yt-dlp 2026.1.19.233146.dev0__py3-none-any.whl → 2026.1.27.233257.dev0__py3-none-any.whl

yt_dlp/extractor/_extractors.py

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

yt_dlp/extractor/boosty.py

@@ -21,21 +21,44 @@ class BoostyIE(InfoExtractor):
         'url': 'https://boosty.to/kuplinov/posts/e55d050c-e3bb-4873-a7db-ac7a49b40c38',
         'info_dict': {
             'id': 'd7473824-352e-48e2-ae53-d4aa39459968',
-            'title': 'phasma_3',
+            'title': 'Бан? А! Бан! (Phasmophobia)',
+            'alt_title': 'Бан? А! Бан! (Phasmophobia)',
             'channel': 'Kuplinov',
             'channel_id': '7958701',
             'timestamp': 1655031975,
             'upload_date': '20220612',
             'release_timestamp': 1655049000,
             'release_date': '20220612',
-            'modified_timestamp': 1668680993,
-            'modified_date': '20221117',
+            'modified_timestamp': 1743328648,
+            'modified_date': '20250330',
             'tags': ['куплинов', 'phasmophobia'],
             'like_count': int,
             'ext': 'mp4',
             'duration': 105,
             'view_count': int,
-            'thumbnail': r're:^https://i\.mycdn\.me/videoPreview\?',
+            'thumbnail': r're:^https://iv\.okcdn\.ru/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
@@ -109,36 +132,41 @@ class BoostyIE(InfoExtractor):
                 'thumbnail': r're:^https://i\.mycdn\.me/videoPreview\?',
             },
         }],
+        'skip': 'post has been deleted',
     }, {
         # single external video (youtube)
-        'url': 'https://boosty.to/denischuzhoy/posts/6094a487-bcec-4cf8-a453-43313b463c38',
+        'url': 'https://boosty.to/futuremusicproduction/posts/32a8cae2-3252-49da-b285-0e014bc6e565',
         'info_dict': {
-            'id': 'EXelTnve5lY',
-            'title': 'Послание Президента Федеральному Собранию | Класс народа',
-            'upload_date': '20210425',
-            'channel': 'Денис Чужой',
-            'tags': 'count:10',
+            'id': '-37FW_YQ3B4',
+            'title': 'Afro | Deep House FREE FLP',
+            'media_type': 'video',
+            'upload_date': '20250829',
+            'timestamp': 1756466005,
+            'channel': 'Future Music Production',
+            'tags': 'count:0',
             'like_count': int,
-            'ext': 'mp4',
-            'duration': 816,
+            'ext': 'm4a',
+            'duration': 170,
             'view_count': int,
             'thumbnail': r're:^https://i\.ytimg\.com/',
             'age_limit': 0,
             'availability': 'public',
             'categories': list,
             'channel_follower_count': int,
-            'channel_id': 'UCCzVNbWZfYpBfyofCCUD_0w',
-            'channel_is_verified': bool,
+            'channel_id': 'UCKVYrFBYmci1e-T8NeHw2qg',
             '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')
@@ -207,13 +235,14 @@ 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': (('previewUrl', 'defaultPreview'), {url_or_none}),
+                        'thumbnail': (('preview', 'defaultPreview'), {url_or_none}),
                     }, get_all=False)})
 
         if not entries and not post.get('hasAccess'):

yt_dlp/extractor/dailymotion.py

@@ -1,5 +1,6 @@
 import functools
 import json
+import random
 import re
 import urllib.parse
 
@@ -363,6 +364,56 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
                 continue
             yield update_url(player_url, query=query_string)
 
+    @staticmethod
+    def _generate_blockbuster_headers():
+        """Randomize our HTTP header fingerprint to bust the HTTP Error 403 block"""
+
+        def random_letters(minimum, maximum):
+            # Omit vowels so we don't generate valid header names like 'authorization', etc
+            return ''.join(random.choices('bcdfghjklmnpqrstvwxz', k=random.randint(minimum, maximum)))
+
+        return {
+            random_letters(8, 24): random_letters(16, 32)
+            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')
@@ -416,6 +467,7 @@ 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:
@@ -424,8 +476,8 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
                 if not media_url or media_type == 'application/vnd.lumberjack.manifest':
                     continue
                 if media_type == 'application/x-mpegURL':
-                    fmt, subs = self._extract_m3u8_formats_and_subtitles(
-                        media_url, video_id, 'mp4', live=is_live, m3u8_id='hls', fatal=False)
+                    fmt, subs, expected_error = self._extract_dailymotion_m3u8_formats_and_subtitles(
+                        media_url, video_id, live=is_live)
                     formats.extend(fmt)
                     self._merge_subtitles(subs, target=subtitles)
                 else:
@@ -442,6 +494,10 @@ 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

@@ -2,6 +2,7 @@ from .common import InfoExtractor
 from ..utils import (
     clean_html,
     int_or_none,
+    parse_iso8601,
     str_or_none,
     url_or_none,
 )
@@ -222,3 +223,70 @@ 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/facebook.py

@@ -4,6 +4,7 @@ import urllib.parse
 
 from .common import InfoExtractor
 from ..compat import compat_etree_fromstring
+from ..networking.exceptions import HTTPError
 from ..utils import (
     ExtractorError,
     clean_html,
@@ -1017,6 +1018,7 @@ class FacebookAdsIE(InfoExtractor):
             'upload_date': '20240812',
             'like_count': int,
         },
+        'skip': 'Invalid URL',
     }, {
         'url': 'https://www.facebook.com/ads/library/?id=893637265423481',
         'info_dict': {
@@ -1031,6 +1033,33 @@ class FacebookAdsIE(InfoExtractor):
         },
         'playlist_count': 3,
         'skip': 'Invalid URL',
+    }, {
+        'url': 'https://www.facebook.com/ads/library/?id=312304267031140',
+        'info_dict': {
+            'id': '312304267031140',
+            'title': 'Casper Wave Hybrid Mattress',
+            'uploader': 'Casper',
+            'uploader_id': '224110981099062',
+            'uploader_url': 'https://www.facebook.com/Casper/',
+            'timestamp': 1766299837,
+            'upload_date': '20251221',
+            'like_count': int,
+        },
+        'playlist_count': 2,
+    }, {
+        'url': 'https://www.facebook.com/ads/library/?id=874812092000430',
+        'info_dict': {
+            'id': '874812092000430',
+            'title': 'TikTok',
+            'uploader': 'Case \u00e0 Chocs',
+            'uploader_id': '112960472096793',
+            'uploader_url': 'https://www.facebook.com/Caseachocs/',
+            'timestamp': 1768498293,
+            'upload_date': '20260115',
+            'like_count': int,
+            'description': 'md5:f02a255fcf7dce6ed40e9494cf4bc49a',
+        },
+        'playlist_count': 3,
     }, {
         'url': 'https://es-la.facebook.com/ads/library/?id=901230958115569',
         'only_matching': True,
@@ -1060,9 +1089,36 @@ class FacebookAdsIE(InfoExtractor):
             })
         return formats
 
+    def _download_fb_webpage_and_verify(self, url, video_id):
+        # See https://github.com/yt-dlp/yt-dlp/issues/15577
+
+        try:
+            return self._download_webpage(url, video_id)
+        except ExtractorError as e:
+            if (
+                not isinstance(e.cause, HTTPError)
+                or e.cause.status != 403
+                or e.cause.reason != 'Client challenge'
+            ):
+                raise
+            error_page = self._webpage_read_content(e.cause.response, url, video_id)
+
+        self.write_debug('Received a client challenge response')
+
+        challenge_path = self._search_regex(
+            r'fetch\s*\(\s*["\'](/__rd_verify[^"\']+)["\']',
+            error_page, 'challenge path')
+
+        # Successful response will set the necessary cookie
+        self._request_webpage(
+            urljoin(url, challenge_path), video_id, 'Requesting verification cookie',
+            'Unable to get verification cookie', data=b'')
+
+        return self._download_webpage(url, video_id)
+
     def _real_extract(self, url):
         video_id = self._match_id(url)
-        webpage = self._download_webpage(url, video_id)
+        webpage = self._download_fb_webpage_and_verify(url, video_id)
 
         post_data = traverse_obj(
             re.findall(r'data-sjs>({.*?ScheduledServerJS.*?})</script>', webpage), (..., {json.loads}))

yt_dlp/extractor/francetv.py

@@ -371,15 +371,16 @@ class FranceTVSiteIE(FranceTVBaseInfoExtractor):
 
 
 class FranceTVInfoIE(FranceTVBaseInfoExtractor):
-    IE_NAME = 'francetvinfo.fr'
-    _VALID_URL = r'https?://(?:www|mobile|france3-regions)\.francetvinfo\.fr/(?:[^/]+/)*(?P<id>[^/?#&.]+)'
+    IE_NAME = 'franceinfo'
+    IE_DESC = 'franceinfo.fr (formerly francetvinfo.fr)'
+    _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',
+            'title': 'Soir 3 - Émission du jeudi 22 août 2019',
             'upload_date': '20190822',
             'timestamp': 1566510730,
             'thumbnail': r're:^https?://.*\.jpe?g$',
@@ -398,7 +399,7 @@ class FranceTVInfoIE(FranceTVBaseInfoExtractor):
         'info_dict': {
             'id': '7d204c9e-a2d3-11eb-9e4c-000d3a23d482',
             'ext': 'mp4',
-            'title': 'Covid-19 : une situation catastrophique à New Dehli - Édition du mercredi 21 avril 2021',
+            'title': 'Journal 20h00 - Covid-19 : une situation catastrophique à New Dehli',
             'thumbnail': r're:^https?://.*\.jpe?g$',
             'duration': 76,
             'timestamp': 1619028518,
@@ -438,6 +439,18 @@ 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,
@@ -445,6 +458,9 @@ 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):
@@ -460,7 +476,7 @@ class FranceTVInfoIE(FranceTVBaseInfoExtractor):
 
         video_id = (
             traverse_obj(webpage, (
-                {find_element(tag='button', attr='data-cy', value='francetv-player-wrapper', html=True)},
+                {find_element(tag='(button|div)', attr='data-cy', value='francetv-player-wrapper', html=True, regex=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/video/(?P<id>[0-9]+)'
+    _VALID_URL = r'https?://(?:www\.)?watch\.thechosen\.tv/watch/(?P<id>[0-9]+)'
     _TESTS = [{
-        'url': 'https://watch.thechosen.tv/video/184683594325',
+        'url': 'https://watch.thechosen.tv/watch/184683594325',
         'md5': '3f878b689588c71b38ec9943c54ff5b0',
         'info_dict': {
             'id': '184683594325',
@@ -124,7 +124,7 @@ class TheChosenIE(FrontroVideoBaseIE):
             'modified_date': str,
         },
     }, {
-        'url': 'https://watch.thechosen.tv/video/184683596189',
+        'url': 'https://watch.thechosen.tv/watch/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/video/%s'
+    _VIDEO_URL_TMPL = 'https://watch.thechosen.tv/watch/%s'
 
     _VALID_URL = r'https?://(?:www\.)?watch\.thechosen\.tv/group/(?P<id>[0-9]+)'
     _TESTS = [{