[^>]+>[^>]+>([^<]+)',
- 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 7794cae6c0..9038b4a7ff 100644
--- a/yt_dlp/extractor/patreon.py
+++ b/yt_dlp/extractor/patreon.py
@@ -19,7 +19,7 @@
url_or_none,
urljoin,
)
-from ..utils.traversal import traverse_obj, value
+from ..utils.traversal import require, traverse_obj, value
class PatreonBaseIE(InfoExtractor):
@@ -340,8 +340,9 @@ def _real_extract(self, url):
'channel_follower_count': ('attributes', 'patron_count', {int_or_none}),
}))
- # all-lowercase 'referer' so we can smuggle it to Generic, SproutVideo, Vimeo
- headers = {'referer': 'https://patreon.com/'}
+ # Must be all-lowercase 'referer' so we can smuggle it to Generic, SproutVideo, and Vimeo.
+ # patreon.com URLs redirect to www.patreon.com; this matters when requesting mux.com m3u8s
+ headers = {'referer': 'https://www.patreon.com/'}
# handle Vimeo embeds
if traverse_obj(attributes, ('embed', 'provider')) == 'Vimeo':
@@ -352,7 +353,7 @@ def _real_extract(self, url):
v_url, video_id, 'Checking Vimeo embed URL', headers=headers,
fatal=False, errnote=False, expected_status=429): # 429 is TLS fingerprint rejection
entries.append(self.url_result(
- VimeoIE._smuggle_referrer(v_url, 'https://patreon.com/'),
+ VimeoIE._smuggle_referrer(v_url, headers['referer']),
VimeoIE, url_transparent=True))
embed_url = traverse_obj(attributes, ('embed', 'url', {url_or_none}))
@@ -379,11 +380,13 @@ def _real_extract(self, url):
'url': post_file['url'],
})
elif name == 'video' or determine_ext(post_file.get('url')) == 'm3u8':
- formats, subtitles = self._extract_m3u8_formats_and_subtitles(post_file['url'], video_id)
+ formats, subtitles = self._extract_m3u8_formats_and_subtitles(
+ post_file['url'], video_id, headers=headers)
entries.append({
'id': video_id,
'formats': formats,
'subtitles': subtitles,
+ 'http_headers': headers,
})
can_view_post = traverse_obj(attributes, 'current_user_can_view')
@@ -459,7 +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/',
@@ -528,6 +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,
@@ -569,8 +594,11 @@ def _real_extract(self, url):
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/picarto.py b/yt_dlp/extractor/picarto.py
index 72e89c31ed..92431fa241 100644
--- a/yt_dlp/extractor/picarto.py
+++ b/yt_dlp/extractor/picarto.py
@@ -10,7 +10,8 @@
class PicartoIE(InfoExtractor):
- _VALID_URL = r'https?://(?:www.)?picarto\.tv/(?P[a-zA-Z0-9]+)'
+ IE_NAME = 'picarto'
+ _VALID_URL = r'https?://(?:www.)?picarto\.tv/(?P[^/#?]+)/?(?:$|[?#])'
_TEST = {
'url': 'https://picarto.tv/Setz',
'info_dict': {
@@ -89,7 +90,8 @@ def _real_extract(self, url):
class PicartoVodIE(InfoExtractor):
- _VALID_URL = r'https?://(?:www\.)?picarto\.tv/(?:videopopout|\w+/videos)/(?P[^/?#&]+)'
+ IE_NAME = 'picarto:vod'
+ _VALID_URL = r'https?://(?:www\.)?picarto\.tv/(?:videopopout|\w+(?:/profile)?/videos)/(?P[^/?#&]+)'
_TESTS = [{
'url': 'https://picarto.tv/videopopout/ArtofZod_2017.12.12.00.13.23.flv',
'md5': '3ab45ba4352c52ee841a28fb73f2d9ca',
@@ -111,6 +113,18 @@ class PicartoVodIE(InfoExtractor):
'channel': 'ArtofZod',
'age_limit': 18,
},
+ }, {
+ 'url': 'https://picarto.tv/DrechuArt/profile/videos/400347',
+ 'md5': 'f9ea54868b1d9dec40eb554b484cc7bf',
+ 'info_dict': {
+ 'id': '400347',
+ 'ext': 'mp4',
+ 'title': 'Welcome to the Show',
+ 'thumbnail': r're:^https?://.*\.jpg',
+ 'channel': 'DrechuArt',
+ 'age_limit': 0,
+ },
+
}, {
'url': 'https://picarto.tv/videopopout/Plague',
'only_matching': True,
diff --git a/yt_dlp/extractor/playerfm.py b/yt_dlp/extractor/playerfm.py
new file mode 100644
index 0000000000..d59d651a32
--- /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/playsuisse.py b/yt_dlp/extractor/playsuisse.py
index 9bf5765fa7..46e3a5b8ff 100644
--- a/yt_dlp/extractor/playsuisse.py
+++ b/yt_dlp/extractor/playsuisse.py
@@ -9,11 +9,10 @@
int_or_none,
join_nonempty,
parse_qs,
- traverse_obj,
update_url_query,
urlencode_postdata,
)
-from ..utils.traversal import unpack
+from ..utils.traversal import traverse_obj, unpack
class PlaySuisseIE(InfoExtractor):
diff --git a/yt_dlp/extractor/plyr.py b/yt_dlp/extractor/plyr.py
new file mode 100644
index 0000000000..c5f27cfd95
--- /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/podchaser.py b/yt_dlp/extractor/podchaser.py
index 4570f0f175..6c125f9ba6 100644
--- a/yt_dlp/extractor/podchaser.py
+++ b/yt_dlp/extractor/podchaser.py
@@ -5,11 +5,13 @@
from ..utils import (
OnDemandPagedList,
float_or_none,
+ int_or_none,
+ orderedSet,
str_or_none,
- str_to_int,
- traverse_obj,
unified_timestamp,
+ url_or_none,
)
+from ..utils.traversal import require, traverse_obj
class PodchaserIE(InfoExtractor):
@@ -21,24 +23,25 @@ class PodchaserIE(InfoExtractor):
'id': '104365585',
'title': 'Ep. 285 – freeze me off',
'description': 'cam ahn',
- 'thumbnail': r're:^https?://.*\.jpg$',
+ 'thumbnail': r're:https?://.+/.+\.jpg',
'ext': 'mp3',
- 'categories': ['Comedy'],
+ 'categories': ['Comedy', 'News', 'Politics', 'Arts'],
'tags': ['comedy', 'dark humor'],
- 'series': 'Cum Town',
+ 'series': 'The Adam Friedland Show Podcast',
'duration': 3708,
'timestamp': 1636531259,
'upload_date': '20211110',
'average_rating': 4.0,
+ 'series_id': '36924',
},
}, {
'url': 'https://www.podchaser.com/podcasts/the-bone-zone-28853',
'info_dict': {
'id': '28853',
'title': 'The Bone Zone',
- 'description': 'Podcast by The Bone Zone',
+ 'description': r're:The official home of the Bone Zone podcast.+',
},
- 'playlist_count': 275,
+ 'playlist_mincount': 275,
}, {
'url': 'https://www.podchaser.com/podcasts/sean-carrolls-mindscape-scienc-699349/episodes',
'info_dict': {
@@ -51,19 +54,33 @@ class PodchaserIE(InfoExtractor):
@staticmethod
def _parse_episode(episode, podcast):
- return {
- 'id': str(episode.get('id')),
- 'title': episode.get('title'),
- 'description': episode.get('description'),
- 'url': episode.get('audio_url'),
- 'thumbnail': episode.get('image_url'),
- 'duration': str_to_int(episode.get('length')),
- 'timestamp': unified_timestamp(episode.get('air_date')),
- 'average_rating': float_or_none(episode.get('rating')),
- 'categories': list(set(traverse_obj(podcast, (('summary', None), 'categories', ..., 'text')))),
- 'tags': traverse_obj(podcast, ('tags', ..., 'text')),
- 'series': podcast.get('title'),
- }
+ info = traverse_obj(episode, {
+ 'id': ('id', {int}, {str_or_none}, {require('episode ID')}),
+ 'title': ('title', {str}),
+ 'description': ('description', {str}),
+ 'url': ('audio_url', {url_or_none}),
+ 'thumbnail': ('image_url', {url_or_none}),
+ 'duration': ('length', {int_or_none}),
+ 'timestamp': ('air_date', {unified_timestamp}),
+ 'average_rating': ('rating', {float_or_none}),
+ })
+ info.update(traverse_obj(podcast, {
+ 'series': ('title', {str}),
+ 'series_id': ('id', {int}, {str_or_none}),
+ 'categories': (('summary', None), 'categories', ..., 'text', {str}, filter, all, {orderedSet}),
+ 'tags': ('tags', ..., 'text', {str}),
+ }))
+ info['vcodec'] = 'none'
+
+ if info.get('series_id'):
+ podcast_slug = traverse_obj(podcast, ('slug', {str})) or 'podcast'
+ episode_slug = traverse_obj(episode, ('slug', {str})) or 'episode'
+ info['webpage_url'] = '/'.join((
+ 'https://www.podchaser.com/podcasts',
+ '-'.join((podcast_slug[:30].rstrip('-'), info['series_id'])),
+ '-'.join((episode_slug[:30].rstrip('-'), info['id']))))
+
+ return info
def _call_api(self, path, *args, **kwargs):
return self._download_json(f'https://api.podchaser.com/{path}', *args, **kwargs)
@@ -93,5 +110,5 @@ def _real_extract(self, url):
OnDemandPagedList(functools.partial(self._fetch_page, podcast_id, podcast), self._PAGE_SIZE),
str_or_none(podcast.get('id')), podcast.get('title'), podcast.get('description'))
- episode = self._call_api(f'episodes/{episode_id}', episode_id)
+ episode = self._call_api(f'podcasts/{podcast_id}/episodes/{episode_id}/player_ids', episode_id)
return self._parse_episode(episode, podcast)
diff --git a/yt_dlp/extractor/qqmusic.py b/yt_dlp/extractor/qqmusic.py
index fb46e0d124..56a8e7300a 100644
--- a/yt_dlp/extractor/qqmusic.py
+++ b/yt_dlp/extractor/qqmusic.py
@@ -15,7 +15,6 @@
str_or_none,
strip_jsonp,
traverse_obj,
- unescapeHTML,
url_or_none,
urljoin,
)
@@ -425,7 +424,7 @@ def _real_extract(self, url):
return self.playlist_result(entries, list_id, **traverse_obj(list_json, ('cdlist', 0, {
'title': ('dissname', {str}),
- 'description': ('desc', {unescapeHTML}, {clean_html}),
+ 'description': ('desc', {clean_html}),
})))
diff --git a/yt_dlp/extractor/rai.py b/yt_dlp/extractor/rai.py
index c489dc7312..d1a4d4c37f 100644
--- a/yt_dlp/extractor/rai.py
+++ b/yt_dlp/extractor/rai.py
@@ -81,7 +81,7 @@ def fix_cdata(s):
# 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 @@ def fix_cdata(s):
'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/sauceplus.py b/yt_dlp/extractor/sauceplus.py
new file mode 100644
index 0000000000..75d7022d3c
--- /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 bc5ec3da7f..70111d0944 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',
- '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',
+ 'title': '10-1',
+ 'description': 'md5:1ec50901efc3437cfbfe3790468d532d',
+ 'duration': 313,
+ '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 _real_extract(self, url):
- video_id = self._match_id(url)
- nuxt_data = self._search_nuxt_data(self._download_webpage(url, video_id), video_id)
+ 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',
+ })
- 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'),
+ def _real_extract(self, url):
+ 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)
+
+ 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 0013d2621e..fe45be7740 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 c70940a606..404e298978 100644
--- a/yt_dlp/extractor/soundcloud.py
+++ b/yt_dlp/extractor/soundcloud.py
@@ -242,7 +242,7 @@ def _extract_info_dict(self, info, full_title=None, secret_token=None, extract_f
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,
@@ -697,7 +697,7 @@ def _real_extract(self, url):
try:
return self._extract_info_dict(info, full_title, token)
except ExtractorError as e:
- if not isinstance(e.cause, HTTPError) or not e.cause.status == 429:
+ if not isinstance(e.cause, HTTPError) or e.cause.status != 429:
raise
self.report_warning(
'You have reached the API rate limit, which is ~600 requests per '
diff --git a/yt_dlp/extractor/sportdeutschland.py b/yt_dlp/extractor/sportdeutschland.py
index 2d6acb8768..0b7d90a071 100644
--- a/yt_dlp/extractor/sportdeutschland.py
+++ b/yt_dlp/extractor/sportdeutschland.py
@@ -8,67 +8,86 @@
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 c0923594e5..ff9dc7dee2 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 @@ def _real_extract(self, url):
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/srmediathek.py b/yt_dlp/extractor/srmediathek.py
index fc63d9b1a5..d6cab6ae70 100644
--- a/yt_dlp/extractor/srmediathek.py
+++ b/yt_dlp/extractor/srmediathek.py
@@ -1,57 +1,102 @@
from .ard import ARDMediathekBaseIE
from ..utils import (
ExtractorError,
- get_element_by_attribute,
+ clean_html,
+ extract_attributes,
+ parse_duration,
+ parse_qs,
+ unified_strdate,
+)
+from ..utils.traversal import (
+ find_element,
+ require,
+ traverse_obj,
)
class SRMediathekIE(ARDMediathekBaseIE):
- _WORKING = False
IE_NAME = 'sr:mediathek'
IE_DESC = 'Saarländischer Rundfunk'
- _VALID_URL = r'https?://sr-mediathek(?:\.sr-online)?\.de/index\.php\?.*?&id=(?P[0-9]+)'
+ _CLS_COMMON = 'teaser__image__caption__text teaser__image__caption__text--'
+ _VALID_URL = r'https?://(?:www\.)?sr-mediathek\.de/index\.php\?.*?&id=(?P\d+)'
_TESTS = [{
- 'url': 'http://sr-mediathek.sr-online.de/index.php?seite=7&id=28455',
+ 'url': 'https://www.sr-mediathek.de/index.php?seite=7&id=141317',
'info_dict': {
- 'id': '28455',
+ 'id': '141317',
'ext': 'mp4',
- 'title': 'sportarena (26.10.2014)',
- 'description': 'Ringen: KSV Köllerbach gegen Aachen-Walheim; Frauen-Fußball: 1. FC Saarbrücken gegen Sindelfingen; Motorsport: Rallye in Losheim; dazu: Interview mit Timo Bernhard; Turnen: TG Saar; Reitsport: Deutscher Voltigier-Pokal; Badminton: Interview mit Michael Fuchs ',
- 'thumbnail': r're:^https?://.*\.jpg$',
- },
- 'skip': 'no longer available',
- }, {
- 'url': 'http://sr-mediathek.sr-online.de/index.php?seite=7&id=37682',
- 'info_dict': {
- 'id': '37682',
- 'ext': 'mp4',
- 'title': 'Love, Cakes and Rock\'n\'Roll',
- 'description': 'md5:18bf9763631c7d326c22603681e1123d',
- },
- 'params': {
- # m3u8 download
- 'skip_download': True,
+ 'title': 'Kärnten, da will ich hin!',
+ 'channel': 'SR Fernsehen',
+ 'description': 'md5:7732e71e803379a499732864a572a456',
+ 'duration': 1788.0,
+ 'release_date': '20250525',
+ 'series': 'da will ich hin!',
+ 'series_id': 'DWIH',
+ 'thumbnail': r're:https?://.+\.jpg',
},
}, {
- 'url': 'http://sr-mediathek.de/index.php?seite=7&id=7480',
- 'only_matching': True,
+ 'url': 'https://www.sr-mediathek.de/index.php?seite=7&id=153853',
+ 'info_dict': {
+ 'id': '153853',
+ 'ext': 'mp3',
+ 'title': 'Kappes, Klöße, Kokosmilch: Bruschetta mit Nduja',
+ 'channel': 'SR 3',
+ 'description': 'md5:3935798de3562b10c4070b408a15e225',
+ 'duration': 139.0,
+ 'release_date': '20250523',
+ 'series': 'Kappes, Klöße, Kokosmilch',
+ 'series_id': 'SR3_KKK_A',
+ 'thumbnail': r're:https?://.+\.jpg',
+ },
+ }, {
+ 'url': 'https://www.sr-mediathek.de/index.php?seite=7&id=31406&pnr=&tbl=pf',
+ 'info_dict': {
+ 'id': '31406',
+ 'ext': 'mp3',
+ 'title': 'Das Leben schwer nehmen, ist einfach zu anstrengend',
+ 'channel': 'SR 1',
+ 'description': 'md5:3e03fd556af831ad984d0add7175fb0c',
+ 'duration': 1769.0,
+ 'release_date': '20230717',
+ 'series': 'Abendrot',
+ 'series_id': 'SR1_AB_P',
+ 'thumbnail': r're:https?://.+\.jpg',
+ },
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
+ description = self._og_search_description(webpage)
- if '>Der gewünschte Beitrag ist leider nicht mehr verfügbar.<' in webpage:
+ if description == 'Der gewünschte Beitrag ist leider nicht mehr vorhanden.':
raise ExtractorError(f'Video {video_id} is no longer available', expected=True)
- media_collection_url = self._search_regex(
- r'data-mediacollection-ardplayer="([^"]+)"', webpage, 'media collection url')
- info = self._extract_media_info(media_collection_url, webpage, video_id)
- info.update({
+ player_url = traverse_obj(webpage, (
+ {find_element(tag='div', id=f'player{video_id}', html=True)},
+ {extract_attributes}, 'data-mediacollection-ardplayer',
+ {self._proto_relative_url}, {require('player URL')}))
+ article = traverse_obj(webpage, (
+ {find_element(cls='article__content')},
+ {find_element(tag='p')}, {clean_html}))
+
+ return {
+ **self._extract_media_info(player_url, webpage, video_id),
'id': video_id,
- 'title': get_element_by_attribute('class', 'ardplayer-title', webpage),
- 'description': self._og_search_description(webpage),
+ 'title': traverse_obj(webpage, (
+ {find_element(cls='ardplayer-title')}, {clean_html})),
+ 'channel': traverse_obj(webpage, (
+ {find_element(cls=f'{self._CLS_COMMON}subheadline')},
+ {lambda x: x.split('|')[0]}, {clean_html})),
+ 'description': description,
+ 'duration': parse_duration(self._search_regex(
+ r'(\d{2}:\d{2}:\d{2})', article, 'duration')),
+ 'release_date': unified_strdate(self._search_regex(
+ r'(\d{2}\.\d{2}\.\d{4})', article, 'release_date')),
+ 'series': traverse_obj(webpage, (
+ {find_element(cls=f'{self._CLS_COMMON}headline')}, {clean_html})),
+ 'series_id': traverse_obj(webpage, (
+ {find_element(cls='teaser__link', html=True)},
+ {extract_attributes}, 'href', {parse_qs}, 'sen', ..., {str}, any)),
'thumbnail': self._og_search_thumbnail(webpage),
- })
- return info
+ }
diff --git a/yt_dlp/extractor/stacommu.py b/yt_dlp/extractor/stacommu.py
index 8300185183..e6866f1517 100644
--- a/yt_dlp/extractor/stacommu.py
+++ b/yt_dlp/extractor/stacommu.py
@@ -4,6 +4,7 @@
from ..utils import (
int_or_none,
traverse_obj,
+ url_basename,
url_or_none,
)
@@ -65,9 +66,19 @@ def _extract_ppv(self, url):
hls_info, decrypt = self._call_encrypted_api(
video_id, ':watchArchive', 'stream information', data={'method': 1})
+ formats = self._get_formats(hls_info, ('hls', 'urls', ..., {url_or_none}), video_id)
+ for f in formats:
+ # bitrates are exaggerated in PPV playlists, so avoid wrong/huge filesize_approx values
+ if f.get('tbr'):
+ f['tbr'] = int(f['tbr'] / 2.5)
+ # prefer variants with the same basename as the master playlist to avoid partial streams
+ f['format_id'] = url_basename(f['url']).partition('.')[0]
+ if not f['format_id'].startswith(url_basename(f['manifest_url']).partition('.')[0]):
+ f['preference'] = -10
+
return {
'id': video_id,
- 'formats': self._get_formats(hls_info, ('hls', 'urls', ..., {url_or_none}), video_id),
+ 'formats': formats,
'hls_aes': self._extract_hls_key(hls_info, 'hls', decrypt),
**traverse_obj(video_info, {
'title': ('displayName', {str}),
diff --git a/yt_dlp/extractor/startrek.py b/yt_dlp/extractor/startrek.py
index c591871731..802702d44e 100644
--- a/yt_dlp/extractor/startrek.py
+++ b/yt_dlp/extractor/startrek.py
@@ -1,76 +1,76 @@
from .common import InfoExtractor
-from ..utils import int_or_none, urljoin
+from .youtube import YoutubeIE
+from ..utils import (
+ clean_html,
+ parse_iso8601,
+ update_url,
+ url_or_none,
+)
+from ..utils.traversal import subs_list_to_dict, traverse_obj
class StarTrekIE(InfoExtractor):
- _WORKING = False
- _VALID_URL = r'(?Phttps?://(?:intl|www)\.startrek\.com)/videos/(?P[^/]+)'
+ IE_NAME = 'startrek'
+ IE_DESC = 'STAR TREK'
+ _VALID_URL = r'https?://(?:www\.)?startrek\.com(?:/en-(?:ca|un))?/videos/(?P[^/?#]+)'
_TESTS = [{
- 'url': 'https://intl.startrek.com/videos/watch-welcoming-jess-bush-to-the-ready-room',
- 'md5': '491df5035c9d4dc7f63c79caaf9c839e',
+ 'url': 'https://www.startrek.com/en-un/videos/official-trailer-star-trek-lower-decks-season-4',
'info_dict': {
- 'id': 'watch-welcoming-jess-bush-to-the-ready-room',
+ 'id': 'official-trailer-star-trek-lower-decks-season-4',
'ext': 'mp4',
- 'title': 'WATCH: Welcoming Jess Bush to The Ready Room',
- 'duration': 1888,
- 'timestamp': 1655388000,
- 'upload_date': '20220616',
- 'description': 'md5:1ffee884e3920afbdd6dd04e926a1221',
- 'thumbnail': r're:https://(?:intl|www)\.startrek\.com/sites/default/files/styles/video_1920x1080/public/images/2022-06/pp_14794_rr_thumb_107_yt_16x9\.jpg(?:\?.+)?',
- 'subtitles': {'en-US': [{
- 'url': r're:https://(?:intl|www)\.startrek\.com/sites/default/files/video/captions/2022-06/TRR_SNW_107_v4\.vtt',
- }, {
- 'url': 'https://media.startrek.com/2022/06/16/2043801155561/1069981_hls/trr_snw_107_v4-c4bfc25d/stream_vtt.m3u8',
- }]},
+ 'title': 'Official Trailer | Star Trek: Lower Decks - Season 4',
+ 'alt_title': 'md5:dd7e3191aaaf9e95db16fc3abd5ef68b',
+ 'categories': ['TRAILERS'],
+ 'description': 'md5:563d7856ddab99bee7a5e50f45531757',
+ 'release_date': '20230722',
+ 'release_timestamp': 1690033200,
+ 'series': 'Star Trek: Lower Decks',
+ 'series_id': 'star-trek-lower-decks',
+ 'thumbnail': r're:https?://.+\.(?:jpg|png)',
},
}, {
- 'url': 'https://www.startrek.com/videos/watch-ethan-peck-and-gia-sandhu-beam-down-to-the-ready-room',
- 'md5': 'f5ad74fbb86e91e0882fc0a333178d1d',
+ 'url': 'https://www.startrek.com/en-ca/videos/my-first-contact-senator-cory-booker',
'info_dict': {
- 'id': 'watch-ethan-peck-and-gia-sandhu-beam-down-to-the-ready-room',
+ 'id': 'my-first-contact-senator-cory-booker',
'ext': 'mp4',
- 'title': 'WATCH: Ethan Peck and Gia Sandhu Beam Down to The Ready Room',
- 'duration': 1986,
- 'timestamp': 1654221600,
- 'upload_date': '20220603',
- 'description': 'md5:b3aa0edacfe119386567362dec8ed51b',
- 'thumbnail': r're:https://www\.startrek\.com/sites/default/files/styles/video_1920x1080/public/images/2022-06/pp_14792_rr_thumb_105_yt_16x9_1.jpg(?:\?.+)?',
- 'subtitles': {'en-US': [{
- 'url': r're:https://(?:intl|www)\.startrek\.com/sites/default/files/video/captions/2022-06/TRR_SNW_105_v5\.vtt',
- }]},
+ 'title': 'My First Contact: Senator Cory Booker',
+ 'alt_title': 'md5:fe74a8bdb0afab421c6e159a7680db4d',
+ 'categories': ['MY FIRST CONTACT'],
+ 'description': 'md5:a3992ab3b3e0395925d71156bbc018ce',
+ 'release_date': '20250401',
+ 'release_timestamp': 1743512400,
+ 'series': 'Star Trek: The Original Series',
+ 'series_id': 'star-trek-the-original-series',
+ 'thumbnail': r're:https?://.+\.(?:jpg|png)',
},
}]
def _real_extract(self, url):
- urlbase, video_id = self._match_valid_url(url).group('base', 'id')
+ video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
- player = self._search_regex(
- r'(<\s*div\s+id\s*=\s*"cvp-player-[^<]+<\s*/div\s*>)', webpage, 'player')
+ page_props = self._search_nextjs_data(webpage, video_id)['props']['pageProps']
+ video_data = page_props['video']['data']
+ if youtube_id := video_data.get('youtube_video_id'):
+ return self.url_result(youtube_id, YoutubeIE)
- hls = self._html_search_regex(r'\bdata-hls\s*=\s*"([^"]+)"', player, 'HLS URL')
- formats, subtitles = self._extract_m3u8_formats_and_subtitles(hls, video_id, 'mp4')
-
- captions = self._html_search_regex(
- r'\bdata-captions-url\s*=\s*"([^"]+)"', player, 'captions URL', fatal=False)
- if captions:
- subtitles.setdefault('en-US', [])[:0] = [{'url': urljoin(urlbase, captions)}]
-
- # NB: Most of the data in the json_ld is undesirable
- json_ld = self._search_json_ld(webpage, video_id, fatal=False)
+ series_id = traverse_obj(video_data, (
+ 'series_and_movies', ..., 'series_or_movie', 'slug', {str}, any))
return {
'id': video_id,
- 'title': self._html_search_regex(
- r'\bdata-title\s*=\s*"([^"]+)"', player, 'title', json_ld.get('title')),
- 'description': self._html_search_regex(
- r'(?s)<\s*div\s+class\s*=\s*"header-body"\s*>(.+?)<\s*/div\s*>',
- webpage, 'description', fatal=False),
- 'duration': int_or_none(self._html_search_regex(
- r'\bdata-duration\s*=\s*"(\d+)"', player, 'duration', fatal=False)),
- 'formats': formats,
- 'subtitles': subtitles,
- 'thumbnail': urljoin(urlbase, self._html_search_regex(
- r'\bdata-poster-url\s*=\s*"([^"]+)"', player, 'thumbnail', fatal=False)),
- 'timestamp': json_ld.get('timestamp'),
+ 'series': traverse_obj(page_props, (
+ 'queried', 'header', 'tab3', 'slices', ..., 'items',
+ lambda _, v: v['link']['slug'] == series_id, 'link_copy', {str}, any)),
+ 'series_id': series_id,
+ **traverse_obj(video_data, {
+ 'title': ('title', ..., 'text', {clean_html}, any),
+ 'alt_title': ('subhead', ..., 'text', {clean_html}, any),
+ 'categories': ('category', 'data', 'category_name', {str.upper}, filter, all),
+ 'description': ('slices', ..., 'primary', 'content', ..., 'text', {clean_html}, any),
+ 'release_timestamp': ('published', {parse_iso8601}),
+ 'subtitles': ({'url': 'legacy_subtitle_file'}, all, {subs_list_to_dict(lang='en')}),
+ 'thumbnail': ('poster_frame', 'url', {url_or_none}, {update_url(query=None)}),
+ 'url': ('legacy_video_url', {url_or_none}),
+ }),
}
diff --git a/yt_dlp/extractor/svt.py b/yt_dlp/extractor/svt.py
index 6a72f8d420..a48d7858d4 100644
--- a/yt_dlp/extractor/svt.py
+++ b/yt_dlp/extractor/svt.py
@@ -6,10 +6,13 @@
determine_ext,
dict_get,
int_or_none,
- traverse_obj,
try_get,
unified_timestamp,
)
+from ..utils.traversal import (
+ require,
+ traverse_obj,
+)
class SVTBaseIE(InfoExtractor):
@@ -97,40 +100,8 @@ def _extract_video(self, video_info, video_id):
}
-class SVTIE(SVTBaseIE):
- _VALID_URL = r'https?://(?:www\.)?svt\.se/wd\?(?:.*?&)?widgetId=(?P\d+)&.*?\barticleId=(?P\d+)'
- _EMBED_REGEX = [rf'(?: |