yt_dlp/extractor/_extractors.py

@@ -564,10 +564,7 @@ from .eroprofile import (
     EroProfileAlbumIE,
     EroProfileIE,
 )
-from .err import (
+from .err import ERRJupiterIE
-    ERRArhiivIE,
-    ERRJupiterIE,
-)
 from .ertgr import (
     ERTFlixCodenameIE,
     ERTFlixIE,
@@ -2363,11 +2360,7 @@ from .voicy import (
     VoicyChannelIE,
     VoicyIE,
 )
-from .volejtv import (
+from .volejtv import VolejTVIE
-    VolejTVCategoryPlaylistIE,
-    VolejTVClubPlaylistIE,
-    VolejTVIE,
-)
 from .voxmedia import (
     VoxMediaIE,
     VoxMediaVolumeIE,

yt_dlp/extractor/boosty.py

@@ -21,44 +21,21 @@ class BoostyIE(InfoExtractor):
         'url': 'https://boosty.to/kuplinov/posts/e55d050c-e3bb-4873-a7db-ac7a49b40c38',
         'info_dict': {
             'id': 'd7473824-352e-48e2-ae53-d4aa39459968',
-            'title': 'Бан? А! Бан! (Phasmophobia)',
+            'title': 'phasma_3',
-            'alt_title': 'Бан? А! Бан! (Phasmophobia)',
             'channel': 'Kuplinov',
             'channel_id': '7958701',
             'timestamp': 1655031975,
             'upload_date': '20220612',
             'release_timestamp': 1655049000,
             'release_date': '20220612',
-            'modified_timestamp': 1743328648,
+            'modified_timestamp': 1668680993,
-            'modified_date': '20250330',
+            'modified_date': '20221117',
             'tags': ['куплинов', 'phasmophobia'],
             'like_count': int,
             'ext': 'mp4',
             'duration': 105,
             'view_count': int,
-            'thumbnail': r're:^https://iv\.okcdn\.ru/videoPreview\?',
+            'thumbnail': r're:^https://i\.mycdn\.me/videoPreview\?',
-        },
-    }, {
-        # single ok_video with truncated title
-        'url': 'https://boosty.to/kuplinov/posts/cc09b7f9-121e-40b8-9392-4a075ef2ce53',
-        'info_dict': {
-            'id': 'fb5ea762-6303-4557-9a17-157947326810',
-            'title': 'Какая там активность была? Не слышу! Повтори еще пару раз! (Phas',
-            'alt_title': 'Какая там активность была? Не слышу! Повтори еще пару раз! (Phasmophobia)',
-            'channel': 'Kuplinov',
-            'channel_id': '7958701',
-            'timestamp': 1655031930,
-            'upload_date': '20220612',
-            'release_timestamp': 1655048400,
-            'release_date': '20220612',
-            'modified_timestamp': 1743328616,
-            'modified_date': '20250330',
-            'tags': ['куплинов', 'phasmophobia'],
-            'like_count': int,
-            'ext': 'mp4',
-            'duration': 39,
-            'view_count': int,
-            'thumbnail': r're:^https://iv\.okcdn\.ru/videoPreview\?',
         },
     }, {
         # multiple ok_video
@@ -132,41 +109,36 @@ class BoostyIE(InfoExtractor):
                 'thumbnail': r're:^https://i\.mycdn\.me/videoPreview\?',
             },
         }],
-        'skip': 'post has been deleted',
     }, {
         # single external video (youtube)
-        'url': 'https://boosty.to/futuremusicproduction/posts/32a8cae2-3252-49da-b285-0e014bc6e565',
+        'url': 'https://boosty.to/denischuzhoy/posts/6094a487-bcec-4cf8-a453-43313b463c38',
         'info_dict': {
-            'id': '-37FW_YQ3B4',
+            'id': 'EXelTnve5lY',
-            'title': 'Afro | Deep House FREE FLP',
+            'title': 'Послание Президента Федеральному Собранию | Класс народа',
-            'media_type': 'video',
+            'upload_date': '20210425',
-            'upload_date': '20250829',
+            'channel': 'Денис Чужой',
-            'timestamp': 1756466005,
+            'tags': 'count:10',
-            'channel': 'Future Music Production',
-            'tags': 'count:0',
             'like_count': int,
-            'ext': 'm4a',
+            'ext': 'mp4',
-            'duration': 170,
+            'duration': 816,
             'view_count': int,
             'thumbnail': r're:^https://i\.ytimg\.com/',
             'age_limit': 0,
             'availability': 'public',
             'categories': list,
             'channel_follower_count': int,
-            'channel_id': 'UCKVYrFBYmci1e-T8NeHw2qg',
+            'channel_id': 'UCCzVNbWZfYpBfyofCCUD_0w',
+            'channel_is_verified': bool,
             'channel_url': r're:^https://www\.youtube\.com/',
             'comment_count': int,
             'description': str,
+            'heatmap': 'count:100',
             'live_status': str,
             'playable_in_embed': bool,
             'uploader': str,
             'uploader_id': str,
             'uploader_url': r're:^https://www\.youtube\.com/',
         },
-        'expected_warnings': [
-            'Remote components challenge solver script',
-            'n challenge solving failed',
-        ],
     }]
 
     _MP4_TYPES = ('tiny', 'lowest', 'low', 'medium', 'high', 'full_hd', 'quad_hd', 'ultra_hd')
@@ -235,14 +207,13 @@ class BoostyIE(InfoExtractor):
                 video_id = item.get('id') or post_id
                 entries.append({
                     'id': video_id,
-                    'alt_title': post_title,
                     'formats': self._extract_formats(item.get('playerUrls'), video_id),
                     **common_metadata,
                     **traverse_obj(item, {
                         'title': ('title', {str}),
                         'duration': ('duration', {int_or_none}),
                         'view_count': ('viewsCounter', {int_or_none}),
-                        'thumbnail': (('preview', 'defaultPreview'), {url_or_none}),
+                        'thumbnail': (('previewUrl', 'defaultPreview'), {url_or_none}),
                     }, get_all=False)})
 
         if not entries and not post.get('hasAccess'):

yt_dlp/extractor/dailymotion.py

@@ -366,7 +366,8 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
 
     @staticmethod
     def _generate_blockbuster_headers():
-        """Randomize our HTTP header fingerprint to bust the HTTP Error 403 block"""
+        # Randomize our HTTP header fingerprint to bust the HTTP Error 403 block
+        # See https://github.com/yt-dlp/yt-dlp/issues/15526
 
         def random_letters(minimum, maximum):
             # Omit vowels so we don't generate valid header names like 'authorization', etc
@@ -377,43 +378,6 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
             for _ in range(random.randint(2, 8))
         }
 
-    def _extract_dailymotion_m3u8_formats_and_subtitles(self, media_url, video_id, live=False):
-        """See https://github.com/yt-dlp/yt-dlp/issues/15526"""
-
-        ERROR_NOTE = 'Unable to download m3u8 information'
-        last_error = None
-
-        for note, kwargs in (
-            ('Downloading m3u8 information', {}),
-            ('Retrying m3u8 download with randomized headers', {
-                'headers': self._generate_blockbuster_headers(),
-            }),
-            ('Retrying m3u8 download with Chrome impersonation', {
-                'impersonate': 'chrome',
-                'require_impersonation': True,
-            }),
-            ('Retrying m3u8 download with Firefox impersonation', {
-                'impersonate': 'firefox',
-                'require_impersonation': True,
-            }),
-        ):
-            try:
-                m3u8_doc = self._download_webpage(media_url, video_id, note, ERROR_NOTE, **kwargs)
-                break
-            except ExtractorError as e:
-                last_error = e.orig_msg
-                self.write_debug(f'{video_id}: {last_error}')
-        else:
-            if 'impersonation' not in last_error:
-                self.report_warning(last_error, video_id=video_id)
-                last_error = None
-            return [], {}, last_error
-
-        formats, subtitles = self._parse_m3u8_formats_and_subtitles(
-            m3u8_doc, media_url, 'mp4', m3u8_id='hls', live=live, fatal=False)
-
-        return formats, subtitles, last_error
-
     def _real_extract(self, url):
         url, smuggled_data = unsmuggle_url(url)
         video_id, is_playlist, playlist_id = self._match_valid_url(url).group('id', 'is_playlist', 'playlist_id')
@@ -467,7 +431,6 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
         is_live = media.get('isOnAir')
         formats = []
         subtitles = {}
-        expected_error = None
 
         for quality, media_list in metadata['qualities'].items():
             for m in media_list:
@@ -476,8 +439,9 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
                 if not media_url or media_type == 'application/vnd.lumberjack.manifest':
                     continue
                 if media_type == 'application/x-mpegURL':
-                    fmt, subs, expected_error = self._extract_dailymotion_m3u8_formats_and_subtitles(
+                    fmt, subs = self._extract_m3u8_formats_and_subtitles(
-                        media_url, video_id, live=is_live)
+                        media_url, video_id, 'mp4', live=is_live, m3u8_id='hls',
+                        fatal=False, headers=self._generate_blockbuster_headers())
                     formats.extend(fmt)
                     self._merge_subtitles(subs, target=subtitles)
                 else:
@@ -494,10 +458,6 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
                             'width': width,
                         })
                     formats.append(f)
-
-        if not formats and expected_error:
-            self.raise_no_formats(expected_error, expected=True)
-
         for f in formats:
             f['url'] = f['url'].split('#')[0]
             if not f.get('fps') and f['format_id'].endswith('@60'):

yt_dlp/extractor/err.py

@@ -2,7 +2,6 @@ from .common import InfoExtractor
 from ..utils import (
     clean_html,
     int_or_none,
-    parse_iso8601,
     str_or_none,
     url_or_none,
 )
@@ -223,70 +222,3 @@ class ERRJupiterIE(InfoExtractor):
                 'episode_id': ('id', {str_or_none}),
             }) if data.get('type') == 'episode' else {}),
         }
-
-
-class ERRArhiivIE(InfoExtractor):
-    _VALID_URL = r'https://arhiiv\.err\.ee/video/(?:vaata/)?(?P<id>[^/?#]+)'
-    _TESTS = [{
-        'url': 'https://arhiiv.err.ee/video/kontsertpalad',
-        'info_dict': {
-            'id': 'kontsertpalad',
-            'ext': 'mp4',
-            'title': 'Kontsertpalad: 255 | L. Beethoveni sonaat c-moll, "Pateetiline"',
-            'description': 'md5:a70f4ff23c3618f3be63f704bccef063',
-            'series': 'Kontsertpalad',
-            'episode_id': 255,
-            'timestamp': 1666152162,
-            'upload_date': '20221019',
-            'release_year': 1970,
-            'modified_timestamp': 1718620982,
-            'modified_date': '20240617',
-        },
-        'params': {'skip_download': 'm3u8'},
-    }, {
-        'url': 'https://arhiiv.err.ee/video/vaata/koalitsioonileppe-allkirjastamine',
-        'info_dict': {
-            'id': 'koalitsioonileppe-allkirjastamine',
-            'ext': 'mp4',
-            'title': 'Koalitsioonileppe allkirjastamine',
-            'timestamp': 1710728222,
-            'upload_date': '20240318',
-            'release_timestamp': 1611532800,
-            'release_date': '20210125',
-        },
-        'params': {'skip_download': 'm3u8'},
-    }]
-
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-        data = self._download_json(
-            f'https://arhiiv.err.ee/api/v1/content/video/{video_id}', video_id)
-
-        formats, subtitles = [], {}
-        if hls_url := traverse_obj(data, ('media', 'src', 'hls', {url_or_none})):
-            fmts, subs = self._extract_m3u8_formats_and_subtitles(
-                hls_url, video_id, 'mp4', m3u8_id='hls', fatal=False)
-            formats.extend(fmts)
-            self._merge_subtitles(subs, target=subtitles)
-        if dash_url := traverse_obj(data, ('media', 'src', 'dash', {url_or_none})):
-            fmts, subs = self._extract_mpd_formats_and_subtitles(
-                dash_url, video_id, mpd_id='dash', fatal=False)
-            formats.extend(fmts)
-            self._merge_subtitles(subs, target=subtitles)
-
-        return {
-            'id': video_id,
-            'formats': formats,
-            'subtitles': subtitles,
-            **traverse_obj(data, ('info', {
-                'title': ('title', {str}),
-                'series': ('seriesTitle', {str}, filter),
-                'series_id': ('seriesId', {str}, filter),
-                'episode_id': ('episode', {int_or_none}),
-                'description': ('synopsis', {str}, filter),
-                'timestamp': ('uploadDate', {parse_iso8601}),
-                'modified_timestamp': ('dateModified', {parse_iso8601}),
-                'release_timestamp': ('date', {parse_iso8601}),
-                'release_year': ('year', {int_or_none}),
-            })),
-        }

yt_dlp/extractor/francetv.py

@@ -371,16 +371,15 @@ class FranceTVSiteIE(FranceTVBaseInfoExtractor):
 
 
 class FranceTVInfoIE(FranceTVBaseInfoExtractor):
-    IE_NAME = 'franceinfo'
+    IE_NAME = 'francetvinfo.fr'
-    IE_DESC = 'franceinfo.fr (formerly francetvinfo.fr)'
+    _VALID_URL = r'https?://(?:www|mobile|france3-regions)\.francetvinfo\.fr/(?:[^/]+/)*(?P<id>[^/?#&.]+)'
-    _VALID_URL = r'https?://(?:www|mobile|france3-regions)\.france(?:tv)?info.fr/(?:[^/?#]+/)*(?P<id>[^/?#&.]+)'
 
     _TESTS = [{
         'url': 'https://www.francetvinfo.fr/replay-jt/france-3/soir-3/jt-grand-soir-3-jeudi-22-aout-2019_3561461.html',
         'info_dict': {
             'id': 'd12458ee-5062-48fe-bfdd-a30d6a01b793',
             'ext': 'mp4',
-            'title': 'Soir 3 - Émission du jeudi 22 août 2019',
+            'title': 'Soir 3',
             'upload_date': '20190822',
             'timestamp': 1566510730,
             'thumbnail': r're:^https?://.*\.jpe?g$',
@@ -399,7 +398,7 @@ class FranceTVInfoIE(FranceTVBaseInfoExtractor):
         'info_dict': {
             'id': '7d204c9e-a2d3-11eb-9e4c-000d3a23d482',
             'ext': 'mp4',
-            'title': 'Journal 20h00 - Covid-19 : une situation catastrophique à New Dehli',
+            'title': 'Covid-19 : une situation catastrophique à New Dehli - Édition du mercredi 21 avril 2021',
             'thumbnail': r're:^https?://.*\.jpe?g$',
             'duration': 76,
             'timestamp': 1619028518,
@@ -439,18 +438,6 @@ class FranceTVInfoIE(FranceTVBaseInfoExtractor):
             'thumbnail': r're:https://[^/?#]+/v/[^/?#]+/x1080',
         },
         'add_ie': ['Dailymotion'],
-        'skip': 'Broken Dailymotion link',
-    }, {
-        'url': 'https://www.franceinfo.fr/monde/usa/presidentielle/donald-trump/etats-unis-un-risque-d-embrasement-apres-la-mort-d-un-manifestant_7764542.html',
-        'info_dict': {
-            'id': 'f920fcc2-fa20-11f0-ac98-57a09c50f7ce',
-            'ext': 'mp4',
-            'title': 'Affaires sensibles - Manifestant tué Le risque d\'embrasement',
-            'duration': 118,
-            'thumbnail': r're:https?://.+/.+\.jpg',
-            'timestamp': 1769367756,
-            'upload_date': '20260125',
-        },
     }, {
         'url': 'http://france3-regions.francetvinfo.fr/limousin/emissions/jt-1213-limousin',
         'only_matching': True,
@@ -458,9 +445,6 @@ class FranceTVInfoIE(FranceTVBaseInfoExtractor):
         # "<figure id=" pattern (#28792)
         'url': 'https://www.francetvinfo.fr/culture/patrimoine/incendie-de-notre-dame-de-paris/notre-dame-de-paris-de-l-incendie-de-la-cathedrale-a-sa-reconstruction_4372291.html',
         'only_matching': True,
-    }, {
-        'url': 'https://www.franceinfo.fr/replay-jt/france-2/20-heures/robert-de-niro-portrait-d-un-monument-du-cinema_7245456.html',
-        'only_matching': True,
     }]
 
     def _real_extract(self, url):
@@ -476,7 +460,7 @@ class FranceTVInfoIE(FranceTVBaseInfoExtractor):
 
         video_id = (
             traverse_obj(webpage, (
-                {find_element(tag='(button|div)', attr='data-cy', value='francetv-player-wrapper', html=True, regex=True)},
+                {find_element(tag='button', attr='data-cy', value='francetv-player-wrapper', html=True)},
                 {extract_attributes}, 'id'))
             or self._search_regex(
                 (r'player\.load[^;]+src:\s*["\']([^"\']+)',

yt_dlp/extractor/frontro.py

@@ -104,9 +104,9 @@ class FrontroGroupBaseIE(FrontoBaseIE):
 class TheChosenIE(FrontroVideoBaseIE):
     _CHANNEL_ID = '12884901895'
 
-    _VALID_URL = r'https?://(?:www\.)?watch\.thechosen\.tv/watch/(?P<id>[0-9]+)'
+    _VALID_URL = r'https?://(?:www\.)?watch\.thechosen\.tv/video/(?P<id>[0-9]+)'
     _TESTS = [{
-        'url': 'https://watch.thechosen.tv/watch/184683594325',
+        'url': 'https://watch.thechosen.tv/video/184683594325',
         'md5': '3f878b689588c71b38ec9943c54ff5b0',
         'info_dict': {
             'id': '184683594325',
@@ -124,7 +124,7 @@ class TheChosenIE(FrontroVideoBaseIE):
             'modified_date': str,
         },
     }, {
-        'url': 'https://watch.thechosen.tv/watch/184683596189',
+        'url': 'https://watch.thechosen.tv/video/184683596189',
         'md5': 'd581562f9d29ce82f5b7770415334151',
         'info_dict': {
             'id': '184683596189',
@@ -147,7 +147,7 @@ class TheChosenIE(FrontroVideoBaseIE):
 class TheChosenGroupIE(FrontroGroupBaseIE):
     _CHANNEL_ID = '12884901895'
     _VIDEO_EXTRACTOR = TheChosenIE
-    _VIDEO_URL_TMPL = 'https://watch.thechosen.tv/watch/%s'
+    _VIDEO_URL_TMPL = 'https://watch.thechosen.tv/video/%s'
 
     _VALID_URL = r'https?://(?:www\.)?watch\.thechosen\.tv/group/(?P<id>[0-9]+)'
     _TESTS = [{

yt_dlp/extractor/neteasemusic.py

@@ -156,36 +156,18 @@ class NetEaseMusicIE(NetEaseMusicBaseIE):
             'id': '17241424',
             'ext': 'mp3',
             'title': 'Opus 28',
-            'upload_date': '20060912',
+            'upload_date': '20080211',
-            'timestamp': 1158076800,
+            'timestamp': 1202745600,
             'duration': 263,
             'thumbnail': r're:^http.*\.jpg',
-            'album': 'Piano Solos, Vol. 2',
+            'album': 'Piano Solos Vol. 2',
             'album_artist': 'Dustin O\'Halloran',
             'average_rating': int,
-            'description': 'md5:b566b92c55ca348df65d206c5d689576',
+            'description': '[00:05.00]纯音乐，请欣赏\n',
             'album_artists': ['Dustin O\'Halloran'],
             'creators': ['Dustin O\'Halloran'],
             'subtitles': {'lyrics': [{'ext': 'lrc'}]},
         },
-    }, {
-        'url': 'https://music.163.com/#/song?id=2755669231',
-        'info_dict': {
-            'id': '2755669231',
-            'ext': 'mp3',
-            'title': '十二月-Departure',
-            'upload_date': '20251111',
-            'timestamp': 1762876800,
-            'duration': 188,
-            'thumbnail': r're:^http.*\.jpg',
-            'album': '円',
-            'album_artist': 'ひとひら',
-            'average_rating': int,
-            'description': 'md5:deee249c8c9c3e2c54ecdab36e87d174',
-            'album_artists': ['ひとひら'],
-            'creators': ['ひとひら'],
-            'subtitles': {'lyrics': [{'ext': 'lrc', 'data': 'md5:d32b4425a5d6c9fa249ca6e803dd0401'}]},
-        },
     }, {
         'url': 'https://y.music.163.com/m/song?app_version=8.8.45&id=95670&uct2=sKnvS4+0YStsWkqsPhFijw%3D%3D&dlt=0846',
         'md5': 'b896be78d8d34bd7bb665b26710913ff',
@@ -259,16 +241,9 @@ class NetEaseMusicIE(NetEaseMusicBaseIE):
                 'lyrics': [{'data': original, 'ext': 'lrc'}],
             }
 
-        def collect_lyrics(lrc):
+        lyrics_expr = r'(\[[0-9]{2}:[0-9]{2}\.[0-9]{2,}\])([^\n]+)'
-            lyrics_expr = r'\[([0-9]{2}):([0-9]{2})[:.]([0-9]{2,})\]([^\n]+)'
+        original_ts_texts = re.findall(lyrics_expr, original)
-            matches = re.findall(lyrics_expr, lrc)
+        translation_ts_dict = dict(re.findall(lyrics_expr, translated))
-            return (
-                (f'[{minute}:{sec}.{msec}]', text)
-                for minute, sec, msec, text in matches
-            )
-
-        original_ts_texts = collect_lyrics(original)
-        translation_ts_dict = dict(collect_lyrics(translated))
 
         merged = '\n'.join(
             join_nonempty(f'{timestamp}{text}', translation_ts_dict.get(timestamp, ''), delim=' / ')

yt_dlp/extractor/patreon.py

@@ -1,5 +1,6 @@
 import functools
 import itertools
+import urllib.parse
 
 from .common import InfoExtractor
 from .sproutvideo import VidsIoIE
@@ -10,23 +11,15 @@ from ..utils import (
     ExtractorError,
     clean_html,
     determine_ext,
-    extract_attributes,
-    float_or_none,
     int_or_none,
     mimetype2ext,
     parse_iso8601,
     smuggle_url,
     str_or_none,
-    update_url_query,
     url_or_none,
     urljoin,
 )
-from ..utils.traversal import (
+from ..utils.traversal import require, traverse_obj, value
-    find_elements,
-    require,
-    traverse_obj,
-    value,
-)
 
 
 class PatreonBaseIE(InfoExtractor):
@@ -128,7 +121,6 @@ class PatreonIE(PatreonBaseIE):
             'channel_is_verified': True,
             'chapters': 'count:4',
             'timestamp': 1423689666,
-            'media_type': 'video',
         },
         'params': {
             'noplaylist': True,
@@ -169,7 +161,7 @@ class PatreonIE(PatreonBaseIE):
             'uploader_url': 'https://www.patreon.com/loish',
             'description': 'md5:e2693e97ee299c8ece47ffdb67e7d9d2',
             'title': 'VIDEO // sketchbook flipthrough',
-            'uploader': 'Loish',
+            'uploader': 'Loish ',
             'tags': ['sketchbook', 'video'],
             'channel_id': '1641751',
             'channel_url': 'https://www.patreon.com/loish',
@@ -282,73 +274,8 @@ class PatreonIE(PatreonBaseIE):
             'channel_id': '9346307',
         },
         'params': {'getcomments': True},
-    }, {
-        # Inlined media in post; uses _extract_from_media_api
-        'url': 'https://www.patreon.com/posts/scottfalco-146966245',
-        'info_dict': {
-            'id': '146966245',
-            'ext': 'mp4',
-            'title': 'scottfalco 1080',
-            'description': 'md5:a3f29bbd0a46b4821ec3400957c98aa2',
-            'uploader': 'Insanimate',
-            'uploader_id': '2828146',
-            'uploader_url': 'https://www.patreon.com/Insanimate',
-            'channel_id': '6260877',
-            'channel_url': 'https://www.patreon.com/Insanimate',
-            'channel_follower_count': int,
-            'comment_count': int,
-            'like_count': int,
-            'duration': 7.833333,
-            'timestamp': 1767061800,
-            'upload_date': '20251230',
-        },
     }]
     _RETURN_TYPE = 'video'
-    _HTTP_HEADERS = {
-        # 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
-        'referer': 'https://www.patreon.com/',
-    }
-
-    def _extract_from_media_api(self, media_id):
-        attributes = traverse_obj(
-            self._call_api(f'media/{media_id}', media_id, fatal=False),
-            ('data', 'attributes', {dict}))
-        if not attributes:
-            return None
-
-        info_dict = traverse_obj(attributes, {
-            'title': ('file_name', {lambda x: x.rpartition('.')[0]}),
-            'timestamp': ('created_at', {parse_iso8601}),
-            'duration': ('display', 'duration', {float_or_none}),
-        })
-        info_dict['id'] = media_id
-
-        playback_url = traverse_obj(
-            attributes, ('display', (None, 'viewer_playback_data'), 'url', {url_or_none}, any))
-        download_url = traverse_obj(attributes, ('download_url', {url_or_none}))
-
-        if playback_url and mimetype2ext(attributes.get('mimetype')) == 'm3u8':
-            info_dict['formats'], info_dict['subtitles'] = self._extract_m3u8_formats_and_subtitles(
-                playback_url, media_id, 'mp4', fatal=False, headers=self._HTTP_HEADERS)
-            for f in info_dict['formats']:
-                f['http_headers'] = self._HTTP_HEADERS
-            if transcript_url := traverse_obj(attributes, ('display', 'transcript_url', {url_or_none})):
-                info_dict['subtitles'].setdefault('en', []).append({
-                    'url': transcript_url,
-                    'ext': 'vtt',
-                })
-        elif playback_url or download_url:
-            info_dict['formats'] = [{
-                # If playback_url is available, download_url is a duplicate lower resolution format
-                'url': playback_url or download_url,
-                'vcodec': 'none' if attributes.get('media_type') != 'video' else None,
-            }]
-
-        if not info_dict.get('formats'):
-            return None
-
-        return info_dict
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
@@ -372,7 +299,6 @@ class PatreonIE(PatreonBaseIE):
             'comment_count': ('comment_count', {int_or_none}),
         })
 
-        seen_media_ids = set()
         entries = []
         idx = 0
         for include in traverse_obj(post, ('included', lambda _, v: v['type'])):
@@ -394,8 +320,6 @@ class PatreonIE(PatreonBaseIE):
                         'url': download_url,
                         'alt_title': traverse_obj(media_attributes, ('file_name', {str})),
                     })
-                if media_id := traverse_obj(include, ('id', {str})):
-                    seen_media_ids.add(media_id)
 
             elif include_type == 'user':
                 info.update(traverse_obj(include, {
@@ -416,29 +340,34 @@ class PatreonIE(PatreonBaseIE):
                     'channel_follower_count': ('attributes', 'patron_count', {int_or_none}),
                 }))
 
-        if embed_url := traverse_obj(attributes, ('embed', 'url', {url_or_none})):
+        # Must be all-lowercase 'referer' so we can smuggle it to Generic, SproutVideo, and Vimeo.
-            # Convert useless vimeo.com URLs to useful player.vimeo.com embed URLs
+        # patreon.com URLs redirect to www.patreon.com; this matters when requesting mux.com m3u8s
-            vimeo_id, vimeo_hash = self._search_regex(
+        headers = {'referer': 'https://www.patreon.com/'}
-                r'//vimeo\.com/(\d+)(?:/([\da-f]+))?', embed_url,
-                'vimeo id', group=(1, 2), default=(None, None))
-            if vimeo_id:
-                embed_url = update_url_query(
-                    f'https://player.vimeo.com/video/{vimeo_id}',
-                    {'h': vimeo_hash or []})
-            if VimeoIE.suitable(embed_url):
-                entry = self.url_result(
-                    VimeoIE._smuggle_referrer(embed_url, self._HTTP_HEADERS['referer']),
-                    VimeoIE, url_transparent=True)
-            else:
-                entry = self.url_result(smuggle_url(embed_url, self._HTTP_HEADERS))
 
-            if urlh := self._request_webpage(
+        # handle Vimeo embeds
-                embed_url, video_id, 'Checking embed URL', headers=self._HTTP_HEADERS,
+        if traverse_obj(attributes, ('embed', 'provider')) == 'Vimeo':
-                fatal=False, errnote=False, expected_status=(403, 429),  # Ignore Vimeo 429's
+            v_url = urllib.parse.unquote(self._html_search_regex(
-            ):
+                r'(https(?:%3A%2F%2F|://)player\.vimeo\.com.+app_id(?:=|%3D)+\d+)',
-                # Password-protected vids.io embeds return 403 errors w/o --video-password or session cookie
+                traverse_obj(attributes, ('embed', 'html', {str})), 'vimeo url', fatal=False) or '')
-                if VidsIoIE.suitable(embed_url) or urlh.status != 403:
+            if url_or_none(v_url) and self._request_webpage(
-                    entries.append(entry)
+                    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, headers['referer']),
+                    VimeoIE, url_transparent=True))
+
+        embed_url = traverse_obj(attributes, ('embed', 'url', {url_or_none}))
+        if embed_url and (urlh := self._request_webpage(
+                embed_url, video_id, 'Checking embed URL', headers=headers,
+                fatal=False, errnote=False, expected_status=403)):
+            # Vimeo's Cloudflare anti-bot protection will return HTTP status 200 for 404, so we need
+            # to check for "Sorry, we couldn’t find that page" in the meta description tag
+            meta_description = clean_html(self._html_search_meta(
+                'description', self._webpage_read_content(urlh, embed_url, video_id, fatal=False), default=None))
+            # Password-protected vids.io embeds return 403 errors w/o --video-password or session cookie
+            if ((urlh.status != 403 and meta_description != 'Sorry, we couldn’t find that page')
+                    or VidsIoIE.suitable(embed_url)):
+                entries.append(self.url_result(smuggle_url(embed_url, headers)))
 
         post_file = traverse_obj(attributes, ('post_file', {dict}))
         if post_file:
@@ -452,27 +381,13 @@ class PatreonIE(PatreonBaseIE):
                 })
             elif name == 'video' or determine_ext(post_file.get('url')) == 'm3u8':
                 formats, subtitles = self._extract_m3u8_formats_and_subtitles(
-                    post_file['url'], video_id, headers=self._HTTP_HEADERS)
+                    post_file['url'], video_id, headers=headers)
-                for f in formats:
-                    f['http_headers'] = self._HTTP_HEADERS
                 entries.append({
                     'id': video_id,
                     'formats': formats,
                     'subtitles': subtitles,
+                    'http_headers': headers,
                 })
-            if media_id := traverse_obj(post_file, ('media_id', {int}, {str_or_none})):
-                seen_media_ids.add(media_id)
-
-        for media_id in traverse_obj(attributes, (
-            'content', {find_elements(attr='data-media-id', value=r'\d+', regex=True, html=True)},
-            ..., {extract_attributes}, 'data-media-id',
-        )):
-            # Inlined media may be duplicates of what was extracted above
-            if media_id in seen_media_ids:
-                continue
-            if media := self._extract_from_media_api(media_id):
-                entries.append(media)
-                seen_media_ids.add(media_id)
 
         can_view_post = traverse_obj(attributes, 'current_user_can_view')
         comments = None

yt_dlp/extractor/pbs.py

@@ -453,23 +453,6 @@ class PBSIE(InfoExtractor):
             'url': 'https://player.pbs.org/portalplayer/3004638221/?uid=',
             'only_matching': True,
         },
-        {
-            # Next.js v13+, see https://github.com/yt-dlp/yt-dlp/issues/13299
-            'url': 'https://www.pbs.org/video/caregiving',
-            'info_dict': {
-                'id': '3101776876',
-                'ext': 'mp4',
-                'title': 'Caregiving - Caregiving',
-                'description': 'A documentary revealing America’s caregiving crisis through intimate stories and expert insight.',
-                'display_id': 'caregiving',
-                'duration': 6783,
-                'thumbnail': 'https://image.pbs.org/video-assets/BSrSkcc-asset-mezzanine-16x9-nlcxQts.jpg',
-                'chapters': [],
-            },
-            'params': {
-                'skip_download': True,
-            },
-        },
     ]
     _ERRORS = {
         101: 'We\'re sorry, but this video is not yet available.',
@@ -523,7 +506,6 @@ class PBSIE(InfoExtractor):
                 r"(?s)window\.PBS\.playerConfig\s*=\s*{.*?id\s*:\s*'([0-9]+)',",
                 r'<div[^>]+\bdata-cove-id=["\'](\d+)"',  # http://www.pbs.org/wgbh/roadshow/watch/episode/2105-indianapolis-hour-2/
                 r'<iframe[^>]+\bsrc=["\'](?:https?:)?//video\.pbs\.org/widget/partnerplayer/(\d+)',  # https://www.pbs.org/wgbh/masterpiece/episodes/victoria-s2-e1/
-                r'\\"videoTPMediaId\\":\\\"(\d+)\\"',  # Next.js v13, e.g. https://www.pbs.org/video/caregiving
                 r'\bhttps?://player\.pbs\.org/[\w-]+player/(\d+)',      # last pattern to avoid false positives
             ]
 

yt_dlp/extractor/volejtv.py

@@ -1,167 +1,40 @@
-import functools
-
 from .common import InfoExtractor
-from ..utils import (
-    InAdvancePagedList,
-    int_or_none,
-    join_nonempty,
-    orderedSet,
-    str_or_none,
-    strftime_or_none,
-    unified_timestamp,
-    url_or_none,
-)
-from ..utils.traversal import (
-    require,
-    traverse_obj,
-)
 
 
-class VolejTVBaseIE(InfoExtractor):
+class VolejTVIE(InfoExtractor):
-    TBR_HEIGHT_MAPPING = {
+    _VALID_URL = r'https?://volej\.tv/video/(?P<id>\d+)'
-        '6000': 1080,
-        '2400': 720,
-        '1500': 480,
-        '800': 360,
-    }
-
-    def _call_api(self, endpoint, display_id, query=None):
-        return self._download_json(
-            f'https://api-volejtv-prod.apps.okd4.devopsie.cloud/api/{endpoint}',
-            display_id, query=query)
-
-
-class VolejTVIE(VolejTVBaseIE):
-    IE_NAME = 'volejtv:match'
-    _VALID_URL = r'https?://volej\.tv/match/(?P<id>\d+)'
     _TESTS = [{
-        'url': 'https://volej.tv/match/270579',
+        'url': 'https://volej.tv/video/725742/',
         'info_dict': {
-            'id': '270579',
+            'id': '725742',
             'ext': 'mp4',
-            'title': 'SWE-CZE (2024-06-16)',
+            'description': 'Zápas VK Královo Pole vs VK Prostějov 10.12.2022 v 19:00 na Volej.TV',
-            'categories': ['ženy'],
+            'thumbnail': 'https://volej.tv/images/og/16/17186/og.png',
-            'series': 'ZLATÁ EVROPSKÁ VOLEJBALOVÁ LIGA',
+            'title': 'VK Královo Pole vs VK Prostějov',
-            'season': '2023-2024',
-            'timestamp': 1718553600,
-            'upload_date': '20240616',
         },
     }, {
-        'url': 'https://volej.tv/match/487520',
+        'url': 'https://volej.tv/video/725605/',
         'info_dict': {
-            'id': '487520',
+            'id': '725605',
             'ext': 'mp4',
-            'thumbnail': r're:https://.+\.(png|jpeg)',
+            'thumbnail': 'https://volej.tv/images/og/15/17185/og.png',
-            'title': 'FRA-CZE (2024-09-06)',
+            'title': 'VK Lvi Praha vs VK Euro Sitex Příbram',
-            'categories': ['mládež'],
+            'description': 'Zápas VK Lvi Praha vs VK Euro Sitex Příbram 11.12.2022 v 19:00 na Volej.TV',
-            'series': 'Mistrovství Evropy do 20 let',
-            'season': '2024-2025',
-            'timestamp': 1725627600,
-            'upload_date': '20240906',
-
         },
     }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
-        json_data = self._call_api(f'match/{video_id}', video_id)
+        webpage = self._download_webpage(url, video_id)
-
+        json_data = self._search_json(
-        formats = []
+            r'<\s*!\[CDATA[^=]+=', webpage, 'CDATA', video_id)
-        for video in traverse_obj(json_data, ('videos', 0, 'qualities', lambda _, v: url_or_none(v['cloud_front_path']))):
+        formats, subtitle = self._extract_m3u8_formats_and_subtitles(
-            formats.append(traverse_obj(video, {
+            json_data['urls']['hls'], video_id)
-                'url': 'cloud_front_path',
+        return {
-                'tbr': ('quality', {int_or_none}),
-                'format_id': ('id', {str_or_none}),
-                'height': ('quality', {self.TBR_HEIGHT_MAPPING.get}),
-            }))
-
-        data = {
             'id': video_id,
-            **traverse_obj(json_data, {
+            'title': self._html_search_meta(['og:title', 'twitter:title'], webpage),
-                'series': ('competition_name', {str}),
+            'thumbnail': self._html_search_meta(['og:image', 'twitter:image'], webpage),
-                'season': ('season', {str}),
+            'description': self._html_search_meta(['description', 'og:description', 'twitter:description'], webpage),
-                'timestamp': ('match_time', {unified_timestamp}),
-                'categories': ('category', ('title'), {str}, filter, all, filter),
-                'thumbnail': ('poster', {url_or_none}),
-            }),
             'formats': formats,
+            'subtitles': subtitle,
         }
-
-        teams = orderedSet(traverse_obj(json_data, ('teams', ..., 'shortcut', {str})))
-        if len(teams) > 2 and 'FIN' in teams:
-            teams.remove('FIN')
-
-        data['title'] = join_nonempty(
-            join_nonempty(*teams, delim='-'),
-            strftime_or_none(data.get('timestamp'), '(%Y-%m-%d)'),
-            delim=' ')
-
-        return data
-
-
-class VolejTVPlaylistBaseIE(VolejTVBaseIE):
-    """Subclasses must set _API_FILTER, _PAGE_SIZE"""
-
-    def _get_page(self, playlist_id, page):
-        return self._call_api(
-            f'match/{self._API_FILTER}/{playlist_id}', playlist_id,
-            query={'page': page + 1, 'take': self._PAGE_SIZE, 'order': 'DESC'})
-
-    def _entries(self, playlist_id, first_page_data, page):
-        entries = first_page_data if page == 0 else self._get_page(playlist_id, page)
-        for match_id in traverse_obj(entries, ('data', ..., 'id')):
-            yield self.url_result(f'https://volej.tv/match/{match_id}', VolejTVIE)
-
-
-class VolejTVClubPlaylistIE(VolejTVPlaylistBaseIE):
-    IE_NAME = 'volejtv:club'
-    _VALID_URL = r'https?://volej\.tv/klub/(?P<id>\d+)'
-    _TESTS = [{
-        'url': 'https://volej.tv/klub/1173',
-        'info_dict': {
-            'id': '1173',
-            'title': 'VK Jihostroj České Budějovice',
-        },
-        'playlist_mincount': 30,
-    }]
-    _API_FILTER = 'by-team-id-paginated'
-    _PAGE_SIZE = 6
-
-    def _real_extract(self, url):
-        playlist_id = self._match_id(url)
-        title = self._call_api(f'team/show/{playlist_id}', playlist_id)['title']
-        first_page_data = self._get_page(playlist_id, 0)
-        total_pages = traverse_obj(first_page_data, ('meta', 'pageCount', {int}, {require('page count')}))
-        return self.playlist_result(InAdvancePagedList(
-            functools.partial(self._entries, playlist_id, first_page_data),
-            total_pages, self._PAGE_SIZE), playlist_id, title)
-
-
-class VolejTVCategoryPlaylistIE(VolejTVPlaylistBaseIE):
-    IE_NAME = 'volejtv:category'
-    _VALID_URL = r'https?://volej\.tv/kategorie/(?P<id>[^/$?]+)'
-    _TESTS = [{
-        'url': 'https://volej.tv/kategorie/chance-cesky-pohar',
-        'info_dict': {
-            'id': 'chance-cesky-pohar',
-            'title': 'Chance Český pohár',
-        },
-        'playlist_mincount': 30,
-    }]
-    _API_FILTER = 'by-category-id-paginated'
-    _PAGE_SIZE = 10
-
-    def _get_category(self, playlist_id):
-        categories = self._call_api('category', playlist_id)
-        for category in traverse_obj(categories, (lambda _, v: v['slug'] and v['id'] and v['title'])):
-            if category['slug'] == playlist_id:
-                return category['id'], category['title']
-
-    def _real_extract(self, url):
-        playlist_id = self._match_id(url)
-        category_id, title = self._get_category(playlist_id)
-        first_page_data = self._get_page(category_id, 0)
-        total_pages = traverse_obj(first_page_data, ('meta', 'pageCount', {int}, {require('page count')}))
-        return self.playlist_result(InAdvancePagedList(
-            functools.partial(self._entries, category_id, first_page_data),
-            total_pages, self._PAGE_SIZE), playlist_id, title)

yt_dlp/extractor/wat.py

@@ -76,7 +76,7 @@ class WatIE(InfoExtractor):
             if error_code == 'GEOBLOCKED':
                 self.raise_geo_restricted(error_desc, video_info.get('geoList'))
             elif error_code == 'DELIVERY_ERROR':
-                if traverse_obj(video_data, ('delivery', 'code')) in (403, 500):
+                if traverse_obj(video_data, ('delivery', 'code')) == 500:
                     self.report_drm(video_id)
                 error_desc = join_nonempty(
                     error_desc, traverse_obj(video_data, ('delivery', 'error', {str})), delim=': ')