[^>]+>[^>]+>([^<]+)',
- webpage, 'description', fatal=False),
- 'uploader': self._html_search_regex(
- r'| [^>]+>Channel:[^>]+>([^<]+)', media_info, 'channel', fatal=False),
- 'thumbnail': media.get('staticImage'),
+ 'subtitles': subtitles,
+ **traverse_obj(video_details, {
+ 'title': (('parlViewTitle', 'title'), {str}, any),
+ 'description': ('parlViewDescription', {str}),
+ 'duration': ('files', 'file', 'duration', {DURATION_RE.fullmatch}, 'duration', {parse_duration}),
+ 'timestamp': ('recordingFrom', {parse_iso8601}),
+ 'thumbnail': ('thumbUrl', {url_or_none}),
+ }),
}
diff --git a/yt_dlp/extractor/patreon.py b/yt_dlp/extractor/patreon.py
index 2c1436cac..9038b4a7f 100644
--- a/yt_dlp/extractor/patreon.py
+++ b/yt_dlp/extractor/patreon.py
@@ -19,7 +19,7 @@ from ..utils import (
url_or_none,
urljoin,
)
-from ..utils.traversal import traverse_obj, value
+from ..utils.traversal import require, traverse_obj, value
class PatreonBaseIE(InfoExtractor):
@@ -462,7 +462,7 @@ class PatreonCampaignIE(PatreonBaseIE):
_VALID_URL = r'''(?x)
https?://(?:www\.)?patreon\.com/(?:
(?:m|api/campaigns)/(?P\d+)|
- (?:c/)?(?P(?!creation[?/]|posts/|rss[?/])[\w-]+)
+ (?:cw?/)?(?P(?!creation[?/]|posts/|rss[?/])[\w-]+)
)(?:/posts)?/?(?:$|[?#])'''
_TESTS = [{
'url': 'https://www.patreon.com/dissonancepod/',
@@ -531,6 +531,28 @@ class PatreonCampaignIE(PatreonBaseIE):
'age_limit': 0,
},
'playlist_mincount': 331,
+ 'skip': 'Channel removed',
+ }, {
+ # next.js v13 data, see https://github.com/yt-dlp/yt-dlp/issues/13622
+ 'url': 'https://www.patreon.com/c/anythingelse/posts',
+ 'info_dict': {
+ 'id': '9631148',
+ 'title': 'Anything Else?',
+ 'description': 'md5:2ee1db4aed2f9460c2b295825a24aa08',
+ 'uploader': 'dan ',
+ 'uploader_id': '13852412',
+ 'uploader_url': 'https://www.patreon.com/anythingelse',
+ 'channel': 'Anything Else?',
+ 'channel_id': '9631148',
+ 'channel_url': 'https://www.patreon.com/anythingelse',
+ 'channel_follower_count': int,
+ 'age_limit': 0,
+ 'thumbnail': r're:https?://.+/.+',
+ },
+ 'playlist_mincount': 151,
+ }, {
+ 'url': 'https://www.patreon.com/cw/anythingelse',
+ 'only_matching': True,
}, {
'url': 'https://www.patreon.com/c/OgSog/posts',
'only_matching': True,
@@ -572,8 +594,11 @@ class PatreonCampaignIE(PatreonBaseIE):
campaign_id, vanity = self._match_valid_url(url).group('campaign_id', 'vanity')
if campaign_id is None:
webpage = self._download_webpage(url, vanity, headers={'User-Agent': self.patreon_user_agent})
- campaign_id = self._search_nextjs_data(
- webpage, vanity)['props']['pageProps']['bootstrapEnvelope']['pageBootstrap']['campaign']['data']['id']
+ campaign_id = traverse_obj(self._search_nextjs_data(webpage, vanity, default=None), (
+ 'props', 'pageProps', 'bootstrapEnvelope', 'pageBootstrap', 'campaign', 'data', 'id', {str}))
+ if not campaign_id:
+ campaign_id = traverse_obj(self._search_nextjs_v13_data(webpage, vanity), (
+ lambda _, v: v['type'] == 'campaign', 'id', {str}, any, {require('campaign ID')}))
params = {
'json-api-use-default-includes': 'false',
diff --git a/yt_dlp/extractor/playerfm.py b/yt_dlp/extractor/playerfm.py
new file mode 100644
index 000000000..d59d651a3
--- /dev/null
+++ b/yt_dlp/extractor/playerfm.py
@@ -0,0 +1,70 @@
+from .common import InfoExtractor
+from ..utils import clean_html, clean_podcast_url, int_or_none, str_or_none, url_or_none
+from ..utils.traversal import traverse_obj
+
+
+class PlayerFmIE(InfoExtractor):
+ _VALID_URL = r'(?Phttps?://(?:www\.)?player\.fm/(?:series/)?[\w-]+/(?P[\w-]+))'
+ _TESTS = [{
+ 'url': 'https://player.fm/series/chapo-trap-house/movie-mindset-33-casino-feat-felix',
+ 'info_dict': {
+ 'ext': 'mp3',
+ 'id': '478606546',
+ 'display_id': 'movie-mindset-33-casino-feat-felix',
+ 'thumbnail': r're:^https://.*\.(jpg|png)',
+ 'title': 'Movie Mindset 33 - Casino feat. Felix',
+ 'creators': ['Chapo Trap House'],
+ 'description': r're:The first episode of this season of Movie Mindset is free .+ we feel about it\.',
+ 'duration': 6830,
+ 'timestamp': 1745406000,
+ 'upload_date': '20250423',
+ },
+ }, {
+ 'url': 'https://player.fm/series/nbc-nightly-news-with-tom-llamas/thursday-april-17-2025',
+ 'info_dict': {
+ 'ext': 'mp3',
+ 'id': '477635490',
+ 'display_id': 'thursday-april-17-2025',
+ 'title': 'Thursday, April 17, 2025',
+ 'thumbnail': r're:^https://.*\.(jpg|png)',
+ 'duration': 1143,
+ 'description': 'md5:4890b8cf9a55a787561cd5d59dfcda82',
+ 'creators': ['NBC News'],
+ 'timestamp': 1744941374,
+ 'upload_date': '20250418',
+ },
+ }, {
+ 'url': 'https://player.fm/series/soccer-101/ep-109-its-kicking-off-how-have-the-rules-for-kickoff-changed-what-are-the-best-approaches-to-getting-the-game-underway-and-how-could-we-improve-on-the-present-system-ack3NzL3yibvs4pf',
+ 'info_dict': {
+ 'ext': 'mp3',
+ 'id': '481418710',
+ 'thumbnail': r're:^https://.*\.(jpg|png)',
+ 'title': r're:#109 It\'s kicking off! How have the rules for kickoff changed, .+ the present system\?',
+ 'creators': ['TSS'],
+ 'duration': 1510,
+ 'display_id': 'md5:b52ecacaefab891b59db69721bfd9b13',
+ 'description': 'md5:52a39e36d08d8919527454f152ad3c25',
+ 'timestamp': 1659102055,
+ 'upload_date': '20220729',
+ },
+ }]
+
+ def _real_extract(self, url):
+ display_id, url = self._match_valid_url(url).group('id', 'url')
+ data = self._download_json(f'{url}.json', display_id)
+
+ return {
+ 'display_id': display_id,
+ 'vcodec': 'none',
+ **traverse_obj(data, {
+ 'id': ('id', {int}, {str_or_none}),
+ 'url': ('url', {clean_podcast_url}),
+ 'title': ('title', {str}),
+ 'description': ('description', {clean_html}),
+ 'duration': ('duration', {int_or_none}),
+ 'thumbnail': (('image', ('series', 'image')), 'url', {url_or_none}, any),
+ 'filesize': ('size', {int_or_none}),
+ 'timestamp': ('publishedAt', {int_or_none}),
+ 'creators': ('series', 'author', {str}, filter, all, filter),
+ }),
+ }
diff --git a/yt_dlp/extractor/plyr.py b/yt_dlp/extractor/plyr.py
new file mode 100644
index 000000000..c5f27cfd9
--- /dev/null
+++ b/yt_dlp/extractor/plyr.py
@@ -0,0 +1,104 @@
+import re
+
+from .common import InfoExtractor
+from .vimeo import VimeoIE
+
+
+class PlyrEmbedIE(InfoExtractor):
+ _VALID_URL = False
+ _WEBPAGE_TESTS = [{
+ # data-plyr-embed-id="https://player.vimeo.com/video/522319456/90e5c96063?dnt=1"
+ 'url': 'https://www.dhm.de/zeughauskino/filmreihen/online-filmreihen/filme-des-marshall-plans/200000000-mouths/',
+ 'info_dict': {
+ 'id': '522319456',
+ 'ext': 'mp4',
+ 'title': '200.000.000 Mouths (1950–51)',
+ 'uploader': 'Zeughauskino',
+ 'uploader_url': '',
+ 'comment_count': int,
+ 'like_count': int,
+ 'duration': 963,
+ 'thumbnail': 'https://i.vimeocdn.com/video/1081797161-9f09ddb4b7faa86e834e006b8e4b9c2cbaa0baa7da493211bf0796ae133a5ab8-d',
+ 'timestamp': 1615467405,
+ 'upload_date': '20210311',
+ 'release_timestamp': 1615467405,
+ 'release_date': '20210311',
+ },
+ 'params': {'skip_download': 'm3u8'},
+ 'expected_warnings': ['Failed to parse XML: not well-formed'],
+ }, {
+ # data-plyr-provider="vimeo" data-plyr-embed-id="803435276"
+ 'url': 'https://www.inarcassa.it/',
+ 'info_dict': {
+ 'id': '803435276',
+ 'ext': 'mp4',
+ 'title': 'HOME_Moto_Perpetuo',
+ 'uploader': 'Inarcassa',
+ 'uploader_url': '',
+ 'duration': 38,
+ 'thumbnail': 'https://i.vimeocdn.com/video/1663734769-945ad7ffabb16dbca009c023fd1d7b36bdb426a3dbae8345ed758136fe28f89a-d',
+ },
+ 'params': {'skip_download': 'm3u8'},
+ 'expected_warnings': ['Failed to parse XML: not well-formed'],
+ }, {
+ # data-plyr-embed-id="https://youtu.be/GF-BjYKoAqI"
+ 'url': 'https://www.profile.nl',
+ 'info_dict': {
+ 'id': 'GF-BjYKoAqI',
+ 'ext': 'mp4',
+ 'title': 'PROFILE: Recruitment Profile',
+ 'description': '',
+ 'media_type': 'video',
+ 'uploader': 'Profile Nederland',
+ 'uploader_id': '@profilenederland',
+ 'uploader_url': 'https://www.youtube.com/@profilenederland',
+ 'channel': 'Profile Nederland',
+ 'channel_id': 'UC9AUkB0Tv39-TBYjs05n3vg',
+ 'channel_url': 'https://www.youtube.com/channel/UC9AUkB0Tv39-TBYjs05n3vg',
+ 'channel_follower_count': int,
+ 'view_count': int,
+ 'like_count': int,
+ 'age_limit': 0,
+ 'duration': 39,
+ 'thumbnail': 'https://i.ytimg.com/vi/GF-BjYKoAqI/maxresdefault.jpg',
+ 'categories': ['Autos & Vehicles'],
+ 'tags': [],
+ 'timestamp': 1675692990,
+ 'upload_date': '20230206',
+ 'playable_in_embed': True,
+ 'availability': 'public',
+ 'live_status': 'not_live',
+ },
+ }, {
+ # data-plyr-embed-id="B1TZV8rNZoc" data-plyr-provider="youtube"
+ 'url': 'https://www.vnis.edu.vn',
+ 'info_dict': {
+ 'id': 'vnis.edu',
+ 'title': 'VNIS Education - Master Agent các Trường hàng đầu Bắc Mỹ',
+ 'description': 'md5:4dafcf7335bb018780e4426da8ab8e4e',
+ 'age_limit': 0,
+ 'thumbnail': 'https://vnis.edu.vn/wp-content/uploads/2021/05/ve-welcome-en.png',
+ 'timestamp': 1753233356,
+ 'upload_date': '20250723',
+ },
+ 'playlist_count': 3,
+ }]
+
+ @classmethod
+ def _extract_embed_urls(cls, url, webpage):
+ plyr_embeds = re.finditer(r'''(?x)
+ ]+(?:
+ data-plyr-embed-id="(?P[^"]+)"[^>]+data-plyr-provider="(?P[^"]+)"|
+ data-plyr-provider="(?P[^"]+)"[^>]+data-plyr-embed-id="(?P[^"]+)"
+ )[^>]*>''', webpage)
+ for mobj in plyr_embeds:
+ embed_id = mobj.group('id1') or mobj.group('id2')
+ provider = mobj.group('provider1') or mobj.group('provider2')
+ if provider == 'vimeo':
+ if not re.match(r'https?://', embed_id):
+ embed_id = f'https://player.vimeo.com/video/{embed_id}'
+ yield VimeoIE._smuggle_referrer(embed_id, url)
+ elif provider == 'youtube':
+ if not re.match(r'https?://', embed_id):
+ embed_id = f'https://youtube.com/watch?v={embed_id}'
+ yield embed_id
diff --git a/yt_dlp/extractor/rai.py b/yt_dlp/extractor/rai.py
index c489dc731..d1a4d4c37 100644
--- a/yt_dlp/extractor/rai.py
+++ b/yt_dlp/extractor/rai.py
@@ -81,7 +81,7 @@ class RaiBaseIE(InfoExtractor):
# geo flag is a bit unreliable and not properly set all the time
geoprotection = xpath_text(relinker, './geoprotection', default='N') == 'Y'
- ext = determine_ext(media_url)
+ ext = determine_ext(media_url).lower()
formats = []
if ext == 'mp3':
@@ -108,7 +108,7 @@ class RaiBaseIE(InfoExtractor):
'format_id': join_nonempty('https', bitrate, delim='-'),
})
else:
- raise ExtractorError('Unrecognized media file found')
+ raise ExtractorError(f'Unrecognized media extension "{ext}"')
if (not formats and geoprotection is True) or '/video_no_available.mp4' in media_url:
self.raise_geo_restricted(countries=self._GEO_COUNTRIES, metadata_available=True)
@@ -503,6 +503,28 @@ class RaiPlaySoundIE(RaiBaseIE):
'upload_date': '20211201',
},
'params': {'skip_download': True},
+ }, {
+ # case-sensitivity test for uppercase extension
+ 'url': 'https://www.raiplaysound.it/audio/2020/05/Storia--Lunita-dItalia-e-lunificazione-della-Germania-b4c16390-7f3f-4282-b353-d94897dacb7c.html',
+ 'md5': 'c69ebd69282f0effd7ef67b7e2f6c7d8',
+ 'info_dict': {
+ 'id': 'b4c16390-7f3f-4282-b353-d94897dacb7c',
+ 'ext': 'mp3',
+ 'title': "Storia | 01 L'unità d'Italia e l'unificazione della Germania",
+ 'alt_title': 'md5:ed4ed82585c52057b71b43994a59b705',
+ 'description': 'md5:92818b6f31b2c150567d56b75db2ea7f',
+ 'uploader': 'rai radio 3',
+ 'duration': 2439.0,
+ 'thumbnail': 'https://www.raiplaysound.it/dl/img/2023/09/07/1694084898279_Maturadio-LOGO-2048x1152.jpg',
+ 'creators': ['rai radio 3'],
+ 'series': 'Maturadio',
+ 'season': 'Season 9',
+ 'season_number': 9,
+ 'episode': "01. L'unità d'Italia e l'unificazione della Germania",
+ 'episode_number': 1,
+ 'timestamp': 1590400740,
+ 'upload_date': '20200525',
+ },
}]
def _real_extract(self, url):
@@ -765,7 +787,7 @@ class RaiCulturaIE(RaiNewsIE): # XXX: Do not subclass from concrete IE
class RaiSudtirolIE(RaiBaseIE):
- _VALID_URL = r'https?://raisudtirol\.rai\.it/.+media=(?P\w+)'
+ _VALID_URL = r'https?://rai(?:bz|sudtirol)\.rai\.it/.+media=(?P\w+)'
_TESTS = [{
# mp4 file
'url': 'https://raisudtirol.rai.it/la/index.php?media=Ptv1619729460',
@@ -791,6 +813,9 @@ class RaiSudtirolIE(RaiBaseIE):
'formats': 'count:6',
},
'params': {'skip_download': True},
+ }, {
+ 'url': 'https://raibz.rai.it/de/index.php?media=Ptv1751660400',
+ 'only_matching': True,
}]
def _real_extract(self, url):
diff --git a/yt_dlp/extractor/rtve.py b/yt_dlp/extractor/rtve.py
index 2812d9305..c2ccf73dd 100644
--- a/yt_dlp/extractor/rtve.py
+++ b/yt_dlp/extractor/rtve.py
@@ -6,9 +6,11 @@ import urllib.parse
from .common import InfoExtractor
from ..utils import (
ExtractorError,
+ InAdvancePagedList,
clean_html,
determine_ext,
float_or_none,
+ int_or_none,
make_archive_id,
parse_iso8601,
qualities,
@@ -371,3 +373,62 @@ class RTVETelevisionIE(InfoExtractor):
raise ExtractorError('The webpage doesn\'t contain any video', expected=True)
return self.url_result(play_url, ie=RTVEALaCartaIE.ie_key())
+
+
+class RTVEProgramIE(RTVEBaseIE):
+ IE_NAME = 'rtve.es:program'
+ IE_DESC = 'RTVE.es programs'
+ _VALID_URL = r'https?://(?:www\.)?rtve\.es/play/videos/(?P[\w-]+)/?(?:[?#]|$)'
+ _TESTS = [{
+ 'url': 'https://www.rtve.es/play/videos/saber-vivir/',
+ 'info_dict': {
+ 'id': '111570',
+ 'title': 'Saber vivir - Programa de ciencia y futuro en RTVE Play',
+ },
+ 'playlist_mincount': 400,
+ }]
+ _PAGE_SIZE = 60
+
+ def _fetch_page(self, program_id, page_num):
+ return self._download_json(
+ f'https://www.rtve.es/api/programas/{program_id}/videos',
+ program_id, note=f'Downloading page {page_num}',
+ query={
+ 'type': 39816,
+ 'page': page_num,
+ 'size': 60,
+ })
+
+ def _entries(self, page_data):
+ for video in traverse_obj(page_data, ('page', 'items', lambda _, v: url_or_none(v['htmlUrl']))):
+ yield self.url_result(
+ video['htmlUrl'], RTVEALaCartaIE, url_transparent=True,
+ **traverse_obj(video, {
+ 'id': ('id', {str}),
+ 'title': ('longTitle', {str}),
+ 'description': ('shortDescription', {str}),
+ 'duration': ('duration', {float_or_none(scale=1000)}),
+ 'series': (('programInfo', 'title'), {str}, any),
+ 'season_number': ('temporadaOrden', {int_or_none}),
+ 'season_id': ('temporadaId', {str}),
+ 'season': ('temporada', {str}),
+ 'episode_number': ('episode', {int_or_none}),
+ 'episode': ('title', {str}),
+ 'thumbnail': ('thumbnail', {url_or_none}),
+ }),
+ )
+
+ def _real_extract(self, url):
+ program_slug = self._match_id(url)
+ program_page = self._download_webpage(url, program_slug)
+
+ program_id = self._html_search_meta('DC.identifier', program_page, 'Program ID', fatal=True)
+
+ first_page = self._fetch_page(program_id, 1)
+ page_count = traverse_obj(first_page, ('page', 'totalPages', {int})) or 1
+
+ entries = InAdvancePagedList(
+ lambda idx: self._entries(self._fetch_page(program_id, idx + 1) if idx else first_page),
+ page_count, self._PAGE_SIZE)
+
+ return self.playlist_result(entries, program_id, self._html_extract_title(program_page))
diff --git a/yt_dlp/extractor/sauceplus.py b/yt_dlp/extractor/sauceplus.py
new file mode 100644
index 000000000..75d7022d3
--- /dev/null
+++ b/yt_dlp/extractor/sauceplus.py
@@ -0,0 +1,41 @@
+from .floatplane import FloatplaneBaseIE
+
+
+class SaucePlusIE(FloatplaneBaseIE):
+ IE_DESC = 'Sauce+'
+ _VALID_URL = r'https?://(?:(?:www|beta)\.)?sauceplus\.com/post/(?P\w+)'
+ _BASE_URL = 'https://www.sauceplus.com'
+ _HEADERS = {
+ 'Origin': _BASE_URL,
+ 'Referer': f'{_BASE_URL}/',
+ }
+ _IMPERSONATE_TARGET = True
+ _TESTS = [{
+ 'url': 'https://www.sauceplus.com/post/YbBwIa2A5g',
+ 'info_dict': {
+ 'id': 'eit4Ugu5TL',
+ 'ext': 'mp4',
+ 'display_id': 'YbBwIa2A5g',
+ 'title': 'Scare the Coyote - Episode 3',
+ 'description': '',
+ 'thumbnail': r're:^https?://.*\.jpe?g$',
+ 'duration': 2975,
+ 'comment_count': int,
+ 'like_count': int,
+ 'dislike_count': int,
+ 'release_date': '20250627',
+ 'release_timestamp': 1750993500,
+ 'uploader': 'Scare The Coyote',
+ 'uploader_id': '683e0a3269688656a5a49a44',
+ 'uploader_url': 'https://www.sauceplus.com/channel/ScareTheCoyote/home',
+ 'channel': 'Scare The Coyote',
+ 'channel_id': '683e0a326968866ceba49a45',
+ 'channel_url': 'https://www.sauceplus.com/channel/ScareTheCoyote/home/main',
+ 'availability': 'subscriber_only',
+ },
+ 'params': {'skip_download': 'm3u8'},
+ }]
+
+ def _real_initialize(self):
+ if not self._get_cookies(self._BASE_URL).get('__Host-sp-sess'):
+ self.raise_login_required()
diff --git a/yt_dlp/extractor/skeb.py b/yt_dlp/extractor/skeb.py
index bc5ec3da7..70111d094 100644
--- a/yt_dlp/extractor/skeb.py
+++ b/yt_dlp/extractor/skeb.py
@@ -1,140 +1,118 @@
from .common import InfoExtractor
-from ..utils import ExtractorError, determine_ext, parse_qs, traverse_obj
+from ..networking.exceptions import HTTPError
+from ..utils import (
+ ExtractorError,
+ clean_html,
+ int_or_none,
+ str_or_none,
+ url_or_none,
+)
+from ..utils.traversal import traverse_obj
class SkebIE(InfoExtractor):
- _VALID_URL = r'https?://skeb\.jp/@[^/]+/works/(?P\d+)'
-
+ _VALID_URL = r'https?://skeb\.jp/@(?P[^/?#]+)/works/(?P\d+)'
_TESTS = [{
'url': 'https://skeb.jp/@riiru_wm/works/10',
'info_dict': {
'id': '466853',
- 'title': '内容はおまかせします！ by 姫ノ森りぃる@一周年',
+ 'ext': 'mp4',
+ 'title': '10-1',
'description': 'md5:1ec50901efc3437cfbfe3790468d532d',
- 'uploader': '姫ノ森りぃる@一周年',
- 'uploader_id': 'riiru_wm',
- 'age_limit': 0,
- 'tags': [],
- 'url': r're:https://skeb.+',
- 'thumbnail': r're:https://skeb.+',
- 'subtitles': {
- 'jpn': [{
- 'url': r're:https://skeb.+',
- 'ext': 'vtt',
- }],
- },
- 'width': 720,
- 'height': 405,
'duration': 313,
- 'fps': 30,
- 'ext': 'mp4',
+ 'genres': ['video'],
+ 'thumbnail': r're:https?://.+',
+ 'uploader': '姫ノ森りぃる@ひとづま',
+ 'uploader_id': 'riiru_wm',
},
}, {
'url': 'https://skeb.jp/@furukawa_nob/works/3',
'info_dict': {
'id': '489408',
- 'title': 'いつもお世話になってお... by 古川ノブ@音楽とVlo...',
- 'description': 'md5:5adc2e41d06d33b558bf7b1faeb7b9c2',
- 'uploader': '古川ノブ@音楽とVlogのVtuber',
- 'uploader_id': 'furukawa_nob',
- 'age_limit': 0,
- 'tags': [
- 'よろしく', '大丈夫', 'お願い', 'でした',
- '是非', 'O', 'バー', '遊び', 'おはよう',
- 'オーバ', 'ボイス',
- ],
- 'url': r're:https://skeb.+',
- 'thumbnail': r're:https://skeb.+',
- 'subtitles': {
- 'jpn': [{
- 'url': r're:https://skeb.+',
- 'ext': 'vtt',
- }],
- },
- 'duration': 98,
'ext': 'mp3',
- 'vcodec': 'none',
- 'abr': 128,
+ 'title': '3-1',
+ 'description': 'md5:6de1f8f876426a6ac321c123848176a8',
+ 'duration': 98,
+ 'genres': ['voice'],
+ 'tags': 'count:11',
+ 'thumbnail': r're:https?://.+',
+ 'uploader': '古川ノブ@宮城の動画勢Vtuber',
+ 'uploader_id': 'furukawa_nob',
},
}, {
- 'url': 'https://skeb.jp/@mollowmollow/works/6',
+ 'url': 'https://skeb.jp/@Rizu_panda_cube/works/626',
'info_dict': {
- 'id': '6',
- 'title': 'ヒロ。\n\n私のキャラク... by 諸々',
- 'description': 'md5:aa6cbf2ba320b50bce219632de195f07',
- '_type': 'playlist',
- 'entries': [{
- 'id': '486430',
- 'title': 'ヒロ。\n\n私のキャラク... by 諸々',
- 'description': 'md5:aa6cbf2ba320b50bce219632de195f07',
- }, {
- 'id': '486431',
- 'title': 'ヒロ。\n\n私のキャラク... by 諸々',
- }],
+ 'id': '626',
+ 'description': 'md5:834557b39ca56960c5f77dd6ddabe775',
+ 'uploader': 'りづ100億%',
+ 'uploader_id': 'Rizu_panda_cube',
+ 'tags': 'count:57',
+ 'genres': ['video'],
},
+ 'playlist_count': 2,
+ 'expected_warnings': ['Skipping unsupported extension'],
}]
+ def _call_api(self, uploader_id, work_id):
+ return self._download_json(
+ f'https://skeb.jp/api/users/{uploader_id}/works/{work_id}', work_id, headers={
+ 'Accept': 'application/json',
+ 'Authorization': 'Bearer null',
+ })
+
def _real_extract(self, url):
- video_id = self._match_id(url)
- nuxt_data = self._search_nuxt_data(self._download_webpage(url, video_id), video_id)
+ uploader_id, work_id = self._match_valid_url(url).group('uploader_id', 'id')
+ try:
+ works = self._call_api(uploader_id, work_id)
+ except ExtractorError as e:
+ if not isinstance(e.cause, HTTPError) or e.cause.status != 429:
+ raise
+ webpage = e.cause.response.read().decode()
+ value = self._search_regex(
+ r'document\.cookie\s*=\s*["\']request_key=([^;"\']+)', webpage, 'request key')
+ self._set_cookie('skeb.jp', 'request_key', value)
+ works = self._call_api(uploader_id, work_id)
- parent = {
- 'id': video_id,
- 'title': nuxt_data.get('title'),
- 'description': nuxt_data.get('description'),
- 'uploader': traverse_obj(nuxt_data, ('creator', 'name')),
- 'uploader_id': traverse_obj(nuxt_data, ('creator', 'screen_name')),
- 'age_limit': 18 if nuxt_data.get('nsfw') else 0,
- 'tags': nuxt_data.get('tag_list'),
+ info = {
+ 'uploader_id': uploader_id,
+ **traverse_obj(works, {
+ 'age_limit': ('nsfw', {bool}, {lambda x: 18 if x else None}),
+ 'description': (('source_body', 'body'), {clean_html}, filter, any),
+ 'genres': ('genre', {str}, filter, all, filter),
+ 'tags': ('tag_list', ..., {str}, filter, all, filter),
+ 'uploader': ('creator', 'name', {str}),
+ }),
}
entries = []
- for item in nuxt_data.get('previews') or []:
- vid_url = item.get('url')
- given_ext = traverse_obj(item, ('information', 'extension'))
- preview_ext = determine_ext(vid_url, default_ext=None)
- if not preview_ext:
- content_disposition = parse_qs(vid_url)['response-content-disposition'][0]
- preview_ext = self._search_regex(
- r'filename="[^"]+\.([^\.]+?)"', content_disposition,
- 'preview file extension', fatal=False, group=1)
- if preview_ext not in ('mp4', 'mp3'):
+ for idx, preview in enumerate(traverse_obj(works, ('previews', lambda _, v: url_or_none(v['url']))), 1):
+ ext = traverse_obj(preview, ('information', 'extension', {str}))
+ if ext not in ('mp3', 'mp4'):
+ self.report_warning(f'Skipping unsupported extension "{ext}"')
continue
- if not vid_url or not item.get('id'):
- continue
- width, height = traverse_obj(item, ('information', 'width')), traverse_obj(item, ('information', 'height'))
- if width is not None and height is not None:
- # the longest side is at most 720px for non-client viewers
- max_size = max(width, height)
- width, height = (x * 720 // max_size for x in (width, height))
+
entries.append({
- **parent,
- 'id': str(item['id']),
- 'url': vid_url,
- 'thumbnail': item.get('poster_url'),
+ 'ext': ext,
+ 'title': f'{work_id}-{idx}',
'subtitles': {
- 'jpn': [{
- 'url': item.get('vtt_url'),
+ 'ja': [{
'ext': 'vtt',
+ 'url': preview['vtt_url'],
}],
- } if item.get('vtt_url') else None,
- 'width': width,
- 'height': height,
- 'duration': traverse_obj(item, ('information', 'duration')),
- 'fps': traverse_obj(item, ('information', 'frame_rate')),
- 'ext': preview_ext or given_ext,
- 'vcodec': 'none' if preview_ext == 'mp3' else None,
- # you'll always get 128kbps MP3 for non-client viewers
- 'abr': 128 if preview_ext == 'mp3' else None,
+ } if url_or_none(preview.get('vtt_url')) else None,
+ 'vcodec': 'none' if ext == 'mp3' else None,
+ **info,
+ **traverse_obj(preview, {
+ 'id': ('id', {str_or_none}),
+ 'thumbnail': ('poster_url', {url_or_none}),
+ 'url': ('url', {url_or_none}),
+ }),
+ **traverse_obj(preview, ('information', {
+ 'duration': ('duration', {int_or_none}),
+ 'fps': ('frame_rate', {int_or_none}),
+ 'height': ('height', {int_or_none}),
+ 'width': ('width', {int_or_none}),
+ })),
})
- if not entries:
- raise ExtractorError('No video/audio attachment found in this commission.', expected=True)
- elif len(entries) == 1:
- return entries[0]
- else:
- parent.update({
- '_type': 'playlist',
- 'entries': entries,
- })
- return parent
+ return self.playlist_result(entries, work_id, **info)
diff --git a/yt_dlp/extractor/skyit.py b/yt_dlp/extractor/skyit.py
index 0013d2621..fe45be774 100644
--- a/yt_dlp/extractor/skyit.py
+++ b/yt_dlp/extractor/skyit.py
@@ -213,7 +213,7 @@ class CieloTVItIE(SkyItIE): # XXX: Do not subclass from concrete IE
class TV8ItIE(SkyItVideoIE): # XXX: Do not subclass from concrete IE
IE_NAME = 'tv8.it'
- _VALID_URL = r'https?://(?:www\.)?tv8\.it/(?:show)?video/[0-9a-z-]+-(?P\d+)'
+ _VALID_URL = r'https?://(?:www\.)?tv8\.it/(?:show)?video/(?:[0-9a-z-]+-)?(?P\d+)'
_TESTS = [{
'url': 'https://www.tv8.it/video/ogni-mattina-ucciso-asino-di-andrea-lo-cicero-630529',
'md5': '9ab906a3f75ea342ed928442f9dabd21',
@@ -227,6 +227,19 @@ class TV8ItIE(SkyItVideoIE): # XXX: Do not subclass from concrete IE
'thumbnail': 'https://videoplatform.sky.it/still/2020/11/18/1605717753954_ogni-mattina-ucciso-asino-di-andrea-lo-cicero_videostill_1.jpg',
},
'params': {'skip_download': 'm3u8'},
+ }, {
+ 'url': 'https://www.tv8.it/video/964361',
+ 'md5': '1e58e807154658a16edc29e45be38107',
+ 'info_dict': {
+ 'id': '964361',
+ 'ext': 'mp4',
+ 'title': 'GialappaShow - S.4 Ep.2',
+ 'description': 'md5:60bb4ff5af18bbeeaedabc1de5f9e1e2',
+ 'duration': 8030,
+ 'thumbnail': 'https://videoplatform.sky.it/captures/494/2024/11/06/964361/964361_1730888412914_thumb_494.jpg',
+ 'timestamp': 1730821499,
+ 'upload_date': '20241105',
+ },
}]
_DOMAIN = 'mtv8'
diff --git a/yt_dlp/extractor/soundcloud.py b/yt_dlp/extractor/soundcloud.py
index 3496a08ef..404e29897 100644
--- a/yt_dlp/extractor/soundcloud.py
+++ b/yt_dlp/extractor/soundcloud.py
@@ -242,7 +242,7 @@ class SoundcloudBaseIE(InfoExtractor):
format_urls.add(format_url)
formats.append({
'format_id': 'download',
- 'ext': urlhandle_detect_ext(urlh, default='mp3'),
+ 'ext': urlhandle_detect_ext(urlh),
'filesize': int_or_none(urlh.headers.get('Content-Length')),
'url': format_url,
'quality': 10,
diff --git a/yt_dlp/extractor/sportdeutschland.py b/yt_dlp/extractor/sportdeutschland.py
index 2d6acb876..0b7d90a07 100644
--- a/yt_dlp/extractor/sportdeutschland.py
+++ b/yt_dlp/extractor/sportdeutschland.py
@@ -8,67 +8,86 @@ from ..utils import (
class SportDeutschlandIE(InfoExtractor):
- _VALID_URL = r'https?://sportdeutschland\.tv/(?P(?:[^/]+/)?[^?#/&]+)'
+ _VALID_URL = r'https?://(?:player\.)?sportdeutschland\.tv/(?P(?:[^/?#]+/)?[^?#/&]+)'
_TESTS = [{
- 'url': 'https://sportdeutschland.tv/blauweissbuchholztanzsport/buchholzer-formationswochenende-2023-samstag-1-bundesliga-landesliga',
+ # Single-part video, direct link
+ 'url': 'https://sportdeutschland.tv/rostock-griffins/gfl2-rostock-griffins-vs-elmshorn-fighting-pirates',
+ 'md5': '35c11a19395c938cdd076b93bda54cde',
'info_dict': {
- 'id': '9839a5c7-0dbb-48a8-ab63-3b408adc7b54',
+ 'id': '9f27a97d-1544-4d0b-aa03-48d92d17a03a',
'ext': 'mp4',
- 'title': 'Buchholzer Formationswochenende 2023 - Samstag - 1. Bundesliga / Landesliga',
- 'display_id': 'blauweissbuchholztanzsport/buchholzer-formationswochenende-2023-samstag-1-bundesliga-landesliga',
- 'description': 'md5:a288c794a5ee69e200d8f12982f81a87',
+ 'title': 'GFL2: Rostock Griffins vs. Elmshorn Fighting Pirates',
+ 'display_id': 'rostock-griffins/gfl2-rostock-griffins-vs-elmshorn-fighting-pirates',
+ 'channel': 'Rostock Griffins',
+ 'channel_url': 'https://sportdeutschland.tv/rostock-griffins',
'live_status': 'was_live',
- 'channel': 'Blau-Weiss Buchholz Tanzsport',
- 'channel_url': 'https://sportdeutschland.tv/blauweissbuchholztanzsport',
- 'channel_id': '93ec33c9-48be-43b6-b404-e016b64fdfa3',
- 'duration': 32447,
- 'upload_date': '20230114',
- 'timestamp': 1673733618,
+ 'description': 'md5:60cb00067e55dafa27b0933a43d72862',
+ 'channel_id': '9635f21c-3f67-4584-9ce4-796e9a47276b',
+ 'timestamp': 1749913117,
+ 'upload_date': '20250614',
+ 'duration': 12287.0,
},
}, {
- 'url': 'https://sportdeutschland.tv/deutscherbadmintonverband/bwf-tour-1-runde-feld-1-yonex-gainward-german-open-2022-0',
+ # Single-part video, embedded player link
+ 'url': 'https://player.sportdeutschland.tv/9e9619c4-7d77-43c4-926d-49fb57dc06dc',
'info_dict': {
- 'id': '95c80c52-6b9a-4ae9-9197-984145adfced',
+ 'id': '9f27a97d-1544-4d0b-aa03-48d92d17a03a',
'ext': 'mp4',
- 'title': 'BWF Tour: 1. Runde Feld 1 - YONEX GAINWARD German Open 2022',
- 'display_id': 'deutscherbadmintonverband/bwf-tour-1-runde-feld-1-yonex-gainward-german-open-2022-0',
- 'description': 'md5:2afb5996ceb9ac0b2ac81f563d3a883e',
+ 'title': 'GFL2: Rostock Griffins vs. Elmshorn Fighting Pirates',
+ 'display_id': '9e9619c4-7d77-43c4-926d-49fb57dc06dc',
+ 'channel': 'Rostock Griffins',
+ 'channel_url': 'https://sportdeutschland.tv/rostock-griffins',
'live_status': 'was_live',
- 'channel': 'Deutscher Badminton Verband',
- 'channel_url': 'https://sportdeutschland.tv/deutscherbadmintonverband',
- 'channel_id': '93ca5866-2551-49fc-8424-6db35af58920',
- 'duration': 41097,
- 'upload_date': '20220309',
- 'timestamp': 1646860727.0,
+ 'description': 'md5:60cb00067e55dafa27b0933a43d72862',
+ 'channel_id': '9635f21c-3f67-4584-9ce4-796e9a47276b',
+ 'timestamp': 1749913117,
+ 'upload_date': '20250614',
+ 'duration': 12287.0,
},
+ 'params': {'skip_download': True},
}, {
- 'url': 'https://sportdeutschland.tv/ggcbremen/formationswochenende-latein-2023',
+ # Multi-part video
+ 'url': 'https://sportdeutschland.tv/rhine-ruhr-2025-fisu-world-university-games/volleyball-w-japan-vs-brasilien-halbfinale-2',
'info_dict': {
- 'id': '9889785e-55b0-4d97-a72a-ce9a9f157cce',
- 'title': 'Formationswochenende Latein 2023 - Samstag',
- 'display_id': 'ggcbremen/formationswochenende-latein-2023',
- 'description': 'md5:6e4060d40ff6a8f8eeb471b51a8f08b2',
+ 'id': '9f63d737-2444-4e3a-a1ea-840df73fd481',
+ 'display_id': 'rhine-ruhr-2025-fisu-world-university-games/volleyball-w-japan-vs-brasilien-halbfinale-2',
+ 'title': 'Volleyball w: Japan vs. Braslien - Halbfinale 2',
+ 'description': 'md5:0a17da15e48a687e6019639c3452572b',
+ 'channel': 'Rhine-Ruhr 2025 FISU World University Games',
+ 'channel_id': '9f5216be-a49d-470b-9a30-4fe9df993334',
+ 'channel_url': 'https://sportdeutschland.tv/rhine-ruhr-2025-fisu-world-university-games',
'live_status': 'was_live',
- 'channel': 'Grün-Gold-Club Bremen e.V.',
- 'channel_id': '9888f04e-bb46-4c7f-be47-df960a4167bb',
- 'channel_url': 'https://sportdeutschland.tv/ggcbremen',
},
- 'playlist_count': 3,
+ 'playlist_count': 2,
'playlist': [{
'info_dict': {
- 'id': '988e1fea-9d44-4fab-8c72-3085fb667547',
+ 'id': '9f725a94-d43e-40ff-859d-13da3081bb04',
'ext': 'mp4',
- 'channel_url': 'https://sportdeutschland.tv/ggcbremen',
- 'channel_id': '9888f04e-bb46-4c7f-be47-df960a4167bb',
- 'channel': 'Grün-Gold-Club Bremen e.V.',
- 'duration': 86,
- 'title': 'Formationswochenende Latein 2023 - Samstag Part 1',
- 'upload_date': '20230225',
- 'timestamp': 1677349909,
+ 'title': 'Volleyball w: Japan vs. Braslien - Halbfinale 2 Part 1',
+ 'channel': 'Rhine-Ruhr 2025 FISU World University Games',
+ 'channel_id': '9f5216be-a49d-470b-9a30-4fe9df993334',
+ 'channel_url': 'https://sportdeutschland.tv/rhine-ruhr-2025-fisu-world-university-games',
+ 'duration': 14773.0,
+ 'timestamp': 1753085197,
+ 'upload_date': '20250721',
+ 'live_status': 'was_live',
+ },
+ }, {
+ 'info_dict': {
+ 'id': '9f725a94-370e-4477-89ac-1751098e3217',
+ 'ext': 'mp4',
+ 'title': 'Volleyball w: Japan vs. Braslien - Halbfinale 2 Part 2',
+ 'channel': 'Rhine-Ruhr 2025 FISU World University Games',
+ 'channel_id': '9f5216be-a49d-470b-9a30-4fe9df993334',
+ 'channel_url': 'https://sportdeutschland.tv/rhine-ruhr-2025-fisu-world-university-games',
+ 'duration': 14773.0,
+ 'timestamp': 1753128421,
+ 'upload_date': '20250721',
'live_status': 'was_live',
},
}],
}, {
+ # Livestream
'url': 'https://sportdeutschland.tv/dtb/gymnastik-international-tag-1',
'info_dict': {
'id': '95d71b8a-370a-4b87-ad16-94680da18528',
@@ -87,8 +106,9 @@ class SportDeutschlandIE(InfoExtractor):
def _process_video(self, asset_id, video):
is_live = video['type'] == 'mux_live'
token = self._download_json(
- f'https://api.sportdeutschland.tv/api/frontend/asset-token/{asset_id}',
- video['id'], query={'type': video['type'], 'playback_id': video['src']})['token']
+ f'https://api.sportdeutschland.tv/api/web/personal/asset-token/{asset_id}',
+ video['id'], query={'type': video['type'], 'playback_id': video['src']},
+ headers={'Referer': 'https://sportdeutschland.tv/'})['token']
formats, subtitles = self._extract_m3u8_formats_and_subtitles(
f'https://stream.mux.com/{video["src"]}.m3u8?token={token}', video['id'], live=is_live)
diff --git a/yt_dlp/extractor/sproutvideo.py b/yt_dlp/extractor/sproutvideo.py
index c0923594e..ff9dc7dee 100644
--- a/yt_dlp/extractor/sproutvideo.py
+++ b/yt_dlp/extractor/sproutvideo.py
@@ -41,6 +41,7 @@ class SproutVideoIE(InfoExtractor):
'duration': 703,
'thumbnail': r're:https?://images\.sproutvideo\.com/.+\.jpg',
},
+ 'skip': 'Account Disabled',
}, {
# http formats 'sd' and 'hd' are available
'url': 'https://videos.sproutvideo.com/embed/119cd6bc1a18e6cd98/30751a1761ae5b90',
@@ -100,8 +101,15 @@ class SproutVideoIE(InfoExtractor):
webpage = self._download_webpage(
url, video_id, headers=traverse_obj(smuggled_data, {'Referer': 'referer'}))
data = self._search_json(
- r'var\s+dat\s*=\s*["\']', webpage, 'data', video_id, contains_pattern=r'[A-Za-z0-9+/=]+',
- end_pattern=r'["\'];', transform_source=lambda x: base64.b64decode(x).decode())
+ r'(?:var|const|let)\s+(?:dat|(?:player|video)Info|)\s*=\s*["\']', webpage, 'player info',
+ video_id, contains_pattern=r'[A-Za-z0-9+/=]+', end_pattern=r'["\'];',
+ transform_source=lambda x: base64.b64decode(x).decode())
+
+ # SproutVideo may send player info for 'SMPTE Color Monitor Test' [a791d7b71b12ecc52e]
+ # e.g. if the user-agent we used with the webpage request is too old
+ video_uid = data['videoUid']
+ if video_id != video_uid:
+ raise ExtractorError(f'{self.IE_NAME} sent the wrong video data ({video_uid})')
formats, subtitles = [], {}
headers = {
diff --git a/yt_dlp/extractor/tbs.py b/yt_dlp/extractor/tbs.py
index 80534731e..f8891671f 100644
--- a/yt_dlp/extractor/tbs.py
+++ b/yt_dlp/extractor/tbs.py
@@ -5,45 +5,110 @@ from .turner import TurnerBaseIE
from ..utils import (
float_or_none,
int_or_none,
+ make_archive_id,
strip_or_none,
)
+from ..utils.traversal import traverse_obj
class TBSIE(TurnerBaseIE):
- _VALID_URL = r'https?://(?:www\.)?(?Ptbs|tntdrama)\.com(?P/(?:movies|watchtnt|watchtbs|shows/[^/]+/(?:clips|season-\d+/episode-\d+))/(?P[^/?#]+))'
+ _SITE_INFO = {
+ 'tbs': ('TBS', 'eyJhbGciOiJSUzI1NiJ9.eyJzdWIiOiJkZTA0NTYxZS1iMTFhLTRlYTgtYTg5NC01NjI3MGM1NmM2MWIiLCJuYmYiOjE1MzcxODkzOTAsImlzcyI6ImF1dGguYWRvYmUuY29tIiwiaWF0IjoxNTM3MTg5MzkwfQ.Z7ny66kaqNDdCHf9Y9KsV12LrBxrLkGGxlYe2XGm6qsw2T-k1OCKC1TMzeqiZP735292MMRAQkcJDKrMIzNbAuf9nCdIcv4kE1E2nqUnjPMBduC1bHffZp8zlllyrN2ElDwM8Vhwv_5nElLRwWGEt0Kaq6KJAMZA__WDxKWC18T-wVtsOZWXQpDqO7nByhfj2t-Z8c3TUNVsA_wHgNXlkzJCZ16F2b7yGLT5ZhLPupOScd3MXC5iPh19HSVIok22h8_F_noTmGzmMnIRQi6bWYWK2zC7TQ_MsYHfv7V6EaG5m1RKZTV6JAwwoJQF_9ByzarLV1DGwZxD9-eQdqswvg'),
+ 'tntdrama': ('TNT', 'eyJhbGciOiJSUzI1NiJ9.eyJzdWIiOiIwOTMxYTU4OS1jZjEzLTRmNjMtYTJmYy03MzhjMjE1NWU5NjEiLCJuYmYiOjE1MzcxOTA4MjcsImlzcyI6ImF1dGguYWRvYmUuY29tIiwiaWF0IjoxNTM3MTkwODI3fQ.AucKvtws7oekTXi80_zX4-BlgJD9GLvlOI9FlBCjdlx7Pa3eJ0AqbogynKMiatMbnLOTMHGjd7tTiq422unmZjBz70dhePAe9BbW0dIo7oQ57vZ-VBYw_tWYRPmON61MwAbLVlqROD3n_zURs85S8TlkQx9aNx9x_riGGELjd8l05CVa_pOluNhYvuIFn6wmrASOKI1hNEblBDWh468UWP571-fe4zzi0rlYeeHd-cjvtWvOB3bQsWrUVbK4pRmqvzEH59j0vNF-ihJF9HncmUicYONe47Mib3elfMok23v4dB1_UAlQY_oawfNcynmEnJQCcqFmbHdEwTW6gMiYsA'),
+ 'trutv': ('truTV', 'eyJhbGciOiJSUzI1NiJ9.eyJzdWIiOiJhYzQyOTkwMi0xMDYzLTQyNTQtYWJlYS1iZTY2ODM4MTVmZGIiLCJuYmYiOjE1MzcxOTA4NjgsImlzcyI6ImF1dGguYWRvYmUuY29tIiwiaWF0IjoxNTM3MTkwODY4fQ.ewXl5LDMDvvx3nDXV4jCdSwUq_sOluKoOVsIjznAo6Zo4zrGe9rjlZ9DOmQKW66g6VRMexJsJ5vM1EkY8TC5-YcQw_BclK1FPGO1rH3Wf7tX_l0b1BVbSJQKIj9UgqDp_QbGcBXz24kN4So3U22mhs6di9PYyyfG68ccKL2iRprcVKWCslIHwUF-T7FaEqb0K57auilxeW1PONG2m-lIAcZ62DUwqXDWvw0CRoWI08aVVqkkhnXaSsQfLs5Ph1Pfh9Oq3g_epUm9Ss45mq6XM7gbOb5omTcKLADRKK-PJVB_JXnZnlsXbG0ttKE1cTKJ738qu7j4aipYTf-W0nKF5Q'),
+ }
+ _VALID_URL = fr'''(?x)
+ https?://(?:www\.)?(?P{"|".join(map(re.escape, _SITE_INFO))})\.com
+ (?P/(?:
+ (?Pwatch(?:tnt|tbs|trutv))|
+ movies|shows/[^/?#]+/(?:clips|season-\d+/episode-\d+)
+ )/(?P[^/?#]+))
+ '''
_TESTS = [{
- 'url': 'http://www.tntdrama.com/shows/the-alienist/clips/monster',
+ 'url': 'https://www.tbs.com/shows/american-dad/season-6/episode-12/you-debt-your-life',
'info_dict': {
- 'id': '8d384cde33b89f3a43ce5329de42903ed5099887',
+ 'id': '984bdcd8db0cc00dc699927f2a411c8c6e0e48f3',
'ext': 'mp4',
- 'title': 'Monster',
- 'description': 'Get a first look at the theatrical trailer for TNT’s highly anticipated new psychological thriller The Alienist, which premieres January 22 on TNT.',
- 'timestamp': 1508175329,
- 'upload_date': '20171016',
+ 'title': 'You Debt Your Life',
+ 'description': 'md5:f211cfeb9187fd3cdb53eb0e8930d499',
+ 'duration': 1231.0,
+ 'thumbnail': r're:https://images\.tbs\.com/tbs/.+\.(?:jpe?g|png)',
+ 'chapters': 'count:4',
+ 'season': 'Season 6',
+ 'season_number': 6,
+ 'episode': 'Episode 12',
+ 'episode_number': 12,
+ 'timestamp': 1478276239,
+ 'upload_date': '20161104',
},
- 'params': {
- # m3u8 download
- 'skip_download': True,
+ 'params': {'skip_download': 'm3u8'},
+ }, {
+ 'url': 'https://www.tntdrama.com/shows/the-librarians-the-next-chapter/season-1/episode-10/and-going-medieval',
+ 'info_dict': {
+ 'id': 'e487b31b663a8001864f62fd20907782f7b8ccb8',
+ 'ext': 'mp4',
+ 'title': 'And Going Medieval',
+ 'description': 'md5:5aed0ae23a6cf148a02fe3c1be8359fa',
+ 'duration': 2528.0,
+ 'thumbnail': r're:https://images\.tntdrama\.com/tnt/.+\.(?:jpe?g|png)',
+ 'chapters': 'count:7',
+ 'season': 'Season 1',
+ 'season_number': 1,
+ 'episode': 'Episode 10',
+ 'episode_number': 10,
+ 'timestamp': 1743107520,
+ 'upload_date': '20250327',
},
+ 'params': {'skip_download': 'm3u8'},
+ }, {
+ 'url': 'https://www.trutv.com/shows/the-carbonaro-effect/season-1/episode-1/got-the-bug-out',
+ 'info_dict': {
+ 'id': 'b457dd7458fd9e64b596355950b13a1ca799dc39',
+ 'ext': 'mp4',
+ 'title': 'Got the Bug Out',
+ 'description': 'md5:9eeddf6248f73517b0e5969b8a43c025',
+ 'duration': 1283.0,
+ 'thumbnail': r're:https://images\.trutv\.com/tru/.+\.(?:jpe?g|png)',
+ 'chapters': 'count:4',
+ 'season': 'Season 1',
+ 'season_number': 1,
+ 'episode': 'Episode 1',
+ 'episode_number': 1,
+ 'timestamp': 1570040829,
+ 'upload_date': '20191002',
+ '_old_archive_ids': ['trutv b457dd7458fd9e64b596355950b13a1ca799dc39'],
+ },
+ 'params': {'skip_download': 'm3u8'},
+ }, {
+ 'url': 'http://www.tntdrama.com/shows/the-alienist/clips/monster',
+ 'only_matching': True,
}, {
'url': 'http://www.tbs.com/shows/search-party/season-1/episode-1/explicit-the-mysterious-disappearance-of-the-girl-no-one-knew',
'only_matching': True,
}, {
'url': 'http://www.tntdrama.com/movies/star-wars-a-new-hope',
'only_matching': True,
+ }, {
+ 'url': 'https://www.trutv.com/shows/impractical-jokers/season-9/episode-1/you-dirty-dog',
+ 'only_matching': True,
+ }, {
+ 'url': 'https://www.trutv.com/watchtrutv/east',
+ 'only_matching': True,
+ }, {
+ 'url': 'https://www.tbs.com/watchtbs/east',
+ 'only_matching': True,
+ }, {
+ 'url': 'https://www.tntdrama.com/watchtnt/east',
+ 'only_matching': True,
}]
- _SOFTWARE_STATEMENT_MAP = {
- 'tbs': 'eyJhbGciOiJSUzI1NiJ9.eyJzdWIiOiJkZTA0NTYxZS1iMTFhLTRlYTgtYTg5NC01NjI3MGM1NmM2MWIiLCJuYmYiOjE1MzcxODkzOTAsImlzcyI6ImF1dGguYWRvYmUuY29tIiwiaWF0IjoxNTM3MTg5MzkwfQ.Z7ny66kaqNDdCHf9Y9KsV12LrBxrLkGGxlYe2XGm6qsw2T-k1OCKC1TMzeqiZP735292MMRAQkcJDKrMIzNbAuf9nCdIcv4kE1E2nqUnjPMBduC1bHffZp8zlllyrN2ElDwM8Vhwv_5nElLRwWGEt0Kaq6KJAMZA__WDxKWC18T-wVtsOZWXQpDqO7nByhfj2t-Z8c3TUNVsA_wHgNXlkzJCZ16F2b7yGLT5ZhLPupOScd3MXC5iPh19HSVIok22h8_F_noTmGzmMnIRQi6bWYWK2zC7TQ_MsYHfv7V6EaG5m1RKZTV6JAwwoJQF_9ByzarLV1DGwZxD9-eQdqswvg',
- 'tntdrama': 'eyJhbGciOiJSUzI1NiJ9.eyJzdWIiOiIwOTMxYTU4OS1jZjEzLTRmNjMtYTJmYy03MzhjMjE1NWU5NjEiLCJuYmYiOjE1MzcxOTA4MjcsImlzcyI6ImF1dGguYWRvYmUuY29tIiwiaWF0IjoxNTM3MTkwODI3fQ.AucKvtws7oekTXi80_zX4-BlgJD9GLvlOI9FlBCjdlx7Pa3eJ0AqbogynKMiatMbnLOTMHGjd7tTiq422unmZjBz70dhePAe9BbW0dIo7oQ57vZ-VBYw_tWYRPmON61MwAbLVlqROD3n_zURs85S8TlkQx9aNx9x_riGGELjd8l05CVa_pOluNhYvuIFn6wmrASOKI1hNEblBDWh468UWP571-fe4zzi0rlYeeHd-cjvtWvOB3bQsWrUVbK4pRmqvzEH59j0vNF-ihJF9HncmUicYONe47Mib3elfMok23v4dB1_UAlQY_oawfNcynmEnJQCcqFmbHdEwTW6gMiYsA',
- }
def _real_extract(self, url):
- site, path, display_id = self._match_valid_url(url).groups()
+ site, path, display_id, watch = self._match_valid_url(url).group('site', 'path', 'id', 'watch')
+ is_live = bool(watch)
webpage = self._download_webpage(url, display_id)
- drupal_settings = self._parse_json(self._search_regex(
- r']+?data-drupal-selector="drupal-settings-json"[^>]*?>({.+?})',
- webpage, 'drupal setting'), display_id)
- is_live = 'watchtnt' in path or 'watchtbs' in path
+ drupal_settings = self._search_json(
+ r']+\bdata-drupal-selector="drupal-settings-json"[^>]*>',
+ webpage, 'drupal settings', display_id)
video_data = next(v for v in drupal_settings['turner_playlist'] if is_live or v.get('url') == path)
media_id = video_data['mediaID']
@@ -51,10 +116,14 @@ class TBSIE(TurnerBaseIE):
tokenizer_query = urllib.parse.parse_qs(urllib.parse.urlparse(
drupal_settings['ngtv_token_url']).query)
+ auth_info = traverse_obj(drupal_settings, ('top2', {dict})) or {}
+ site_name = auth_info.get('siteName') or self._SITE_INFO[site][0]
+ software_statement = auth_info.get('softwareStatement') or self._SITE_INFO[site][1]
+
info = self._extract_ngtv_info(
- media_id, tokenizer_query, self._SOFTWARE_STATEMENT_MAP[site], {
+ media_id, tokenizer_query, software_statement, {
'url': url,
- 'site_name': site[:3].upper(),
+ 'site_name': site_name,
'auth_required': video_data.get('authRequired') == '1' or is_live,
'is_live': is_live,
})
@@ -87,4 +156,6 @@ class TBSIE(TurnerBaseIE):
'thumbnails': thumbnails,
'is_live': is_live,
})
+ if site == 'trutv':
+ info['_old_archive_ids'] = [make_archive_id(site, media_id)]
return info
diff --git a/yt_dlp/extractor/telecinco.py b/yt_dlp/extractor/telecinco.py
index 2dbe2a776..a34f2afd4 100644
--- a/yt_dlp/extractor/telecinco.py
+++ b/yt_dlp/extractor/telecinco.py
@@ -63,17 +63,6 @@ class TelecincoBaseIE(InfoExtractor):
'http_headers': headers,
}
- def _download_akamai_webpage(self, url, display_id):
- try: # yt-dlp's default user-agents are too old and blocked by akamai
- return self._download_webpage(url, display_id, headers={
- 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; rv:136.0) Gecko/20100101 Firefox/136.0',
- })
- except ExtractorError as e:
- if not isinstance(e.cause, HTTPError) or e.cause.status != 403:
- raise
- # Retry with impersonation if hardcoded UA is insufficient to bypass akamai
- return self._download_webpage(url, display_id, impersonate=True)
-
class TelecincoIE(TelecincoBaseIE):
IE_DESC = 'telecinco.es, cuatro.com and mediaset.es'
@@ -151,7 +140,7 @@ class TelecincoIE(TelecincoBaseIE):
def _real_extract(self, url):
display_id = self._match_id(url)
- webpage = self._download_akamai_webpage(url, display_id)
+ webpage = self._download_webpage(url, display_id)
article = self._search_json(
r'window\.\$REACTBASE_STATE\.article(?:_multisite)?\s*=',
webpage, 'article', display_id)['article']
diff --git a/yt_dlp/extractor/tenplay.py b/yt_dlp/extractor/tenplay.py
index 825da6516..dd4ea5658 100644
--- a/yt_dlp/extractor/tenplay.py
+++ b/yt_dlp/extractor/tenplay.py
@@ -7,11 +7,11 @@ from ..utils import int_or_none, traverse_obj, url_or_none, urljoin
class TenPlayIE(InfoExtractor):
IE_NAME = '10play'
- _VALID_URL = r'https?://(?:www\.)?10play\.com\.au/(?:[^/?#]+/)+(?Ptpv\d{6}[a-z]{5})'
+ _VALID_URL = r'https?://(?:www\.)?10(?:play)?\.com\.au/(?:[^/?#]+/)+(?Ptpv\d{6}[a-z]{5})'
_NETRC_MACHINE = '10play'
_TESTS = [{
# Geo-restricted to Australia
- 'url': 'https://10play.com.au/australian-survivor/web-extras/season-10-brains-v-brawn-ii/myless-journey/tpv250414jdmtf',
+ 'url': 'https://10.com.au/australian-survivor/web-extras/season-10-brains-v-brawn-ii/myless-journey/tpv250414jdmtf',
'info_dict': {
'id': '7440980000013868',
'ext': 'mp4',
@@ -32,7 +32,7 @@ class TenPlayIE(InfoExtractor):
'params': {'skip_download': 'm3u8'},
}, {
# Geo-restricted to Australia
- 'url': 'https://10play.com.au/neighbours/episodes/season-42/episode-9107/tpv240902nzqyp',
+ 'url': 'https://10.com.au/neighbours/episodes/season-42/episode-9107/tpv240902nzqyp',
'info_dict': {
'id': '9000000000091177',
'ext': 'mp4',
@@ -55,7 +55,7 @@ class TenPlayIE(InfoExtractor):
'params': {'skip_download': 'm3u8'},
}, {
# Geo-restricted to Australia; upgrading the m3u8 quality fails and we need the fallback
- 'url': 'https://10play.com.au/tiny-chef-show/episodes/season-1/episode-2/tpv240228pofvt',
+ 'url': 'https://10.com.au/tiny-chef-show/episodes/season-1/episode-2/tpv240228pofvt',
'info_dict': {
'id': '9000000000084116',
'ext': 'mp4',
@@ -77,6 +77,7 @@ class TenPlayIE(InfoExtractor):
},
'params': {'skip_download': 'm3u8'},
'expected_warnings': ['Failed to download m3u8 information: HTTP Error 502'],
+ 'skip': 'video unavailable',
}, {
'url': 'https://10play.com.au/how-to-stay-married/web-extras/season-1/terrys-talks-ep-1-embracing-change/tpv190915ylupc',
'only_matching': True,
@@ -96,7 +97,7 @@ class TenPlayIE(InfoExtractor):
def _real_extract(self, url):
content_id = self._match_id(url)
data = self._download_json(
- 'https://10play.com.au/api/v1/videos/' + content_id, content_id)
+ 'https://10.com.au/api/v1/videos/' + content_id, content_id)
video_data = self._download_json(
f'https://vod.ten.com.au/api/videos/bcquery?command=find_videos_by_id&video_id={data["altId"]}',
@@ -137,21 +138,24 @@ class TenPlayIE(InfoExtractor):
class TenPlaySeasonIE(InfoExtractor):
IE_NAME = '10play:season'
- _VALID_URL = r'https?://(?:www\.)?10play\.com\.au/(?P[^/?#]+)/episodes/(?P[^/?#]+)/?(?:$|[?#])'
+ _VALID_URL = r'https?://(?:www\.)?10(?:play)?\.com\.au/(?P[^/?#]+)/episodes/(?P[^/?#]+)/?(?:$|[?#])'
_TESTS = [{
- 'url': 'https://10play.com.au/masterchef/episodes/season-15',
+ 'url': 'https://10.com.au/masterchef/episodes/season-15',
'info_dict': {
'title': 'Season 15',
'id': 'MTQ2NjMxOQ==',
},
'playlist_mincount': 50,
}, {
- 'url': 'https://10play.com.au/the-bold-and-the-beautiful-fast-tracked/episodes/season-2024',
+ 'url': 'https://10.com.au/the-bold-and-the-beautiful-fast-tracked/episodes/season-2024',
'info_dict': {
'title': 'Season 2024',
'id': 'Mjc0OTIw',
},
'playlist_mincount': 159,
+ }, {
+ 'url': 'https://10play.com.au/the-bold-and-the-beautiful-fast-tracked/episodes/season-2024',
+ 'only_matching': True,
}]
def _entries(self, load_more_url, display_id=None):
@@ -172,7 +176,7 @@ class TenPlaySeasonIE(InfoExtractor):
def _real_extract(self, url):
show, season = self._match_valid_url(url).group('show', 'season')
season_info = self._download_json(
- f'https://10play.com.au/api/shows/{show}/episodes/{season}', f'{show}/{season}')
+ f'https://10.com.au/api/shows/{show}/episodes/{season}', f'{show}/{season}')
episodes_carousel = traverse_obj(season_info, (
'content', 0, 'components', (
diff --git a/yt_dlp/extractor/tfo.py b/yt_dlp/extractor/tfo.py
index 0d1b25217..1884ab2e8 100644
--- a/yt_dlp/extractor/tfo.py
+++ b/yt_dlp/extractor/tfo.py
@@ -6,6 +6,7 @@ from ..utils import ExtractorError, clean_html, int_or_none
class TFOIE(InfoExtractor):
+ _WORKING = False
_GEO_COUNTRIES = ['CA']
_VALID_URL = r'https?://(?:www\.)?tfo\.org/(?:en|fr)/(?:[^/]+/){2}(?P\d+)'
_TEST = {
diff --git a/yt_dlp/extractor/thehighwire.py b/yt_dlp/extractor/thehighwire.py
new file mode 100644
index 000000000..8b596143f
--- /dev/null
+++ b/yt_dlp/extractor/thehighwire.py
@@ -0,0 +1,43 @@
+from .common import InfoExtractor
+from ..utils import (
+ clean_html,
+ extract_attributes,
+ url_or_none,
+)
+from ..utils.traversal import (
+ find_element,
+ require,
+ traverse_obj,
+)
+
+
+class TheHighWireIE(InfoExtractor):
+ _VALID_URL = r'https?://(?:www\.)?thehighwire\.com/ark-videos/(?P[^/?#]+)'
+ _TESTS = [{
+ 'url': 'https://thehighwire.com/ark-videos/the-deposition-of-stanley-plotkin/',
+ 'info_dict': {
+ 'id': 'the-deposition-of-stanley-plotkin',
+ 'ext': 'mp4',
+ 'title': 'THE DEPOSITION OF STANLEY PLOTKIN',
+ 'description': 'md5:6d0be4f1181daaa10430fd8b945a5e54',
+ 'thumbnail': r're:https?://static\.arkengine\.com/video/.+\.jpg',
+ },
+ }]
+
+ def _real_extract(self, url):
+ display_id = self._match_id(url)
+ webpage = self._download_webpage(url, display_id)
+
+ embed_url = traverse_obj(webpage, (
+ {find_element(cls='ark-video-embed', html=True)},
+ {extract_attributes}, 'src', {url_or_none}, {require('embed URL')}))
+ embed_page = self._download_webpage(embed_url, display_id)
+
+ return {
+ 'id': display_id,
+ **traverse_obj(webpage, {
+ 'title': ({find_element(cls='section-header')}, {clean_html}),
+ 'description': ({find_element(cls='episode-description__copy')}, {clean_html}),
+ }),
+ **self._parse_html5_media_entries(embed_url, embed_page, display_id, m3u8_id='hls')[0],
+ }
diff --git a/yt_dlp/extractor/trutv.py b/yt_dlp/extractor/trutv.py
deleted file mode 100644
index c1d0cb0d1..000000000
--- a/yt_dlp/extractor/trutv.py
+++ /dev/null
@@ -1,71 +0,0 @@
-from .turner import TurnerBaseIE
-from ..utils import (
- int_or_none,
- parse_iso8601,
-)
-
-
-class TruTVIE(TurnerBaseIE):
- _VALID_URL = r'https?://(?:www\.)?trutv\.com/(?:shows|full-episodes)/(?P[0-9A-Za-z-]+)/(?:videos/(?P[0-9A-Za-z-]+)|(?P\d+))'
- _TEST = {
- 'url': 'https://www.trutv.com/shows/the-carbonaro-effect/videos/sunlight-activated-flower.html',
- 'info_dict': {
- 'id': 'f16c03beec1e84cd7d1a51f11d8fcc29124cc7f1',
- 'ext': 'mp4',
- 'title': 'Sunlight-Activated Flower',
- 'description': "A customer is stunned when he sees Michael's sunlight-activated flower.",
- },
- 'params': {
- # m3u8 download
- 'skip_download': True,
- },
- }
- _SOFTWARE_STATEMENT = 'eyJhbGciOiJSUzI1NiJ9.eyJzdWIiOiJhYzQyOTkwMi0xMDYzLTQyNTQtYWJlYS1iZTY2ODM4MTVmZGIiLCJuYmYiOjE1MzcxOTA4NjgsImlzcyI6ImF1dGguYWRvYmUuY29tIiwiaWF0IjoxNTM3MTkwODY4fQ.ewXl5LDMDvvx3nDXV4jCdSwUq_sOluKoOVsIjznAo6Zo4zrGe9rjlZ9DOmQKW66g6VRMexJsJ5vM1EkY8TC5-YcQw_BclK1FPGO1rH3Wf7tX_l0b1BVbSJQKIj9UgqDp_QbGcBXz24kN4So3U22mhs6di9PYyyfG68ccKL2iRprcVKWCslIHwUF-T7FaEqb0K57auilxeW1PONG2m-lIAcZ62DUwqXDWvw0CRoWI08aVVqkkhnXaSsQfLs5Ph1Pfh9Oq3g_epUm9Ss45mq6XM7gbOb5omTcKLADRKK-PJVB_JXnZnlsXbG0ttKE1cTKJ738qu7j4aipYTf-W0nKF5Q'
-
- def _real_extract(self, url):
- series_slug, clip_slug, video_id = self._match_valid_url(url).groups()
-
- if video_id:
- path = 'episode'
- display_id = video_id
- else:
- path = 'series/clip'
- display_id = clip_slug
-
- data = self._download_json(
- f'https://api.trutv.com/v2/web/{path}/{series_slug}/{display_id}',
- display_id)
- video_data = data['episode'] if video_id else data['info']
- media_id = video_data['mediaId']
- title = video_data['title'].strip()
-
- info = self._extract_ngtv_info(
- media_id, {}, self._SOFTWARE_STATEMENT, {
- 'url': url,
- 'site_name': 'truTV',
- 'auth_required': video_data.get('isAuthRequired'),
- })
-
- thumbnails = []
- for image in video_data.get('images', []):
- image_url = image.get('srcUrl')
- if not image_url:
- continue
- thumbnails.append({
- 'url': image_url,
- 'width': int_or_none(image.get('width')),
- 'height': int_or_none(image.get('height')),
- })
-
- info.update({
- 'id': media_id,
- 'display_id': display_id,
- 'title': title,
- 'description': video_data.get('description'),
- 'thumbnails': thumbnails,
- 'timestamp': parse_iso8601(video_data.get('publicationDate')),
- 'series': video_data.get('showTitle'),
- 'season_number': int_or_none(video_data.get('seasonNum')),
- 'episode_number': int_or_none(video_data.get('episodeNum')),
- })
- return info
diff --git a/yt_dlp/extractor/turner.py b/yt_dlp/extractor/turner.py
index 4493705e9..a1a7fd690 100644
--- a/yt_dlp/extractor/turner.py
+++ b/yt_dlp/extractor/turner.py
@@ -251,6 +251,11 @@ class TurnerBaseIE(AdobePassIE):
'end_time': start_time + chapter_duration,
})
+ if is_live:
+ for f in formats:
+ # Prevent ffmpeg from adding its own http headers or else we get HTTP Error 403
+ f['downloader_options'] = {'ffmpeg_args': ['-seekable', '0', '-icy', '0']}
+
return {
'formats': formats,
'chapters': chapters,
diff --git a/yt_dlp/extractor/tv5unis.py b/yt_dlp/extractor/tv5unis.py
index 88fd33482..fe7fd0325 100644
--- a/yt_dlp/extractor/tv5unis.py
+++ b/yt_dlp/extractor/tv5unis.py
@@ -51,6 +51,7 @@ class TV5UnisBaseIE(InfoExtractor):
class TV5UnisVideoIE(TV5UnisBaseIE):
+ _WORKING = False
IE_NAME = 'tv5unis:video'
_VALID_URL = r'https?://(?:www\.)?tv5unis\.ca/videos/[^/]+/(?P\d+)'
_TEST = {
@@ -71,6 +72,7 @@ class TV5UnisVideoIE(TV5UnisBaseIE):
class TV5UnisIE(TV5UnisBaseIE):
+ _WORKING = False
IE_NAME = 'tv5unis'
_VALID_URL = r'https?://(?:www\.)?tv5unis\.ca/videos/(?P[^/]+)(?:/saisons/(?P\d+)/episodes/(?P\d+))?/?(?:[?#&]|$)'
_TESTS = [{
diff --git a/yt_dlp/extractor/tvw.py b/yt_dlp/extractor/tvw.py
index 0ab926dbd..74d9b6424 100644
--- a/yt_dlp/extractor/tvw.py
+++ b/yt_dlp/extractor/tvw.py
@@ -10,12 +10,15 @@ from ..utils import (
unified_timestamp,
url_or_none,
)
-from ..utils.traversal import find_element, traverse_obj
+from ..utils.traversal import find_element, find_elements, traverse_obj
class TvwIE(InfoExtractor):
IE_NAME = 'tvw'
- _VALID_URL = r'https?://(?:www\.)?tvw\.org/video/(?P[^/?#]+)'
+ _VALID_URL = [
+ r'https?://(?:www\.)?tvw\.org/video/(?P[^/?#]+)',
+ r'https?://(?:www\.)?tvw\.org/watch/?\?(?:[^#]+&)?eventID=(?P\d+)',
+ ]
_TESTS = [{
'url': 'https://tvw.org/video/billy-frank-jr-statue-maquette-unveiling-ceremony-2024011211/',
'md5': '9ceb94fe2bb7fd726f74f16356825703',
@@ -75,6 +78,20 @@ class TvwIE(InfoExtractor):
'display_id': 'washington-to-washington-a-new-space-race-2022041111',
'categories': ['Washington to Washington', 'General Interest'],
},
+ }, {
+ 'url': 'https://tvw.org/watch?eventID=2025041235',
+ 'md5': '7d697c02f110b37d6a47622ea608ca90',
+ 'info_dict': {
+ 'id': '2025041235',
+ 'ext': 'mp4',
+ 'title': 'Legislative Review - Medicaid Postpartum Bill Sparks Debate & Senate Approves Automatic Voter Registration',
+ 'thumbnail': r're:^https?://.*\.(?:jpe?g|png)$',
+ 'description': 'md5:37d0f3a9187ae520aac261b3959eaee6',
+ 'timestamp': 1745006400,
+ 'upload_date': '20250418',
+ 'location': 'Hayner Media Center',
+ 'categories': ['Legislative Review'],
+ },
}]
def _real_extract(self, url):
@@ -125,6 +142,41 @@ class TvwIE(InfoExtractor):
}
+class TvwNewsIE(InfoExtractor):
+ IE_NAME = 'tvw:news'
+ _VALID_URL = r'https?://(?:www\.)?tvw\.org/\d{4}/\d{2}/(?P[^/?#]+)'
+ _TESTS = [{
+ 'url': 'https://tvw.org/2024/01/the-impact-issues-to-watch-in-the-2024-legislative-session/',
+ 'info_dict': {
+ 'id': 'the-impact-issues-to-watch-in-the-2024-legislative-session',
+ 'title': 'The Impact - Issues to Watch in the 2024 Legislative Session',
+ 'description': 'md5:65f0b33ec8f18ff1cd401c5547aa5441',
+ },
+ 'playlist_count': 6,
+ }, {
+ 'url': 'https://tvw.org/2024/06/the-impact-water-rights-and-the-skookumchuck-dam-debate/',
+ 'info_dict': {
+ 'id': 'the-impact-water-rights-and-the-skookumchuck-dam-debate',
+ 'title': 'The Impact - Water Rights and the Skookumchuck Dam Debate',
+ 'description': 'md5:185f3a2350ef81e3fa159ac3e040a94b',
+ },
+ 'playlist_count': 1,
+ }]
+
+ def _real_extract(self, url):
+ playlist_id = self._match_id(url)
+ webpage = self._download_webpage(url, playlist_id)
+
+ video_ids = traverse_obj(webpage, (
+ {find_elements(cls='invintus-player', html=True)}, ..., {extract_attributes}, 'data-eventid'))
+
+ return self.playlist_from_matches(
+ video_ids, playlist_id,
+ playlist_title=remove_end(self._og_search_title(webpage, default=None), ' - TVW'),
+ playlist_description=self._og_search_description(webpage, default=None),
+ getter=lambda x: f'https://tvw.org/watch?eventID={x}', ie=TvwIE)
+
+
class TvwTvChannelsIE(InfoExtractor):
IE_NAME = 'tvw:tvchannels'
_VALID_URL = r'https?://(?:www\.)?tvw\.org/tvchannels/(?P[^/?#]+)'
diff --git a/yt_dlp/extractor/twitch.py b/yt_dlp/extractor/twitch.py
index e4f2aec46..1b6020204 100644
--- a/yt_dlp/extractor/twitch.py
+++ b/yt_dlp/extractor/twitch.py
@@ -6,6 +6,7 @@ import re
import urllib.parse
from .common import InfoExtractor
+from ..networking.exceptions import HTTPError
from ..utils import (
ExtractorError,
UserNotLive,
@@ -188,19 +189,39 @@ class TwitchBaseIE(InfoExtractor):
}] if thumbnail else None
def _extract_twitch_m3u8_formats(self, path, video_id, token, signature, live_from_start=False):
- formats = self._extract_m3u8_formats(
- f'{self._USHER_BASE}/{path}/{video_id}.m3u8', video_id, 'mp4', query={
- 'allow_source': 'true',
- 'allow_audio_only': 'true',
- 'allow_spectre': 'true',
- 'p': random.randint(1000000, 10000000),
- 'platform': 'web',
- 'player': 'twitchweb',
- 'supported_codecs': 'av1,h265,h264',
- 'playlist_include_framerate': 'true',
- 'sig': signature,
- 'token': token,
- })
+ try:
+ formats = self._extract_m3u8_formats(
+ f'{self._USHER_BASE}/{path}/{video_id}.m3u8', video_id, 'mp4', query={
+ 'allow_source': 'true',
+ 'allow_audio_only': 'true',
+ 'allow_spectre': 'true',
+ 'p': random.randint(1000000, 10000000),
+ 'platform': 'web',
+ 'player': 'twitchweb',
+ 'supported_codecs': 'av1,h265,h264',
+ 'playlist_include_framerate': 'true',
+ 'sig': signature,
+ 'token': token,
+ })
+ except ExtractorError as e:
+ if (
+ not isinstance(e.cause, HTTPError)
+ or e.cause.status != 403
+ or e.cause.response.get_header('content-type') != 'application/json'
+ ):
+ raise
+
+ error_info = traverse_obj(e.cause.response.read(), ({json.loads}, 0, {dict})) or {}
+ if error_info.get('error_code') in ('vod_manifest_restricted', 'unauthorized_entitlements'):
+ common_msg = 'access to this subscriber-only content'
+ if self._get_cookies('https://gql.twitch.tv').get('auth-token'):
+ raise ExtractorError(f'Your account does not have {common_msg}', expected=True)
+ self.raise_login_required(f'You must be logged into an account that has {common_msg}')
+
+ if error_msg := join_nonempty('error_code', 'error', from_dict=error_info, delim=': '):
+ raise ExtractorError(error_msg, expected=True)
+ raise
+
for fmt in formats:
if fmt.get('vcodec') and fmt['vcodec'].startswith('av01'):
# mpegts does not yet have proper support for av1
diff --git a/yt_dlp/extractor/unitednations.py b/yt_dlp/extractor/unitednations.py
new file mode 100644
index 000000000..f9283fd6c
--- /dev/null
+++ b/yt_dlp/extractor/unitednations.py
@@ -0,0 +1,32 @@
+from .common import InfoExtractor
+from .kaltura import KalturaIE
+
+
+class UnitedNationsWebTvIE(InfoExtractor):
+ _VALID_URL = r'https?://webtv\.un\.org/(?:ar|zh|en|fr|ru|es)/asset/\w+/(?P\w+)'
+ _TESTS = [{
+ 'url': 'https://webtv.un.org/en/asset/k1o/k1o7stmi6p',
+ 'md5': 'b2f8b3030063298ae841b4b7ddc01477',
+ 'info_dict': {
+ 'id': '1_o7stmi6p',
+ 'ext': 'mp4',
+ 'title': 'António Guterres (Secretary-General) on Israel and Iran - Security Council, 9939th meeting',
+ 'thumbnail': 'http://cfvod.kaltura.com/p/2503451/sp/250345100/thumbnail/entry_id/1_o7stmi6p/version/100021',
+ 'uploader_id': 'evgeniia.alisova@un.org',
+ 'upload_date': '20250620',
+ 'timestamp': 1750430976,
+ 'duration': 234,
+ 'view_count': int,
+ },
+ }]
+
+ def _real_extract(self, url):
+ video_id = self._match_id(url)
+ webpage = self._download_webpage(url, video_id)
+
+ partner_id = self._html_search_regex(
+ r'partnerId:\s*(\d+)', webpage, 'partner_id')
+ entry_id = self._html_search_regex(
+ r'const\s+kentryID\s*=\s*["\'](\w+)["\']', webpage, 'kentry_id')
+
+ return self.url_result(f'kaltura:{partner_id}:{entry_id}', KalturaIE)
diff --git a/yt_dlp/extractor/unsupported.py b/yt_dlp/extractor/unsupported.py
index 31393b02a..05ae4dd18 100644
--- a/yt_dlp/extractor/unsupported.py
+++ b/yt_dlp/extractor/unsupported.py
@@ -53,6 +53,10 @@ class KnownDRMIE(UnsupportedInfoExtractor):
r'(?:beta\.)?crunchyroll\.com',
r'viki\.com',
r'deezer\.com',
+ r'b-ch\.com',
+ r'ctv\.ca',
+ r'noovo\.ca',
+ r'tsn\.ca',
)
_TESTS = [{
@@ -168,6 +172,18 @@ class KnownDRMIE(UnsupportedInfoExtractor):
}, {
'url': 'http://www.deezer.com/playlist/176747451',
'only_matching': True,
+ }, {
+ 'url': 'https://www.b-ch.com/titles/8203/001',
+ 'only_matching': True,
+ }, {
+ 'url': 'https://www.ctv.ca/shows/masterchef-53506/the-audition-battles-s15e1',
+ 'only_matching': True,
+ }, {
+ 'url': 'https://www.noovo.ca/emissions/lamour-est-dans-le-pre/prets-pour-lamour-s10e1',
+ 'only_matching': True,
+ }, {
+ 'url': 'https://www.tsn.ca/video/relaxed-oilers-look-to-put-emotional-game-2-loss-in-the-rearview%7E3148747',
+ 'only_matching': True,
}]
def _real_extract(self, url):
diff --git a/yt_dlp/extractor/vimeo.py b/yt_dlp/extractor/vimeo.py
index b268fad56..c45264bb5 100644
--- a/yt_dlp/extractor/vimeo.py
+++ b/yt_dlp/extractor/vimeo.py
@@ -21,6 +21,7 @@ from ..utils import (
js_to_json,
jwt_decode_hs256,
merge_dicts,
+ mimetype2ext,
parse_filesize,
parse_iso8601,
parse_qs,
@@ -28,9 +29,11 @@ from ..utils import (
smuggle_url,
str_or_none,
traverse_obj,
+ try_call,
try_get,
unified_timestamp,
unsmuggle_url,
+ url_basename,
url_or_none,
urlencode_postdata,
urlhandle_detect_ext,
@@ -45,14 +48,58 @@ class VimeoBaseInfoExtractor(InfoExtractor):
_REFERER_HINT = (
'Cannot download embed-only video without embedding URL. Please call yt-dlp '
'with the URL of the page that embeds this video.')
- _IOS_CLIENT_AUTH = 'MTMxNzViY2Y0NDE0YTQ5YzhjZTc0YmU0NjVjNDQxYzNkYWVjOWRlOTpHKzRvMmgzVUh4UkxjdU5FRW80cDNDbDhDWGR5dVJLNUJZZ055dHBHTTB4V1VzaG41bEx1a2hiN0NWYWNUcldSSW53dzRUdFRYZlJEZmFoTTArOTBUZkJHS3R4V2llYU04Qnl1bERSWWxUdXRidjNqR2J4SHFpVmtFSUcyRktuQw=='
- _IOS_CLIENT_HEADERS = {
+
+ _DEFAULT_CLIENT = 'web'
+ _DEFAULT_AUTHED_CLIENT = 'web'
+ _CLIENT_HEADERS = {
'Accept': 'application/vnd.vimeo.*+json; version=3.4.10',
'Accept-Language': 'en',
- 'User-Agent': 'Vimeo/11.10.0 (com.vimeo; build:250424.164813.0; iOS 18.4.1) Alamofire/5.9.0 VimeoNetworking/5.0.0',
}
- _IOS_OAUTH_CACHE_KEY = 'oauth-token-ios'
- _ios_oauth_token = None
+ _CLIENT_CONFIGS = {
+ 'android': {
+ 'CACHE_KEY': 'oauth-token-android',
+ 'CACHE_ONLY': True,
+ 'VIEWER_JWT': False,
+ 'REQUIRES_AUTH': False,
+ 'AUTH': 'NzRmYTg5YjgxMWExY2JiNzUwZDg1MjhkMTYzZjQ4YWYyOGEyZGJlMTp4OGx2NFd3QnNvY1lkamI2UVZsdjdDYlNwSDUrdm50YzdNNThvWDcwN1JrenJGZC9tR1lReUNlRjRSVklZeWhYZVpRS0tBcU9YYzRoTGY2Z1dlVkJFYkdJc0dMRHpoZWFZbU0reDRqZ1dkZ1diZmdIdGUrNUM5RVBySlM0VG1qcw==',
+ 'USER_AGENT': 'com.vimeo.android.videoapp (OnePlus, ONEPLUS A6003, OnePlus, Android 14/34 Version 11.8.1) Kotlin VimeoNetworking/3.12.0',
+ 'VIDEOS_FIELDS': (
+ 'uri', 'name', 'description', 'type', 'link', 'player_embed_url', 'duration', 'width',
+ 'language', 'height', 'embed', 'created_time', 'modified_time', 'release_time', 'content_rating',
+ 'content_rating_class', 'rating_mod_locked', 'license', 'privacy', 'pictures', 'tags', 'stats',
+ 'categories', 'uploader', 'metadata', 'user', 'files', 'download', 'app', 'play', 'status',
+ 'resource_key', 'badge', 'upload', 'transcode', 'is_playable', 'has_audio',
+ ),
+ },
+ 'ios': {
+ 'CACHE_KEY': 'oauth-token-ios',
+ 'CACHE_ONLY': True,
+ 'VIEWER_JWT': False,
+ 'REQUIRES_AUTH': False,
+ 'AUTH': 'MTMxNzViY2Y0NDE0YTQ5YzhjZTc0YmU0NjVjNDQxYzNkYWVjOWRlOTpHKzRvMmgzVUh4UkxjdU5FRW80cDNDbDhDWGR5dVJLNUJZZ055dHBHTTB4V1VzaG41bEx1a2hiN0NWYWNUcldSSW53dzRUdFRYZlJEZmFoTTArOTBUZkJHS3R4V2llYU04Qnl1bERSWWxUdXRidjNqR2J4SHFpVmtFSUcyRktuQw==',
+ 'USER_AGENT': 'Vimeo/11.10.0 (com.vimeo; build:250424.164813.0; iOS 18.4.1) Alamofire/5.9.0 VimeoNetworking/5.0.0',
+ 'VIDEOS_FIELDS': (
+ 'uri', 'name', 'description', 'type', 'link', 'player_embed_url', 'duration',
+ 'width', 'language', 'height', 'embed', 'created_time', 'modified_time', 'release_time',
+ 'content_rating', 'content_rating_class', 'rating_mod_locked', 'license', 'config_url',
+ 'embed_player_config_url', 'privacy', 'pictures', 'tags', 'stats', 'categories', 'uploader',
+ 'metadata', 'user', 'files', 'download', 'app', 'play', 'status', 'resource_key', 'badge',
+ 'upload', 'transcode', 'is_playable', 'has_audio',
+ ),
+ },
+ 'web': {
+ 'CACHE_ONLY': False,
+ 'VIEWER_JWT': True,
+ 'REQUIRES_AUTH': True,
+ 'USER_AGENT': None,
+ 'VIDEOS_FIELDS': (
+ 'config_url', 'created_time', 'description', 'license',
+ 'metadata.connections.comments.total', 'metadata.connections.likes.total',
+ 'release_time', 'stats.plays',
+ ),
+ },
+ }
+ _oauth_tokens = {}
_viewer_info = None
@staticmethod
@@ -80,7 +127,14 @@ class VimeoBaseInfoExtractor(InfoExtractor):
return self._viewer_info
+ @property
+ def _is_logged_in(self):
+ return 'vimeo' in self._get_cookies('https://vimeo.com')
+
def _perform_login(self, username, password):
+ if self._is_logged_in:
+ return
+
viewer = self._fetch_viewer_info()
data = {
'action': 'login',
@@ -89,7 +143,6 @@ class VimeoBaseInfoExtractor(InfoExtractor):
'service': 'vimeo',
'token': viewer['xsrft'],
}
- self._set_vimeo_cookie('vuid', viewer['vuid'])
try:
self._download_webpage(
self._LOGIN_URL, None, 'Logging in',
@@ -98,15 +151,39 @@ class VimeoBaseInfoExtractor(InfoExtractor):
'Referer': self._LOGIN_URL,
})
except ExtractorError as e:
- if isinstance(e.cause, HTTPError) and e.cause.status == 418:
+ if isinstance(e.cause, HTTPError) and e.cause.status in (405, 418):
raise ExtractorError(
'Unable to log in: bad username or password',
expected=True)
raise ExtractorError('Unable to log in')
+ # Clear unauthenticated viewer info
+ self._viewer_info = None
+
def _real_initialize(self):
- if self._LOGIN_REQUIRED and not self._get_cookies('https://vimeo.com').get('vuid'):
- self._raise_login_required()
+ if self._is_logged_in:
+ return
+
+ if self._LOGIN_REQUIRED:
+ self.raise_login_required()
+
+ if self._DEFAULT_CLIENT != 'web':
+ return
+
+ for client_name, client_config in self._CLIENT_CONFIGS.items():
+ if not client_config['CACHE_ONLY']:
+ continue
+
+ cache_key = client_config['CACHE_KEY']
+ if cache_key not in self._oauth_tokens:
+ if token := self.cache.load(self._NETRC_MACHINE, cache_key):
+ self._oauth_tokens[cache_key] = token
+
+ if self._oauth_tokens.get(cache_key):
+ self._DEFAULT_CLIENT = client_name
+ self.write_debug(
+ f'Found cached {client_name} token; using {client_name} as default API client')
+ return
def _get_video_password(self):
password = self.get_param('videopassword')
@@ -147,9 +224,6 @@ class VimeoBaseInfoExtractor(InfoExtractor):
if vimeo_config:
return self._parse_json(vimeo_config, video_id)
- def _set_vimeo_cookie(self, name, value):
- self._set_cookie('vimeo.com', name, value)
-
def _parse_config(self, config, video_id):
video_data = config['video']
video_title = video_data.get('title')
@@ -277,52 +351,99 @@ class VimeoBaseInfoExtractor(InfoExtractor):
'_format_sort_fields': ('quality', 'res', 'fps', 'hdr:12', 'source'),
}
- def _fetch_oauth_token(self):
- if not self._ios_oauth_token:
- self._ios_oauth_token = self.cache.load(self._NETRC_MACHINE, self._IOS_OAUTH_CACHE_KEY)
+ def _fetch_oauth_token(self, client):
+ client_config = self._CLIENT_CONFIGS[client]
+
+ if client_config['VIEWER_JWT']:
+ return f'jwt {self._fetch_viewer_info()["jwt"]}'
+
+ cache_key = client_config['CACHE_KEY']
+
+ if not self._oauth_tokens.get(cache_key):
+ self._oauth_tokens[cache_key] = self.cache.load(self._NETRC_MACHINE, cache_key)
- if not self._ios_oauth_token:
- self._ios_oauth_token = self._download_json(
+ if not self._oauth_tokens.get(cache_key):
+ if client_config['CACHE_ONLY']:
+ raise ExtractorError(
+ f'The {client} client is unable to fetch new OAuth tokens '
+ f'and is only intended for use with previously cached tokens', expected=True)
+
+ self._oauth_tokens[cache_key] = self._download_json(
'https://api.vimeo.com/oauth/authorize/client', None,
- 'Fetching OAuth token', 'Failed to fetch OAuth token',
+ f'Fetching {client} OAuth token', f'Failed to fetch {client} OAuth token',
headers={
- 'Authorization': f'Basic {self._IOS_CLIENT_AUTH}',
- **self._IOS_CLIENT_HEADERS,
+ 'Authorization': f'Basic {client_config["AUTH"]}',
+ 'User-Agent': client_config['USER_AGENT'],
+ **self._CLIENT_HEADERS,
}, data=urlencode_postdata({
'grant_type': 'client_credentials',
- 'scope': 'private public create edit delete interact upload purchased stats',
+ 'scope': 'private public create edit delete interact upload purchased stats video_files',
}, quote_via=urllib.parse.quote))['access_token']
- self.cache.store(self._NETRC_MACHINE, self._IOS_OAUTH_CACHE_KEY, self._ios_oauth_token)
+ self.cache.store(self._NETRC_MACHINE, cache_key, self._oauth_tokens[cache_key])
- return self._ios_oauth_token
+ return f'Bearer {self._oauth_tokens[cache_key]}'
+
+ def _get_requested_client(self):
+ if client := self._configuration_arg('client', [None], ie_key=VimeoIE)[0]:
+ if client not in self._CLIENT_CONFIGS:
+ raise ExtractorError(
+ f'Unsupported API client "{client}" requested. '
+ f'Supported clients are: {", ".join(self._CLIENT_CONFIGS)}', expected=True)
+ self.write_debug(
+ f'Using {client} API client as specified by extractor argument', only_once=True)
+ return client
+
+ if self._is_logged_in:
+ return self._DEFAULT_AUTHED_CLIENT
+
+ return self._DEFAULT_CLIENT
+
+ def _call_videos_api(self, video_id, unlisted_hash=None, path=None, *, force_client=None, query=None, **kwargs):
+ client = force_client or self._get_requested_client()
+
+ client_config = self._CLIENT_CONFIGS[client]
+ if client_config['REQUIRES_AUTH'] and not self._is_logged_in:
+ self.raise_login_required(f'The {client} client only works when logged-in')
- def _call_videos_api(self, video_id, unlisted_hash=None, **kwargs):
return self._download_json(
- join_nonempty(f'https://api.vimeo.com/videos/{video_id}', unlisted_hash, delim=':'),
- video_id, 'Downloading API JSON', headers={
- 'Authorization': f'Bearer {self._fetch_oauth_token()}',
- **self._IOS_CLIENT_HEADERS,
- }, query={
- 'fields': ','.join((
- 'config_url', 'embed_player_config_url', 'player_embed_url', 'download', 'play',
- 'files', 'description', 'license', 'release_time', 'created_time', 'stats.plays',
- 'metadata.connections.comments.total', 'metadata.connections.likes.total')),
+ join_nonempty(
+ 'https://api.vimeo.com/videos',
+ join_nonempty(video_id, unlisted_hash, delim=':'),
+ path, delim='/'),
+ video_id, f'Downloading {client} API JSON', f'Unable to download {client} API JSON',
+ headers=filter_dict({
+ 'Authorization': self._fetch_oauth_token(client),
+ 'User-Agent': client_config['USER_AGENT'],
+ **self._CLIENT_HEADERS,
+ }), query={
+ 'fields': ','.join(client_config['VIDEOS_FIELDS']),
+ **(query or {}),
}, **kwargs)
- def _extract_original_format(self, url, video_id, unlisted_hash=None, api_data=None):
+ def _extract_original_format(self, url, video_id, unlisted_hash=None):
# Original/source formats are only available when logged in
- if not self._get_cookies('https://vimeo.com/').get('vimeo'):
- return
+ if not self._is_logged_in:
+ return None
- query = {'action': 'load_download_config'}
- if unlisted_hash:
- query['unlisted_hash'] = unlisted_hash
- download_data = self._download_json(
- url, video_id, 'Loading download config JSON', fatal=False,
- query=query, headers={'X-Requested-With': 'XMLHttpRequest'},
- expected_status=(403, 404)) or {}
- source_file = download_data.get('source_file')
- download_url = try_get(source_file, lambda x: x['download_url'])
+ policy = self._configuration_arg('original_format_policy', ['auto'], ie_key=VimeoIE)[0]
+ if policy == 'never':
+ return None
+
+ try:
+ download_data = self._download_json(
+ url, video_id, 'Loading download config JSON', query=filter_dict({
+ 'action': 'load_download_config',
+ 'unlisted_hash': unlisted_hash,
+ }), headers={
+ 'Accept': 'application/json',
+ 'X-Requested-With': 'XMLHttpRequest',
+ })
+ except ExtractorError as error:
+ self.write_debug(f'Unable to load download config JSON: {error.cause}')
+ download_data = None
+
+ source_file = traverse_obj(download_data, ('source_file', {dict})) or {}
+ download_url = traverse_obj(source_file, ('download_url', {url_or_none}))
if download_url and not source_file.get('is_cold') and not source_file.get('is_defrosting'):
source_name = source_file.get('public_name', 'Original')
if self._is_valid_url(download_url, video_id, f'{source_name} video'):
@@ -340,8 +461,27 @@ class VimeoBaseInfoExtractor(InfoExtractor):
'quality': 1,
}
- original_response = api_data or self._call_videos_api(
- video_id, unlisted_hash, fatal=False, expected_status=(403, 404))
+ # Most web client API requests are subject to rate-limiting (429) when logged-in.
+ # Requesting only the 'privacy' field is NOT rate-limited,
+ # so first we should check if video even has 'download' formats available
+ try:
+ privacy_info = self._call_videos_api(
+ video_id, unlisted_hash, force_client='web', query={'fields': 'privacy'})
+ except ExtractorError as error:
+ self.write_debug(f'Unable to download privacy info: {error.cause}')
+ return None
+
+ if not traverse_obj(privacy_info, ('privacy', 'download', {bool})):
+ msg = f'{video_id}: Vimeo says this video is not downloadable'
+ if policy != 'always':
+ self.write_debug(
+ f'{msg}, so yt-dlp is not attempting to extract the original/source format. '
+ f'To try anyways, use --extractor-args "vimeo:original_format_policy=always"')
+ return None
+ self.write_debug(f'{msg}; attempting to extract original/source format anyways')
+
+ original_response = self._call_videos_api(
+ video_id, unlisted_hash, force_client='web', query={'fields': 'download'}, fatal=False)
for download_data in traverse_obj(original_response, ('download', ..., {dict})):
download_url = download_data.get('link')
if not download_url or download_data.get('quality') != 'source':
@@ -919,25 +1059,125 @@ class VimeoIE(VimeoBaseInfoExtractor):
raise ExtractorError('Wrong video password', expected=True)
return checked
+ def _get_subtitles(self, video_id, unlisted_hash):
+ subs = {}
+ text_tracks = self._call_videos_api(
+ video_id, unlisted_hash, path='texttracks', query={
+ 'include_transcript': 'true',
+ 'fields': ','.join((
+ 'active', 'display_language', 'id', 'language', 'link', 'name', 'type', 'uri',
+ )),
+ }, fatal=False)
+ for tt in traverse_obj(text_tracks, ('data', lambda _, v: url_or_none(v['link']))):
+ subs.setdefault(tt.get('language'), []).append({
+ 'url': tt['link'],
+ 'ext': 'vtt',
+ 'name': tt.get('display_language'),
+ })
+ return subs
+
+ def _parse_api_response(self, video, video_id, unlisted_hash=None):
+ formats, subtitles = [], {}
+ seen_urls = set()
+ duration = traverse_obj(video, ('duration', {int_or_none}))
+
+ for file in traverse_obj(video, (
+ (('play', (None, 'progressive')), 'files', 'download'), lambda _, v: url_or_none(v['link']),
+ )):
+ format_url = file['link']
+ if format_url in seen_urls:
+ continue
+ seen_urls.add(format_url)
+ quality = file.get('quality')
+ ext = determine_ext(format_url)
+ if quality == 'hls' or ext == 'm3u8':
+ fmts, subs = self._extract_m3u8_formats_and_subtitles(
+ format_url, video_id, 'mp4', m3u8_id='hls', fatal=False)
+ elif quality == 'dash' or ext == 'mpd':
+ fmts, subs = self._extract_mpd_formats_and_subtitles(
+ format_url, video_id, mpd_id='dash', fatal=False)
+ for fmt in fmts:
+ fmt['format_id'] = join_nonempty(
+ *fmt['format_id'].split('-', 2)[:2], int_or_none(fmt.get('tbr')))
+ else:
+ fmt = traverse_obj(file, {
+ 'ext': ('type', {mimetype2ext(default='mp4')}),
+ 'vcodec': ('codec', {str.lower}),
+ 'width': ('width', {int_or_none}),
+ 'height': ('height', {int_or_none}),
+ 'filesize': ('size', {int_or_none}),
+ 'fps': ('fps', {int_or_none}),
+ })
+ fmt.update({
+ 'url': format_url,
+ 'format_id': join_nonempty(
+ 'http', traverse_obj(file, 'public_name', 'rendition'), quality),
+ 'tbr': try_call(lambda: fmt['filesize'] * 8 / duration / 1024),
+ })
+ formats.append(fmt)
+ continue
+ formats.extend(fmts)
+ self._merge_subtitles(subs, target=subtitles)
+
+ if traverse_obj(video, ('metadata', 'connections', 'texttracks', 'total', {int})):
+ self._merge_subtitles(self.extract_subtitles(video_id, unlisted_hash), target=subtitles)
+
+ return {
+ **traverse_obj(video, {
+ 'title': ('name', {str}),
+ 'uploader': ('user', 'name', {str}),
+ 'uploader_id': ('user', 'link', {url_basename}),
+ 'uploader_url': ('user', 'link', {url_or_none}),
+ 'release_timestamp': ('live', 'scheduled_start_time', {int_or_none}),
+ 'thumbnails': ('pictures', 'sizes', lambda _, v: url_or_none(v['link']), {
+ 'url': 'link',
+ 'width': ('width', {int_or_none}),
+ 'height': ('height', {int_or_none}),
+ }),
+ }),
+ 'id': video_id,
+ 'duration': duration,
+ 'formats': formats,
+ 'subtitles': subtitles,
+ 'live_status': {
+ 'streaming': 'is_live',
+ 'done': 'was_live',
+ }.get(traverse_obj(video, ('live', 'status', {str}))),
+ }
+
def _extract_from_api(self, video_id, unlisted_hash=None):
for retry in (False, True):
try:
video = self._call_videos_api(video_id, unlisted_hash)
break
except ExtractorError as e:
- if (not retry and isinstance(e.cause, HTTPError) and e.cause.status == 400
- and 'password' in traverse_obj(
- self._webpage_read_content(e.cause.response, e.cause.response.url, video_id, fatal=False),
- ({json.loads}, 'invalid_parameters', ..., 'field'),
- )):
+ if not isinstance(e.cause, HTTPError):
+ raise
+ response = traverse_obj(
+ self._webpage_read_content(e.cause.response, e.cause.response.url, video_id, fatal=False),
+ ({json.loads}, {dict})) or {}
+ if (
+ not retry and e.cause.status == 400
+ and 'password' in traverse_obj(response, ('invalid_parameters', ..., 'field'))
+ ):
self._verify_video_password(video_id)
- continue
- raise
+ elif e.cause.status == 404 and response.get('error_code') == 5460:
+ self.raise_login_required(join_nonempty(
+ traverse_obj(response, ('error', {str.strip})),
+ 'Authentication may be needed due to your location.',
+ 'If your IP address is located in Europe you could try using a VPN/proxy,',
+ f'or else u{self._login_hint()[1:]}',
+ delim=' '), method=None)
+ else:
+ raise
+
+ if config_url := traverse_obj(video, ('config_url', {url_or_none})):
+ info = self._parse_config(self._download_json(config_url, video_id), video_id)
+ else:
+ info = self._parse_api_response(video, video_id, unlisted_hash)
- info = self._parse_config(self._download_json(
- video['config_url'], video_id), video_id)
source_format = self._extract_original_format(
- f'https://vimeo.com/{video_id}', video_id, unlisted_hash, api_data=video)
+ f'https://vimeo.com/{video_id}', video_id, unlisted_hash)
if source_format:
info['formats'].append(source_format)
@@ -977,7 +1217,6 @@ class VimeoIE(VimeoBaseInfoExtractor):
raise ExtractorError(
'This album is protected by a password, use the --video-password option',
expected=True)
- self._set_vimeo_cookie('vuid', viewer['vuid'])
try:
self._download_json(
f'https://vimeo.com/showcase/{album_id}/auth',
@@ -1374,7 +1613,6 @@ class VimeoAlbumIE(VimeoBaseInfoExtractor):
raise ExtractorError(
'This album is protected by a password, use the --video-password option',
expected=True)
- self._set_vimeo_cookie('vuid', viewer['vuid'])
try:
hashed_pass = self._download_json(
f'https://vimeo.com/showcase/{album_id}/auth',
diff --git a/yt_dlp/extractor/youtube/_base.py b/yt_dlp/extractor/youtube/_base.py
index 90e392715..0a9b510c7 100644
--- a/yt_dlp/extractor/youtube/_base.py
+++ b/yt_dlp/extractor/youtube/_base.py
@@ -1,5 +1,6 @@
import calendar
import copy
+import dataclasses
import datetime as dt
import enum
import functools
@@ -38,6 +39,60 @@ class _PoTokenContext(enum.Enum):
SUBS = 'subs'
+class StreamingProtocol(enum.Enum):
+ HTTPS = 'https'
+ DASH = 'dash'
+ HLS = 'hls'
+
+
+@dataclasses.dataclass
+class BasePoTokenPolicy:
+ required: bool = False
+ # Try to fetch a PO Token even if it is not required.
+ recommended: bool = False
+ not_required_for_premium: bool = False
+
+
+@dataclasses.dataclass
+class GvsPoTokenPolicy(BasePoTokenPolicy):
+ not_required_with_player_token: bool = False
+
+
+@dataclasses.dataclass
+class PlayerPoTokenPolicy(BasePoTokenPolicy):
+ pass
+
+
+@dataclasses.dataclass
+class SubsPoTokenPolicy(BasePoTokenPolicy):
+ pass
+
+
+WEB_PO_TOKEN_POLICIES = {
+ 'GVS_PO_TOKEN_POLICY': {
+ StreamingProtocol.HTTPS: GvsPoTokenPolicy(
+ required=True,
+ recommended=True,
+ not_required_for_premium=True,
+ not_required_with_player_token=False,
+ ),
+ StreamingProtocol.DASH: GvsPoTokenPolicy(
+ required=True,
+ recommended=True,
+ not_required_for_premium=True,
+ not_required_with_player_token=False,
+ ),
+ StreamingProtocol.HLS: GvsPoTokenPolicy(
+ required=False,
+ recommended=True,
+ ),
+ },
+ 'PLAYER_PO_TOKEN_POLICY': PlayerPoTokenPolicy(required=False),
+ # In rollout, currently detected via experiment
+ # Premium users DO require a PO Token for subtitles
+ 'SUBS_PO_TOKEN_POLICY': SubsPoTokenPolicy(required=False),
+}
+
# any clients starting with _ cannot be explicitly requested by the user
INNERTUBE_CLIENTS = {
'web': {
@@ -48,8 +103,9 @@ INNERTUBE_CLIENTS = {
},
},
'INNERTUBE_CONTEXT_CLIENT_NAME': 1,
- 'PO_TOKEN_REQUIRED_CONTEXTS': [_PoTokenContext.GVS],
'SUPPORTS_COOKIES': True,
+ **WEB_PO_TOKEN_POLICIES,
+ 'PLAYER_PARAMS': '8AEB',
},
# Safari UA returns pre-merged video+audio 144p/240p/360p/720p/1080p HLS formats
'web_safari': {
@@ -61,8 +117,9 @@ INNERTUBE_CLIENTS = {
},
},
'INNERTUBE_CONTEXT_CLIENT_NAME': 1,
- 'PO_TOKEN_REQUIRED_CONTEXTS': [_PoTokenContext.GVS],
'SUPPORTS_COOKIES': True,
+ **WEB_PO_TOKEN_POLICIES,
+ 'PLAYER_PARAMS': '8AEB',
},
'web_embedded': {
'INNERTUBE_CONTEXT': {
@@ -83,7 +140,24 @@ INNERTUBE_CLIENTS = {
},
},
'INNERTUBE_CONTEXT_CLIENT_NAME': 67,
- 'PO_TOKEN_REQUIRED_CONTEXTS': [_PoTokenContext.GVS],
+ 'GVS_PO_TOKEN_POLICY': {
+ StreamingProtocol.HTTPS: GvsPoTokenPolicy(
+ required=True,
+ recommended=True,
+ not_required_for_premium=True,
+ not_required_with_player_token=False,
+ ),
+ StreamingProtocol.DASH: GvsPoTokenPolicy(
+ required=True,
+ recommended=True,
+ not_required_for_premium=True,
+ not_required_with_player_token=False,
+ ),
+ StreamingProtocol.HLS: GvsPoTokenPolicy(
+ required=False,
+ recommended=True,
+ ),
+ },
'SUPPORTS_COOKIES': True,
},
# This client now requires sign-in for every video
@@ -95,7 +169,24 @@ INNERTUBE_CLIENTS = {
},
},
'INNERTUBE_CONTEXT_CLIENT_NAME': 62,
- 'PO_TOKEN_REQUIRED_CONTEXTS': [_PoTokenContext.GVS],
+ 'GVS_PO_TOKEN_POLICY': {
+ StreamingProtocol.HTTPS: GvsPoTokenPolicy(
+ required=True,
+ recommended=True,
+ not_required_for_premium=True,
+ not_required_with_player_token=False,
+ ),
+ StreamingProtocol.DASH: GvsPoTokenPolicy(
+ required=True,
+ recommended=True,
+ not_required_for_premium=True,
+ not_required_with_player_token=False,
+ ),
+ StreamingProtocol.HLS: GvsPoTokenPolicy(
+ required=False,
+ recommended=True,
+ ),
+ },
'REQUIRE_AUTH': True,
'SUPPORTS_COOKIES': True,
},
@@ -112,7 +203,24 @@ INNERTUBE_CLIENTS = {
},
'INNERTUBE_CONTEXT_CLIENT_NAME': 3,
'REQUIRE_JS_PLAYER': False,
- 'PO_TOKEN_REQUIRED_CONTEXTS': [_PoTokenContext.GVS],
+ 'GVS_PO_TOKEN_POLICY': {
+ StreamingProtocol.HTTPS: GvsPoTokenPolicy(
+ required=True,
+ recommended=True,
+ not_required_with_player_token=True,
+ ),
+ StreamingProtocol.DASH: GvsPoTokenPolicy(
+ required=True,
+ recommended=True,
+ not_required_with_player_token=True,
+ ),
+ StreamingProtocol.HLS: GvsPoTokenPolicy(
+ required=False,
+ recommended=True,
+ not_required_with_player_token=True,
+ ),
+ },
+ 'PLAYER_PO_TOKEN_POLICY': PlayerPoTokenPolicy(required=False, recommended=True),
},
# YouTube Kids videos aren't returned on this client for some reason
'android_vr': {
@@ -146,7 +254,21 @@ INNERTUBE_CLIENTS = {
},
},
'INNERTUBE_CONTEXT_CLIENT_NAME': 5,
- 'PO_TOKEN_REQUIRED_CONTEXTS': [_PoTokenContext.GVS],
+ 'GVS_PO_TOKEN_POLICY': {
+ StreamingProtocol.HTTPS: GvsPoTokenPolicy(
+ required=True,
+ recommended=True,
+ not_required_with_player_token=True,
+ ),
+ # HLS Livestreams require POT 30 seconds in
+ # TODO: Rolling out
+ StreamingProtocol.HLS: GvsPoTokenPolicy(
+ required=False,
+ recommended=True,
+ not_required_with_player_token=True,
+ ),
+ },
+ 'PLAYER_PO_TOKEN_POLICY': PlayerPoTokenPolicy(required=False, recommended=True),
'REQUIRE_JS_PLAYER': False,
},
# mweb has 'ultralow' formats
@@ -161,7 +283,24 @@ INNERTUBE_CLIENTS = {
},
},
'INNERTUBE_CONTEXT_CLIENT_NAME': 2,
- 'PO_TOKEN_REQUIRED_CONTEXTS': [_PoTokenContext.GVS],
+ 'GVS_PO_TOKEN_POLICY': {
+ StreamingProtocol.HTTPS: GvsPoTokenPolicy(
+ required=True,
+ recommended=True,
+ not_required_for_premium=True,
+ not_required_with_player_token=False,
+ ),
+ StreamingProtocol.DASH: GvsPoTokenPolicy(
+ required=True,
+ recommended=True,
+ not_required_for_premium=True,
+ not_required_with_player_token=False,
+ ),
+ StreamingProtocol.HLS: GvsPoTokenPolicy(
+ required=False,
+ recommended=True,
+ ),
+ },
'SUPPORTS_COOKIES': True,
},
'tv': {
@@ -174,6 +313,7 @@ INNERTUBE_CLIENTS = {
},
'INNERTUBE_CONTEXT_CLIENT_NAME': 7,
'SUPPORTS_COOKIES': True,
+ 'PLAYER_PARAMS': '8AEB',
},
'tv_simply': {
'INNERTUBE_CONTEXT': {
@@ -224,7 +364,11 @@ def build_innertube_clients():
for client, ytcfg in tuple(INNERTUBE_CLIENTS.items()):
ytcfg.setdefault('INNERTUBE_HOST', 'www.youtube.com')
ytcfg.setdefault('REQUIRE_JS_PLAYER', True)
- ytcfg.setdefault('PO_TOKEN_REQUIRED_CONTEXTS', [])
+ ytcfg.setdefault('GVS_PO_TOKEN_POLICY', {})
+ for protocol in StreamingProtocol:
+ ytcfg['GVS_PO_TOKEN_POLICY'].setdefault(protocol, GvsPoTokenPolicy())
+ ytcfg.setdefault('PLAYER_PO_TOKEN_POLICY', PlayerPoTokenPolicy())
+ ytcfg.setdefault('SUBS_PO_TOKEN_POLICY', SubsPoTokenPolicy())
ytcfg.setdefault('REQUIRE_AUTH', False)
ytcfg.setdefault('SUPPORTS_COOKIES', False)
ytcfg.setdefault('PLAYER_PARAMS', None)
diff --git a/yt_dlp/extractor/youtube/_tab.py b/yt_dlp/extractor/youtube/_tab.py
index c018ee8cf..226e5ede3 100644
--- a/yt_dlp/extractor/youtube/_tab.py
+++ b/yt_dlp/extractor/youtube/_tab.py
@@ -317,17 +317,31 @@ class YoutubeTabBaseInfoExtractor(YoutubeBaseInfoExtractor):
content_id = view_model.get('contentId')
if not content_id:
return
+
content_type = view_model.get('contentType')
- if content_type not in ('LOCKUP_CONTENT_TYPE_PLAYLIST', 'LOCKUP_CONTENT_TYPE_PODCAST'):
+ if content_type == 'LOCKUP_CONTENT_TYPE_VIDEO':
+ ie = YoutubeIE
+ url = f'https://www.youtube.com/watch?v={content_id}'
+ thumb_keys = (None,)
+ elif content_type in ('LOCKUP_CONTENT_TYPE_PLAYLIST', 'LOCKUP_CONTENT_TYPE_PODCAST'):
+ ie = YoutubeTabIE
+ url = f'https://www.youtube.com/playlist?list={content_id}'
+ thumb_keys = ('collectionThumbnailViewModel', 'primaryThumbnail')
+ else:
self.report_warning(
- f'Unsupported lockup view model content type "{content_type}"{bug_reports_message()}', only_once=True)
+ f'Unsupported lockup view model content type "{content_type}"{bug_reports_message()}',
+ only_once=True)
return
+
return self.url_result(
- f'https://www.youtube.com/playlist?list={content_id}', ie=YoutubeTabIE, video_id=content_id,
+ url, ie, content_id,
title=traverse_obj(view_model, (
'metadata', 'lockupMetadataViewModel', 'title', 'content', {str})),
thumbnails=self._extract_thumbnails(view_model, (
- 'contentImage', 'collectionThumbnailViewModel', 'primaryThumbnail', 'thumbnailViewModel', 'image'), final_key='sources'))
+ 'contentImage', *thumb_keys, 'thumbnailViewModel', 'image'), final_key='sources'),
+ duration=traverse_obj(view_model, (
+ 'contentImage', 'thumbnailViewModel', 'overlays', ..., 'thumbnailOverlayBadgeViewModel',
+ 'thumbnailBadges', ..., 'thumbnailBadgeViewModel', 'text', {parse_duration}, any)))
def _rich_entries(self, rich_grid_renderer):
if lockup_view_model := traverse_obj(rich_grid_renderer, ('content', 'lockupViewModel', {dict})):
diff --git a/yt_dlp/extractor/youtube/_video.py b/yt_dlp/extractor/youtube/_video.py
index 55ebdce1b..171aa9b5c 100644
--- a/yt_dlp/extractor/youtube/_video.py
+++ b/yt_dlp/extractor/youtube/_video.py
@@ -18,6 +18,9 @@ import urllib.parse
from ._base import (
INNERTUBE_CLIENTS,
BadgeType,
+ GvsPoTokenPolicy,
+ PlayerPoTokenPolicy,
+ StreamingProtocol,
YoutubeBaseInfoExtractor,
_PoTokenContext,
_split_innertube_client,
@@ -26,7 +29,7 @@ from ._base import (
from .pot._director import initialize_pot_director
from .pot.provider import PoTokenContext, PoTokenRequest
from ..openload import PhantomJSwrapper
-from ...jsinterp import JSInterpreter
+from ...jsinterp import JSInterpreter, LocalNameSpace
from ...networking.exceptions import HTTPError
from ...utils import (
NO_DEFAULT,
@@ -71,9 +74,11 @@ from ...utils import (
from ...utils.networking import clean_headers, clean_proxies, select_proxy
STREAMING_DATA_CLIENT_NAME = '__yt_dlp_client'
-STREAMING_DATA_INITIAL_PO_TOKEN = '__yt_dlp_po_token'
STREAMING_DATA_FETCH_SUBS_PO_TOKEN = '__yt_dlp_fetch_subs_po_token'
+STREAMING_DATA_FETCH_GVS_PO_TOKEN = '__yt_dlp_fetch_gvs_po_token'
+STREAMING_DATA_PLAYER_TOKEN_PROVIDED = '__yt_dlp_player_token_provided'
STREAMING_DATA_INNERTUBE_CONTEXT = '__yt_dlp_innertube_context'
+STREAMING_DATA_IS_PREMIUM_SUBSCRIBER = '__yt_dlp_is_premium_subscriber'
PO_TOKEN_GUIDE_URL = 'https://github.com/yt-dlp/yt-dlp/wiki/PO-Token-Guide'
@@ -253,6 +258,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
_SUBTITLE_FORMATS = ('json3', 'srv1', 'srv2', 'srv3', 'ttml', 'srt', 'vtt')
_DEFAULT_CLIENTS = ('tv', 'ios', 'web')
_DEFAULT_AUTHED_CLIENTS = ('tv', 'web')
+ # Premium does not require POT (except for subtitles)
+ _DEFAULT_PREMIUM_CLIENTS = ('tv', 'web')
_GEO_BYPASS = False
@@ -1801,6 +1808,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
'tablet': 'player-plasma-ias-tablet-en_US.vflset/base.js',
}
_INVERSE_PLAYER_JS_VARIANT_MAP = {v: k for k, v in _PLAYER_JS_VARIANT_MAP.items()}
+ _NSIG_FUNC_CACHE_ID = 'nsig func'
+ _DUMMY_STRING = 'dlp_wins'
@classmethod
def suitable(cls, url):
@@ -1831,7 +1840,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
if time.time() <= start_time + delay:
return
- _, _, prs, player_url = self._download_player_responses(url, smuggled_data, video_id, webpage_url)
+ _, _, _, _, prs, player_url = self._initial_extract(
+ url, smuggled_data, webpage_url, 'web', video_id)
video_details = traverse_obj(prs, (..., 'videoDetails'), expected_type=dict)
microformats = traverse_obj(
prs, (..., 'microformat', 'playerMicroformatRenderer'),
@@ -2066,7 +2076,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
assert os.path.basename(func_id) == func_id
self.write_debug(f'Extracting signature function {func_id}')
- cache_spec, code = self.cache.load('youtube-sigfuncs', func_id, min_ver='2025.03.31'), None
+ cache_spec, code = self.cache.load('youtube-sigfuncs', func_id, min_ver='2025.07.21'), None
if not cache_spec:
code = self._load_player(video_id, player_url)
@@ -2170,7 +2180,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
if data := self._player_cache.get(cache_id):
return data
- data = self.cache.load(*cache_id, min_ver='2025.03.31')
+ data = self.cache.load(*cache_id, min_ver='2025.07.21')
if data:
self._player_cache[cache_id] = data
@@ -2204,7 +2214,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
self.to_screen(f'Extracted nsig function from {player_id}:\n{func_code[1]}\n')
try:
- extract_nsig = self._cached(self._extract_n_function_from_code, 'nsig func', player_url)
+ extract_nsig = self._cached(self._extract_n_function_from_code, self._NSIG_FUNC_CACHE_ID, player_url)
ret = extract_nsig(jsi, func_code)(s)
except JSInterpreter.Exception as e:
try:
@@ -2312,16 +2322,18 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
jsi = JSInterpreter(varcode)
interpret_global_var = self._cached(jsi.interpret_expression, 'js global list', player_url)
- return varname, interpret_global_var(varvalue, {}, allow_recursion=10)
+ return varname, interpret_global_var(varvalue, LocalNameSpace(), allow_recursion=10)
def _fixup_n_function_code(self, argnames, nsig_code, jscode, player_url):
+ # Fixup global array
varname, global_list = self._interpret_player_js_global_var(jscode, player_url)
if varname and global_list:
nsig_code = f'var {varname}={json.dumps(global_list)}; {nsig_code}'
else:
- varname = 'dlp_wins'
+ varname = self._DUMMY_STRING
global_list = []
+ # Fixup typeof check
undefined_idx = global_list.index('undefined') if 'undefined' in global_list else r'\d+'
fixed_code = re.sub(
fr'''(?x)
@@ -2334,6 +2346,32 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
self.write_debug(join_nonempty(
'No typeof statement found in nsig function code',
player_url and f' player = {player_url}', delim='\n'), only_once=True)
+
+ # Fixup global funcs
+ jsi = JSInterpreter(fixed_code)
+ cache_id = (self._NSIG_FUNC_CACHE_ID, player_url)
+ try:
+ self._cached(
+ self._extract_n_function_from_code, *cache_id)(jsi, (argnames, fixed_code))(self._DUMMY_STRING)
+ except JSInterpreter.Exception:
+ self._player_cache.pop(cache_id, None)
+
+ global_funcnames = jsi._undefined_varnames
+ debug_names = []
+ jsi = JSInterpreter(jscode)
+ for func_name in global_funcnames:
+ try:
+ func_args, func_code = jsi.extract_function_code(func_name)
+ fixed_code = f'var {func_name} = function({", ".join(func_args)}) {{ {func_code} }}; {fixed_code}'
+ debug_names.append(func_name)
+ except Exception:
+ self.report_warning(join_nonempty(
+ f'Unable to extract global nsig function {func_name} from player JS',
+ player_url and f' player = {player_url}', delim='\n'), only_once=True)
+
+ if debug_names:
+ self.write_debug(f'Extracted global nsig functions: {", ".join(debug_names)}')
+
return argnames, fixed_code
def _extract_n_function_code(self, video_id, player_url):
@@ -2347,7 +2385,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
func_name = self._extract_n_function_name(jscode, player_url=player_url)
- # XXX: Workaround for the global array variable and lack of `typeof` implementation
+ # XXX: Work around (a) global array variable, (b) `typeof` short-circuit, (c) global functions
func_code = self._fixup_n_function_code(*jsi.extract_function_code(func_name), jscode, player_url)
return jsi, player_id, func_code
@@ -2861,7 +2899,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
only_once=True)
continue
- def fetch_po_token(self, client='web', context=_PoTokenContext.GVS, ytcfg=None, visitor_data=None,
+ def fetch_po_token(self, client='web', context: _PoTokenContext = _PoTokenContext.GVS, ytcfg=None, visitor_data=None,
data_sync_id=None, session_index=None, player_url=None, video_id=None, webpage=None,
required=False, **kwargs):
"""
@@ -2946,7 +2984,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
fetch_pot_policy == 'never'
or (
fetch_pot_policy == 'auto'
- and _PoTokenContext(context) not in self._get_default_ytcfg(client)['PO_TOKEN_REQUIRED_CONTEXTS']
and not kwargs.get('required', False)
)
):
@@ -3005,19 +3042,19 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
def _is_unplayable(player_response):
return traverse_obj(player_response, ('playabilityStatus', 'status')) == 'UNPLAYABLE'
- def _extract_player_response(self, client, video_id, master_ytcfg, player_ytcfg, player_url, initial_pr, visitor_data, data_sync_id, po_token):
+ def _extract_player_response(self, client, video_id, webpage_ytcfg, player_ytcfg, player_url, initial_pr, visitor_data, data_sync_id, po_token):
headers = self.generate_api_headers(
ytcfg=player_ytcfg,
default_client=client,
visitor_data=visitor_data,
- session_index=self._extract_session_index(master_ytcfg, player_ytcfg),
+ session_index=self._extract_session_index(webpage_ytcfg, player_ytcfg),
delegated_session_id=(
self._parse_data_sync_id(data_sync_id)[0]
- or self._extract_delegated_session_id(master_ytcfg, initial_pr, player_ytcfg)
+ or self._extract_delegated_session_id(webpage_ytcfg, initial_pr, player_ytcfg)
),
user_session_id=(
self._parse_data_sync_id(data_sync_id)[1]
- or self._extract_user_session_id(master_ytcfg, initial_pr, player_ytcfg)
+ or self._extract_user_session_id(webpage_ytcfg, initial_pr, player_ytcfg)
),
)
@@ -3033,7 +3070,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
if po_token:
yt_query['serviceIntegrityDimensions'] = {'poToken': po_token}
- sts = self._extract_signature_timestamp(video_id, player_url, master_ytcfg, fatal=False) if player_url else None
+ sts = self._extract_signature_timestamp(video_id, player_url, webpage_ytcfg, fatal=False) if player_url else None
yt_query.update(self._generate_player_context(sts))
return self._extract_response(
item_id=video_id, ep='player', query=yt_query,
@@ -3042,10 +3079,14 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
note='Downloading {} player API JSON'.format(client.replace('_', ' ').strip()),
) or None
- def _get_requested_clients(self, url, smuggled_data):
+ def _get_requested_clients(self, url, smuggled_data, is_premium_subscriber):
requested_clients = []
excluded_clients = []
- default_clients = self._DEFAULT_AUTHED_CLIENTS if self.is_authenticated else self._DEFAULT_CLIENTS
+ default_clients = (
+ self._DEFAULT_PREMIUM_CLIENTS if is_premium_subscriber
+ else self._DEFAULT_AUTHED_CLIENTS if self.is_authenticated
+ else self._DEFAULT_CLIENTS
+ )
allowed_clients = sorted(
(client for client in INNERTUBE_CLIENTS if client[:1] != '_'),
key=lambda client: INNERTUBE_CLIENTS[client]['priority'], reverse=True)
@@ -3087,11 +3128,12 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
if (pr_id := traverse_obj(pr, ('videoDetails', 'videoId'))) != video_id:
return pr_id
- def _extract_player_responses(self, clients, video_id, webpage, master_ytcfg, smuggled_data):
+ def _extract_player_responses(self, clients, video_id, webpage, webpage_client, webpage_ytcfg, is_premium_subscriber):
initial_pr = None
if webpage:
initial_pr = self._search_json(
- self._YT_INITIAL_PLAYER_RESPONSE_RE, webpage, 'initial player response', video_id, fatal=False)
+ self._YT_INITIAL_PLAYER_RESPONSE_RE, webpage,
+ f'{webpage_client} client initial player response', video_id, fatal=False)
prs = []
deprioritized_prs = []
@@ -3122,11 +3164,11 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
while clients:
deprioritize_pr = False
client, base_client, variant = _split_innertube_client(clients.pop())
- player_ytcfg = master_ytcfg if client == 'web' else {}
- if 'configs' not in self._configuration_arg('player_skip') and client != 'web':
+ player_ytcfg = webpage_ytcfg if client == webpage_client else {}
+ if 'configs' not in self._configuration_arg('player_skip') and client != webpage_client:
player_ytcfg = self._download_ytcfg(client, video_id) or player_ytcfg
- player_url = player_url or self._extract_player_url(master_ytcfg, player_ytcfg, webpage=webpage)
+ player_url = player_url or self._extract_player_url(webpage_ytcfg, player_ytcfg, webpage=webpage)
require_js_player = self._get_default_ytcfg(client).get('REQUIRE_JS_PLAYER')
if 'js' in self._configuration_arg('player_skip'):
require_js_player = False
@@ -3136,10 +3178,12 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
player_url = self._download_player_url(video_id)
tried_iframe_fallback = True
- pr = initial_pr if client == 'web' else None
+ pr = None
+ if client == webpage_client and 'player_response' not in self._configuration_arg('webpage_skip'):
+ pr = initial_pr
- visitor_data = visitor_data or self._extract_visitor_data(master_ytcfg, initial_pr, player_ytcfg)
- data_sync_id = data_sync_id or self._extract_data_sync_id(master_ytcfg, initial_pr, player_ytcfg)
+ visitor_data = visitor_data or self._extract_visitor_data(webpage_ytcfg, initial_pr, player_ytcfg)
+ data_sync_id = data_sync_id or self._extract_data_sync_id(webpage_ytcfg, initial_pr, player_ytcfg)
fetch_po_token_args = {
'client': client,
@@ -3148,53 +3192,26 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
'data_sync_id': data_sync_id if self.is_authenticated else None,
'player_url': player_url if require_js_player else None,
'webpage': webpage,
- 'session_index': self._extract_session_index(master_ytcfg, player_ytcfg),
+ 'session_index': self._extract_session_index(webpage_ytcfg, player_ytcfg),
'ytcfg': player_ytcfg or self._get_default_ytcfg(client),
}
# Don't need a player PO token for WEB if using player response from webpage
+ player_pot_policy: PlayerPoTokenPolicy = self._get_default_ytcfg(client)['PLAYER_PO_TOKEN_POLICY']
player_po_token = None if pr else self.fetch_po_token(
- context=_PoTokenContext.PLAYER, **fetch_po_token_args)
+ context=_PoTokenContext.PLAYER, **fetch_po_token_args,
+ required=player_pot_policy.required or player_pot_policy.recommended)
- gvs_po_token = self.fetch_po_token(
- context=_PoTokenContext.GVS, **fetch_po_token_args)
+ fetch_gvs_po_token_func = functools.partial(
+ self.fetch_po_token, context=_PoTokenContext.GVS, **fetch_po_token_args)
fetch_subs_po_token_func = functools.partial(
- self.fetch_po_token,
- context=_PoTokenContext.SUBS,
- **fetch_po_token_args,
- )
-
- required_pot_contexts = self._get_default_ytcfg(client)['PO_TOKEN_REQUIRED_CONTEXTS']
-
- if (
- not player_po_token
- and _PoTokenContext.PLAYER in required_pot_contexts
- ):
- # TODO: may need to skip player response request. Unsure yet..
- self.report_warning(
- f'No Player PO Token provided for {client} client, '
- f'which may be required for working {client} formats. This client will be deprioritized'
- f'You can manually pass a Player PO Token for this client with --extractor-args "youtube:po_token={client}.player+XXX". '
- f'For more information, refer to {PO_TOKEN_GUIDE_URL} .', only_once=True)
- deprioritize_pr = True
-
- if (
- not gvs_po_token
- and _PoTokenContext.GVS in required_pot_contexts
- and 'missing_pot' in self._configuration_arg('formats')
- ):
- # note: warning with help message is provided later during format processing
- self.report_warning(
- f'No GVS PO Token provided for {client} client, '
- f'which may be required for working {client} formats. This client will be deprioritized',
- only_once=True)
- deprioritize_pr = True
+ self.fetch_po_token, context=_PoTokenContext.SUBS, **fetch_po_token_args)
try:
pr = pr or self._extract_player_response(
client, video_id,
- master_ytcfg=player_ytcfg or master_ytcfg,
+ webpage_ytcfg=player_ytcfg or webpage_ytcfg,
player_ytcfg=player_ytcfg,
player_url=player_url,
initial_pr=initial_pr,
@@ -3212,12 +3229,16 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
innertube_context = traverse_obj(player_ytcfg or self._get_default_ytcfg(client), 'INNERTUBE_CONTEXT')
sd = pr.setdefault('streamingData', {})
sd[STREAMING_DATA_CLIENT_NAME] = client
- sd[STREAMING_DATA_INITIAL_PO_TOKEN] = gvs_po_token
+ sd[STREAMING_DATA_FETCH_GVS_PO_TOKEN] = fetch_gvs_po_token_func
+ sd[STREAMING_DATA_PLAYER_TOKEN_PROVIDED] = bool(player_po_token)
sd[STREAMING_DATA_INNERTUBE_CONTEXT] = innertube_context
sd[STREAMING_DATA_FETCH_SUBS_PO_TOKEN] = fetch_subs_po_token_func
+ sd[STREAMING_DATA_IS_PREMIUM_SUBSCRIBER] = is_premium_subscriber
for f in traverse_obj(sd, (('formats', 'adaptiveFormats'), ..., {dict})):
f[STREAMING_DATA_CLIENT_NAME] = client
- f[STREAMING_DATA_INITIAL_PO_TOKEN] = gvs_po_token
+ f[STREAMING_DATA_FETCH_GVS_PO_TOKEN] = fetch_gvs_po_token_func
+ f[STREAMING_DATA_IS_PREMIUM_SUBSCRIBER] = is_premium_subscriber
+ f[STREAMING_DATA_PLAYER_TOKEN_PROVIDED] = bool(player_po_token)
if deprioritize_pr:
deprioritized_prs.append(pr)
else:
@@ -3243,6 +3264,10 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
# web_creator may work around age-verification for all videos but requires PO token
append_client('tv_embedded', 'web_creator')
+ status = traverse_obj(pr, ('playabilityStatus', 'status', {str}))
+ if status not in ('OK', 'LIVE_STREAM_OFFLINE', 'AGE_CHECK_REQUIRED', 'AGE_VERIFICATION_REQUIRED'):
+ self.write_debug(f'{video_id}: {client} player response playability status: {status}')
+
prs.extend(deprioritized_prs)
if skipped_clients:
@@ -3323,6 +3348,15 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
}),
} for range_start in range(0, f['filesize'], CHUNK_SIZE))
+ def gvs_pot_required(policy, is_premium_subscriber, has_player_token):
+ return (
+ policy.required
+ and not (policy.not_required_with_player_token and has_player_token)
+ and not (policy.not_required_for_premium and is_premium_subscriber))
+
+ # save pots per client to avoid fetching again
+ gvs_pots = {}
+
for fmt in streaming_formats:
client_name = fmt[STREAMING_DATA_CLIENT_NAME]
if fmt.get('targetDurationSec'):
@@ -3382,7 +3416,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
encrypted_sig = try_get(sc, lambda x: x['s'][0])
if not all((sc, fmt_url, player_url, encrypted_sig)):
msg = f'Some {client_name} client https formats have been skipped as they are missing a url. '
- if client_name == 'web':
+ if client_name in ('web', 'web_safari'):
msg += 'YouTube is forcing SABR streaming for this client. '
else:
msg += (
@@ -3442,18 +3476,25 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
self.report_warning(
'Some formats are possibly damaged. They will be deprioritized', video_id, only_once=True)
- po_token = fmt.get(STREAMING_DATA_INITIAL_PO_TOKEN)
+ fetch_po_token_func = fmt[STREAMING_DATA_FETCH_GVS_PO_TOKEN]
+ pot_policy: GvsPoTokenPolicy = self._get_default_ytcfg(client_name)['GVS_PO_TOKEN_POLICY'][StreamingProtocol.HTTPS]
+
+ require_po_token = (
+ itag not in ['18']
+ and gvs_pot_required(
+ pot_policy, fmt[STREAMING_DATA_IS_PREMIUM_SUBSCRIBER],
+ fmt[STREAMING_DATA_PLAYER_TOKEN_PROVIDED]))
+
+ po_token = (
+ gvs_pots.get(client_name)
+ or fetch_po_token_func(required=require_po_token or pot_policy.recommended))
if po_token:
fmt_url = update_url_query(fmt_url, {'pot': po_token})
+ if client_name not in gvs_pots:
+ gvs_pots[client_name] = po_token
- # Clients that require PO Token return videoplayback URLs that may return 403
- require_po_token = (
- not po_token
- and _PoTokenContext.GVS in self._get_default_ytcfg(client_name)['PO_TOKEN_REQUIRED_CONTEXTS']
- and itag not in ['18']) # these formats do not require PO Token
-
- if require_po_token and 'missing_pot' not in self._configuration_arg('formats'):
+ if not po_token and require_po_token and 'missing_pot' not in self._configuration_arg('formats'):
self._report_pot_format_skipped(video_id, client_name, 'https')
continue
@@ -3468,7 +3509,7 @@ 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()),
- is_damaged and 'DAMAGED', require_po_token and 'MISSING POT',
+ is_damaged and 'DAMAGED', require_po_token and not po_token and 'MISSING POT',
(self.get_param('verbose') or all_formats) and short_client_name(client_name),
delim=', '),
# Format 22 is likely to be damaged. See https://github.com/yt-dlp/yt-dlp/issues/3372
@@ -3531,7 +3572,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
elif skip_bad_formats and live_status == 'is_live' and needs_live_processing != 'is_live':
skip_manifests.add('dash')
- def process_manifest_format(f, proto, client_name, itag, po_token):
+ def process_manifest_format(f, proto, client_name, itag, missing_pot):
key = (proto, f.get('language'))
if not all_formats and key in itags[itag]:
return False
@@ -3539,19 +3580,15 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
if f.get('source_preference') is None:
f['source_preference'] = -1
- # Clients that require PO Token return videoplayback URLs that may return 403
- # hls does not currently require PO Token
- if (
- not po_token
- and _PoTokenContext.GVS in self._get_default_ytcfg(client_name)['PO_TOKEN_REQUIRED_CONTEXTS']
- and proto != 'hls'
- ):
- if 'missing_pot' not in self._configuration_arg('formats'):
- self._report_pot_format_skipped(video_id, client_name, proto)
- return False
+ if missing_pot:
f['format_note'] = join_nonempty(f.get('format_note'), 'MISSING POT', delim=' ')
f['source_preference'] -= 20
+ # XXX: Check if IOS HLS formats are affected by PO token enforcement; temporary
+ # See https://github.com/yt-dlp/yt-dlp/issues/13511
+ if proto == 'hls' and client_name == 'ios':
+ f['__needs_testing'] = True
+
itags[itag].add(key)
if itag and all_formats:
@@ -3586,39 +3623,62 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
subtitles = {}
for sd in streaming_data:
client_name = sd[STREAMING_DATA_CLIENT_NAME]
- po_token = sd.get(STREAMING_DATA_INITIAL_PO_TOKEN)
+ fetch_pot_func = sd[STREAMING_DATA_FETCH_GVS_PO_TOKEN]
+ is_premium_subscriber = sd[STREAMING_DATA_IS_PREMIUM_SUBSCRIBER]
+ has_player_token = sd[STREAMING_DATA_PLAYER_TOKEN_PROVIDED]
+
hls_manifest_url = 'hls' not in skip_manifests and sd.get('hlsManifestUrl')
if hls_manifest_url:
+ pot_policy: GvsPoTokenPolicy = self._get_default_ytcfg(
+ client_name)['GVS_PO_TOKEN_POLICY'][StreamingProtocol.HLS]
+ require_po_token = gvs_pot_required(pot_policy, is_premium_subscriber, has_player_token)
+ po_token = gvs_pots.get(client_name, fetch_pot_func(required=require_po_token or pot_policy.recommended))
if po_token:
hls_manifest_url = hls_manifest_url.rstrip('/') + f'/pot/{po_token}'
- fmts, subs = self._extract_m3u8_formats_and_subtitles(
- hls_manifest_url, video_id, 'mp4', fatal=False, live=live_status == 'is_live')
- for sub in traverse_obj(subs, (..., ..., {dict})):
- # HLS subs (m3u8) do not need a PO token; save client name for debugging
- sub[STREAMING_DATA_CLIENT_NAME] = client_name
- subtitles = self._merge_subtitles(subs, subtitles)
- for f in fmts:
- if process_manifest_format(f, 'hls', client_name, self._search_regex(
- r'/itag/(\d+)', f['url'], 'itag', default=None), po_token):
- yield f
+ if client_name not in gvs_pots:
+ gvs_pots[client_name] = po_token
+ if require_po_token and not po_token and 'missing_pot' not in self._configuration_arg('formats'):
+ self._report_pot_format_skipped(video_id, client_name, 'hls')
+ else:
+ fmts, subs = self._extract_m3u8_formats_and_subtitles(
+ hls_manifest_url, video_id, 'mp4', fatal=False, live=live_status == 'is_live')
+ for sub in traverse_obj(subs, (..., ..., {dict})):
+ # TODO: If HLS video requires a PO Token, do the subs also require pot?
+ # Save client name for debugging
+ sub[STREAMING_DATA_CLIENT_NAME] = client_name
+ subtitles = self._merge_subtitles(subs, subtitles)
+ for f in fmts:
+ if process_manifest_format(f, 'hls', client_name, self._search_regex(
+ r'/itag/(\d+)', f['url'], 'itag', default=None), require_po_token and not po_token):
+ yield f
dash_manifest_url = 'dash' not in skip_manifests and sd.get('dashManifestUrl')
if dash_manifest_url:
+ pot_policy: GvsPoTokenPolicy = self._get_default_ytcfg(
+ client_name)['GVS_PO_TOKEN_POLICY'][StreamingProtocol.DASH]
+ require_po_token = gvs_pot_required(pot_policy, is_premium_subscriber, has_player_token)
+ po_token = gvs_pots.get(client_name, fetch_pot_func(required=require_po_token or pot_policy.recommended))
if po_token:
dash_manifest_url = dash_manifest_url.rstrip('/') + f'/pot/{po_token}'
- formats, subs = self._extract_mpd_formats_and_subtitles(dash_manifest_url, video_id, fatal=False)
- for sub in traverse_obj(subs, (..., ..., {dict})):
- # TODO: Investigate if DASH subs ever need a PO token; save client name for debugging
- sub[STREAMING_DATA_CLIENT_NAME] = client_name
- subtitles = self._merge_subtitles(subs, subtitles) # Prioritize HLS subs over DASH
- for f in formats:
- if process_manifest_format(f, 'dash', client_name, f['format_id'], po_token):
- f['filesize'] = int_or_none(self._search_regex(
- r'/clen/(\d+)', f.get('fragment_base_url') or f['url'], 'file size', default=None))
- if needs_live_processing:
- f['is_from_start'] = True
-
- yield f
+ if client_name not in gvs_pots:
+ gvs_pots[client_name] = po_token
+ if require_po_token and not po_token and 'missing_pot' not in self._configuration_arg('formats'):
+ self._report_pot_format_skipped(video_id, client_name, 'dash')
+ else:
+ formats, subs = self._extract_mpd_formats_and_subtitles(dash_manifest_url, video_id, fatal=False)
+ for sub in traverse_obj(subs, (..., ..., {dict})):
+ # TODO: If DASH video requires a PO Token, do the subs also require pot?
+ # Save client name for debugging
+ sub[STREAMING_DATA_CLIENT_NAME] = client_name
+ subtitles = self._merge_subtitles(subs, subtitles) # Prioritize HLS subs over DASH
+ for f in formats:
+ if process_manifest_format(f, 'dash', client_name, f['format_id'], require_po_token and not po_token):
+ f['filesize'] = int_or_none(self._search_regex(
+ r'/clen/(\d+)', f.get('fragment_base_url') or f['url'], 'file size', default=None))
+ if needs_live_processing:
+ f['is_from_start'] = True
+
+ yield f
yield subtitles
def _extract_storyboard(self, player_responses, duration):
@@ -3659,22 +3719,22 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
} for j in range(math.ceil(fragment_count))],
}
- def _download_player_responses(self, url, smuggled_data, video_id, webpage_url):
+ def _download_initial_webpage(self, webpage_url, webpage_client, video_id):
webpage = None
- if 'webpage' not in self._configuration_arg('player_skip'):
+ if webpage_url and 'webpage' not in self._configuration_arg('player_skip'):
query = {'bpctr': '9999999999', 'has_verified': '1'}
- pp = self._configuration_arg('player_params', [None], casesense=True)[0]
+ pp = (
+ self._configuration_arg('player_params', [None], casesense=True)[0]
+ or traverse_obj(INNERTUBE_CLIENTS, (webpage_client, 'PLAYER_PARAMS', {str}))
+ )
if pp:
query['pp'] = pp
- webpage = self._download_webpage_with_retries(webpage_url, video_id, query=query)
-
- master_ytcfg = self.extract_ytcfg(video_id, webpage) or self._get_default_ytcfg()
-
- player_responses, player_url = self._extract_player_responses(
- self._get_requested_clients(url, smuggled_data),
- video_id, webpage, master_ytcfg, smuggled_data)
-
- return webpage, master_ytcfg, player_responses, player_url
+ webpage = self._download_webpage_with_retries(
+ webpage_url, video_id, query=query,
+ headers=traverse_obj(self._get_default_ytcfg(webpage_client), {
+ 'User-Agent': ('INNERTUBE_CONTEXT', 'client', 'userAgent', {str}),
+ }))
+ return webpage
def _list_formats(self, video_id, microformats, video_details, player_responses, player_url, duration=None):
live_broadcast_details = traverse_obj(microformats, (..., 'liveBroadcastDetails'))
@@ -3699,14 +3759,60 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
return live_broadcast_details, live_status, streaming_data, formats, subtitles
+ def _download_initial_data(self, video_id, webpage, webpage_client, webpage_ytcfg):
+ initial_data = None
+ if webpage and 'initial_data' not in self._configuration_arg('webpage_skip'):
+ initial_data = self.extract_yt_initial_data(video_id, webpage, fatal=False)
+ if not traverse_obj(initial_data, 'contents'):
+ self.report_warning('Incomplete data received in embedded initial data; re-fetching using API.')
+ initial_data = None
+ if not initial_data and 'initial_data' not in self._configuration_arg('player_skip'):
+ query = {'videoId': video_id}
+ query.update(self._get_checkok_params())
+ initial_data = self._extract_response(
+ item_id=video_id, ep='next', fatal=False,
+ ytcfg=webpage_ytcfg, query=query, check_get_keys='contents',
+ note='Downloading initial data API JSON', default_client=webpage_client)
+ return initial_data
+
+ def _is_premium_subscriber(self, initial_data):
+ if not self.is_authenticated or not initial_data:
+ return False
+
+ tlr = traverse_obj(
+ initial_data, ('topbar', 'desktopTopbarRenderer', 'logo', 'topbarLogoRenderer'))
+ return (
+ traverse_obj(tlr, ('iconImage', 'iconType')) == 'YOUTUBE_PREMIUM_LOGO'
+ or 'premium' in (self._get_text(tlr, 'tooltipText') or '').lower()
+ )
+
+ def _initial_extract(self, url, smuggled_data, webpage_url, webpage_client, video_id):
+ # This function is also used by live-from-start refresh
+ webpage = self._download_initial_webpage(webpage_url, webpage_client, video_id)
+ webpage_ytcfg = self.extract_ytcfg(video_id, webpage) or self._get_default_ytcfg(webpage_client)
+
+ initial_data = self._download_initial_data(video_id, webpage, webpage_client, webpage_ytcfg)
+
+ is_premium_subscriber = self._is_premium_subscriber(initial_data)
+ if is_premium_subscriber:
+ self.write_debug('Detected YouTube Premium subscription')
+
+ player_responses, player_url = self._extract_player_responses(
+ self._get_requested_clients(url, smuggled_data, is_premium_subscriber),
+ video_id, webpage, webpage_client, webpage_ytcfg, is_premium_subscriber)
+
+ return webpage, webpage_ytcfg, initial_data, is_premium_subscriber, player_responses, player_url
+
def _real_extract(self, url):
url, smuggled_data = unsmuggle_url(url, {})
video_id = self._match_id(url)
base_url = self.http_scheme() + '//www.youtube.com/'
webpage_url = base_url + 'watch?v=' + video_id
+ webpage_client = 'web'
- webpage, master_ytcfg, player_responses, player_url = self._download_player_responses(url, smuggled_data, video_id, webpage_url)
+ webpage, webpage_ytcfg, initial_data, is_premium_subscriber, player_responses, player_url = self._initial_extract(
+ url, smuggled_data, webpage_url, webpage_client, video_id)
playability_statuses = traverse_obj(
player_responses, (..., 'playabilityStatus'), expected_type=dict)
@@ -3943,11 +4049,14 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
def process_language(container, base_url, lang_code, sub_name, client_name, query):
lang_subs = container.setdefault(lang_code, [])
for fmt in self._SUBTITLE_FORMATS:
- query = {**query, 'fmt': fmt}
+ # xosf=1 results in undesirable text position data for vtt, json3 & srv* subtitles
+ # See: https://github.com/yt-dlp/yt-dlp/issues/13654
+ query = {**query, 'fmt': fmt, 'xosf': []}
lang_subs.append({
'ext': fmt,
'url': urljoin('https://www.youtube.com', update_url_query(base_url, query)),
'name': sub_name,
+ 'impersonate': True,
STREAMING_DATA_CLIENT_NAME: client_name,
})
@@ -3979,7 +4088,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
pctr = pr['captions']['playerCaptionsTracklistRenderer']
client_name = pr['streamingData'][STREAMING_DATA_CLIENT_NAME]
innertube_client_name = pr['streamingData'][STREAMING_DATA_INNERTUBE_CONTEXT]['client']['clientName']
- required_contexts = self._get_default_ytcfg(client_name)['PO_TOKEN_REQUIRED_CONTEXTS']
+ pot_policy: GvsPoTokenPolicy = self._get_default_ytcfg(client_name)['SUBS_PO_TOKEN_POLICY']
fetch_subs_po_token_func = pr['streamingData'][STREAMING_DATA_FETCH_SUBS_PO_TOKEN]
pot_params = {}
@@ -3992,11 +4101,11 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
requires_pot = (
# We can detect the experiment for now
any(e in traverse_obj(qs, ('exp', ...)) for e in ('xpe', 'xpv'))
- or _PoTokenContext.SUBS in required_contexts)
+ or (pot_policy.required and not (pot_policy.not_required_for_premium and is_premium_subscriber)))
if not already_fetched_pot:
already_fetched_pot = True
- if subs_po_token := fetch_subs_po_token_func(required=requires_pot):
+ if subs_po_token := fetch_subs_po_token_func(required=requires_pot or pot_policy.recommended):
pot_params.update({
'pot': subs_po_token,
'potc': '1',
@@ -4099,21 +4208,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
'release_year': int_or_none(release_year),
})
- initial_data = None
- if webpage:
- initial_data = self.extract_yt_initial_data(video_id, webpage, fatal=False)
- if not traverse_obj(initial_data, 'contents'):
- self.report_warning('Incomplete data received in embedded initial data; re-fetching using API.')
- initial_data = None
- if not initial_data and 'initial_data' not in self._configuration_arg('player_skip'):
- query = {'videoId': video_id}
- query.update(self._get_checkok_params())
- initial_data = self._extract_response(
- item_id=video_id, ep='next', fatal=False,
- ytcfg=master_ytcfg, query=query, check_get_keys='contents',
- headers=self.generate_api_headers(ytcfg=master_ytcfg),
- note='Downloading initial data API JSON')
-
COMMENTS_SECTION_IDS = ('comment-item-section', 'engagement-panel-comments-section')
info['comment_count'] = traverse_obj(initial_data, (
'contents', 'twoColumnWatchNextResults', 'results', 'results', 'contents', ..., 'itemSectionRenderer',
@@ -4280,6 +4374,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
if upload_date and live_status not in ('is_live', 'post_live', 'is_upcoming'):
# Newly uploaded videos' HLS formats are potentially problematic and need to be checked
+ # XXX: This is redundant for as long as we are already checking all IOS HLS formats
upload_datetime = datetime_from_str(upload_date).replace(tzinfo=dt.timezone.utc)
if upload_datetime >= datetime_from_str('today-2days'):
for fmt in info['formats']:
@@ -4311,7 +4406,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
self._has_badge(badges, BadgeType.AVAILABILITY_UNLISTED)
or get_first(microformats, 'isUnlisted', expected_type=bool))))
- info['__post_extractor'] = self.extract_comments(master_ytcfg, video_id, contents, webpage)
+ info['__post_extractor'] = self.extract_comments(webpage_ytcfg, video_id, contents, webpage)
self.mark_watched(video_id, player_responses)
diff --git a/yt_dlp/globals.py b/yt_dlp/globals.py
index 0cf276cc9..81ad00448 100644
--- a/yt_dlp/globals.py
+++ b/yt_dlp/globals.py
@@ -1,3 +1,4 @@
+import os
from collections import defaultdict
# Please Note: Due to necessary changes and the complex nature involved in the plugin/globals system,
@@ -28,3 +29,4 @@ plugin_ies_overrides = Indirect(defaultdict(list))
# Misc
IN_CLI = Indirect(False)
LAZY_EXTRACTORS = Indirect(None) # `False`=force, `None`=disabled, `True`=enabled
+WINDOWS_VT_MODE = Indirect(False if os.name == 'nt' else None)
diff --git a/yt_dlp/jsinterp.py b/yt_dlp/jsinterp.py
index 45aeffa22..460bc2c03 100644
--- a/yt_dlp/jsinterp.py
+++ b/yt_dlp/jsinterp.py
@@ -222,6 +222,14 @@ class LocalNameSpace(collections.ChainMap):
def __delitem__(self, key):
raise NotImplementedError('Deleting is not supported')
+ def set_local(self, key, value):
+ self.maps[0][key] = value
+
+ def get_local(self, key):
+ if key in self.maps[0]:
+ return self.maps[0][key]
+ return JS_Undefined
+
class Debugger:
import sys
@@ -271,6 +279,7 @@ class JSInterpreter:
def __init__(self, code, objects=None):
self.code, self._functions = code, {}
self._objects = {} if objects is None else objects
+ self._undefined_varnames = set()
class Exception(ExtractorError): # noqa: A001
def __init__(self, msg, expr=None, *args, **kwargs):
@@ -381,7 +390,7 @@ class JSInterpreter:
return self._named_object(namespace, obj)
@Debugger.wrap_interpreter
- def interpret_statement(self, stmt, local_vars, allow_recursion=100):
+ def interpret_statement(self, stmt, local_vars, allow_recursion=100, _is_var_declaration=False):
if allow_recursion < 0:
raise self.Exception('Recursion limit reached')
allow_recursion -= 1
@@ -401,6 +410,7 @@ class JSInterpreter:
if m.group('throw'):
raise JS_Throw(self.interpret_expression(expr, local_vars, allow_recursion))
should_return = not m.group('var')
+ _is_var_declaration = _is_var_declaration or bool(m.group('var'))
if not expr:
return None, should_return
@@ -585,7 +595,8 @@ class JSInterpreter:
sub_expressions = list(self._separate(expr))
if len(sub_expressions) > 1:
for sub_expr in sub_expressions:
- ret, should_abort = self.interpret_statement(sub_expr, local_vars, allow_recursion)
+ ret, should_abort = self.interpret_statement(
+ sub_expr, local_vars, allow_recursion, _is_var_declaration=_is_var_declaration)
if should_abort:
return ret, True
return ret, False
@@ -599,8 +610,12 @@ class JSInterpreter:
left_val = local_vars.get(m.group('out'))
if not m.group('index'):
- local_vars[m.group('out')] = self._operator(
+ eval_result = self._operator(
m.group('op'), left_val, m.group('expr'), expr, local_vars, allow_recursion)
+ if _is_var_declaration:
+ local_vars.set_local(m.group('out'), eval_result)
+ else:
+ local_vars[m.group('out')] = eval_result
return local_vars[m.group('out')], should_return
elif left_val in (None, JS_Undefined):
raise self.Exception(f'Cannot index undefined variable {m.group("out")}', expr)
@@ -654,7 +669,19 @@ class JSInterpreter:
return float('NaN'), should_return
elif m and m.group('return'):
- return local_vars.get(m.group('name'), JS_Undefined), should_return
+ var = m.group('name')
+ # Declared variables
+ if _is_var_declaration:
+ ret = local_vars.get_local(var)
+ # Register varname in local namespace
+ # Set value as JS_Undefined or its pre-existing value
+ local_vars.set_local(var, ret)
+ else:
+ ret = local_vars.get(var, NO_DEFAULT)
+ if ret is NO_DEFAULT:
+ ret = JS_Undefined
+ self._undefined_varnames.add(var)
+ return ret, should_return
with contextlib.suppress(ValueError):
return json.loads(js_to_json(expr, strict=True)), should_return
@@ -857,7 +884,7 @@ class JSInterpreter:
obj = {}
obj_m = re.search(
r'''(?x)
- (?(%s\s*:\s*function\s*\(.*?\)\s*{.*?}(?:,\s*)?)*)
}\s*;
''' % (re.escape(objname), _FUNC_NAME_RE),
diff --git a/yt_dlp/networking/_requests.py b/yt_dlp/networking/_requests.py
index d02e976b5..6582038fc 100644
--- a/yt_dlp/networking/_requests.py
+++ b/yt_dlp/networking/_requests.py
@@ -140,6 +140,12 @@ class RequestsResponseAdapter(Response):
def read(self, amt: int | None = None):
try:
+ # Work around issue with `.read(amt)` then `.read()`
+ # See: https://github.com/urllib3/urllib3/issues/3636
+ if amt is None:
+ # Python 3.9 preallocates the whole read buffer, read in chunks
+ read_chunk = functools.partial(self.fp.read, 1 << 20, decode_content=True)
+ return b''.join(iter(read_chunk, b''))
# Interact with urllib3 response directly.
return self.fp.read(amt, decode_content=True)
@@ -307,7 +313,7 @@ class RequestsRH(RequestHandler, InstanceStoreMixin):
max_retries=urllib3.util.retry.Retry(False),
)
session.adapters.clear()
- session.headers = requests.models.CaseInsensitiveDict({'Connection': 'keep-alive'})
+ session.headers = requests.models.CaseInsensitiveDict()
session.mount('https://', http_adapter)
session.mount('http://', http_adapter)
session.cookies = cookiejar
@@ -316,6 +322,7 @@ class RequestsRH(RequestHandler, InstanceStoreMixin):
def _prepare_headers(self, _, headers):
add_accept_encoding_header(headers, SUPPORTED_ENCODINGS)
+ headers.setdefault('Connection', 'keep-alive')
def _send(self, request):
diff --git a/yt_dlp/options.py b/yt_dlp/options.py
index b4d3d4d66..13ba445df 100644
--- a/yt_dlp/options.py
+++ b/yt_dlp/options.py
@@ -529,14 +529,14 @@ def create_parser():
'no-attach-info-json', 'embed-thumbnail-atomicparsley', 'no-external-downloader-progress',
'embed-metadata', 'seperate-video-versions', 'no-clean-infojson', 'no-keep-subs', 'no-certifi',
'no-youtube-channel-redirect', 'no-youtube-unavailable-videos', 'no-youtube-prefer-utc-upload-date',
- 'prefer-legacy-http-handler', 'manifest-filesize-approx', 'allow-unsafe-ext', 'prefer-vp9-sort',
+ 'prefer-legacy-http-handler', 'manifest-filesize-approx', 'allow-unsafe-ext', 'prefer-vp9-sort', 'mtime-by-default',
}, 'aliases': {
'youtube-dl': ['all', '-multistreams', '-playlist-match-filter', '-manifest-filesize-approx', '-allow-unsafe-ext', '-prefer-vp9-sort'],
'youtube-dlc': ['all', '-no-youtube-channel-redirect', '-no-live-chat', '-playlist-match-filter', '-manifest-filesize-approx', '-allow-unsafe-ext', '-prefer-vp9-sort'],
'2021': ['2022', 'no-certifi', 'filename-sanitization'],
'2022': ['2023', 'no-external-downloader-progress', 'playlist-match-filter', 'prefer-legacy-http-handler', 'manifest-filesize-approx'],
'2023': ['2024', 'prefer-vp9-sort'],
- '2024': [],
+ '2024': ['mtime-by-default'],
},
}, help=(
'Options that can help keep compatibility with youtube-dl or youtube-dlc '
@@ -1466,12 +1466,12 @@ def create_parser():
help='Do not use .part files - write directly into output file')
filesystem.add_option(
'--mtime',
- action='store_true', dest='updatetime', default=True,
- help='Use the Last-modified header to set the file modification time (default)')
+ action='store_true', dest='updatetime', default=None,
+ help='Use the Last-modified header to set the file modification time')
filesystem.add_option(
'--no-mtime',
action='store_false', dest='updatetime',
- help='Do not use the Last-modified header to set the file modification time')
+ help='Do not use the Last-modified header to set the file modification time (default)')
filesystem.add_option(
'--write-description',
action='store_true', dest='writedescription', default=False,
diff --git a/yt_dlp/postprocessor/embedthumbnail.py b/yt_dlp/postprocessor/embedthumbnail.py
index d8ba220ca..39e8826c6 100644
--- a/yt_dlp/postprocessor/embedthumbnail.py
+++ b/yt_dlp/postprocessor/embedthumbnail.py
@@ -90,7 +90,7 @@ class EmbedThumbnailPP(FFmpegPostProcessor):
if info['ext'] == 'mp3':
options = [
'-c', 'copy', '-map', '0:0', '-map', '1:0', '-write_id3v1', '1', '-id3v2_version', '3',
- '-metadata:s:v', 'title="Album cover"', '-metadata:s:v', 'comment=Cover (front)']
+ '-metadata:s:v', 'title=Album cover', '-metadata:s:v', 'comment=Cover (front)']
self._report_run('ffmpeg', filename)
self.run_ffmpeg_multiple_files([filename, thumbnail_filename], temp_filename, options)
diff --git a/yt_dlp/postprocessor/exec.py b/yt_dlp/postprocessor/exec.py
index 1f0a0015e..243487dd2 100644
--- a/yt_dlp/postprocessor/exec.py
+++ b/yt_dlp/postprocessor/exec.py
@@ -18,7 +18,7 @@ class ExecPP(PostProcessor):
if filepath:
if '{}' not in cmd:
cmd += ' {}'
- cmd = cmd.replace('{}', shell_quote(filepath))
+ cmd = cmd.replace('{}', shell_quote(filepath, shell=True))
return cmd
def run(self, info):
diff --git a/yt_dlp/postprocessor/xattrpp.py b/yt_dlp/postprocessor/xattrpp.py
index e486b797b..fd83d783b 100644
--- a/yt_dlp/postprocessor/xattrpp.py
+++ b/yt_dlp/postprocessor/xattrpp.py
@@ -33,8 +33,17 @@ class XAttrMetadataPP(PostProcessor):
# (e.g., 4kB on ext4), and we don't want to have the other ones fail
'user.dublincore.description': 'description',
# 'user.xdg.comment': 'description',
+ 'com.apple.metadata:kMDItemWhereFroms': 'webpage_url',
}
+ APPLE_PLIST_TEMPLATE = '''
+
+
+
+\t%s
+
+'''
+
def run(self, info):
mtime = os.stat(info['filepath']).st_mtime
self.to_screen('Writing metadata to file\'s xattrs')
@@ -44,6 +53,8 @@ class XAttrMetadataPP(PostProcessor):
if value:
if infoname == 'upload_date':
value = hyphenate_date(value)
+ elif xattrname == 'com.apple.metadata:kMDItemWhereFroms':
+ value = self.APPLE_PLIST_TEMPLATE % value
write_xattr(info['filepath'], xattrname, value.encode())
except XAttrUnavailableError as e:
diff --git a/yt_dlp/update.py b/yt_dlp/update.py
index de289cb78..30cbf538e 100644
--- a/yt_dlp/update.py
+++ b/yt_dlp/update.py
@@ -139,7 +139,18 @@ def _get_binary_name():
def _get_system_deprecation():
- MIN_SUPPORTED, MIN_RECOMMENDED = (3, 9), (3, 9)
+ MIN_SUPPORTED, MIN_RECOMMENDED = (3, 9), (3, 10)
+
+ EXE_MSG_TMPL = ('Support for {} has been deprecated. '
+ 'See https://github.com/yt-dlp/yt-dlp/{} for details.\n{}')
+ STOP_MSG = 'You may stop receiving updates on this version at any time!'
+ variant = detect_variant()
+
+ # Temporary until macos_legacy executable builds are discontinued
+ if variant == 'darwin_legacy_exe':
+ return EXE_MSG_TMPL.format(
+ f'{variant} (the PyInstaller-bundled executable for macOS versions older than 10.15)',
+ 'issues/13856', STOP_MSG)
if sys.version_info > MIN_RECOMMENDED:
return None
@@ -150,6 +161,13 @@ def _get_system_deprecation():
if sys.version_info < MIN_SUPPORTED:
return f'Python version {major}.{minor} is no longer supported! {PYTHON_MSG}'
+ # Temporary until aarch64/armv7l build flow is bumped to Ubuntu 22.04 and Python 3.10
+ if variant in ('linux_aarch64_exe', 'linux_armv7l_exe'):
+ libc_ver = version_tuple(os.confstr('CS_GNU_LIBC_VERSION').partition(' ')[2])
+ if libc_ver < (2, 35):
+ return EXE_MSG_TMPL.format('system glibc version < 2.35', 'issues/13858', STOP_MSG)
+ return None
+
return f'Support for Python version {major}.{minor} has been deprecated. {PYTHON_MSG}'
diff --git a/yt_dlp/utils/_utils.py b/yt_dlp/utils/_utils.py
index 20aa341ca..a5471da4d 100644
--- a/yt_dlp/utils/_utils.py
+++ b/yt_dlp/utils/_utils.py
@@ -52,7 +52,7 @@ from ..compat import (
compat_HTMLParseError,
)
from ..dependencies import xattr
-from ..globals import IN_CLI
+from ..globals import IN_CLI, WINDOWS_VT_MODE
__name__ = __name__.rsplit('.', 1)[0] # noqa: A001 # Pretend to be the parent module
@@ -1285,7 +1285,7 @@ def unified_timestamp(date_str, day_first=True):
timetuple = email.utils.parsedate_tz(date_str)
if timetuple:
- return calendar.timegm(timetuple) + pm_delta * 3600 - timezone.total_seconds()
+ return calendar.timegm(timetuple) + pm_delta * 3600 - int(timezone.total_seconds())
@partial_application
@@ -1875,6 +1875,11 @@ def parse_resolution(s, *, lenient=False):
if mobj:
return {'height': int(mobj.group(1)) * 540}
+ if lenient:
+ mobj = re.search(r'(?[^"]+)"', cd)
- if m:
- e = determine_ext(m.group('filename'), default_ext=None)
- if e:
- return e
-
- meta_ext = getheader('x-amz-meta-name')
- if meta_ext:
- e = meta_ext.rpartition('.')[2]
- if e:
- return e
+ if cd := getheader('Content-Disposition'):
+ if m := re.match(r'attachment;\s*filename="(?P[^"]+)"', cd):
+ if ext := determine_ext(m.group('filename'), default_ext=None):
+ return ext
- return mimetype2ext(getheader('Content-Type'), default=default)
+ return (
+ determine_ext(getheader('x-amz-meta-name'), default_ext=None)
+ or getheader('x-amz-meta-file-type')
+ or mimetype2ext(getheader('Content-Type'), default=default))
def encode_data_uri(data, mime_type):
@@ -4764,13 +4764,10 @@ def jwt_decode_hs256(jwt):
return json.loads(base64.urlsafe_b64decode(f'{payload_b64}==='))
-WINDOWS_VT_MODE = False if os.name == 'nt' else None
-
-
@functools.cache
def supports_terminal_sequences(stream):
if os.name == 'nt':
- if not WINDOWS_VT_MODE:
+ if not WINDOWS_VT_MODE.value:
return False
elif not os.getenv('TERM'):
return False
@@ -4807,8 +4804,7 @@ def windows_enable_vt_mode():
finally:
os.close(handle)
- global WINDOWS_VT_MODE
- WINDOWS_VT_MODE = True
+ WINDOWS_VT_MODE.value = True
supports_terminal_sequences.cache_clear()
diff --git a/yt_dlp/utils/networking.py b/yt_dlp/utils/networking.py
index 9fcab6456..467312ce7 100644
--- a/yt_dlp/utils/networking.py
+++ b/yt_dlp/utils/networking.py
@@ -15,48 +15,10 @@ from .traversal import traverse_obj
def random_user_agent():
- _USER_AGENT_TPL = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/%s Safari/537.36'
- _CHROME_VERSIONS = (
- '90.0.4430.212',
- '90.0.4430.24',
- '90.0.4430.70',
- '90.0.4430.72',
- '90.0.4430.85',
- '90.0.4430.93',
- '91.0.4472.101',
- '91.0.4472.106',
- '91.0.4472.114',
- '91.0.4472.124',
- '91.0.4472.164',
- '91.0.4472.19',
- '91.0.4472.77',
- '92.0.4515.107',
- '92.0.4515.115',
- '92.0.4515.131',
- '92.0.4515.159',
- '92.0.4515.43',
- '93.0.4556.0',
- '93.0.4577.15',
- '93.0.4577.63',
- '93.0.4577.82',
- '94.0.4606.41',
- '94.0.4606.54',
- '94.0.4606.61',
- '94.0.4606.71',
- '94.0.4606.81',
- '94.0.4606.85',
- '95.0.4638.17',
- '95.0.4638.50',
- '95.0.4638.54',
- '95.0.4638.69',
- '95.0.4638.74',
- '96.0.4664.18',
- '96.0.4664.45',
- '96.0.4664.55',
- '96.0.4664.93',
- '97.0.4692.20',
- )
- return _USER_AGENT_TPL % random.choice(_CHROME_VERSIONS)
+ USER_AGENT_TMPL = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/{} Safari/537.36'
+ # Target versions released within the last ~6 months
+ CHROME_MAJOR_VERSION_RANGE = (132, 138)
+ return USER_AGENT_TMPL.format(f'{random.randint(*CHROME_MAJOR_VERSION_RANGE)}.0.0.0')
class HTTPHeaderDict(dict):
diff --git a/yt_dlp/version.py b/yt_dlp/version.py
index b97c01499..868429ffb 100644
--- a/yt_dlp/version.py
+++ b/yt_dlp/version.py
@@ -1,8 +1,8 @@
# Autogenerated by devscripts/update-version.py
-__version__ = '2025.06.09'
+__version__ = '2025.07.21'
-RELEASE_GIT_HEAD = '339614a173c74b42d63e858c446a9cae262a13af'
+RELEASE_GIT_HEAD = '9951fdd0d08b655cb1af8cd7f32a3fb7e2b1324e'
VARIANT = None
@@ -12,4 +12,4 @@ CHANNEL = 'stable'
ORIGIN = 'yt-dlp/yt-dlp'
-_pkg_version = '2025.06.09'
+_pkg_version = '2025.07.21'
|