i_type == 'user':
user_attributes = i.get('attributes')
if user_attributes:
info.update({
'uploader': user_attributes.get('full_name'),
'uploader_id': str_or_none(i.get('id')),
'uploader_url': user_attributes.get('url'),
})
elif i_type == 'post_tag':
info.setdefault('tags', []).append(traverse_obj(i, ('attributes', 'value')))
elif include_type == 'user':
info.update(traverse_obj(include, {
'uploader': ('attributes', 'full_name', {str}),
'uploader_id': ('id', {str_or_none}),
'uploader_url': ('attributes', 'url', {url_or_none}),
}))
elif i_type == 'campaign':
info.update({
'channel': traverse_obj(i, ('attributes', 'title')),
'channel_id': str_or_none(i.get('id')),
'channel_url': traverse_obj(i, ('attributes', 'url')),
'channel_follower_count': int_or_none(traverse_obj(i, ('attributes', 'patron_count'))),
})
elif include_type == 'post_tag':
if post_tag := traverse_obj(include, ('attributes', 'value', {str})):
info.setdefault('tags', []).append(post_tag)
elif include_type == 'campaign':
info.update(traverse_obj(include, {
'channel': ('attributes', 'title', {str}),
'channel_id': ('id', {str_or_none}),
'channel_url': ('attributes', 'url', {url_or_none}),
'channel_follower_count': ('attributes', 'patron_count', {int_or_none}),
}))
# handle Vimeo embeds
if traverse_obj(attributes, ('embed', 'provider')) == 'Vimeo':
@@ -296,36 +314,50 @@ class PatreonIE(PatreonBaseIE):
v_url, video_id, 'Checking Vimeo embed URL',
headers={'Referer': 'https://patreon.com/'},
fatal=False, errnote=False):
return self.url_result(
entries.append(self.url_result(
VimeoIE._smuggle_referrer(v_url, 'https://patreon.com/'),
VimeoIE, url_transparent=True, **info)
VimeoIE, url_transparent=True))
embed_url = traverse_obj(attributes, ('embed', 'url', {url_or_none}))
if embed_url and self._request_webpage(embed_url, video_id, 'Checking embed URL', fatal=False, errnote=False):
return self.url_result(embed_url, **info)
entries.append(self.url_result(embed_url))
post_file = traverse_obj(attributes, 'post_file')
post_file = traverse_obj(attributes, ('post_file', {dict}))
if post_file:
name = post_file.get('name')
ext = determine_ext(name)
if ext in KNOWN_EXTENSIONS:
return {
**info,
entries.append({
'id': video_id,
'ext': ext,
'url': post_file['url'],
}
})
elif name == 'video' or determine_ext(post_file.get('url')) == 'm3u8':
formats, subtitles = self._extract_m3u8_formats_and_subtitles(post_file['url'], video_id)
return {
**info,
entries.append({
'id': video_id,
'formats': formats,
'subtitles': subtitles,
}
})
if can_view_post is False:
can_view_post = traverse_obj(attributes, 'current_user_can_view')
comments = None
if can_view_post and info.get('comment_count'):
comments = self.extract_comments(video_id)
if not entries and can_view_post is False:
self.raise_no_formats('You do not have access to this post', video_id=video_id, expected=True)
else:
elif not entries:
self.raise_no_formats('No supported media found in this post', video_id=video_id, expected=True)
elif len(entries) == 1:
info.update(entries[0])
else:
for entry in entries:
entry.update(info)
return self.playlist_result(entries, video_id, **info, __post_extractor=comments)
info['id'] = video_id
info['__post_extractor'] = comments
return info
def _get_comments(self, post_id):

95
yt_dlp/extractor/porn91.py
View File

@@ -1,95 +0,0 @@
import urllib.parse
from .common import InfoExtractor
from ..utils import (
determine_ext,
int_or_none,
parse_duration,
remove_end,
unified_strdate,
ExtractorError,
)
class Porn91IE(InfoExtractor):
IE_NAME = '91porn'
_VALID_URL = r'(?:https?://)(?:www\.|)91porn\.com/view_video.php\?([^#]+&)?viewkey=(?P<id>\w+)'
_TESTS = [{
'url': 'http://91porn.com/view_video.php?viewkey=7e42283b4f5ab36da134',
'md5': 'd869db281402e0ef4ddef3c38b866f86',
'info_dict': {
'id': '7e42283b4f5ab36da134',
'title': '18岁大一漂亮学妹，水嫩性感，再爽一次！',
'description': 'md5:1ff241f579b07ae936a54e810ad2e891',
'ext': 'mp4',
'duration': 431,
'upload_date': '20150520',
'comment_count': int,
'view_count': int,
'age_limit': 18,
}
}, {
'url': 'https://91porn.com/view_video.php?viewkey=7ef0cf3d362c699ab91c',
'md5': 'f8fd50540468a6d795378cd778b40226',
'info_dict': {
'id': '7ef0cf3d362c699ab91c',
'title': '真实空乘，冲上云霄第二部',
'description': 'md5:618bf9652cafcc66cd277bd96789baea',
'ext': 'mp4',
'duration': 248,
'upload_date': '20221119',
'comment_count': int,
'view_count': int,
'age_limit': 18,
}
}]
def _real_extract(self, url):
video_id = self._match_id(url)
self._set_cookie('91porn.com', 'language', 'cn_CN')
webpage = self._download_webpage(
'http://91porn.com/view_video.php?viewkey=%s' % video_id, video_id)
if '视频不存在,可能已经被删除或者被举报为不良内容!' in webpage:
raise ExtractorError('91 Porn says: Video does not exist', expected=True)
daily_limit = self._search_regex(
r'作为游客，你每天只可观看([\d]+)个视频', webpage, 'exceeded daily limit', default=None, fatal=False)
if daily_limit:
raise ExtractorError(f'91 Porn says: Daily limit {daily_limit} videos exceeded', expected=True)
video_link_url = self._search_regex(
r'document\.write\(\s*strencode2\s*\(\s*((?:"[^"]+")|(?:\'[^\']+\'))', webpage, 'video link')
video_link_url = self._search_regex(
r'src=["\']([^"\']+)["\']', urllib.parse.unquote(video_link_url), 'unquoted video link')
formats, subtitles = self._get_formats_and_subtitle(video_link_url, video_id)
return {
'id': video_id,
'title': remove_end(self._html_extract_title(webpage).replace('\n', ''), 'Chinese homemade video').strip(),
'formats': formats,
'subtitles': subtitles,
'upload_date': unified_strdate(self._search_regex(
r'<span\s+class=["\']title-yakov["\']>(\d{4}-\d{2}-\d{2})</span>', webpage, 'upload_date', fatal=False)),
'description': self._html_search_regex(
r'<span\s+class=["\']more title["\']>\s*([^<]+)', webpage, 'description', fatal=False),
'duration': parse_duration(self._search_regex(
r'时长:\s*<span[^>]*>\s*(\d+(?::\d+){1,2})', webpage, 'duration', fatal=False)),
'comment_count': int_or_none(self._search_regex(
r'留言:\s*<span[^>]*>\s*(\d+)\s*</span>', webpage, 'comment count', fatal=False)),
'view_count': int_or_none(self._search_regex(
r'热度:\s*<span[^>]*>\s*(\d+)\s*</span>', webpage, 'view count', fatal=False)),
'age_limit': 18,
}
def _get_formats_and_subtitle(self, video_link_url, video_id):
ext = determine_ext(video_link_url)
if ext == 'm3u8':
formats, subtitles = self._extract_m3u8_formats_and_subtitles(video_link_url, video_id, ext='mp4')
else:
formats = [{'url': video_link_url, 'ext': ext}]
subtitles = {}
return formats, subtitles

2
yt_dlp/extractor/pornhub.py
View File

@@ -97,7 +97,7 @@ class PornHubBaseIE(InfoExtractor):
login_form = self._hidden_inputs(login_page)
login_form.update({
'username': username,
'email': username,
'password': password,
})

50
yt_dlp/extractor/soundcloud.py
View File

@@ -361,7 +361,7 @@ class SoundcloudBaseIE(InfoExtractor):
'like_count': extract_count('favoritings') or extract_count('likes'),
'comment_count': extract_count('comment'),
'repost_count': extract_count('reposts'),
'genre': info.get('genre'),
'genres': traverse_obj(info, ('genre', {str}, {lambda x: x or None}, all)),
'formats': formats if not extract_flat else None
}
@@ -395,10 +395,10 @@ class SoundcloudIE(SoundcloudBaseIE):
_TESTS = [
{
'url': 'http://soundcloud.com/ethmusic/lostin-powers-she-so-heavy',
'md5': 'ebef0a451b909710ed1d7787dddbf0d7',
'md5': 'de9bac153e7427a7333b4b0c1b6a18d2',
'info_dict': {
'id': '62986583',
'ext': 'mp3',
'ext': 'opus',
'title': 'Lostin Powers - She so Heavy (SneakPreview) Adrian Ackers Blueprint 1',
'description': 'No Downloads untill we record the finished version this weekend, i was too pumped n i had to post it , earl is prolly gonna b hella p.o\'d',
'uploader': 'E.T. ExTerrestrial Music',
@@ -411,6 +411,9 @@ class SoundcloudIE(SoundcloudBaseIE):
'like_count': int,
'comment_count': int,
'repost_count': int,
'thumbnail': 'https://i1.sndcdn.com/artworks-000031955188-rwb18x-original.jpg',
'uploader_url': 'https://soundcloud.com/ethmusic',
'genres': [],
}
},
# geo-restricted
@@ -418,7 +421,7 @@ class SoundcloudIE(SoundcloudBaseIE):
'url': 'https://soundcloud.com/the-concept-band/goldrushed-mastered?in=the-concept-band/sets/the-royal-concept-ep',
'info_dict': {
'id': '47127627',
'ext': 'mp3',
'ext': 'opus',
'title': 'Goldrushed',
'description': 'From Stockholm Sweden\r\nPovel / Magnus / Filip / David\r\nwww.theroyalconcept.com',
'uploader': 'The Royal Concept',
@@ -431,6 +434,9 @@ class SoundcloudIE(SoundcloudBaseIE):
'like_count': int,
'comment_count': int,
'repost_count': int,
'uploader_url': 'https://soundcloud.com/the-concept-band',
'thumbnail': 'https://i1.sndcdn.com/artworks-v8bFHhXm7Au6-0-original.jpg',
'genres': ['Alternative'],
},
},
# private link
@@ -452,6 +458,9 @@ class SoundcloudIE(SoundcloudBaseIE):
'like_count': int,
'comment_count': int,
'repost_count': int,
'uploader_url': 'https://soundcloud.com/jaimemf',
'thumbnail': 'https://a1.sndcdn.com/images/default_avatar_large.png',
'genres': ['youtubedl'],
},
},
# private link (alt format)
@@ -473,6 +482,9 @@ class SoundcloudIE(SoundcloudBaseIE):
'like_count': int,
'comment_count': int,
'repost_count': int,
'uploader_url': 'https://soundcloud.com/jaimemf',
'thumbnail': 'https://a1.sndcdn.com/images/default_avatar_large.png',
'genres': ['youtubedl'],
},
},
# downloadable song
@@ -482,6 +494,21 @@ class SoundcloudIE(SoundcloudBaseIE):
'info_dict': {
'id': '343609555',
'ext': 'wav',
'title': 'The Following',
'description': '',
'uploader': '80M',
'uploader_id': '312384765',
'uploader_url': 'https://soundcloud.com/the80m',
'upload_date': '20170922',
'timestamp': 1506120436,
'duration': 397.228,
'thumbnail': 'https://i1.sndcdn.com/artworks-000243916348-ktoo7d-original.jpg',
'license': 'all-rights-reserved',
'like_count': int,
'comment_count': int,
'repost_count': int,
'view_count': int,
'genres': ['Dance & EDM'],
},
},
# private link, downloadable format
@@ -503,6 +530,9 @@ class SoundcloudIE(SoundcloudBaseIE):
'like_count': int,
'comment_count': int,
'repost_count': int,
'thumbnail': 'https://i1.sndcdn.com/artworks-000240712245-kedn4p-original.jpg',
'uploader_url': 'https://soundcloud.com/oriuplift',
'genres': ['Trance'],
},
},
# no album art, use avatar pic for thumbnail
@@ -525,6 +555,8 @@ class SoundcloudIE(SoundcloudBaseIE):
'like_count': int,
'comment_count': int,
'repost_count': int,
'uploader_url': 'https://soundcloud.com/garyvee',
'genres': [],
},
'params': {
'skip_download': True,
@@ -532,13 +564,13 @@ class SoundcloudIE(SoundcloudBaseIE):
},
{
'url': 'https://soundcloud.com/giovannisarani/mezzo-valzer',
'md5': 'e22aecd2bc88e0e4e432d7dcc0a1abf7',
'md5': '8227c3473a4264df6b02ad7e5b7527ac',
'info_dict': {
'id': '583011102',
'ext': 'mp3',
'ext': 'opus',
'title': 'Mezzo Valzer',
'description': 'md5:4138d582f81866a530317bae316e8b61',
'uploader': 'Micronie',
'description': 'md5:f4d5f39d52e0ccc2b4f665326428901a',
'uploader': 'Giovanni Sarani',
'uploader_id': '3352531',
'timestamp': 1551394171,
'upload_date': '20190228',
@@ -549,6 +581,8 @@ class SoundcloudIE(SoundcloudBaseIE):
'like_count': int,
'comment_count': int,
'repost_count': int,
'genres': ['Piano'],
'uploader_url': 'https://soundcloud.com/giovannisarani',
},
},
{

28
yt_dlp/extractor/tiktok.py
View File

@@ -45,19 +45,18 @@ class TikTokBaseIE(InfoExtractor):
# "app id": aweme = 1128, trill = 1180, musical_ly = 1233, universal = 0
'aid': '0',
}
_KNOWN_APP_INFO = [
'7351144126450059040',
'7351149742343391009',
'7351153174894626592',
]
_APP_INFO_POOL = None
_APP_INFO = None
_APP_USER_AGENT = None
@property
def _KNOWN_APP_INFO(self):
return self._configuration_arg('app_info', ie_key=TikTokIE)
@property
def _API_HOSTNAME(self):
return self._configuration_arg(
'api_hostname', ['api22-normal-c-useast2a.tiktokv.com'], ie_key=TikTokIE)[0]
'api_hostname', ['api16-normal-c-useast1a.tiktokv.com'], ie_key=TikTokIE)[0]
def _get_next_app_info(self):
if self._APP_INFO_POOL is None:
@@ -66,13 +65,10 @@ class TikTokBaseIE(InfoExtractor):
for key, default in self._APP_INFO_DEFAULTS.items()
if key != 'iid'
}
app_info_list = (
self._configuration_arg('app_info', ie_key=TikTokIE)
or random.sample(self._KNOWN_APP_INFO, len(self._KNOWN_APP_INFO)))
self._APP_INFO_POOL = [
{**defaults, **dict(
(k, v) for k, v in zip(self._APP_INFO_DEFAULTS, app_info.split('/')) if v
)} for app_info in app_info_list
)} for app_info in self._KNOWN_APP_INFO
]
if not self._APP_INFO_POOL:
@@ -757,11 +753,13 @@ class TikTokIE(TikTokBaseIE):
def _real_extract(self, url):
video_id, user_id = self._match_valid_url(url).group('id', 'user_id')
try:
return self._extract_aweme_app(video_id)
except ExtractorError as e:
e.expected = True
self.report_warning(f'{e}; trying with webpage')
if self._KNOWN_APP_INFO:
try:
return self._extract_aweme_app(video_id)
except ExtractorError as e:
e.expected = True
self.report_warning(f'{e}; trying with webpage')
url = self._create_url(user_id, video_id)
webpage = self._download_webpage(url, video_id, headers={'User-Agent': 'Mozilla/5.0'})

149
yt_dlp/extractor/tv5mondeplus.py
View File

@@ -2,85 +2,88 @@ import urllib.parse
from .common import InfoExtractor
from ..utils import (
clean_html,
determine_ext,
extract_attributes,
get_element_by_class,
get_element_html_by_class,
int_or_none,
parse_duration,
traverse_obj,
try_get,
url_or_none,
)
from ..utils.traversal import traverse_obj
class TV5MondePlusIE(InfoExtractor):
IE_DESC = 'TV5MONDE+'
_VALID_URL = r'https?://(?:www\.)?(?:tv5mondeplus|revoir\.tv5monde)\.com/toutes-les-videos/[^/]+/(?P<id>[^/?#]+)'
IE_NAME = 'TV5MONDE'
_VALID_URL = r'https?://(?:www\.)?tv5monde\.com/tv/video/(?P<id>[^/?#]+)'
_TESTS = [{
# movie
'url': 'https://revoir.tv5monde.com/toutes-les-videos/cinema/les-novices',
'md5': 'c86f60bf8b75436455b1b205f9745955',
# documentary
'url': 'https://www.tv5monde.com/tv/video/65931-baudouin-l-heritage-d-un-roi-baudouin-l-heritage-d-un-roi',
'md5': 'd2a708902d3df230a357c99701aece05',
'info_dict': {
'id': 'ZX0ipMyFQq_6D4BA7b',
'display_id': 'les-novices',
'id': '3FPa7JMu21_6D4BA7b',
'display_id': '65931-baudouin-l-heritage-d-un-roi-baudouin-l-heritage-d-un-roi',
'ext': 'mp4',
'title': 'Les novices',
'description': 'md5:2e7c33ba3ad48dabfcc2a956b88bde2b',
'upload_date': '20230821',
'thumbnail': 'https://revoir.tv5monde.com/uploads/media/video_thumbnail/0738/60/01e952b7ccf36b7c6007ec9131588954ab651de9.jpeg',
'duration': 5177,
'episode': 'Les novices',
'title': "Baudouin, l'héritage d'un roi",
'thumbnail': 'https://psi.tv5monde.com/upsilon-images/960x540/6f/baudouin-f49c6b0e.jpg',
'duration': 4842,
'upload_date': '20240130',
'timestamp': 1706641242,
'episode': "BAUDOUIN, L'HERITAGE D'UN ROI",
'description': 'md5:78125c74a5cac06d7743a2d09126edad',
'series': "Baudouin, l'héritage d'un roi",
},
}, {
# series episode
'url': 'https://revoir.tv5monde.com/toutes-les-videos/series-fictions/opj-les-dents-de-la-terre-2',
'url': 'https://www.tv5monde.com/tv/video/52952-toute-la-vie-mardi-23-mars-2021',
'md5': 'f5e09637cadd55639c05874e22eb56bf',
'info_dict': {
'id': 'wJ0eeEPozr_6D4BA7b',
'display_id': 'opj-les-dents-de-la-terre-2',
'id': 'obRRZ8m6g9_6D4BA7b',
'display_id': '52952-toute-la-vie-mardi-23-mars-2021',
'ext': 'mp4',
'title': "OPJ - Les dents de la Terre (2)",
'description': 'md5:288f87fd68d993f814e66e60e5302d9d',
'upload_date': '20230823',
'series': 'OPJ',
'episode': 'Les dents de la Terre (2)',
'duration': 2877,
'thumbnail': 'https://dl-revoir.tv5monde.com/images/1a/5753448.jpg'
'title': 'Toute la vie',
'description': 'md5:a824a2e1dfd94cf45fa379a1fb43ce65',
'thumbnail': 'https://psi.tv5monde.com/media/image/960px/5880553.jpg',
'duration': 2526,
'upload_date': '20230721',
'timestamp': 1689971646,
'series': 'Toute la vie',
'episode': 'Mardi 23 mars 2021',
},
}, {
# movie
'url': 'https://revoir.tv5monde.com/toutes-les-videos/cinema/ceux-qui-travaillent',
'md5': '32fa0cde16a4480d1251502a66856d5f',
'url': 'https://www.tv5monde.com/tv/video/8771-ce-fleuve-qui-nous-charrie-ce-fleuve-qui-nous-charrie-p001-ce-fleuve-qui-nous-charrie',
'md5': '87cefc34e10a6bf4f7823cccd7b36eb2',
'info_dict': {
'id': 'dc57a011-ec4b-4648-2a9a-4f03f8352ed3',
'display_id': 'ceux-qui-travaillent',
'id': 'DOcfvdLKXL_6D4BA7b',
'display_id': '8771-ce-fleuve-qui-nous-charrie-ce-fleuve-qui-nous-charrie-p001-ce-fleuve-qui-nous-charrie',
'ext': 'mp4',
'title': 'Ceux qui travaillent',
'description': 'md5:570e8bb688036ace873b2d50d24c026d',
'upload_date': '20210819',
'title': 'Ce fleuve qui nous charrie',
'description': 'md5:62ba3f875343c7fc4082bdfbbc1be992',
'thumbnail': 'https://psi.tv5monde.com/media/image/960px/5476617.jpg',
'duration': 5300,
'upload_date': '20210822',
'timestamp': 1629594105,
'episode': 'CE FLEUVE QUI NOUS CHARRIE-P001-CE FLEUVE QUI NOUS CHARRIE',
'series': 'Ce fleuve qui nous charrie',
},
'skip': 'no longer available',
}, {
# series episode
'url': 'https://revoir.tv5monde.com/toutes-les-videos/series-fictions/vestiaires-caro-actrice',
# news
'url': 'https://www.tv5monde.com/tv/video/70402-tv5monde-le-journal-edition-du-08-05-24-11h',
'md5': 'c62977d6d10754a2ecebba70ad370479',
'info_dict': {
'id': '9e9d599e-23af-6915-843e-ecbf62e97925',
'display_id': 'vestiaires-caro-actrice',
'id': 'LgQFrOCNsc_6D4BA7b',
'display_id': '70402-tv5monde-le-journal-edition-du-08-05-24-11h',
'ext': 'mp4',
'title': "Vestiaires - Caro actrice",
'description': 'md5:db15d2e1976641e08377f942778058ea',
'upload_date': '20210819',
'series': "Vestiaires",
'episode': 'Caro actrice',
'title': 'TV5MONDE, le journal',
'description': 'md5:777dc209eaa4423b678477c36b0b04a8',
'thumbnail': 'https://psi.tv5monde.com/media/image/960px/6184105.jpg',
'duration': 854,
'upload_date': '20240508',
'timestamp': 1715159640,
'series': 'TV5MONDE, le journal',
'episode': 'EDITION DU 08/05/24 - 11H',
},
'params': {
'skip_download': True,
},
'skip': 'no longer available',
}, {
'url': 'https://revoir.tv5monde.com/toutes-les-videos/series-fictions/neuf-jours-en-hiver-neuf-jours-en-hiver',
'only_matching': True,
}, {
'url': 'https://revoir.tv5monde.com/toutes-les-videos/info-societe/le-journal-de-la-rts-edition-du-30-01-20-19h30',
'only_matching': True,
}]
_GEO_BYPASS = False
@@ -98,7 +101,6 @@ class TV5MondePlusIE(InfoExtractor):
if ">Ce programme n'est malheureusement pas disponible pour votre zone géographique.<" in webpage:
self.raise_geo_restricted(countries=['FR'])
title = episode = self._html_search_regex(r'<h1>([^<]+)', webpage, 'title')
vpl_data = extract_attributes(self._search_regex(
r'(<[^>]+class="video_player_loader"[^>]+>)',
webpage, 'video player loader'))
@@ -147,26 +149,7 @@ class TV5MondePlusIE(InfoExtractor):
process_video_files(video_files)
metadata = self._parse_json(
vpl_data['data-metadata'], display_id)
duration = (int_or_none(try_get(metadata, lambda x: x['content']['duration']))
or parse_duration(self._html_search_meta('duration', webpage)))
description = self._html_search_regex(
r'(?s)<div[^>]+class=["\']episode-texte[^>]+>(.+?)</div>', webpage,
'description', fatal=False)
series = self._html_search_regex(
r'<p[^>]+class=["\']episode-emission[^>]+>([^<]+)', webpage,
'series', default=None)
if series and series != title:
title = '%s - %s' % (series, title)
upload_date = self._search_regex(
r'(?:date_publication|publish_date)["\']\s*:\s*["\'](\d{4}_\d{2}_\d{2})',
webpage, 'upload date', default=None)
if upload_date:
upload_date = upload_date.replace('_', '')
vpl_data.get('data-metadata') or '{}', display_id, fatal=False)
if not video_id:
video_id = self._search_regex(
@@ -175,16 +158,20 @@ class TV5MondePlusIE(InfoExtractor):
default=display_id)
return {
**traverse_obj(metadata, ('content', {
'id': ('id', {str}),
'title': ('title', {str}),
'episode': ('title', {str}),
'series': ('series', {str}),
'timestamp': ('publishDate_ts', {int_or_none}),
'duration': ('duration', {int_or_none}),
})),
'id': video_id,
'display_id': display_id,
'title': title,
'description': description,
'thumbnail': vpl_data.get('data-image'),
'duration': duration,
'upload_date': upload_date,
'title': clean_html(get_element_by_class('main-title', webpage)),
'description': clean_html(get_element_by_class('text', get_element_html_by_class('ep-summary', webpage) or '')),
'thumbnail': url_or_none(vpl_data.get('data-image')),
'formats': formats,
'subtitles': self._extract_subtitles(self._parse_json(
traverse_obj(vpl_data, ('data-captions', {str}), default='{}'), display_id, fatal=False)),
'series': series,
'episode': episode,
}

44
yt_dlp/extractor/tva.py
View File

@@ -1,10 +1,9 @@
import functools
import re
from .common import InfoExtractor
from ..utils import (
float_or_none,
int_or_none,
smuggle_url,
strip_or_none,
)
from ..utils import float_or_none, int_or_none, smuggle_url, strip_or_none
from ..utils.traversal import traverse_obj
class TVAIE(InfoExtractor):
@@ -49,11 +48,20 @@ class QubIE(InfoExtractor):
'info_dict': {
'id': '6084352463001',
'ext': 'mp4',
'title': 'Épisode 01',
'title': 'Ép 01. Mon dernier jour',
'uploader_id': '5481942443001',
'upload_date': '20190907',
'timestamp': 1567899756,
'description': 'md5:9c0d7fbb90939420c651fd977df90145',
'thumbnail': r're:https://.+\.jpg',
'episode': 'Ép 01. Mon dernier jour',
'episode_number': 1,
'tags': ['alerte amber', 'alerte amber saison 1', 'surdemande'],
'duration': 2625.963,
'season': 'Season 1',
'season_number': 1,
'series': 'Alerte Amber',
'channel': 'TVA',
},
}, {
'url': 'https://www.qub.ca/tele/video/lcn-ca-vous-regarde-rev-30s-ap369664-1009357943',
@@ -64,22 +72,24 @@ class QubIE(InfoExtractor):
def _real_extract(self, url):
entity_id = self._match_id(url)
entity = self._download_json(
'https://www.qub.ca/proxy/pfu/content-delivery-service/v1/entities',
entity_id, query={'id': entity_id})
webpage = self._download_webpage(url, entity_id)
entity = self._search_nextjs_data(webpage, entity_id)['props']['initialProps']['pageProps']['fallbackData']
video_id = entity['videoId']
episode = strip_or_none(entity.get('name'))
return {
'_type': 'url_transparent',
'url': f'https://videos.tva.ca/details/_{video_id}',
'ie_key': TVAIE.ie_key(),
'id': video_id,
'title': episode,
# 'url': self.BRIGHTCOVE_URL_TEMPLATE % entity['referenceId'],
'url': 'https://videos.tva.ca/details/_' + video_id,
'description': entity.get('longDescription'),
'duration': float_or_none(entity.get('durationMillis'), 1000),
'episode': episode,
'episode_number': int_or_none(entity.get('episodeNumber')),
# 'ie_key': 'BrightcoveNew',
'ie_key': TVAIE.ie_key(),
**traverse_obj(entity, {
'description': ('longDescription', {str}),
'duration': ('durationMillis', {functools.partial(float_or_none, scale=1000)}),
'channel': ('knownEntities', 'channel', 'name', {str}),
'series': ('knownEntities', 'videoShow', 'name', {str}),
'season_number': ('slug', {lambda x: re.search(r'/s(?:ai|ea)son-(\d+)/', x)}, 1, {int_or_none}),
'episode_number': ('episodeNumber', {int_or_none}),
}),
}

47
yt_dlp/extractor/twitter.py
View File

@@ -34,9 +34,9 @@ from ..utils import (
class TwitterBaseIE(InfoExtractor):
_NETRC_MACHINE = 'twitter'
_API_BASE = 'https://api.twitter.com/1.1/'
_GRAPHQL_API_BASE = 'https://twitter.com/i/api/graphql/'
_BASE_REGEX = r'https?://(?:(?:www|m(?:obile)?)\.)?(?:twitter\.com|twitter3e4tixl4xyajtrzo62zg5vztmjuricljdp2c5kshju4avyoid\.onion)/'
_API_BASE = 'https://api.x.com/1.1/'
_GRAPHQL_API_BASE = 'https://x.com/i/api/graphql/'
_BASE_REGEX = r'https?://(?:(?:www|m(?:obile)?)\.)?(?:(?:twitter|x)\.com|twitter3e4tixl4xyajtrzo62zg5vztmjuricljdp2c5kshju4avyoid\.onion)/'
_AUTH = 'AAAAAAAAAAAAAAAAAAAAANRILgAAAAAAnNwIzUejRCOuH5E6I8xnZz4puTs%3D1Zv7ttfk8LF81IUq16cHjhLTvJu4FA33AGWWjCpTnA'
_LEGACY_AUTH = 'AAAAAAAAAAAAAAAAAAAAAIK1zgAAAAAA2tUWuhGZ2JceoId5GwYWU5GspY4%3DUq7gzFoCZs1QfwGoVdvSac3IniczZEYXIcDyumCauIXpcAPorE'
_flow_token = None
@@ -153,6 +153,14 @@ class TwitterBaseIE(InfoExtractor):
def is_logged_in(self):
return bool(self._get_cookies(self._API_BASE).get('auth_token'))
# XXX: Temporary workaround until twitter.com => x.com migration is completed
def _real_initialize(self):
if self.is_logged_in or not self._get_cookies('https://twitter.com/').get('auth_token'):
return
# User has not yet been migrated to x.com and has passed twitter.com cookies
TwitterBaseIE._API_BASE = 'https://api.twitter.com/1.1/'
TwitterBaseIE._GRAPHQL_API_BASE = 'https://twitter.com/i/api/graphql/'
@functools.cached_property
def _selected_api(self):
return self._configuration_arg('api', ['graphql'], ie_key='Twitter')[0]
@@ -196,17 +204,15 @@ class TwitterBaseIE(InfoExtractor):
if self.is_logged_in:
return
webpage = self._download_webpage('https://twitter.com/', None, 'Downloading login page')
guest_token = self._search_regex(
r'\.cookie\s*=\s*["\']gt=(\d+);', webpage, 'gt', default=None) or self._fetch_guest_token(None)
guest_token = self._fetch_guest_token(None)
headers = {
**self._set_base_headers(),
'content-type': 'application/json',
'x-guest-token': guest_token,
'x-twitter-client-language': 'en',
'x-twitter-active-user': 'yes',
'Referer': 'https://twitter.com/',
'Origin': 'https://twitter.com',
'Referer': 'https://x.com/',
'Origin': 'https://x.com',
}
def build_login_json(*subtask_inputs):
@@ -1191,6 +1197,31 @@ class TwitterIE(TwitterBaseIE):
'age_limit': 0,
'_old_archive_ids': ['twitter 1724884212803834154'],
},
}, {
# x.com
'url': 'https://x.com/historyinmemes/status/1790637656616943991',
'md5': 'daca3952ba0defe2cfafb1276d4c1ea5',
'info_dict': {
'id': '1790637589910654976',
'ext': 'mp4',
'title': 'Historic Vids - One of the most intense moments in history',
'description': 'One of the most intense moments in history https://t.co/Zgzhvix8ES',
'display_id': '1790637656616943991',
'uploader': 'Historic Vids',
'uploader_id': 'historyinmemes',
'uploader_url': 'https://twitter.com/historyinmemes',
'channel_id': '855481986290524160',
'upload_date': '20240515',
'timestamp': 1715756260.0,
'duration': 15.488,
'tags': [],
'comment_count': int,
'repost_count': int,
'like_count': int,
'thumbnail': r're:https://pbs\.twimg\.com/amplify_video_thumb/.+',
'age_limit': 0,
'_old_archive_ids': ['twitter 1790637656616943991'],
}
}, {
# onion route
'url': 'https://twitter3e4tixl4xyajtrzo62zg5vztmjuricljdp2c5kshju4avyoid.onion/TwitterBlue/status/1484226494708662273',

14
yt_dlp/extractor/unsupported.py
View File

@@ -173,6 +173,20 @@ class KnownPiracyIE(UnsupportedInfoExtractor):
r'filemoon\.sx',
r'hentai\.animestigma\.com',
r'thisav\.com',
r'gounlimited\.to',
r'highstream\.tv',
r'uqload\.com',
r'vedbam\.xyz',
r'vadbam\.net'
r'vidlo\.us',
r'wolfstream\.tv',
r'xvideosharing\.com',
r'(?:\w+\.)?viidshar\.com',
r'sxyprn\.com',
r'jable\.tv',
r'91porn\.com',
r'einthusan\.(?:tv|com|ca)',
r'yourupload\.com',
)
_TESTS = [{

16
yt_dlp/extractor/vk.py
View File

@@ -451,6 +451,7 @@ class VKIE(VKBaseIE):
info_page, 'view count', default=None))
formats = []
subtitles = {}
for format_id, format_url in data.items():
format_url = url_or_none(format_url)
if not format_url or not format_url.startswith(('http', '//', 'rtmp')):
@@ -462,12 +463,21 @@ class VKIE(VKBaseIE):
formats.append({
'format_id': format_id,
'url': format_url,
'ext': 'mp4',
'source_preference': 1,
'height': height,
})
elif format_id == 'hls':
formats.extend(self._extract_m3u8_formats(
fmts, subs = self._extract_m3u8_formats_and_subtitles(
format_url, video_id, 'mp4', 'm3u8_native',
m3u8_id=format_id, fatal=False, live=is_live))
m3u8_id=format_id, fatal=False, live=is_live)
formats.extend(fmts)
self._merge_subtitles(subs, target=subtitles)
elif format_id.startswith('dash_'):
fmts, subs = self._extract_mpd_formats_and_subtitles(
format_url, video_id, mpd_id=format_id, fatal=False)
formats.extend(fmts)
self._merge_subtitles(subs, target=subtitles)
elif format_id == 'rtmp':
formats.append({
'format_id': format_id,
@@ -475,7 +485,6 @@ class VKIE(VKBaseIE):
'ext': 'flv',
})
subtitles = {}
for sub in data.get('subs') or {}:
subtitles.setdefault(sub.get('lang', 'en'), []).append({
'ext': sub.get('title', '.srt').split('.')[-1],
@@ -496,6 +505,7 @@ class VKIE(VKBaseIE):
'comment_count': int_or_none(mv_data.get('commcount')),
'is_live': is_live,
'subtitles': subtitles,
'_format_sort_fields': ('res', 'source'),
}

16
yt_dlp/extractor/wrestleuniverse.py
View File

@@ -12,6 +12,7 @@ from ..utils import (
jwt_decode_hs256,
traverse_obj,
try_call,
url_basename,
url_or_none,
urlencode_postdata,
variadic,
@@ -194,8 +195,7 @@ class WrestleUniverseVODIE(WrestleUniverseBaseIE):
return {
'id': video_id,
'formats': self._get_formats(video_data, (
(('protocolHls', 'url'), ('chromecastUrls', ...)), {url_or_none}), video_id),
'formats': self._get_formats(video_data, ('protocolHls', 'url', {url_or_none}), video_id),
**traverse_obj(metadata, {
'title': ('displayName', {str}),
'description': ('description', {str}),
@@ -259,6 +259,10 @@ class WrestleUniversePPVIE(WrestleUniverseBaseIE):
'params': {
'skip_download': 'm3u8',
},
}, {
'note': 'manifest provides live-a (partial) and live-b (full) streams',
'url': 'https://www.wrestle-universe.com/en/lives/umc99R9XsexXrxr9VjTo9g',
'only_matching': True,
}]
_API_PATH = 'events'
@@ -285,12 +289,16 @@ class WrestleUniversePPVIE(WrestleUniverseBaseIE):
video_data, decrypt = self._call_encrypted_api(
video_id, ':watchArchive', 'watch archive', data={'method': 1})
info['formats'] = self._get_formats(video_data, (
('hls', None), ('urls', 'chromecastUrls'), ..., {url_or_none}), video_id)
# 'chromecastUrls' can be only partial videos, avoid
info['formats'] = self._get_formats(video_data, ('hls', (('urls', ...), 'url'), {url_or_none}), video_id)
for f in info['formats']:
# bitrates are exaggerated in PPV playlists, so avoid wrong/huge filesize_approx values
if f.get('tbr'):
f['tbr'] = int(f['tbr'] / 2.5)
# prefer variants with the same basename as the master playlist to avoid partial streams
f['format_id'] = url_basename(f['url']).partition('.')[0]
if not f['format_id'].startswith(url_basename(f['manifest_url']).partition('.')[0]):
f['preference'] = -10
hls_aes_key = traverse_obj(video_data, ('hls', 'key', {decrypt}))
if hls_aes_key:

198
yt_dlp/extractor/xfileshare.py
View File

@@ -1,198 +0,0 @@
import re
from .common import InfoExtractor
from ..utils import (
ExtractorError,
decode_packed_codes,
determine_ext,
int_or_none,
js_to_json,
urlencode_postdata,
)
# based on openload_decode from 2bfeee69b976fe049761dd3012e30b637ee05a58
def aa_decode(aa_code):
symbol_table = [
('7', '((ﾟｰﾟ) + (o^_^o))'),
('6', '((o^_^o) +(o^_^o))'),
('5', '((ﾟｰﾟ) + (ﾟΘﾟ))'),
('2', '((o^_^o) - (ﾟΘﾟ))'),
('4', '(ﾟｰﾟ)'),
('3', '(o^_^o)'),
('1', '(ﾟΘﾟ)'),
('0', '(c^_^o)'),
]
delim = '(ﾟДﾟ)[ﾟεﾟ]+'
ret = ''
for aa_char in aa_code.split(delim):
for val, pat in symbol_table:
aa_char = aa_char.replace(pat, val)
aa_char = aa_char.replace('+ ', '')
m = re.match(r'^\d+', aa_char)
if m:
ret += chr(int(m.group(0), 8))
else:
m = re.match(r'^u([\da-f]+)', aa_char)
if m:
ret += chr(int(m.group(1), 16))
return ret
class XFileShareIE(InfoExtractor):
_SITES = (
(r'aparat\.cam', 'Aparat'),
(r'clipwatching\.com', 'ClipWatching'),
(r'gounlimited\.to', 'GoUnlimited'),
(r'govid\.me', 'GoVid'),
(r'holavid\.com', 'HolaVid'),
(r'streamty\.com', 'Streamty'),
(r'thevideobee\.to', 'TheVideoBee'),
(r'uqload\.com', 'Uqload'),
(r'vidbom\.com', 'VidBom'),
(r'vidlo\.us', 'vidlo'),
(r'vidlocker\.xyz', 'VidLocker'),
(r'vidshare\.tv', 'VidShare'),
(r'vup\.to', 'VUp'),
(r'wolfstream\.tv', 'WolfStream'),
(r'xvideosharing\.com', 'XVideoSharing'),
)
IE_DESC = 'XFileShare based sites: %s' % ', '.join(list(zip(*_SITES))[1])
_VALID_URL = (r'https?://(?:www\.)?(?P<host>%s)/(?:embed-)?(?P<id>[0-9a-zA-Z]+)'
% '|'.join(site for site in list(zip(*_SITES))[0]))
_EMBED_REGEX = [r'<iframe\b[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//(?:%s)/embed-[0-9a-zA-Z]+.*?)\1' % '|'.join(site for site in list(zip(*_SITES))[0])]
_FILE_NOT_FOUND_REGEXES = (
r'>(?:404 - )?File Not Found<',
r'>The file was removed by administrator<',
)
_TESTS = [{
'url': 'https://uqload.com/dltx1wztngdz',
'md5': '3cfbb65e4c90e93d7b37bcb65a595557',
'info_dict': {
'id': 'dltx1wztngdz',
'ext': 'mp4',
'title': 'Rick Astley Never Gonna Give You mp4',
'thumbnail': r're:https://.*\.jpg'
}
}, {
'url': 'http://xvideosharing.com/fq65f94nd2ve',
'md5': '4181f63957e8fe90ac836fa58dc3c8a6',
'info_dict': {
'id': 'fq65f94nd2ve',
'ext': 'mp4',
'title': 'sample',
'thumbnail': r're:http://.*\.jpg',
},
}, {
'url': 'https://aparat.cam/n4d6dh0wvlpr',
'only_matching': True,
}, {
'url': 'https://wolfstream.tv/nthme29v9u2x',
'only_matching': True,
}]
def _real_extract(self, url):
host, video_id = self._match_valid_url(url).groups()
url = 'https://%s/' % host + ('embed-%s.html' % video_id if host in ('govid.me', 'vidlo.us') else video_id)
webpage = self._download_webpage(url, video_id)
if any(re.search(p, webpage) for p in self._FILE_NOT_FOUND_REGEXES):
raise ExtractorError('Video %s does not exist' % video_id, expected=True)
fields = self._hidden_inputs(webpage)
if fields.get('op') == 'download1':
countdown = int_or_none(self._search_regex(
r'<span id="countdown_str">(?:[Ww]ait)?\s*<span id="cxc">(\d+)</span>\s*(?:seconds?)?</span>',
webpage, 'countdown', default=None))
if countdown:
self._sleep(countdown, video_id)
webpage = self._download_webpage(
url, video_id, 'Downloading video page',
data=urlencode_postdata(fields), headers={
'Referer': url,
'Content-type': 'application/x-www-form-urlencoded',
})
title = (self._search_regex(
(r'style="z-index: [0-9]+;">([^<]+)</span>',
r'<td nowrap>([^<]+)</td>',
r'h4-fine[^>]*>([^<]+)<',
r'>Watch (.+)[ <]',
r'<h2 class="video-page-head">([^<]+)</h2>',
r'<h2 style="[^"]*color:#403f3d[^"]*"[^>]*>([^<]+)<', # streamin.to
r'title\s*:\s*"([^"]+)"'), # govid.me
webpage, 'title', default=None) or self._og_search_title(
webpage, default=None) or video_id).strip()
for regex, func in (
(r'(eval\(function\(p,a,c,k,e,d\){.+)', decode_packed_codes),
(r'(ﾟ.+)', aa_decode)):
obf_code = self._search_regex(regex, webpage, 'obfuscated code', default=None)
if obf_code:
webpage = webpage.replace(obf_code, func(obf_code))
formats = []
jwplayer_data = self._search_regex(
[
r'jwplayer\("[^"]+"\)\.load\(\[({.+?})\]\);',
r'jwplayer\("[^"]+"\)\.setup\(({.+?})\);',
], webpage,
'jwplayer data', default=None)
if jwplayer_data:
jwplayer_data = self._parse_json(
jwplayer_data.replace(r"\'", "'"), video_id, js_to_json)
if jwplayer_data:
formats = self._parse_jwplayer_data(
jwplayer_data, video_id, False,
m3u8_id='hls', mpd_id='dash')['formats']
if not formats:
urls = []
for regex in (
r'(?:file|src)\s*:\s*(["\'])(?P<url>http(?:(?!\1).)+\.(?:m3u8|mp4|flv)(?:(?!\1).)*)\1',
r'file_link\s*=\s*(["\'])(?P<url>http(?:(?!\1).)+)\1',
r'addVariable\((\\?["\'])file\1\s*,\s*(\\?["\'])(?P<url>http(?:(?!\2).)+)\2\)',
r'<embed[^>]+src=(["\'])(?P<url>http(?:(?!\1).)+\.(?:m3u8|mp4|flv)(?:(?!\1).)*)\1'):
for mobj in re.finditer(regex, webpage):
video_url = mobj.group('url')
if video_url not in urls:
urls.append(video_url)
sources = self._search_regex(
r'sources\s*:\s*(\[(?!{)[^\]]+\])', webpage, 'sources', default=None)
if sources:
urls.extend(self._parse_json(sources, video_id))
formats = []
for video_url in urls:
if determine_ext(video_url) == 'm3u8':
formats.extend(self._extract_m3u8_formats(
video_url, video_id, 'mp4',
entry_protocol='m3u8_native', m3u8_id='hls',
fatal=False))
else:
formats.append({
'url': video_url,
'format_id': 'sd',
})
thumbnail = self._search_regex(
[
r'<video[^>]+poster="([^"]+)"',
r'(?:image|poster)\s*:\s*["\'](http[^"\']+)["\'],',
], webpage, 'thumbnail', default=None)
return {
'id': video_id,
'title': title,
'thumbnail': thumbnail,
'formats': formats,
'http_headers': {'Referer': url}
}

37
yt_dlp/extractor/xvideos.py
View File

@@ -173,8 +173,41 @@ class XVideosIE(InfoExtractor):
class XVideosQuickiesIE(InfoExtractor):
IE_NAME = 'xvideos:quickies'
_VALID_URL = r'https?://(?P<domain>(?:[^/]+\.)?xvideos2?\.com)/amateur-channels/[^#]+#quickies/a/(?P<id>\d+)'
_VALID_URL = r'https?://(?P<domain>(?:[^/?#]+\.)?xvideos2?\.com)/(?:profiles/|amateur-channels/)?[^/?#]+#quickies/a/(?P<id>\w+)'
_TESTS = [{
'url': 'https://www.xvideos.com/lili_love#quickies/a/ipdtikh1a4c',
'md5': 'f9e4f518ff1de14b99a400bbd0fc5ee0',
'info_dict': {
'id': 'ipdtikh1a4c',
'ext': 'mp4',
'title': 'Mexican chichóna putisima',
'age_limit': 18,
'duration': 81,
'thumbnail': r're:^https://cdn.*-pic.xvideos-cdn.com/.+\.jpg',
}
}, {
'url': 'https://www.xvideos.com/profiles/lili_love#quickies/a/ipphaob6fd1',
'md5': '5340938aac6b46e19ebdd1d84535862e',
'info_dict': {
'id': 'ipphaob6fd1',
'ext': 'mp4',
'title': 'Puta chichona mexicana squirting',
'age_limit': 18,
'duration': 56,
'thumbnail': r're:^https://cdn.*-pic.xvideos-cdn.com/.+\.jpg',
}
}, {
'url': 'https://www.xvideos.com/amateur-channels/lili_love#quickies/a/hfmffmd7661',
'md5': '92428518bbabcb4c513e55922e022491',
'info_dict': {
'id': 'hfmffmd7661',
'ext': 'mp4',
'title': 'Chichona mexican slut',
'age_limit': 18,
'duration': 9,
'thumbnail': r're:^https://cdn.*-pic.xvideos-cdn.com/.+\.jpg',
}
}, {
'url': 'https://www.xvideos.com/amateur-channels/wifeluna#quickies/a/47258683',
'md5': '16e322a93282667f1963915568f782c1',
'info_dict': {
@@ -189,4 +222,4 @@ class XVideosQuickiesIE(InfoExtractor):
def _real_extract(self, url):
domain, id_ = self._match_valid_url(url).group('domain', 'id')
return self.url_result(f'https://{domain}/video{id_}/_', XVideosIE, id_)
return self.url_result(f'https://{domain}/video{"" if id_.isdecimal() else "."}{id_}/_', XVideosIE, id_)

10
yt_dlp/extractor/yandexvideo.py
View File

@@ -259,15 +259,15 @@ class ZenYandexIE(InfoExtractor):
webpage = self._download_webpage(redirect, video_id, note='Redirecting')
data_json = self._search_json(
r'("data"\s*:|data\s*=)', webpage, 'metadata', video_id, contains_pattern=r'{["\']_*serverState_*video.+}')
serverstate = self._search_regex(r'(_+serverState_+video-site_[^_]+_+)',
webpage, 'server state').replace('State', 'Settings')
serverstate = self._search_regex(r'(_+serverState_+video-site_[^_]+_+)', webpage, 'server state')
uploader = self._search_regex(r'(<a\s*class=["\']card-channel-link[^"\']+["\'][^>]+>)',
webpage, 'uploader', default='<a>')
uploader_name = extract_attributes(uploader).get('aria-label')
video_json = try_get(data_json, lambda x: x[serverstate]['exportData']['video'], dict)
stream_urls = try_get(video_json, lambda x: x['video']['streams'])
item_id = traverse_obj(data_json, (serverstate, 'videoViewer', 'openedItemId', {str}))
video_json = traverse_obj(data_json, (serverstate, 'videoViewer', 'items', item_id, {dict})) or {}
formats, subtitles = [], {}
for s_url in stream_urls:
for s_url in traverse_obj(video_json, ('video', 'streams', ..., {url_or_none})):
ext = determine_ext(s_url)
if ext == 'mpd':
fmts, subs = self._extract_mpd_formats_and_subtitles(s_url, video_id, mpd_id='dash')

24
yt_dlp/extractor/youporn.py
View File

@@ -72,15 +72,15 @@ class YouPornIE(InfoExtractor):
'id': '16290308',
'age_limit': 18,
'categories': [],
'description': 'md5:00ea70f642f431c379763c17c2f396bc',
'description': str, # TODO: detect/remove SEO spam description in ytdl backport
'display_id': 'tinderspecial-trailer1',
'duration': 298.0,
'ext': 'mp4',
'upload_date': '20201123',
'uploader': 'Ersties',
'tags': [],
'thumbnail': 'https://fi1.ypncdn.com/202011/23/16290308/original/8/tinderspecial-trailer1-8(m=eaAaaEPbaaaa).jpg',
'timestamp': 1606089600,
'thumbnail': r're:https://.+\.jpg',
'timestamp': 1606147564,
'title': 'Tinder In Real Life',
'view_count': int,
}
@@ -88,11 +88,17 @@ class YouPornIE(InfoExtractor):
def _real_extract(self, url):
video_id, display_id = self._match_valid_url(url).group('id', 'display_id')
definitions = self._download_json(
f'https://www.youporn.com/api/video/media_definitions/{video_id}/', display_id or video_id)
self._set_cookie('.youporn.com', 'age_verified', '1')
webpage = self._download_webpage(f'https://www.youporn.com/watch/{video_id}', video_id)
definitions = self._search_json(r'\bplayervars\s*:', webpage, 'player vars', video_id)['mediaDefinitions']
def get_format_data(data, f):
return traverse_obj(data, lambda _, v: v['format'] == f and url_or_none(v['videoUrl']))
def get_format_data(data, stream_type):
info_url = traverse_obj(data, (lambda _, v: v['format'] == stream_type, 'videoUrl', {url_or_none}, any))
if not info_url:
return []
return traverse_obj(
self._download_json(info_url, video_id, f'Downloading {stream_type} info JSON', fatal=False),
lambda _, v: v['format'] == stream_type and url_or_none(v['videoUrl']))
formats = []
# Try to extract only the actual master m3u8 first, avoiding the duplicate single resolution "master" m3u8s
@@ -123,10 +129,6 @@ class YouPornIE(InfoExtractor):
f['height'] = height
formats.append(f)
webpage = self._download_webpage(
'http://www.youporn.com/watch/%s' % video_id, display_id,
headers={'Cookie': 'age_verified=1'})
title = self._html_search_regex(
r'(?s)<div[^>]+class=["\']watchVideoTitle[^>]+>(.+?)</div>',
webpage, 'title', default=None) or self._og_search_title(

65
yt_dlp/extractor/yourporn.py
View File

@@ -1,65 +0,0 @@
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
parse_duration,
urljoin,
)
class YourPornIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?sxyprn\.com/post/(?P<id>[^/?#&.]+)'
_TESTS = [{
'url': 'https://sxyprn.com/post/57ffcb2e1179b.html',
'md5': '6f8682b6464033d87acaa7a8ff0c092e',
'info_dict': {
'id': '57ffcb2e1179b',
'ext': 'mp4',
'title': 'md5:c9f43630bd968267672651ba905a7d35',
'thumbnail': r're:^https?://.*\.jpg$',
'duration': 165,
'age_limit': 18,
},
'params': {
'skip_download': True,
},
}, {
'url': 'https://sxyprn.com/post/57ffcb2e1179b.html',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
parts = self._parse_json(
self._search_regex(
r'data-vnfo=(["\'])(?P<data>{.+?})\1', webpage, 'data info',
group='data'),
video_id)[video_id].split('/')
num = 0
for c in parts[6] + parts[7]:
if c.isnumeric():
num += int(c)
parts[5] = compat_str(int(parts[5]) - num)
parts[1] += '8'
video_url = urljoin(url, '/'.join(parts))
title = (self._search_regex(
r'<[^>]+\bclass=["\']PostEditTA[^>]+>([^<]+)', webpage, 'title',
default=None) or self._og_search_description(webpage)).strip()
thumbnail = self._og_search_thumbnail(webpage)
duration = parse_duration(self._search_regex(
r'duration\s*:\s*<[^>]+>([\d:]+)', webpage, 'duration',
default=None))
return {
'id': video_id,
'url': video_url,
'title': title,
'thumbnail': thumbnail,
'duration': duration,
'age_limit': 18,
'ext': 'mp4',
}

43
yt_dlp/extractor/yourupload.py
View File

@@ -1,43 +0,0 @@
from .common import InfoExtractor
from ..utils import urljoin
class YourUploadIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?(?:yourupload\.com/(?:watch|embed)|embed\.yourupload\.com)/(?P<id>[A-Za-z0-9]+)'
_TESTS = [{
'url': 'http://yourupload.com/watch/14i14h',
'md5': '5e2c63385454c557f97c4c4131a393cd',
'info_dict': {
'id': '14i14h',
'ext': 'mp4',
'title': 'BigBuckBunny_320x180.mp4',
'thumbnail': r're:^https?://.*\.jpe?g',
}
}, {
'url': 'http://www.yourupload.com/embed/14i14h',
'only_matching': True,
}, {
'url': 'http://embed.yourupload.com/14i14h',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
embed_url = 'http://www.yourupload.com/embed/%s' % video_id
webpage = self._download_webpage(embed_url, video_id)
title = self._og_search_title(webpage)
video_url = urljoin(embed_url, self._og_search_video_url(webpage))
thumbnail = self._og_search_thumbnail(webpage, default=None)
return {
'id': video_id,
'title': title,
'url': video_url,
'thumbnail': thumbnail,
'http_headers': {
'Referer': embed_url,
},
}

110
yt_dlp/extractor/youtube.py
View File

@@ -240,6 +240,16 @@ INNERTUBE_CLIENTS = {
},
'INNERTUBE_CONTEXT_CLIENT_NAME': 85
},
# This client has pre-merged video+audio 720p/1080p streams
'mediaconnect': {
'INNERTUBE_CONTEXT': {
'client': {
'clientName': 'MEDIA_CONNECT_FRONTEND',
'clientVersion': '0.1',
},
},
'INNERTUBE_CONTEXT_CLIENT_NAME': 95
},
}
@@ -1171,7 +1181,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
r'/(?P<id>[a-zA-Z0-9_-]{8,})/player(?:_ias\.vflset(?:/[a-zA-Z]{2,3}_[a-zA-Z]{2,3})?|-plasma-ias-(?:phone|tablet)-[a-z]{2}_[A-Z]{2}\.vflset)/base\.js$',
r'\b(?P<id>vfl[a-zA-Z0-9_-]+)\b.*?\.js$',
)
_formats = {
_formats = { # NB: Used in YoutubeWebArchiveIE and GoogleDriveIE
'5': {'ext': 'flv', 'width': 400, 'height': 240, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
'6': {'ext': 'flv', 'width': 450, 'height': 270, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
'13': {'ext': '3gp', 'acodec': 'aac', 'vcodec': 'mp4v'},
@@ -2343,6 +2353,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
'format': '17', # 3gp format available on android
'extractor_args': {'youtube': {'player_client': ['android']}},
},
'skip': 'android client broken',
},
{
# Skip download of additional client configs (remix client config in this case)
@@ -2720,7 +2731,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
'heatmap': 'count:100',
},
'params': {
'extractor_args': {'youtube': {'player_client': ['android'], 'player_skip': ['webpage']}},
'extractor_args': {'youtube': {'player_client': ['ios'], 'player_skip': ['webpage']}},
},
},
]
@@ -3307,7 +3318,36 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
'value': ('intensityScoreNormalized', {float_or_none}),
})) or None
def _extract_comment(self, comment_renderer, parent=None):
def _extract_comment(self, entities, parent=None):
comment_entity_payload = get_first(entities, ('payload', 'commentEntityPayload', {dict}))
if not (comment_id := traverse_obj(comment_entity_payload, ('properties', 'commentId', {str}))):
return
toolbar_entity_payload = get_first(entities, ('payload', 'engagementToolbarStateEntityPayload', {dict}))
time_text = traverse_obj(comment_entity_payload, ('properties', 'publishedTime', {str})) or ''
return {
'id': comment_id,
'parent': parent or 'root',
**traverse_obj(comment_entity_payload, {
'text': ('properties', 'content', 'content', {str}),
'like_count': ('toolbar', 'likeCountA11y', {parse_count}),
'author_id': ('author', 'channelId', {self.ucid_or_none}),
'author': ('author', 'displayName', {str}),
'author_thumbnail': ('author', 'avatarThumbnailUrl', {url_or_none}),
'author_is_uploader': ('author', 'isCreator', {bool}),
'author_is_verified': ('author', 'isVerified', {bool}),
'author_url': ('author', 'channelCommand', 'innertubeCommand', (
('browseEndpoint', 'canonicalBaseUrl'), ('commandMetadata', 'webCommandMetadata', 'url')
), {lambda x: urljoin('https://www.youtube.com', x)}),
}, get_all=False),
'is_favorited': (None if toolbar_entity_payload is None else
toolbar_entity_payload.get('heartState') == 'TOOLBAR_HEART_STATE_HEARTED'),
'_time_text': time_text, # FIXME: non-standard, but we need a way of showing that it is an estimate.
'timestamp': self._parse_time_text(time_text),
}
def _extract_comment_old(self, comment_renderer, parent=None):
comment_id = comment_renderer.get('commentId')
if not comment_id:
return
@@ -3388,21 +3428,39 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
break
return _continuation
def extract_thread(contents):
def extract_thread(contents, entity_payloads):
if not parent:
tracker['current_page_thread'] = 0
for content in contents:
if not parent and tracker['total_parent_comments'] >= max_parents:
yield
comment_thread_renderer = try_get(content, lambda x: x['commentThreadRenderer'])
comment_renderer = get_first(
(comment_thread_renderer, content), [['commentRenderer', ('comment', 'commentRenderer')]],
expected_type=dict, default={})
comment = self._extract_comment(comment_renderer, parent)
# old comment format
if not entity_payloads:
comment_renderer = get_first(
(comment_thread_renderer, content), [['commentRenderer', ('comment', 'commentRenderer')]],
expected_type=dict, default={})
comment = self._extract_comment_old(comment_renderer, parent)
# new comment format
else:
view_model = (
traverse_obj(comment_thread_renderer, ('commentViewModel', 'commentViewModel', {dict}))
or traverse_obj(content, ('commentViewModel', {dict})))
comment_keys = traverse_obj(view_model, (('commentKey', 'toolbarStateKey'), {str}))
if not comment_keys:
continue
entities = traverse_obj(entity_payloads, lambda _, v: v['entityKey'] in comment_keys)
comment = self._extract_comment(entities, parent)
if comment:
comment['is_pinned'] = traverse_obj(view_model, ('pinnedText', {str})) is not None
if not comment:
continue
comment_id = comment['id']
if comment.get('is_pinned'):
tracker['pinned_comment_ids'].add(comment_id)
# Sometimes YouTube may break and give us infinite looping comments.
@@ -3495,7 +3553,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
check_get_keys = None
if not is_forced_continuation and not (tracker['est_total'] == 0 and tracker['running_total'] == 0):
check_get_keys = [[*continuation_items_path, ..., (
'commentsHeaderRenderer' if is_first_continuation else ('commentThreadRenderer', 'commentRenderer'))]]
'commentsHeaderRenderer' if is_first_continuation else ('commentThreadRenderer', 'commentViewModel', 'commentRenderer'))]]
try:
response = self._extract_response(
item_id=None, query=continuation,
@@ -3519,6 +3577,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
raise
is_forced_continuation = False
continuation = None
mutations = traverse_obj(response, ('frameworkUpdates', 'entityBatchUpdate', 'mutations', ..., {dict}))
for continuation_items in traverse_obj(response, continuation_items_path, expected_type=list, default=[]):
if is_first_continuation:
continuation = extract_header(continuation_items)
@@ -3527,7 +3586,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
break
continue
for entry in extract_thread(continuation_items):
for entry in extract_thread(continuation_items, mutations):
if not entry:
return
yield entry
@@ -3604,8 +3663,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
yt_query = {
'videoId': video_id,
}
if _split_innertube_client(client)[0] in ('android', 'android_embedscreen'):
yt_query['params'] = 'CgIIAQ=='
pp_arg = self._configuration_arg('player_params', [None], casesense=True)[0]
if pp_arg:
@@ -3621,19 +3678,24 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
def _get_requested_clients(self, url, smuggled_data):
requested_clients = []
default = ['ios', 'android', 'web']
android_clients = []
default = ['ios', 'web']
allowed_clients = sorted(
(client for client in INNERTUBE_CLIENTS.keys() if client[:1] != '_'),
key=lambda client: INNERTUBE_CLIENTS[client]['priority'], reverse=True)
for client in self._configuration_arg('player_client'):
if client in allowed_clients:
requested_clients.append(client)
elif client == 'default':
if client == 'default':
requested_clients.extend(default)
elif client == 'all':
requested_clients.extend(allowed_clients)
else:
elif client not in allowed_clients:
self.report_warning(f'Skipping unsupported client {client}')
elif client.startswith('android'):
android_clients.append(client)
else:
requested_clients.append(client)
# Force deprioritization of broken Android clients for format de-duplication
requested_clients.extend(android_clients)
if not requested_clients:
requested_clients = default
@@ -3852,6 +3914,14 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
f'{video_id}: Some formats are possibly damaged. They will be deprioritized', only_once=True)
client_name = fmt.get(STREAMING_DATA_CLIENT_NAME)
# Android client formats are broken due to integrity check enforcement
# Ref: https://github.com/yt-dlp/yt-dlp/issues/9554
is_broken = client_name and client_name.startswith(short_client_name('android'))
if is_broken:
self.report_warning(
f'{video_id}: Android client formats are broken and may yield HTTP Error 403. '
'They will be deprioritized', only_once=True)
name = fmt.get('qualityLabel') or quality.replace('audio_quality_', '') or ''
fps = int_or_none(fmt.get('fps')) or 0
dct = {
@@ -3864,7 +3934,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
name, fmt.get('isDrc') and 'DRC',
try_get(fmt, lambda x: x['projectionType'].replace('RECTANGULAR', '').lower()),
try_get(fmt, lambda x: x['spatialAudioType'].replace('SPATIAL_AUDIO_TYPE_', '').lower()),
throttled and 'THROTTLED', is_damaged and 'DAMAGED',
throttled and 'THROTTLED', is_damaged and 'DAMAGED', is_broken and 'BROKEN',
(self.get_param('verbose') or all_formats) and client_name,
delim=', '),
# Format 22 is likely to be damaged. See https://github.com/yt-dlp/yt-dlp/issues/3372
@@ -3882,8 +3952,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
'language': join_nonempty(audio_track.get('id', '').split('.')[0],
'desc' if language_preference < -1 else '') or None,
'language_preference': language_preference,
# Strictly de-prioritize damaged and 3gp formats
'preference': -10 if is_damaged else -2 if itag == '17' else None,
# Strictly de-prioritize broken, damaged and 3gp formats
'preference': -20 if is_broken else -10 if is_damaged else -2 if itag == '17' else None,
}
mime_mobj = re.match(
r'((?:[^/]+)/(?:[^;]+))(?:;\s*codecs="([^"]+)")?', fmt.get('mimeType') or '')