Updated yt_dlp version; added extremly basic dumb cache setup in thumbnailer; moved build and script as well as deb folder to build

plugins/youtube_download/yt_dlp/YoutubeDL.py

@@ -42,6 +42,8 @@ from .globals import (
     plugin_pps,
     all_plugins_loaded,
     plugin_dirs,
+    supported_js_runtimes,
+    supported_remote_components,
 )
 from .minicurses import format_text
 from .networking import HEADRequest, Request, RequestDirector
@@ -533,6 +535,18 @@ class YoutubeDL:
                        See "EXTRACTOR ARGUMENTS" for details.
                        Argument values must always be a list of string(s).
                        E.g. {'youtube': {'skip': ['dash', 'hls']}}
+    js_runtimes:       A dictionary of JavaScript runtime keys (in lower case) to enable
+                       and a dictionary of additional configuration for the runtime.
+                       Currently supported runtimes are 'deno', 'node', 'bun', and 'quickjs'.
+                       If None, the default runtime of "deno" will be enabled.
+                       The runtime configuration dictionary can have the following keys:
+                        - path: Path to the executable (optional)
+                       E.g. {'deno': {'path': '/path/to/deno'}
+    remote_components: A list of remote components that are allowed to be fetched when required.
+                       Supported components:
+                       - ejs:npm (external JavaScript components from npm)
+                       - ejs:github (external JavaScript components from yt-dlp-ejs GitHub)
+                       By default, no remote components are allowed to be fetched.
     mark_watched:      Mark videos watched (even with --simulate). Only for YouTube
 
     The following options are deprecated and may be removed in the future:
@@ -581,7 +595,7 @@ class YoutubeDL:
         'width', 'height', 'asr', 'audio_channels', 'fps',
         'tbr', 'abr', 'vbr', 'filesize', 'filesize_approx',
         'timestamp', 'release_timestamp', 'available_at',
-        'duration', 'view_count', 'like_count', 'dislike_count', 'repost_count',
+        'duration', 'view_count', 'like_count', 'dislike_count', 'repost_count', 'save_count',
         'average_rating', 'comment_count', 'age_limit',
         'start_time', 'end_time',
         'chapter_number', 'season_number', 'episode_number',
@@ -717,6 +731,13 @@ class YoutubeDL:
                 else:
                     raise
 
+        # Note: this must be after plugins are loaded
+        self.params['js_runtimes'] = self.params.get('js_runtimes', {'deno': {}})
+        self._clean_js_runtimes(self.params['js_runtimes'])
+
+        self.params['remote_components'] = set(self.params.get('remote_components', ()))
+        self._clean_remote_components(self.params['remote_components'])
+
         self.params['compat_opts'] = set(self.params.get('compat_opts', ()))
         self.params['http_headers'] = HTTPHeaderDict(std_headers, self.params.get('http_headers'))
         self._load_cookies(self.params['http_headers'].get('Cookie'))  # compat
@@ -829,6 +850,36 @@ class YoutubeDL:
 
         self.archive = preload_download_archive(self.params.get('download_archive'))
 
+    def _clean_js_runtimes(self, runtimes):
+        if not (
+            isinstance(runtimes, dict)
+            and all(isinstance(k, str) and (v is None or isinstance(v, dict)) for k, v in runtimes.items())
+        ):
+            raise ValueError('Invalid js_runtimes format, expected a dict of {runtime: {config}}')
+
+        if unsupported_runtimes := runtimes.keys() - supported_js_runtimes.value.keys():
+            self.report_warning(
+                f'Ignoring unsupported JavaScript runtime(s): {", ".join(unsupported_runtimes)}.'
+                f' Supported runtimes: {", ".join(supported_js_runtimes.value.keys())}.')
+            for rt in unsupported_runtimes:
+                runtimes.pop(rt)
+
+    def _clean_remote_components(self, remote_components: set):
+        if unsupported_remote_components := set(remote_components) - set(supported_remote_components.value):
+            self.report_warning(
+                f'Ignoring unsupported remote component(s): {", ".join(unsupported_remote_components)}.'
+                f' Supported remote components: {", ".join(supported_remote_components.value)}.')
+            for rt in unsupported_remote_components:
+                remote_components.remove(rt)
+
+    @functools.cached_property
+    def _js_runtimes(self):
+        runtimes = {}
+        for name, config in self.params.get('js_runtimes', {}).items():
+            runtime_cls = supported_js_runtimes.value.get(name)
+            runtimes[name] = runtime_cls(path=config.get('path')) if runtime_cls else None
+        return runtimes
+
     def warn_if_short_id(self, argv):
         # short YouTube ID starting with dash?
         idxs = [
@@ -2975,6 +3026,10 @@ class YoutubeDL:
         format_selector = self.format_selector
         while True:
             if interactive_format_selection:
+                if not formats:
+                    # Bypass interactive format selection if no formats & --ignore-no-formats-error
+                    formats_to_download = None
+                    break
                 req_format = input(self._format_screen('\nEnter format selector ', self.Styles.EMPHASIS)
                                    + '(Press ENTER for default, or Ctrl+C to quit)'
                                    + self._format_screen(': ', self.Styles.EMPHASIS))
@@ -4064,6 +4119,18 @@ class YoutubeDL:
             join_nonempty(*get_package_info(m)) for m in available_dependencies.values()
         })) or 'none'))
 
+        if not self.params.get('js_runtimes'):
+            write_debug('JS runtimes: none (disabled)')
+        else:
+            write_debug('JS runtimes: %s' % (', '.join(sorted(
+                f'{name} (unknown)' if runtime is None
+                else join_nonempty(
+                    runtime.info.name,
+                    runtime.info.version + (' (unsupported)' if runtime.info.supported is False else ''),
+                )
+                for name, runtime in self._js_runtimes.items() if runtime is None or runtime.info is not None
+            )) or 'none'))
+
         write_debug(f'Proxy map: {self.proxies}')
         write_debug(f'Request Handlers: {", ".join(rh.RH_NAME for rh in self._request_director.handlers.values())}')
 

plugins/youtube_download/yt_dlp/__init__.py

@@ -61,8 +61,15 @@ from .utils import (
     shell_quote,
     variadic,
     write_string,
+
 )
 from .utils._utils import _UnsafeExtensionError
+from .utils._jsruntime import (
+    BunJsRuntime as _BunJsRuntime,
+    DenoJsRuntime as _DenoJsRuntime,
+    NodeJsRuntime as _NodeJsRuntime,
+    QuickJsRuntime as _QuickJsRuntime,
+)
 from .YoutubeDL import YoutubeDL
 
 
@@ -773,6 +780,10 @@ def parse_options(argv=None):
         else opts.audioformat if (opts.extractaudio and opts.audioformat in FFmpegExtractAudioPP.SUPPORTED_EXTS)
         else None)
 
+    js_runtimes = {
+        runtime.lower(): {'path': path} for runtime, path in (
+            [*arg.split(':', 1), None][:2] for arg in opts.js_runtimes)}
+
     return ParsedOptions(parser, opts, urls, {
         'usenetrc': opts.usenetrc,
         'netrc_location': opts.netrc_location,
@@ -940,6 +951,8 @@ def parse_options(argv=None):
         'geo_bypass_country': opts.geo_bypass_country,
         'geo_bypass_ip_block': opts.geo_bypass_ip_block,
         'useid': opts.useid or None,
+        'js_runtimes': js_runtimes,
+        'remote_components': opts.remote_components,
         'warn_when_outdated': opts.update_self is None,
         '_warnings': warnings,
         '_deprecation_warnings': deprecation_warnings,
@@ -1081,6 +1094,16 @@ def main(argv=None):
 
 from .extractor import gen_extractors, list_extractors
 
+# Register JS runtimes and remote components
+from .globals import supported_js_runtimes, supported_remote_components
+supported_js_runtimes.value['deno'] = _DenoJsRuntime
+supported_js_runtimes.value['node'] = _NodeJsRuntime
+supported_js_runtimes.value['bun'] = _BunJsRuntime
+supported_js_runtimes.value['quickjs'] = _QuickJsRuntime
+
+supported_remote_components.value.append('ejs:github')
+supported_remote_components.value.append('ejs:npm')
+
 __all__ = [
     'YoutubeDL',
     'gen_extractors',

plugins/youtube_download/yt_dlp/__pyinstaller/hook-yt_dlp.py

@@ -34,3 +34,4 @@ print(f'Adding imports: {hiddenimports}')
 excludedimports = ['youtube_dl', 'youtube_dlc', 'test', 'ytdlp_plugins', 'devscripts', 'bundle']
 
 datas = collect_data_files('curl_cffi', includes=['cacert.pem'])
+datas += collect_data_files('yt_dlp_ejs', includes=['**/*.js'])

plugins/youtube_download/yt_dlp/cookies.py

@@ -125,7 +125,7 @@ def extract_cookies_from_browser(browser_name, profile=None, logger=YDLLogger(),
 
 
 def _extract_firefox_cookies(profile, container, logger):
-    MAX_SUPPORTED_DB_SCHEMA_VERSION = 16
+    MAX_SUPPORTED_DB_SCHEMA_VERSION = 17
 
     logger.info('Extracting cookies from firefox')
     if not sqlite3:
@@ -166,6 +166,8 @@ def _extract_firefox_cookies(profile, container, logger):
             db_schema_version = cursor.execute('PRAGMA user_version;').fetchone()[0]
             if db_schema_version > MAX_SUPPORTED_DB_SCHEMA_VERSION:
                 logger.warning(f'Possibly unsupported firefox cookies database version: {db_schema_version}')
+            else:
+                logger.debug(f'Firefox cookies database version: {db_schema_version}')
             if isinstance(container_id, int):
                 logger.debug(
                     f'Only loading cookies from firefox container "{container}", ID {container_id}')
@@ -210,9 +212,16 @@ def _firefox_browser_dirs():
 
     else:
         yield from map(os.path.expanduser, (
+            # New installations of FF147+ respect the XDG base directory specification
+            # Ref: https://bugzilla.mozilla.org/show_bug.cgi?id=259356
+            os.path.join(_config_home(), 'mozilla/firefox'),
+            # Existing FF version<=146 installations
             '~/.mozilla/firefox',
-            '~/snap/firefox/common/.mozilla/firefox',
+            # Flatpak XDG: https://docs.flatpak.org/en/latest/conventions.html#xdg-base-directories
+            '~/.var/app/org.mozilla.firefox/config/mozilla/firefox',
             '~/.var/app/org.mozilla.firefox/.mozilla/firefox',
+            # Snap installations do not respect the XDG base directory specification
+            '~/snap/firefox/common/.mozilla/firefox',
         ))
 
 
@@ -557,7 +566,7 @@ class WindowsChromeCookieDecryptor(ChromeCookieDecryptor):
 
 
 def _extract_safari_cookies(profile, logger):
-    if sys.platform != 'darwin':
+    if sys.platform not in ('darwin', 'ios'):
         raise ValueError(f'unsupported platform: {sys.platform}')
 
     if profile:

plugins/youtube_download/yt_dlp/dependencies/__init__.py

@@ -81,6 +81,12 @@ except ImportError:
 
 from . import Cryptodome
 
+try:
+    import yt_dlp_ejs
+except ImportError:
+    yt_dlp_ejs = None
+
+
 all_dependencies = {k: v for k, v in globals().items() if not k.startswith('_')}
 available_dependencies = {k: v for k, v in all_dependencies.items() if v}
 

plugins/youtube_download/yt_dlp/downloader/common.py

@@ -461,7 +461,8 @@ class FileDownloader:
             min_sleep_interval = self.params.get('sleep_interval') or 0
             max_sleep_interval = self.params.get('max_sleep_interval') or 0
 
-            if available_at := info_dict.get('available_at'):
+            requested_formats = info_dict.get('requested_formats') or [info_dict]
+            if available_at := max(f.get('available_at') or 0 for f in requested_formats):
                 forced_sleep_interval = available_at - int(time.time())
                 if forced_sleep_interval > min_sleep_interval:
                     sleep_note = 'as required by the site'

plugins/youtube_download/yt_dlp/downloader/external.py

@@ -457,6 +457,8 @@ class FFmpegFD(ExternalFD):
 
     @classmethod
     def available(cls, path=None):
+        # TODO: Fix path for ffmpeg
+        # Fixme: This may be wrong when --ffmpeg-location is used
         return FFmpegPostProcessor().available
 
     def on_process_started(self, proc, stdin):
@@ -488,20 +490,6 @@ class FFmpegFD(ExternalFD):
         if not self.params.get('verbose'):
             args += ['-hide_banner']
 
-        args += traverse_obj(info_dict, ('downloader_options', 'ffmpeg_args', ...))
-
-        # These exists only for compatibility. Extractors should use
-        # info_dict['downloader_options']['ffmpeg_args'] instead
-        args += info_dict.get('_ffmpeg_args') or []
-        seekable = info_dict.get('_seekable')
-        if seekable is not None:
-            # setting -seekable prevents ffmpeg from guessing if the server
-            # supports seeking(by adding the header `Range: bytes=0-`), which
-            # can cause problems in some cases
-            # https://github.com/ytdl-org/youtube-dl/issues/11800#issuecomment-275037127
-            # http://trac.ffmpeg.org/ticket/6125#comment:10
-            args += ['-seekable', '1' if seekable else '0']
-
         env = None
         proxy = self.params.get('proxy')
         if proxy:
@@ -521,39 +509,10 @@ class FFmpegFD(ExternalFD):
             env['HTTP_PROXY'] = proxy
             env['http_proxy'] = proxy
 
-        protocol = info_dict.get('protocol')
-
-        if protocol == 'rtmp':
-            player_url = info_dict.get('player_url')
-            page_url = info_dict.get('page_url')
-            app = info_dict.get('app')
-            play_path = info_dict.get('play_path')
-            tc_url = info_dict.get('tc_url')
-            flash_version = info_dict.get('flash_version')
-            live = info_dict.get('rtmp_live', False)
-            conn = info_dict.get('rtmp_conn')
-            if player_url is not None:
-                args += ['-rtmp_swfverify', player_url]
-            if page_url is not None:
-                args += ['-rtmp_pageurl', page_url]
-            if app is not None:
-                args += ['-rtmp_app', app]
-            if play_path is not None:
-                args += ['-rtmp_playpath', play_path]
-            if tc_url is not None:
-                args += ['-rtmp_tcurl', tc_url]
-            if flash_version is not None:
-                args += ['-rtmp_flashver', flash_version]
-            if live:
-                args += ['-rtmp_live', 'live']
-            if isinstance(conn, list):
-                for entry in conn:
-                    args += ['-rtmp_conn', entry]
-            elif isinstance(conn, str):
-                args += ['-rtmp_conn', conn]
-
         start_time, end_time = info_dict.get('section_start') or 0, info_dict.get('section_end')
 
+        fallback_input_args = traverse_obj(info_dict, ('downloader_options', 'ffmpeg_args', ...))
+
         selected_formats = info_dict.get('requested_formats') or [info_dict]
         for i, fmt in enumerate(selected_formats):
             is_http = re.match(r'https?://', fmt['url'])
@@ -572,6 +531,44 @@ class FFmpegFD(ExternalFD):
             if end_time:
                 args += ['-t', str(end_time - start_time)]
 
+            protocol = fmt.get('protocol')
+
+            if protocol == 'rtmp':
+                player_url = fmt.get('player_url')
+                page_url = fmt.get('page_url')
+                app = fmt.get('app')
+                play_path = fmt.get('play_path')
+                tc_url = fmt.get('tc_url')
+                flash_version = fmt.get('flash_version')
+                live = fmt.get('rtmp_live', False)
+                conn = fmt.get('rtmp_conn')
+                if player_url is not None:
+                    args += ['-rtmp_swfverify', player_url]
+                if page_url is not None:
+                    args += ['-rtmp_pageurl', page_url]
+                if app is not None:
+                    args += ['-rtmp_app', app]
+                if play_path is not None:
+                    args += ['-rtmp_playpath', play_path]
+                if tc_url is not None:
+                    args += ['-rtmp_tcurl', tc_url]
+                if flash_version is not None:
+                    args += ['-rtmp_flashver', flash_version]
+                if live:
+                    args += ['-rtmp_live', 'live']
+                if isinstance(conn, list):
+                    for entry in conn:
+                        args += ['-rtmp_conn', entry]
+                elif isinstance(conn, str):
+                    args += ['-rtmp_conn', conn]
+
+            elif protocol == 'http_dash_segments' and info_dict.get('is_live'):
+                # ffmpeg may try to read past the latest available segments for
+                # live DASH streams unless we pass `-re`. In modern ffmpeg, this
+                # is an alias of `-readrate 1`, but `-readrate` was not added
+                # until ffmpeg 5.0, so we must stick to using `-re`
+                args += ['-re']
+
             url = fmt['url']
             if self.params.get('enable_file_urls') and url.startswith('file:'):
                 # The default protocol_whitelist is 'file,crypto,data' when reading local m3u8 URLs,
@@ -586,6 +583,7 @@ class FFmpegFD(ExternalFD):
                 #      https://trac.ffmpeg.org/ticket/2702
                 url = re.sub(r'^file://(?:localhost)?/', 'file:' if os.name == 'nt' else 'file:/', url)
 
+            args += traverse_obj(fmt, ('downloader_options', 'ffmpeg_args', ...)) or fallback_input_args
             args += [*self._configuration_args((f'_i{i + 1}', '_i')), '-i', url]
 
         if not (start_time or end_time) or not self.params.get('force_keyframes_at_cuts'):

plugins/youtube_download/yt_dlp/extractor/_extractors.py

@@ -75,6 +75,7 @@ from .afreecatv import (
     AfreecaTVLiveIE,
     AfreecaTVUserIE,
 )
+from .agalega import AGalegaIE
 from .agora import (
     TokFMAuditionIE,
     TokFMPodcastIE,
@@ -83,6 +84,7 @@ from .agora import (
 )
 from .airtv import AirTVIE
 from .aitube import AitubeKZVideoIE
+from .alibaba import AlibabaIE
 from .aliexpress import AliExpressLiveIE
 from .aljazeera import AlJazeeraIE
 from .allocine import AllocineIE
@@ -143,6 +145,8 @@ from .archiveorg import (
 from .arcpublishing import ArcPublishingIE
 from .ard import (
     ARDIE,
+    ARDAudiothekIE,
+    ARDAudiothekPlaylistIE,
     ARDBetaMediathekIE,
     ARDMediathekCollectionIE,
 )
@@ -266,6 +270,7 @@ from .bitchute import (
     BitChuteChannelIE,
     BitChuteIE,
 )
+from .bitmovin import BitmovinIE
 from .blackboardcollaborate import (
     BlackboardCollaborateIE,
     BlackboardCollaborateLaunchIE,
@@ -426,6 +431,7 @@ from .cpac import (
 )
 from .cracked import CrackedIE
 from .craftsy import CraftsyIE
+from .croatianfilm import CroatianFilmIE
 from .crooksandliars import CrooksAndLiarsIE
 from .crowdbunker import (
     CrowdBunkerChannelIE,
@@ -633,12 +639,16 @@ from .fc2 import (
 )
 from .fczenit import FczenitIE
 from .fifa import FifaIE
+from .filmarchiv import FilmArchivIE
 from .filmon import (
     FilmOnChannelIE,
     FilmOnIE,
 )
 from .filmweb import FilmwebIE
-from .firsttv import FirstTVIE
+from .firsttv import (
+    FirstTVIE,
+    FirstTVLiveIE,
+)
 from .fivetv import FiveTVIE
 from .flextv import FlexTVIE
 from .flickr import FlickrIE
@@ -685,6 +695,10 @@ from .frontendmasters import (
     FrontendMastersIE,
     FrontendMastersLessonIE,
 )
+from .frontro import (
+    TheChosenGroupIE,
+    TheChosenIE,
+)
 from .fujitv import FujiTVFODPlus7IE
 from .funk import FunkIE
 from .funker530 import Funker530IE
@@ -1074,11 +1088,6 @@ from .mangomolo import (
     MangomoloLiveIE,
     MangomoloVideoIE,
 )
-from .manoto import (
-    ManotoTVIE,
-    ManotoTVLiveIE,
-    ManotoTVShowIE,
-)
 from .manyvids import ManyVidsIE
 from .maoritv import MaoriTVIE
 from .markiza import (
@@ -1088,7 +1097,10 @@ from .markiza import (
 from .massengeschmacktv import MassengeschmackTVIE
 from .masters import MastersIE
 from .matchtv import MatchTVIE
-from .mave import MaveIE
+from .mave import (
+    MaveChannelIE,
+    MaveIE,
+)
 from .mbn import MBNIE
 from .mdr import MDRIE
 from .medaltv import MedalTVIE
@@ -1195,6 +1207,7 @@ from .musicdex import (
     MusicdexPlaylistIE,
     MusicdexSongIE,
 )
+from .mux import MuxIE
 from .mx3 import (
     Mx3IE,
     Mx3NeoIE,
@@ -1216,6 +1229,7 @@ from .n1 import (
     N1InfoAssetIE,
     N1InfoIIE,
 )
+from .nascar import NascarClassicsIE
 from .nate import (
     NateIE,
     NateProgramIE,
@@ -1261,6 +1275,7 @@ from .nebula import (
     NebulaChannelIE,
     NebulaClassIE,
     NebulaIE,
+    NebulaSeasonIE,
     NebulaSubscriptionsIE,
 )
 from .nekohacker import NekoHackerIE
@@ -1269,6 +1284,10 @@ from .nest import (
     NestClipIE,
     NestIE,
 )
+from .netapp import (
+    NetAppCollectionIE,
+    NetAppVideoIE,
+)
 from .neteasemusic import (
     NetEaseMusicAlbumIE,
     NetEaseMusicDjRadioIE,
@@ -1291,12 +1310,6 @@ from .newgrounds import (
 )
 from .newspicks import NewsPicksIE
 from .newsy import NewsyIE
-from .nextmedia import (
-    AppleDailyIE,
-    NextMediaActionNewsIE,
-    NextMediaIE,
-    NextTVIE,
-)
 from .nexx import (
     NexxEmbedIE,
     NexxIE,
@@ -1361,6 +1374,7 @@ from .nova import (
     NovaIE,
 )
 from .novaplay import NovaPlayIE
+from .nowcanal import NowCanalIE
 from .nowness import (
     NownessIE,
     NownessPlaylistIE,
@@ -1464,6 +1478,7 @@ from .palcomp3 import (
     PalcoMP3IE,
     PalcoMP3VideoIE,
 )
+from .pandatv import PandaTvIE
 from .panopto import (
     PanoptoIE,
     PanoptoListIE,
@@ -1812,10 +1827,6 @@ from .scrippsnetworks import (
     ScrippsNetworksWatchIE,
 )
 from .scrolller import ScrolllerIE
-from .scte import (
-    SCTEIE,
-    SCTECourseIE,
-)
 from .sejmpl import SejmIE
 from .sen import SenIE
 from .senalcolombia import SenalColombiaLiveIE
@@ -1997,6 +2008,11 @@ from .taptap import (
     TapTapMomentIE,
     TapTapPostIntlIE,
 )
+from .tarangplus import (
+    TarangPlusEpisodesIE,
+    TarangPlusPlaylistIE,
+    TarangPlusVideoIE,
+)
 from .tass import TassIE
 from .tbs import TBSIE
 from .tbsjp import (
@@ -2514,6 +2530,7 @@ from .yappy import (
     YappyIE,
     YappyProfileIE,
 )
+from .yfanefa import YfanefaIE
 from .yle_areena import YleAreenaIE
 from .youjizz import YouJizzIE
 from .youku import (

plugins/youtube_download/yt_dlp/extractor/abc.py

@@ -321,6 +321,8 @@ class ABCIViewIE(InfoExtractor):
                 entry_protocol='m3u8_native', m3u8_id='hls', fatal=False)
             if formats:
                 break
+        else:
+            formats = []
 
         subtitles = {}
         src_vtt = stream.get('captions', {}).get('src-vtt')

plugins/youtube_download/yt_dlp/extractor/agalega.py

@@ -0,0 +1,91 @@
+import json
+import time
+
+from .common import InfoExtractor
+from ..utils import jwt_decode_hs256, url_or_none
+from ..utils.traversal import traverse_obj
+
+
+class AGalegaBaseIE(InfoExtractor):
+    _access_token = None
+
+    @staticmethod
+    def _jwt_is_expired(token):
+        return jwt_decode_hs256(token)['exp'] - time.time() < 120
+
+    def _refresh_access_token(self, video_id):
+        AGalegaBaseIE._access_token = self._download_json(
+            'https://www.agalega.gal/api/fetch-api/jwt/token', video_id,
+            note='Downloading access token',
+            data=json.dumps({
+                'username': None,
+                'password': None,
+                'client': 'crtvg',
+                'checkExistsCookies': False,
+            }).encode())['access']
+
+    def _call_api(self, endpoint, display_id, note, fatal=True, query=None):
+        if not AGalegaBaseIE._access_token or self._jwt_is_expired(AGalegaBaseIE._access_token):
+            self._refresh_access_token(endpoint)
+        return self._download_json(
+            f'https://api-agalega.interactvty.com/api/2.0/contents/{endpoint}', display_id,
+            note=note, fatal=fatal, query=query,
+            headers={'Authorization': f'jwtok {AGalegaBaseIE._access_token}'})
+
+
+class AGalegaIE(AGalegaBaseIE):
+    IE_NAME = 'agalega:videos'
+    _VALID_URL = r'https?://(?:www\.)?agalega\.gal/videos/(?:detail/)?(?P<id>[0-9]+)'
+    _TESTS = [{
+        'url': 'https://www.agalega.gal/videos/288664-lr-ninguencheconta',
+        'md5': '04533a66c5f863d08dd9724b11d1c223',
+        'info_dict': {
+            'id': '288664',
+            'title': 'Roberto e Ángel Martín atenden consultas dos espectadores',
+            'description': 'O cómico ademais fai un repaso dalgúns momentos da súa traxectoria profesional',
+            'thumbnail': 'https://crtvg-bucket.flumotion.cloud/content_cards/2ef32c3b9f6249d9868fd8f11d389d3d.png',
+            'ext': 'mp4',
+        },
+    }, {
+        'url': 'https://www.agalega.gal/videos/detail/296152-pulso-activo-7',
+        'md5': '26df7fdcf859f38ad92d837279d6b56d',
+        'info_dict': {
+            'id': '296152',
+            'title': 'Pulso activo | 18-11-2025',
+            'description': 'Anxo, Noemí, Silvia e Estrella  comparten as sensacións da clase de Eddy.',
+            'thumbnail': 'https://crtvg-bucket.flumotion.cloud/content_cards/a6bb7da6c8994b82bf961ac6cad1707b.png',
+            'ext': 'mp4',
+        },
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        content_data = self._call_api(
+            f'content/{video_id}/', video_id, note='Downloading content data', fatal=False,
+            query={
+                'optional_fields': 'image,is_premium,short_description,has_subtitle',
+            })
+        resource_data = self._call_api(
+            f'content_resources/{video_id}/', video_id, note='Downloading resource data',
+            query={
+                'optional_fields': 'media_url',
+            })
+
+        formats = []
+        subtitles = {}
+        for m3u8_url in traverse_obj(resource_data, ('results', ..., 'media_url', {url_or_none})):
+            fmts, subs = self._extract_m3u8_formats_and_subtitles(
+                m3u8_url, video_id, ext='mp4', m3u8_id='hls')
+            formats.extend(fmts)
+            self._merge_subtitles(subs, target=subtitles)
+
+        return {
+            'id': video_id,
+            'formats': formats,
+            'subtitles': subtitles,
+            **traverse_obj(content_data, {
+                'title': ('name', {str}),
+                'description': (('description', 'short_description'), {str}, any),
+                'thumbnail': ('image', {url_or_none}),
+            }),
+        }

plugins/youtube_download/yt_dlp/extractor/alibaba.py

@@ -0,0 +1,42 @@
+from .common import InfoExtractor
+from ..utils import int_or_none, str_or_none, url_or_none
+from ..utils.traversal import traverse_obj
+
+
+class AlibabaIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?alibaba\.com/product-detail/[\w-]+_(?P<id>\d+)\.html'
+    _TESTS = [{
+        'url': 'https://www.alibaba.com/product-detail/Kids-Entertainment-Bouncer-Bouncy-Castle-Waterslide_1601271126969.html',
+        'info_dict': {
+            'id': '6000280444270',
+            'display_id': '1601271126969',
+            'ext': 'mp4',
+            'title': 'Kids Entertainment Bouncer Bouncy Castle Waterslide Juex Gonflables Commercial Inflatable Tropical Water Slide',
+            'duration': 30,
+            'thumbnail': 'https://sc04.alicdn.com/kf/Hc5bb391974454af18c7a4f91cbe4062bg.jpg_120x120.jpg',
+        },
+    }]
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_id)
+        product_data = self._search_json(
+            r'window\.detailData\s*=', webpage, 'detail data', display_id)['globalData']['product']
+
+        return {
+            **traverse_obj(product_data, ('mediaItems', lambda _, v: v['type'] == 'video' and v['videoId'], any, {
+                'id': ('videoId', {int}, {str_or_none}),
+                'duration': ('duration', {int_or_none}),
+                'thumbnail': ('videoCoverUrl', {url_or_none}),
+                'formats': ('videoUrl', lambda _, v: url_or_none(v['videoUrl']), {
+                    'url': 'videoUrl',
+                    'format_id': ('definition', {str_or_none}),
+                    'tbr': ('bitrate', {int_or_none}),
+                    'width': ('width', {int_or_none}),
+                    'height': ('height', {int_or_none}),
+                    'filesize': ('length', {int_or_none}),
+                }),
+            })),
+            'title': traverse_obj(product_data, ('subject', {str})),
+            'display_id': display_id,
+        }

plugins/youtube_download/yt_dlp/extractor/archiveorg.py

@@ -5,12 +5,9 @@ import re
 import urllib.parse
 
 from .common import InfoExtractor
-from .youtube import YoutubeBaseInfoExtractor, YoutubeIE
-from ..networking import HEADRequest
-from ..networking.exceptions import HTTPError
+from .youtube import YoutubeBaseInfoExtractor
 from ..utils import (
     KNOWN_EXTENSIONS,
-    ExtractorError,
     bug_reports_message,
     clean_html,
     dict_get,
@@ -21,18 +18,14 @@ from ..utils import (
     join_nonempty,
     js_to_json,
     merge_dicts,
-    mimetype2ext,
     orderedSet,
     parse_duration,
     parse_qs,
     str_or_none,
-    str_to_int,
     traverse_obj,
-    try_get,
     unified_strdate,
     unified_timestamp,
     url_or_none,
-    urlhandle_detect_ext,
 )
 
 
@@ -286,7 +279,7 @@ class ArchiveOrgIE(InfoExtractor):
                     'url': 'https://archive.org/' + track['file'].lstrip('/'),
                 }
 
-        metadata = self._download_json('http://archive.org/metadata/' + identifier, identifier)
+        metadata = self._download_json(f'https://archive.org/metadata/{identifier}', identifier)
         m = metadata['metadata']
         identifier = m['identifier']
 
@@ -471,7 +464,7 @@ class YoutubeWebArchiveIE(InfoExtractor):
             'url': 'https://web.archive.org/web/20110712231407/http://www.youtube.com/watch?v=lTx3G6h2xyA',
             'info_dict': {
                 'id': 'lTx3G6h2xyA',
-                'ext': 'flv',
+                'ext': 'mp4',
                 'title': 'Madeon - Pop Culture (live mashup)',
                 'upload_date': '20110711',
                 'uploader': 'Madeon',
@@ -578,7 +571,7 @@ class YoutubeWebArchiveIE(InfoExtractor):
             'url': 'https://web.archive.org/web/20110126141719/http://www.youtube.com/watch?v=Q_yjX80U7Yc',
             'info_dict': {
                 'id': 'Q_yjX80U7Yc',
-                'ext': 'flv',
+                'ext': 'webm',
                 'title': 'Spray Paint Art by Clay Butler: Purple Fantasy Forest',
                 'uploader_id': 'claybutlermusic',
                 'description': 'md5:4595264559e3d0a0ceb3f011f6334543',
@@ -680,6 +673,55 @@ class YoutubeWebArchiveIE(InfoExtractor):
                 'upload_date': '20120407',
                 'uploader_id': 'thecomputernerd01',
             },
+        }, {
+            # Contains split audio/video formats
+            'url': 'ytarchive:o_T_S_TU12M',
+            'info_dict': {
+                'id': 'o_T_S_TU12M',
+                'ext': 'mp4',
+                'title': 'Prairie Pulse 1218; Lin Enger, Paul Olson',
+                'description': 'md5:36e7a34cdc8508e35a920ec042e799c7',
+                'uploader': 'Prairie Public',
+                'channel_id': 'UC4BOzQel6tvJm7OEDd3vZlw',
+                'channel_url': 'https://www.youtube.com/channel/UC4BOzQel6tvJm7OEDd3vZlw',
+                'duration': 1606,
+                'upload_date': '20150213',
+            },
+        }, {
+            # Video unavailable through wayback-fakeurl
+            'url': 'ytarchive:SQCom7wjGDs',
+            'info_dict': {
+                'id': 'SQCom7wjGDs',
+                'ext': 'mp4',
+                'title': 'Jamin Warren from PBS Game/Show decides that Portal is a feminist Game [Top Hats and No Brain]',
+                'description': 'md5:c0cb876dd075483ead9afcc86798efb0',
+                'uploader': 'Top Hats and Champagne',
+                'uploader_id': 'sparrowtm',
+                'uploader_url': 'https://www.youtube.com/user/sparrowtm',
+                'channel_id': 'UCW3T5nG4iEkI7HjG-Du3HQA',
+                'channel_url': 'https://www.youtube.com/channel/UCW3T5nG4iEkI7HjG-Du3HQA',
+                'duration': 1500,
+                'thumbnail': 'https://web.archive.org/web/20160108040020if_/https://i.ytimg.com/vi/SQCom7wjGDs/maxresdefault.jpg',
+                'upload_date': '20160107',
+            },
+        }, {
+            # dmuxed formats
+            'url': 'https://web.archive.org/web/20240922160632/https://www.youtube.com/watch?v=z7hzvTL3k1k',
+            'info_dict': {
+                'id': 'z7hzvTL3k1k',
+                'ext': 'webm',
+                'title': 'Praise the Lord and Pass the Ammunition (BARRXN REMIX)',
+                'description': 'md5:45dbf2c71c23b0734c8dfb82dd1e94b6',
+                'uploader': 'Barrxn',
+                'uploader_id': 'TheRockstar6086',
+                'uploader_url': 'https://www.youtube.com/user/TheRockstar6086',
+                'channel_id': 'UCjJPGUTtvR9uizmawn2ThqA',
+                'channel_url': 'https://www.youtube.com/channel/UCjJPGUTtvR9uizmawn2ThqA',
+                'duration': 125,
+                'thumbnail': r're:https?://.*\.(jpg|webp)',
+                'upload_date': '20201207',
+            },
+            'params': {'format': 'bv'},
         }, {
             'url': 'https://web.archive.org/web/http://www.youtube.com/watch?v=kH-G_aIBlFw',
             'only_matching': True,
@@ -724,6 +766,113 @@ class YoutubeWebArchiveIE(InfoExtractor):
     _OLDEST_CAPTURE_DATE = 20050214000000
     _NEWEST_CAPTURE_DATE = 20500101000000
 
+    _FORMATS = {
+        '5': {'ext': 'flv', 'width': 400, 'height': 240, 'acodec': 'mp3', 'vcodec': 'h263'},
+        '6': {'ext': 'flv', 'width': 450, 'height': 270, 'acodec': 'mp3', 'vcodec': 'h263'},
+        '13': {'ext': '3gp', 'acodec': 'aac', 'vcodec': 'mp4v'},
+        '17': {'ext': '3gp', 'width': 176, 'height': 144, 'acodec': 'aac', 'vcodec': 'mp4v'},
+        '18': {'ext': 'mp4', 'width': 640, 'height': 360, 'acodec': 'aac', 'vcodec': 'h264'},
+        '22': {'ext': 'mp4', 'width': 1280, 'height': 720, 'acodec': 'aac', 'vcodec': 'h264'},
+        '34': {'ext': 'flv', 'width': 640, 'height': 360, 'acodec': 'aac', 'vcodec': 'h264'},
+        '35': {'ext': 'flv', 'width': 854, 'height': 480, 'acodec': 'aac', 'vcodec': 'h264'},
+        # itag 36 videos are either 320x180 (BaW_jenozKc) or 320x240 (__2ABJjxzNo), abr varies as well
+        '36': {'ext': '3gp', 'width': 320, 'acodec': 'aac', 'vcodec': 'mp4v'},
+        '37': {'ext': 'mp4', 'width': 1920, 'height': 1080, 'acodec': 'aac', 'vcodec': 'h264'},
+        '38': {'ext': 'mp4', 'width': 4096, 'height': 3072, 'acodec': 'aac', 'vcodec': 'h264'},
+        '43': {'ext': 'webm', 'width': 640, 'height': 360, 'acodec': 'vorbis', 'vcodec': 'vp8'},
+        '44': {'ext': 'webm', 'width': 854, 'height': 480, 'acodec': 'vorbis', 'vcodec': 'vp8'},
+        '45': {'ext': 'webm', 'width': 1280, 'height': 720, 'acodec': 'vorbis', 'vcodec': 'vp8'},
+        '46': {'ext': 'webm', 'width': 1920, 'height': 1080, 'acodec': 'vorbis', 'vcodec': 'vp8'},
+        '59': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'vcodec': 'h264'},
+        '78': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'vcodec': 'h264'},
+
+
+        # 3D videos
+        '82': {'ext': 'mp4', 'height': 360, 'format_note': '3D', 'acodec': 'aac', 'vcodec': 'h264', 'preference': -20},
+        '83': {'ext': 'mp4', 'height': 480, 'format_note': '3D', 'acodec': 'aac', 'vcodec': 'h264', 'preference': -20},
+        '84': {'ext': 'mp4', 'height': 720, 'format_note': '3D', 'acodec': 'aac', 'vcodec': 'h264', 'preference': -20},
+        '85': {'ext': 'mp4', 'height': 1080, 'format_note': '3D', 'acodec': 'aac', 'vcodec': 'h264', 'preference': -20},
+        '100': {'ext': 'webm', 'height': 360, 'format_note': '3D', 'acodec': 'vorbis', 'vcodec': 'vp8', 'preference': -20},
+        '101': {'ext': 'webm', 'height': 480, 'format_note': '3D', 'acodec': 'vorbis', 'vcodec': 'vp8', 'preference': -20},
+        '102': {'ext': 'webm', 'height': 720, 'format_note': '3D', 'acodec': 'vorbis', 'vcodec': 'vp8', 'preference': -20},
+
+        # Apple HTTP Live Streaming
+        '91': {'ext': 'mp4', 'height': 144, 'format_note': 'HLS', 'acodec': 'aac', 'vcodec': 'h264'},
+        '92': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'vcodec': 'h264'},
+        '93': {'ext': 'mp4', 'height': 360, 'format_note': 'HLS', 'acodec': 'aac', 'vcodec': 'h264'},
+        '94': {'ext': 'mp4', 'height': 480, 'format_note': 'HLS', 'acodec': 'aac', 'vcodec': 'h264'},
+        '95': {'ext': 'mp4', 'height': 720, 'format_note': 'HLS', 'acodec': 'aac', 'vcodec': 'h264'},
+        '96': {'ext': 'mp4', 'height': 1080, 'format_note': 'HLS', 'acodec': 'aac', 'vcodec': 'h264'},
+        '132': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'vcodec': 'h264'},
+        '151': {'ext': 'mp4', 'height': 72, 'format_note': 'HLS', 'acodec': 'aac', 'vcodec': 'h264'},
+
+        # DASH mp4 video
+        '133': {'ext': 'mp4', 'height': 240, 'vcodec': 'h264', 'acodec': 'none'},
+        '134': {'ext': 'mp4', 'height': 360, 'vcodec': 'h264', 'acodec': 'none'},
+        '135': {'ext': 'mp4', 'height': 480, 'vcodec': 'h264', 'acodec': 'none'},
+        '136': {'ext': 'mp4', 'height': 720, 'vcodec': 'h264', 'acodec': 'none'},
+        '137': {'ext': 'mp4', 'height': 1080, 'vcodec': 'h264', 'acodec': 'none'},
+        '138': {'ext': 'mp4', 'vcodec': 'h264', 'acodec': 'none'},  # Height can vary (https://github.com/ytdl-org/youtube-dl/issues/4559)
+        '160': {'ext': 'mp4', 'height': 144, 'vcodec': 'h264', 'acodec': 'none'},
+        '212': {'ext': 'mp4', 'height': 480, 'vcodec': 'h264', 'acodec': 'none'},
+        '264': {'ext': 'mp4', 'height': 1440, 'vcodec': 'h264', 'acodec': 'none'},
+        '298': {'ext': 'mp4', 'height': 720, 'vcodec': 'h264', 'fps': 60, 'acodec': 'none'},
+        '299': {'ext': 'mp4', 'height': 1080, 'vcodec': 'h264', 'fps': 60, 'acodec': 'none'},
+        '266': {'ext': 'mp4', 'height': 2160, 'vcodec': 'h264', 'acodec': 'none'},
+
+        # Dash mp4 audio
+        '139': {'ext': 'm4a', 'acodec': 'aac', 'vcodec': 'none'},
+        '140': {'ext': 'm4a', 'acodec': 'aac', 'vcodec': 'none'},
+        '141': {'ext': 'm4a', 'acodec': 'aac', 'vcodec': 'none'},
+        '256': {'ext': 'm4a', 'acodec': 'aac', 'vcodec': 'none'},
+        '258': {'ext': 'm4a', 'acodec': 'aac', 'vcodec': 'none'},
+        '325': {'ext': 'm4a', 'acodec': 'dtse', 'vcodec': 'none'},
+        '328': {'ext': 'm4a', 'acodec': 'ec-3', 'vcodec': 'none'},
+
+        # Dash webm
+        '167': {'ext': 'webm', 'height': 360, 'width': 640, 'vcodec': 'vp8'},
+        '168': {'ext': 'webm', 'height': 480, 'width': 854, 'vcodec': 'vp8'},
+        '169': {'ext': 'webm', 'height': 720, 'width': 1280, 'vcodec': 'vp8'},
+        '170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'vcodec': 'vp8'},
+        '218': {'ext': 'webm', 'height': 480, 'width': 854, 'vcodec': 'vp8'},
+        '219': {'ext': 'webm', 'height': 480, 'width': 854, 'vcodec': 'vp8'},
+        '278': {'ext': 'webm', 'height': 144, 'vcodec': 'vp9', 'acodec': 'none'},
+        '242': {'ext': 'webm', 'height': 240, 'vcodec': 'vp9', 'acodec': 'none'},
+        '243': {'ext': 'webm', 'height': 360, 'vcodec': 'vp9', 'acodec': 'none'},
+        '244': {'ext': 'webm', 'height': 480, 'vcodec': 'vp9', 'acodec': 'none'},
+        '245': {'ext': 'webm', 'height': 480, 'vcodec': 'vp9', 'acodec': 'none'},
+        '246': {'ext': 'webm', 'height': 480, 'vcodec': 'vp9', 'acodec': 'none'},
+        '247': {'ext': 'webm', 'height': 720, 'vcodec': 'vp9', 'acodec': 'none'},
+        '248': {'ext': 'webm', 'height': 1080, 'vcodec': 'vp9', 'acodec': 'none'},
+        '271': {'ext': 'webm', 'height': 1440, 'vcodec': 'vp9', 'acodec': 'none'},
+        # itag 272 videos are either 3840x2160 (e.g. RtoitU2A-3E) or 7680x4320 (sLprVF6d7Ug)
+        '272': {'ext': 'webm', 'height': 2160, 'vcodec': 'vp9', 'acodec': 'none'},
+        '302': {'ext': 'webm', 'height': 720, 'vcodec': 'vp9', 'fps': 60, 'acodec': 'none'},
+        '303': {'ext': 'webm', 'height': 1080, 'vcodec': 'vp9', 'fps': 60, 'acodec': 'none'},
+        '308': {'ext': 'webm', 'height': 1440, 'vcodec': 'vp9', 'fps': 60, 'acodec': 'none'},
+        '313': {'ext': 'webm', 'height': 2160, 'vcodec': 'vp9', 'acodec': 'none'},
+        '315': {'ext': 'webm', 'height': 2160, 'vcodec': 'vp9', 'fps': 60, 'acodec': 'none'},
+
+        # Dash webm audio
+        '171': {'ext': 'webm', 'acodec': 'vorbis', 'vcodec': 'none'},
+        '172': {'ext': 'webm', 'acodec': 'vorbis', 'vcodec': 'none'},
+
+        # Dash webm audio with opus inside
+        '249': {'ext': 'webm', 'acodec': 'opus', 'vcodec': 'none'},
+        '250': {'ext': 'webm', 'acodec': 'opus', 'vcodec': 'none'},
+        '251': {'ext': 'webm', 'acodec': 'opus', 'vcodec': 'none'},
+
+        # av01 video only formats sometimes served with "unknown" codecs
+        '394': {'ext': 'mp4', 'height': 144, 'vcodec': 'av01.0.00M.08', 'acodec': 'none'},
+        '395': {'ext': 'mp4', 'height': 240, 'vcodec': 'av01.0.00M.08', 'acodec': 'none'},
+        '396': {'ext': 'mp4', 'height': 360, 'vcodec': 'av01.0.01M.08', 'acodec': 'none'},
+        '397': {'ext': 'mp4', 'height': 480, 'vcodec': 'av01.0.04M.08', 'acodec': 'none'},
+        '398': {'ext': 'mp4', 'height': 720, 'vcodec': 'av01.0.05M.08', 'acodec': 'none'},
+        '399': {'ext': 'mp4', 'height': 1080, 'vcodec': 'av01.0.08M.08', 'acodec': 'none'},
+        '400': {'ext': 'mp4', 'height': 1440, 'vcodec': 'av01.0.12M.08', 'acodec': 'none'},
+        '401': {'ext': 'mp4', 'height': 2160, 'vcodec': 'av01.0.12M.08', 'acodec': 'none'},
+    }
+
     def _call_cdx_api(self, item_id, url, filters: list | None = None, collapse: list | None = None, query: dict | None = None, note=None, fatal=False):
         # CDX docs: https://github.com/internetarchive/wayback/blob/master/wayback-cdx-server/README.md
         query = {
@@ -929,27 +1078,30 @@ class YoutubeWebArchiveIE(InfoExtractor):
         capture_dates.extend([self._OLDEST_CAPTURE_DATE, self._NEWEST_CAPTURE_DATE])
         return orderedSet(filter(None, capture_dates))
 
+    def _parse_fmt(self, fmt, extra_info=None):
+        format_id = traverse_obj(fmt, ('url', {parse_qs}, 'itag', 0))
+        return {
+            'format_id': format_id,
+            **self._FORMATS.get(format_id, {}),
+            **traverse_obj(fmt, {
+                'url': ('url', {lambda x: f'https://web.archive.org/web/2id_/{x}'}),
+                'ext': ('ext', {str}),
+                'filesize': ('url', {parse_qs}, 'clen', 0, {int_or_none}),
+            }),
+            **(extra_info or {}),
+        }
+
     def _real_extract(self, url):
         video_id, url_date, url_date_2 = self._match_valid_url(url).group('id', 'date', 'date2')
         url_date = url_date or url_date_2
 
-        urlh = None
-        retry_manager = self.RetryManager(fatal=False)
-        for retry in retry_manager:
-            try:
-                urlh = self._request_webpage(
-                    HEADRequest(f'https://web.archive.org/web/2oe_/http://wayback-fakeurl.archive.org/yt/{video_id}'),
-                    video_id, note='Fetching archived video file url', expected_status=True)
-            except ExtractorError as e:
-                # HTTP Error 404 is expected if the video is not saved.
-                if isinstance(e.cause, HTTPError) and e.cause.status == 404:
-                    self.raise_no_formats(
-                        'The requested video is not archived, indexed, or there is an issue with web.archive.org (try again later)', expected=True)
-                else:
-                    retry.error = e
+        video_info = self._download_json(
+            'https://web.archive.org/__wb/videoinfo', video_id,
+            query={'vtype': 'youtube', 'vid': video_id})
 
-        if retry_manager.error:
-            self.raise_no_formats(retry_manager.error, expected=True, video_id=video_id)
+        if not traverse_obj(video_info, 'formats'):
+            self.raise_no_formats(
+                'The requested video is not archived or indexed', expected=True)
 
         capture_dates = self._get_capture_dates(video_id, int_or_none(url_date))
         self.write_debug('Captures to try: ' + join_nonempty(*capture_dates, delim=', '))
@@ -968,25 +1120,15 @@ class YoutubeWebArchiveIE(InfoExtractor):
 
         info['thumbnails'] = self._extract_thumbnails(video_id)
 
-        if urlh:
-            url = urllib.parse.unquote(urlh.url)
-            video_file_url_qs = parse_qs(url)
-            # Attempt to recover any ext & format info from playback url & response headers
-            fmt = {'url': url, 'filesize': int_or_none(urlh.headers.get('x-archive-orig-content-length'))}
-            itag = try_get(video_file_url_qs, lambda x: x['itag'][0])
-            if itag and itag in YoutubeIE._formats:
-                fmt.update(YoutubeIE._formats[itag])
-                fmt.update({'format_id': itag})
-            else:
-                mime = try_get(video_file_url_qs, lambda x: x['mime'][0])
-                ext = (mimetype2ext(mime)
-                       or urlhandle_detect_ext(urlh)
-                       or mimetype2ext(urlh.headers.get('x-archive-guessed-content-type')))
-                fmt.update({'ext': ext})
-            info['formats'] = [fmt]
-            if not info.get('duration'):
-                info['duration'] = str_to_int(try_get(video_file_url_qs, lambda x: x['dur'][0]))
+        formats = []
+        if video_info.get('dmux'):
+            for vf in traverse_obj(video_info, ('formats', 'video', lambda _, v: url_or_none(v['url']))):
+                formats.append(self._parse_fmt(vf, {'acodec': 'none'}))
+            for af in traverse_obj(video_info, ('formats', 'audio', lambda _, v: url_or_none(v['url']))):
+                formats.append(self._parse_fmt(af, {'vcodec': 'none'}))
+        else:
+            for fmt in traverse_obj(video_info, ('formats', lambda _, v: url_or_none(v['url']))):
+                formats.append(self._parse_fmt(fmt))
+        info['formats'] = formats
 
-        if not info.get('title'):
-            info['title'] = video_id
         return info

plugins/youtube_download/yt_dlp/extractor/ard.py

@@ -1,4 +1,5 @@
 import functools
+import json
 import re
 
 from .common import InfoExtractor
@@ -15,11 +16,12 @@ from ..utils import (
     remove_start,
     str_or_none,
     unified_strdate,
+    update_url,
     update_url_query,
     url_or_none,
     xpath_text,
 )
-from ..utils.traversal import traverse_obj
+from ..utils.traversal import traverse_obj, value
 
 
 class ARDMediathekBaseIE(InfoExtractor):
@@ -601,3 +603,163 @@ class ARDMediathekCollectionIE(InfoExtractor):
         return self.playlist_result(
             OnDemandPagedList(fetch_page, self._PAGE_SIZE), full_id, display_id=display_id,
             title=page_data.get('title'), description=page_data.get('synopsis'))
+
+
+class ARDAudiothekBaseIE(InfoExtractor):
+    def _graphql_query(self, urn, query):
+        return self._download_json(
+            'https://api.ardaudiothek.de/graphql', urn,
+            data=json.dumps({
+                'query': query,
+                'variables': {'id': urn},
+            }).encode(), headers={
+                'Content-Type': 'application/json',
+            })['data']
+
+
+class ARDAudiothekIE(ARDAudiothekBaseIE):
+    _VALID_URL = r'https:?//(?:www\.)?ardaudiothek\.de/episode/(?P<id>urn:ard:(?:episode|section|extra):[a-f0-9]{16})'
+
+    _TESTS = [{
+        'url': 'https://www.ardaudiothek.de/episode/urn:ard:episode:eabead1add170e93/',
+        'info_dict': {
+            'id': 'urn:ard:episode:eabead1add170e93',
+            'ext': 'mp3',
+            'upload_date': '20240717',
+            'duration': 3339,
+            'title': 'CAIMAN CLUB (S04E04): Cash Out',
+            'thumbnail': 'https://api.ardmediathek.de/image-service/images/urn:ard:image:ed64411a07a4b405',
+            'description': 'md5:0e5d127a3832ae59e8bab40a91a5dadc',
+            'display_id': 'urn:ard:episode:eabead1add170e93',
+            'timestamp': 1721181641,
+            'series': '1LIVE Caiman Club',
+            'channel': 'WDR',
+            'episode': 'Episode 4',
+            'episode_number': 4,
+        },
+    }, {
+        'url': 'https://www.ardaudiothek.de/episode/urn:ard:section:855c7a53dac72e0a/',
+        'info_dict': {
+            'id': 'urn:ard:section:855c7a53dac72e0a',
+            'ext': 'mp4',
+            'upload_date': '20241231',
+            'duration': 3304,
+            'title': 'Illegaler DDR-Detektiv: Doberschütz und die letzte Staatsjagd (1/2) - Wendezeit',
+            'thumbnail': 'https://api.ardmediathek.de/image-service/images/urn:ard:image:b9b4f1e8b93da4dd',
+            'description': 'md5:3552d571e1959754cff66c1da6c0fdae',
+            'display_id': 'urn:ard:section:855c7a53dac72e0a',
+            'timestamp': 1735629900,
+            'series': 'Auf der Spur – Die ARD Ermittlerkrimis',
+            'channel': 'ARD',
+            'episode': 'Episode 1',
+            'episode_number': 1,
+        },
+    }, {
+        'url': 'https://www.ardaudiothek.de/episode/urn:ard:extra:d2fe7303d2dcbf5d/',
+        'info_dict': {
+            'id': 'urn:ard:extra:d2fe7303d2dcbf5d',
+            'ext': 'mp3',
+            'title': 'Trailer: Fanta Vier Forever, Baby!?!',
+            'description': 'md5:b64a586f2e976b8bb5ea0a79dbd8751c',
+            'channel': 'SWR',
+            'duration': 62,
+            'thumbnail': 'https://api.ardmediathek.de/image-service/images/urn:ard:image:48d3c255969be803',
+            'series': 'Fanta Vier Forever, Baby!?!',
+            'timestamp': 1732108217,
+            'upload_date': '20241120',
+        },
+    }]
+
+    _QUERY_ITEM = '''\
+    query($id: ID!) {
+        item(id: $id) {
+            audioList {
+                href
+                distributionType
+                audioBitrate
+                audioCodec
+            }
+            show {
+              title
+            }
+            image {
+              url1X1
+            }
+            programSet {
+              publicationService {
+                organizationName
+              }
+            }
+            description
+            title
+            duration
+            startDate
+            episodeNumber
+        }
+    }'''
+
+    def _real_extract(self, url):
+        urn = self._match_id(url)
+        item = self._graphql_query(urn, self._QUERY_ITEM)['item']
+        return {
+            'id': urn,
+            **traverse_obj(item, {
+                'formats': ('audioList', lambda _, v: url_or_none(v['href']), {
+                    'url': 'href',
+                    'format_id': ('distributionType', {str}),
+                    'abr': ('audioBitrate', {int_or_none}),
+                    'acodec': ('audioCodec', {str}),
+                    'vcodec': {value('none')},
+                }),
+                'channel': ('programSet', 'publicationService', 'organizationName', {str}),
+                'description': ('description', {str}),
+                'duration': ('duration', {int_or_none}),
+                'series': ('show', 'title', {str}),
+                'episode_number': ('episodeNumber', {int_or_none}),
+                'thumbnail': ('image', 'url1X1', {url_or_none}, {update_url(query=None)}),
+                'timestamp': ('startDate', {parse_iso8601}),
+                'title': ('title', {str}),
+            }),
+        }
+
+
+class ARDAudiothekPlaylistIE(ARDAudiothekBaseIE):
+    _VALID_URL = r'https:?//(?:www\.)?ardaudiothek\.de/sendung/(?P<playlist>[\w-]+)/(?P<id>urn:ard:show:[a-f0-9]{16})'
+
+    _TESTS = [{
+        'url': 'https://www.ardaudiothek.de/sendung/mia-insomnia/urn:ard:show:c405aa26d9a4060a/',
+        'info_dict': {
+            'display_id': 'mia-insomnia',
+            'title': 'Mia Insomnia',
+            'id': 'urn:ard:show:c405aa26d9a4060a',
+            'description': 'md5:d9ceb7a6b4d26a4db3316573bb564292',
+        },
+        'playlist_mincount': 37,
+    }, {
+        'url': 'https://www.ardaudiothek.de/sendung/100-berlin/urn:ard:show:4d248e0806ce37bc/',
+        'only_matching': True,
+    }]
+
+    _QUERY_PLAYLIST = '''
+    query($id: ID!) {
+        show(id: $id) {
+            title
+            description
+            items(filter: { isPublished: { equalTo: true } }) {
+                nodes {
+                    url
+                }
+            }
+        }
+    }'''
+
+    def _real_extract(self, url):
+        urn, playlist = self._match_valid_url(url).group('id', 'playlist')
+        playlist_info = self._graphql_query(urn, self._QUERY_PLAYLIST)['show']
+        entries = []
+        for url in traverse_obj(playlist_info, ('items', 'nodes', ..., 'url', {url_or_none})):
+            entries.append(self.url_result(url, ie=ARDAudiothekIE))
+        return self.playlist_result(entries, urn, display_id=playlist, **traverse_obj(playlist_info, {
+            'title': ('title', {str}),
+            'description': ('description', {str}),
+        }))

plugins/youtube_download/yt_dlp/extractor/bandcamp.py

@@ -5,16 +5,18 @@ import time
 
 from .common import InfoExtractor
 from ..utils import (
-    KNOWN_EXTENSIONS,
     ExtractorError,
     clean_html,
     extract_attributes,
     float_or_none,
+    format_field,
     int_or_none,
+    join_nonempty,
     parse_filesize,
+    parse_qs,
     str_or_none,
+    strftime_or_none,
     try_get,
-    unified_strdate,
     unified_timestamp,
     update_url_query,
     url_or_none,
@@ -411,70 +413,67 @@ class BandcampAlbumIE(BandcampIE):  # XXX: Do not subclass from concrete IE
 
 class BandcampWeeklyIE(BandcampIE):  # XXX: Do not subclass from concrete IE
     IE_NAME = 'Bandcamp:weekly'
-    _VALID_URL = r'https?://(?:www\.)?bandcamp\.com/?\?(?:.*?&)?show=(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:www\.)?bandcamp\.com/radio/?\?(?:[^#]+&)?show=(?P<id>\d+)'
     _TESTS = [{
-        'url': 'https://bandcamp.com/?show=224',
+        'url': 'https://bandcamp.com/radio?show=224',
         'md5': '61acc9a002bed93986b91168aa3ab433',
         'info_dict': {
             'id': '224',
             'ext': 'mp3',
-            'title': 'BC Weekly April 4th 2017 - Magic Moments',
+            'title': 'Bandcamp Weekly, 2017-04-04',
             'description': 'md5:5d48150916e8e02d030623a48512c874',
-            'duration': 5829.77,
-            'release_date': '20170404',
+            'thumbnail': 'https://f4.bcbits.com/img/9982549_0.jpg',
             'series': 'Bandcamp Weekly',
-            'episode': 'Magic Moments',
             'episode_id': '224',
+            'release_timestamp': 1491264000,
+            'release_date': '20170404',
+            'duration': 5829.77,
         },
         'params': {
             'format': 'mp3-128',
         },
     }, {
-        'url': 'https://bandcamp.com/?blah/blah@&show=228',
+        'url': 'https://bandcamp.com/radio/?foo=bar&show=224',
         'only_matching': True,
     }]
 
     def _real_extract(self, url):
         show_id = self._match_id(url)
-        webpage = self._download_webpage(url, show_id)
+        audio_data = self._download_json(
+            'https://bandcamp.com/api/bcradio_api/1/get_show',
+            show_id, 'Downloading radio show JSON',
+            data=json.dumps({'id': show_id}).encode(),
+            headers={'Content-Type': 'application/json'})['radioShowAudio']
 
-        blob = self._extract_data_attr(webpage, show_id, 'blob')
+        stream_url = audio_data['streamUrl']
+        format_id = traverse_obj(stream_url, ({parse_qs}, 'enc', -1))
+        encoding, _, bitrate_str = (format_id or '').partition('-')
 
-        show = blob['bcw_data'][show_id]
+        webpage = self._download_webpage(url, show_id, fatal=False)
+        metadata = traverse_obj(
+            self._extract_data_attr(webpage, show_id, 'blob', fatal=False),
+            ('appData', 'shows', lambda _, v: str(v['showId']) == show_id, any)) or {}
 
-        formats = []
-        for format_id, format_url in show['audio_stream'].items():
-            if not url_or_none(format_url):
-                continue
-            for known_ext in KNOWN_EXTENSIONS:
-                if known_ext in format_id:
-                    ext = known_ext
-                    break
-            else:
-                ext = None
-            formats.append({
-                'format_id': format_id,
-                'url': format_url,
-                'ext': ext,
-                'vcodec': 'none',
-            })
-
-        title = show.get('audio_title') or 'Bandcamp Weekly'
-        subtitle = show.get('subtitle')
-        if subtitle:
-            title += f' - {subtitle}'
+        series_title = audio_data.get('title') or metadata.get('title')
+        release_timestamp = unified_timestamp(audio_data.get('date')) or unified_timestamp(metadata.get('date'))
 
         return {
             'id': show_id,
-            'title': title,
-            'description': show.get('desc') or show.get('short_desc'),
-            'duration': float_or_none(show.get('audio_duration')),
-            'is_live': False,
-            'release_date': unified_strdate(show.get('published_date')),
-            'series': 'Bandcamp Weekly',
-            'episode': show.get('subtitle'),
             'episode_id': show_id,
-            'formats': formats,
+            'title': join_nonempty(series_title, strftime_or_none(release_timestamp, '%Y-%m-%d'), delim=', '),
+            'series': series_title,
+            'thumbnail': format_field(metadata, 'imageId', 'https://f4.bcbits.com/img/%s_0.jpg', default=None),
+            'description': metadata.get('desc') or metadata.get('short_desc'),
+            'duration': float_or_none(audio_data.get('duration')),
+            'release_timestamp': release_timestamp,
+            'formats': [{
+                'url': stream_url,
+                'format_id': format_id,
+                'ext': encoding or 'mp3',
+                'acodec': encoding or None,
+                'vcodec': 'none',
+                'abr': int_or_none(bitrate_str),
+            }],
         }
 
 

plugins/youtube_download/yt_dlp/extractor/bigo.py

@@ -1,5 +1,5 @@
 from .common import InfoExtractor
-from ..utils import ExtractorError, urlencode_postdata
+from ..utils import ExtractorError, UserNotLive, urlencode_postdata
 
 
 class BigoIE(InfoExtractor):
@@ -40,7 +40,7 @@ class BigoIE(InfoExtractor):
         info = info_raw.get('data') or {}
 
         if not info.get('alive'):
-            raise ExtractorError('This user is offline.', expected=True)
+            raise UserNotLive(video_id=user_id)
 
         formats, subs = self._extract_m3u8_formats_and_subtitles(
             info.get('hls_src'), user_id, 'mp4', 'm3u8')

plugins/youtube_download/yt_dlp/extractor/bitmovin.py

@@ -0,0 +1,74 @@
+import re
+
+from .common import InfoExtractor
+from ..utils.traversal import traverse_obj
+
+
+class BitmovinIE(InfoExtractor):
+    _VALID_URL = r'https?://streams\.bitmovin\.com/(?P<id>\w+)'
+    _EMBED_REGEX = [r'<iframe\b[^>]+\bsrc=["\'](?P<url>(?:https?:)?//streams\.bitmovin\.com/(?P<id>\w+)[^"\']+)']
+    _TESTS = [{
+        'url': 'https://streams.bitmovin.com/cqkl1t5giv3lrce7pjbg/embed',
+        'info_dict': {
+            'id': 'cqkl1t5giv3lrce7pjbg',
+            'ext': 'mp4',
+            'title': 'Developing Osteopathic Residents as Faculty',
+            'thumbnail': 'https://streams.bitmovin.com/cqkl1t5giv3lrce7pjbg/poster',
+        },
+        'params': {'skip_download': 'm3u8'},
+    }, {
+        'url': 'https://streams.bitmovin.com/cgl9rh94uvs51rqc8jhg/share',
+        'info_dict': {
+            'id': 'cgl9rh94uvs51rqc8jhg',
+            'ext': 'mp4',
+            'title': 'Big Buck Bunny (Streams Docs)',
+            'thumbnail': 'https://streams.bitmovin.com/cgl9rh94uvs51rqc8jhg/poster',
+        },
+        'params': {'skip_download': 'm3u8'},
+    }]
+    _WEBPAGE_TESTS = [{
+        # bitmovin-stream web component
+        'url': 'https://www.institutionalinvestor.com/article/2bsw1in1l9k68mp9kritc/video-war-stories-over-board-games/best-case-i-get-fired-war-stories',
+        'info_dict': {
+            'id': 'cuiumeil6g115lc4li3g',
+            'ext': 'mp4',
+            'title': '[media] War Stories over Board Games: “Best Case: I Get Fired” ',
+            'thumbnail': 'https://streams.bitmovin.com/cuiumeil6g115lc4li3g/poster',
+        },
+        'params': {'skip_download': 'm3u8'},
+    }, {
+        # iframe embed
+        'url': 'https://www.clearblueionizer.com/en/pool-ionizers/mineral-pool-vs-saltwater-pool/',
+        'info_dict': {
+            'id': 'cvpvfsm1pf7itg7cfvtg',
+            'ext': 'mp4',
+            'title': 'Pool Ionizer vs. Salt Chlorinator',
+            'thumbnail': 'https://streams.bitmovin.com/cvpvfsm1pf7itg7cfvtg/poster',
+        },
+        'params': {'skip_download': 'm3u8'},
+    }]
+
+    @classmethod
+    def _extract_embed_urls(cls, url, webpage):
+        yield from super()._extract_embed_urls(url, webpage)
+        for stream_id in re.findall(r'<bitmovin-stream\b[^>]*\bstream-id=["\'](?P<id>\w+)', webpage):
+            yield f'https://streams.bitmovin.com/{stream_id}'
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        player_config = self._download_json(
+            f'https://streams.bitmovin.com/{video_id}/config', video_id)['sources']
+
+        formats, subtitles = self._extract_m3u8_formats_and_subtitles(
+            player_config['hls'], video_id, 'mp4')
+
+        return {
+            'id': video_id,
+            'formats': formats,
+            'subtitles': subtitles,
+            **traverse_obj(player_config, {
+                'title': ('title', {str}),
+                'thumbnail': ('poster', {str}),
+            }),
+        }

plugins/youtube_download/yt_dlp/extractor/bunnycdn.py

@@ -16,7 +16,7 @@ from ..utils.traversal import find_element, traverse_obj
 
 
 class BunnyCdnIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:iframe\.mediadelivery\.net|video\.bunnycdn\.com)/(?:embed|play)/(?P<library_id>\d+)/(?P<id>[\da-f-]+)'
+    _VALID_URL = r'https?://(?:(?:iframe|player)\.mediadelivery\.net|video\.bunnycdn\.com)/(?:embed|play)/(?P<library_id>\d+)/(?P<id>[\da-f-]+)'
     _EMBED_REGEX = [rf'<iframe[^>]+src=[\'"](?P<url>{_VALID_URL}[^\'"]*)[\'"]']
     _TESTS = [{
         'url': 'https://iframe.mediadelivery.net/embed/113933/e73edec1-e381-4c8b-ae73-717a140e0924',
@@ -39,7 +39,7 @@ class BunnyCdnIE(InfoExtractor):
             'timestamp': 1691145748,
             'thumbnail': r're:^https?://.*\.b-cdn\.net/32e34c4b-0d72-437c-9abb-05e67657da34/thumbnail_9172dc16\.jpg',
             'duration': 106.0,
-            'description': 'md5:981a3e899a5c78352b21ed8b2f1efd81',
+            'description': 'md5:11452bcb31f379ee3eaf1234d3264e44',
             'upload_date': '20230804',
             'title': 'Sanela ist Teil der #arbeitsmarktkraft',
         },
@@ -58,6 +58,23 @@ class BunnyCdnIE(InfoExtractor):
             'thumbnail': r're:^https?://.*\.b-cdn\.net/2e8545ec-509d-4571-b855-4cf0235ccd75/thumbnail\.jpg',
         },
         'params': {'skip_download': True},
+    }, {
+        # Requires any Referer
+        'url': 'https://iframe.mediadelivery.net/embed/289162/6372f5a3-68df-4ef7-a115-e1110186c477',
+        'info_dict': {
+            'id': '6372f5a3-68df-4ef7-a115-e1110186c477',
+            'ext': 'mp4',
+            'title': '12-Creating Small Asset Blockouts -Timelapse.mp4',
+            'description': '',
+            'duration': 263.0,
+            'timestamp': 1724485440,
+            'upload_date': '20240824',
+            'thumbnail': r're:^https?://.*\.b-cdn\.net/6372f5a3-68df-4ef7-a115-e1110186c477/thumbnail\.jpg',
+        },
+        'params': {'skip_download': True},
+    }, {
+        'url': 'https://player.mediadelivery.net/embed/519128/875880a9-bcc2-4038-9e05-e5024bba9b70',
+        'only_matching': True,
     }]
     _WEBPAGE_TESTS = [{
         # Stream requires Referer
@@ -100,7 +117,7 @@ class BunnyCdnIE(InfoExtractor):
         video_id, library_id = self._match_valid_url(url).group('id', 'library_id')
         webpage = self._download_webpage(
             f'https://iframe.mediadelivery.net/embed/{library_id}/{video_id}', video_id,
-            headers=traverse_obj(smuggled_data, {'Referer': 'Referer'}),
+            headers={'Referer': smuggled_data.get('Referer') or 'https://iframe.mediadelivery.net/'},
             query=traverse_obj(parse_qs(url), {'token': 'token', 'expires': 'expires'}))
 
         if html_title := self._html_extract_title(webpage, default=None) == '403':

plugins/youtube_download/yt_dlp/extractor/cda.py

@@ -27,7 +27,7 @@ from ..utils.traversal import traverse_obj
 
 
 class CDAIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:(?:www\.)?cda\.pl/video|ebd\.cda\.pl/[0-9]+x[0-9]+)/(?P<id>[0-9a-z]+)'
+    _VALID_URL = r'https?://(?:(?:(?:www|m)\.)?cda\.pl/video|ebd\.cda\.pl/[0-9]+x[0-9]+)/(?P<id>[0-9a-z]+)'
     _NETRC_MACHINE = 'cdapl'
 
     _BASE_URL = 'https://www.cda.pl'
@@ -110,6 +110,9 @@ class CDAIE(InfoExtractor):
     }, {
         'url': 'http://ebd.cda.pl/0x0/5749950c',
         'only_matching': True,
+    }, {
+        'url': 'https://m.cda.pl/video/617297677',
+        'only_matching': True,
     }]
 
     def _download_age_confirm_page(self, url, video_id, *args, **kwargs):
@@ -367,35 +370,35 @@ class CDAIE(InfoExtractor):
 
 class CDAFolderIE(InfoExtractor):
     _MAX_PAGE_SIZE = 36
-    _VALID_URL = r'https?://(?:www\.)?cda\.pl/(?P<channel>[\w-]+)/folder/(?P<id>\d+)'
-    _TESTS = [
-        {
-            'url': 'https://www.cda.pl/domino264/folder/31188385',
-            'info_dict': {
-                'id': '31188385',
-                'title': 'SERIA DRUGA',
-            },
-            'playlist_mincount': 13,
+    _VALID_URL = r'https?://(?:(?:www|m)\.)?cda\.pl/(?P<channel>[\w-]+)/folder/(?P<id>\d+)'
+    _TESTS = [{
+        'url': 'https://www.cda.pl/domino264/folder/31188385',
+        'info_dict': {
+            'id': '31188385',
+            'title': 'SERIA DRUGA',
         },
-        {
-            'url': 'https://www.cda.pl/smiechawaTV/folder/2664592/vfilm',
-            'info_dict': {
-                'id': '2664592',
-                'title': 'VideoDowcipy - wszystkie odcinki',
-            },
-            'playlist_mincount': 71,
+        'playlist_mincount': 13,
+    }, {
+        'url': 'https://www.cda.pl/smiechawaTV/folder/2664592/vfilm',
+        'info_dict': {
+            'id': '2664592',
+            'title': 'VideoDowcipy - wszystkie odcinki',
         },
-        {
-            'url': 'https://www.cda.pl/DeliciousBeauty/folder/19129979/vfilm',
-            'info_dict': {
-                'id': '19129979',
-                'title': 'TESTY KOSMETYKÓW',
-            },
-            'playlist_mincount': 139,
-        }, {
-            'url': 'https://www.cda.pl/FILMY-SERIALE-ANIME-KRESKOWKI-BAJKI/folder/18493422',
-            'only_matching': True,
-        }]
+        'playlist_mincount': 71,
+    }, {
+        'url': 'https://www.cda.pl/DeliciousBeauty/folder/19129979/vfilm',
+        'info_dict': {
+            'id': '19129979',
+            'title': 'TESTY KOSMETYKÓW',
+        },
+        'playlist_mincount': 139,
+    }, {
+        'url': 'https://www.cda.pl/FILMY-SERIALE-ANIME-KRESKOWKI-BAJKI/folder/18493422',
+        'only_matching': True,
+    }, {
+        'url': 'https://m.cda.pl/smiechawaTV/folder/2664592/vfilm',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
         folder_id, channel = self._match_valid_url(url).group('id', 'channel')

plugins/youtube_download/yt_dlp/extractor/common.py

@@ -348,6 +348,7 @@ class InfoExtractor:
     duration:       Length of the video in seconds, as an integer or float.
     view_count:     How many users have watched the video on the platform.
     concurrent_view_count: How many users are currently watching the video on the platform.
+    save_count:     Number of times the video has been saved or bookmarked
     like_count:     Number of positive ratings of the video
     dislike_count:  Number of negative ratings of the video
     repost_count:   Number of reposts of the video

plugins/youtube_download/yt_dlp/extractor/croatianfilm.py

@@ -0,0 +1,79 @@
+from .common import InfoExtractor
+from .vimeo import VimeoIE
+from ..utils import (
+    ExtractorError,
+    join_nonempty,
+)
+from ..utils.traversal import traverse_obj
+
+
+class CroatianFilmIE(InfoExtractor):
+    IE_NAME = 'croatian.film'
+    _VALID_URL = r'https://?(?:www\.)?croatian\.film/[a-z]{2}/[^/?#]+/(?P<id>\d+)'
+    _GEO_COUNTRIES = ['HR']
+
+    _TESTS = [{
+        'url': 'https://www.croatian.film/hr/films/72472',
+        'info_dict': {
+            'id': '1078340774',
+            'ext': 'mp4',
+            'title': '“ŠKAFETIN”, r. Paško Vukasović',
+            'uploader': 'croatian.film',
+            'uploader_id': 'user94192658',
+            'uploader_url': 'https://vimeo.com/user94192658',
+            'duration': 1357,
+            'thumbnail': 'https://i.vimeocdn.com/video/2008556407-40eb1315ec11be5fcb8dda4d7059675b0881e182b9fc730892e267db72cb57f5-d',
+        },
+        'params': {'skip_download': 'm3u8'},
+        'expected_warnings': ['Failed to parse XML: not well-formed'],
+    }, {
+        # geo-restricted but works with xff
+        'url': 'https://www.croatian.film/en/films/77144',
+        'info_dict': {
+            'id': '1144997795',
+            'ext': 'mp4',
+            'title': '“ROKO” r. Ivana Marinić Kragić',
+            'uploader': 'croatian.film',
+            'uploader_id': 'user94192658',
+            'uploader_url': 'https://vimeo.com/user94192658',
+            'duration': 1023,
+            'thumbnail': 'https://i.vimeocdn.com/video/2093793231-11c2928698ff8347489e679b4d563a576e7acd0681ce95b383a9a25f6adb5e8f-d',
+        },
+        'params': {'skip_download': 'm3u8'},
+        'expected_warnings': ['Failed to parse XML: not well-formed'],
+    }, {
+        'url': 'https://www.croatian.film/en/films/75904/watch',
+        'info_dict': {
+            'id': '1134883757',
+            'ext': 'mp4',
+            'title': '"CARPE DIEM" r. Nina Damjanović',
+            'uploader': 'croatian.film',
+            'uploader_id': 'user94192658',
+            'uploader_url': 'https://vimeo.com/user94192658',
+            'duration': 1123,
+            'thumbnail': 'https://i.vimeocdn.com/video/2080022187-bb691c470c28c4d979258cf235e594bf9a11c14b837a0784326c25c95edd83f9-d',
+        },
+        'params': {'skip_download': 'm3u8'},
+        'expected_warnings': ['Failed to parse XML: not well-formed'],
+    }]
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        api_data = self._download_json(
+            f'https://api.croatian.film/api/videos/{display_id}',
+            display_id)
+
+        if errors := traverse_obj(api_data, ('errors', lambda _, v: v['code'])):
+            codes = traverse_obj(errors, (..., 'code', {str}))
+            if 'INVALID_COUNTRY' in codes:
+                self.raise_geo_restricted(countries=self._GEO_COUNTRIES)
+            raise ExtractorError(join_nonempty(
+                *(traverse_obj(errors, (..., 'details', {str})) or codes),
+                delim='; '))
+
+        vimeo_id = self._search_regex(
+            r'/videos/(\d+)', api_data['video']['vimeoURL'], 'vimeo ID')
+
+        return self.url_result(
+            VimeoIE._smuggle_referrer(f'https://player.vimeo.com/video/{vimeo_id}', url),
+            VimeoIE, vimeo_id)

plugins/youtube_download/yt_dlp/extractor/digiteka.py

@@ -1,5 +1,6 @@
 from .common import InfoExtractor
-from ..utils import int_or_none
+from ..utils import int_or_none, url_or_none
+from ..utils.traversal import traverse_obj
 
 
 class DigitekaIE(InfoExtractor):
@@ -25,74 +26,56 @@ class DigitekaIE(InfoExtractor):
         )/(?P<id>[\d+a-z]+)'''
     _EMBED_REGEX = [r'<(?:iframe|script)[^>]+src=["\'](?P<url>(?:https?:)?//(?:www\.)?ultimedia\.com/deliver/(?:generic|musique)(?:/[^/]+)*/(?:src|article)/[\d+a-z]+)']
     _TESTS = [{
-        # news
-        'url': 'https://www.ultimedia.com/default/index/videogeneric/id/s8uk0r',
-        'md5': '276a0e49de58c7e85d32b057837952a2',
+        'url': 'https://www.ultimedia.com/default/index/videogeneric/id/3x5x55k',
         'info_dict': {
-            'id': 's8uk0r',
+            'id': '3x5x55k',
             'ext': 'mp4',
-            'title': 'Loi sur la fin de vie: le texte prévoit un renforcement des directives anticipées',
+            'title': 'Il est passionné de DS',
             'thumbnail': r're:^https?://.*\.jpg',
-            'duration': 74,
-            'upload_date': '20150317',
-            'timestamp': 1426604939,
-            'uploader_id': '3fszv',
+            'duration': 89,
+            'upload_date': '20251012',
+            'timestamp': 1760285363,
+            'uploader_id': '3pz33',
         },
-    }, {
-        # music
-        'url': 'https://www.ultimedia.com/default/index/videomusic/id/xvpfp8',
-        'md5': '2ea3513813cf230605c7e2ffe7eca61c',
-        'info_dict': {
-            'id': 'xvpfp8',
-            'ext': 'mp4',
-            'title': 'Two - C\'est La Vie (clip)',
-            'thumbnail': r're:^https?://.*\.jpg',
-            'duration': 233,
-            'upload_date': '20150224',
-            'timestamp': 1424760500,
-            'uploader_id': '3rfzk',
-        },
-    }, {
-        'url': 'https://www.digiteka.net/deliver/generic/iframe/mdtk/01637594/src/lqm3kl/zone/1/showtitle/1/autoplay/yes',
-        'only_matching': True,
+        'params': {'skip_download': True},
     }]
+    _IFRAME_MD_ID = '01836272'   # One static ID working for Ultimedia iframes
 
     def _real_extract(self, url):
-        mobj = self._match_valid_url(url)
-        video_id = mobj.group('id')
-        video_type = mobj.group('embed_type') or mobj.group('site_type')
-        if video_type == 'music':
-            video_type = 'musique'
+        video_id = self._match_id(url)
 
-        deliver_info = self._download_json(
-            f'http://www.ultimedia.com/deliver/video?video={video_id}&topic={video_type}',
-            video_id)
-
-        yt_id = deliver_info.get('yt_id')
-        if yt_id:
-            return self.url_result(yt_id, 'Youtube')
-
-        jwconf = deliver_info['jwconf']
+        video_info = self._download_json(
+            f'https://www.ultimedia.com/player/getConf/{self._IFRAME_MD_ID}/1/{video_id}', video_id,
+            note='Downloading player configuration')['video']
 
         formats = []
-        for source in jwconf['playlist'][0]['sources']:
-            formats.append({
-                'url': source['file'],
-                'format_id': source.get('label'),
-            })
+        subtitles = {}
 
-        title = deliver_info['title']
-        thumbnail = jwconf.get('image')
-        duration = int_or_none(deliver_info.get('duration'))
-        timestamp = int_or_none(deliver_info.get('release_time'))
-        uploader_id = deliver_info.get('owner_id')
+        if hls_url := traverse_obj(video_info, ('media_sources', 'hls', 'hls_auto', {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)
+
+        for format_id, mp4_url in traverse_obj(video_info, ('media_sources', 'mp4', {dict.items}, ...)):
+            if not mp4_url:
+                continue
+            formats.append({
+                'url': mp4_url,
+                'format_id': format_id,
+                'height': int_or_none(format_id.partition('_')[2]),
+                'ext': 'mp4',
+            })
 
         return {
             'id': video_id,
-            'title': title,
-            'thumbnail': thumbnail,
-            'duration': duration,
-            'timestamp': timestamp,
-            'uploader_id': uploader_id,
             'formats': formats,
+            'subtitles': subtitles,
+            **traverse_obj(video_info, {
+                'title': ('title', {str}),
+                'thumbnail': ('image', {url_or_none}),
+                'duration': ('duration', {int_or_none}),
+                'timestamp': ('creationDate', {int_or_none}),
+                'uploader_id': ('ownerId', {str}),
+            }),
         }

plugins/youtube_download/yt_dlp/extractor/dplay.py

@@ -13,6 +13,7 @@ from ..utils import (
     try_get,
     unified_timestamp,
 )
+from ..utils.traversal import traverse_obj
 
 
 class DPlayBaseIE(InfoExtractor):
@@ -1053,7 +1054,7 @@ class DiscoveryPlusIndiaIE(DiscoveryPlusBaseIE):
 
 
 class DiscoveryNetworksDeIE(DiscoveryPlusBaseIE):
-    _VALID_URL = r'https?://(?:www\.)?(?P<domain>(?:tlc|dmax)\.de|dplay\.co\.uk)/(?:programme|show|sendungen)/(?P<programme>[^/]+)/(?:video/)?(?P<alternate_id>[^/]+)'
+    _VALID_URL = r'https?://(?:www\.)?(?P<domain>(?:tlc|dmax)\.de)/(?:programme|show|sendungen)/(?P<programme>[^/?#]+)/(?:video/)?(?P<alternate_id>[^/?#]+)'
 
     _TESTS = [{
         'url': 'https://dmax.de/sendungen/goldrausch-in-australien/german-gold',
@@ -1074,6 +1075,7 @@ class DiscoveryNetworksDeIE(DiscoveryPlusBaseIE):
             'creators': ['DMAX'],
             'thumbnail': 'https://eu1-prod-images.disco-api.com/2023/05/09/f72fb510-7992-3b12-af7f-f16a2c22d1e3.jpeg',
             'tags': ['schatzsucher', 'schatz', 'nugget', 'bodenschätze', 'down under', 'australien', 'goldrausch'],
+            'categories': ['Gold', 'Schatzsucher'],
         },
         'params': {'skip_download': 'm3u8'},
     }, {
@@ -1100,20 +1102,96 @@ class DiscoveryNetworksDeIE(DiscoveryPlusBaseIE):
     }, {
         'url': 'https://www.dmax.de/programme/dmax-highlights/video/tuning-star-sidney-hoffmann-exklusiv-bei-dmax/191023082312316',
         'only_matching': True,
-    }, {
-        'url': 'https://www.dplay.co.uk/show/ghost-adventures/video/hotel-leger-103620/EHD_280313B',
-        'only_matching': True,
     }, {
         'url': 'https://tlc.de/sendungen/breaking-amish/die-welt-da-drauen/',
         'only_matching': True,
+    }, {
+        'url': 'https://dmax.de/sendungen/feuerwache-3-alarm-in-muenchen/24-stunden-auf-der-feuerwache-3',
+        'info_dict': {
+            'id': '8873549',
+            'ext': 'mp4',
+            'title': '24 Stunden auf der Feuerwache 3',
+            'description': 'md5:f3084ef6170bfb79f9a6e0c030e09330',
+            'display_id': 'feuerwache-3-alarm-in-muenchen/24-stunden-auf-der-feuerwache-3',
+            'episode': 'Episode 1',
+            'episode_number': 1,
+            'season': 'Season 1',
+            'season_number': 1,
+            'series': 'Feuerwache 3 - Alarm in München',
+            'duration': 2632.0,
+            'upload_date': '20251016',
+            'timestamp': 1760645100,
+            'creators': ['DMAX'],
+            'thumbnail': 'https://eu1-prod-images.disco-api.com/2025/10/14/0bdee68c-a8d8-33d9-9204-16eb61108552.jpeg',
+            'tags': [],
+            'categories': ['DMAX Originals', 'Jobs', 'Blaulicht'],
+        },
+        'params': {'skip_download': 'm3u8'},
+    }, {
+        'url': 'https://tlc.de/sendungen/ghost-adventures/der-poltergeist-im-kostumladen',
+        'info_dict': {
+            'id': '4550602',
+            'ext': 'mp4',
+            'title': 'Der Poltergeist im Kostümladen',
+            'description': 'md5:20b52b9736a0a3a7873d19a238fad7fc',
+            'display_id': 'ghost-adventures/der-poltergeist-im-kostumladen',
+            'episode': 'Episode 1',
+            'episode_number': 1,
+            'season': 'Season 25',
+            'season_number': 25,
+            'series': 'Ghost Adventures',
+            'duration': 2493.0,
+            'upload_date': '20241223',
+            'timestamp': 1734948900,
+            'creators': ['TLC'],
+            'thumbnail': 'https://eu1-prod-images.disco-api.com/2023/04/05/59941d26-a81b-365f-829f-69d8cd81fd0f.jpeg',
+            'tags': [],
+            'categories': ['Paranormal', 'Gruselig!'],
+        },
+        'params': {'skip_download': 'm3u8'},
+    }, {
+        'url': 'https://tlc.de/sendungen/evil-gesichter-des-boesen/das-geheimnis-meines-bruders',
+        'info_dict': {
+            'id': '7792288',
+            'ext': 'mp4',
+            'title': 'Das Geheimnis meines Bruders',
+            'description': 'md5:3167550bb582eb9c92875c86a0a20882',
+            'display_id': 'evil-gesichter-des-boesen/das-geheimnis-meines-bruders',
+            'episode': 'Episode 1',
+            'episode_number': 1,
+            'season': 'Season 1',
+            'season_number': 1,
+            'series': 'Evil - Gesichter des Bösen',
+            'duration': 2626.0,
+            'upload_date': '20240926',
+            'timestamp': 1727388000,
+            'creators': ['TLC'],
+            'thumbnail': 'https://eu1-prod-images.disco-api.com/2024/11/29/e9f3e3ae-74ec-3631-81b7-fc7bbe844741.jpeg',
+            'tags': 'count:13',
+            'categories': ['True Crime', 'Mord'],
+        },
+        'params': {'skip_download': 'm3u8'},
     }]
 
     def _real_extract(self, url):
         domain, programme, alternate_id = self._match_valid_url(url).groups()
-        country = 'GB' if domain == 'dplay.co.uk' else 'DE'
-        realm = 'questuk' if country == 'GB' else domain.replace('.', '')
-        return self._get_disco_api_info(
-            url, f'{programme}/{alternate_id}', 'eu1-prod.disco-api.com', realm, country)
+        display_id = f'{programme}/{alternate_id}'
+        meta = self._download_json(
+            f'https://de-api.loma-cms.com/feloma/videos/{alternate_id}/',
+            display_id, query={
+                'environment': domain.split('.')[0],
+                'v': '2',
+                'filter[show.slug]': programme,
+            }, fatal=False)
+        video_id = traverse_obj(meta, ('uid', {str}, {lambda s: s[-7:]})) or display_id
+
+        disco_api_info = self._get_disco_api_info(
+            url, video_id, 'eu1-prod.disco-api.com', domain.replace('.', ''), 'DE')
+        disco_api_info['display_id'] = display_id
+        disco_api_info['categories'] = traverse_obj(meta, (
+            'taxonomies', lambda _, v: v['category'] == 'genre', 'title', {str.strip}, filter, all, filter))
+
+        return disco_api_info
 
     def _update_disco_api_headers(self, headers, disco_base, display_id, realm):
         headers.update({

plugins/youtube_download/yt_dlp/extractor/dropbox.py

@@ -14,7 +14,7 @@ from ..utils import (
 
 
 class DropboxIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?dropbox\.com/(?:(?:e/)?scl/fi|sh?)/(?P<id>\w+)'
+    _VALID_URL = r'https?://(?:www\.)?dropbox\.com/(?:(?:e/)?scl/f[io]|sh?)/(?P<id>\w+)'
     _TESTS = [
         {
             'url': 'https://www.dropbox.com/s/nelirfsxnmcfbfh/youtube-dl%20test%20video%20%27%C3%A4%22BaW_jenozKc.mp4?dl=0',
@@ -35,6 +35,9 @@ class DropboxIE(InfoExtractor):
         }, {
             'url': 'https://www.dropbox.com/e/scl/fi/r2kd2skcy5ylbbta5y1pz/DJI_0003.MP4?dl=0&rlkey=wcdgqangn7t3lnmmv6li9mu9h',
             'only_matching': True,
+        }, {
+            'url': 'https://www.dropbox.com/scl/fo/zjfqse5txqfd7twa8iewj/AOfZzSYWUSKle2HD7XF7kzQ/A-BEAT%20C.mp4?rlkey=6tg3jkp4tv6a5vt58a6dag0mm&dl=0',
+            'only_matching': True,
         },
     ]
 

plugins/youtube_download/yt_dlp/extractor/facebook.py

@@ -4,8 +4,6 @@ import urllib.parse
 
 from .common import InfoExtractor
 from ..compat import compat_etree_fromstring
-from ..networking import Request
-from ..networking.exceptions import network_exceptions
 from ..utils import (
     ExtractorError,
     clean_html,
@@ -64,9 +62,6 @@ class FacebookIE(InfoExtractor):
                 class=(?P<q1>[\'"])[^\'"]*\bfb-(?:video|post)\b[^\'"]*(?P=q1)[^>]+
                 data-href=(?P<q2>[\'"])(?P<url>(?:https?:)?//(?:www\.)?facebook.com/.+?)(?P=q2)''',
     ]
-    _LOGIN_URL = 'https://www.facebook.com/login.php?next=http%3A%2F%2Ffacebook.com%2Fhome.php&login_attempt=1'
-    _CHECKPOINT_URL = 'https://www.facebook.com/checkpoint/?next=http%3A%2F%2Ffacebook.com%2Fhome.php&_fb_noscript=1'
-    _NETRC_MACHINE = 'facebook'
     IE_NAME = 'facebook'
 
     _VIDEO_PAGE_TEMPLATE = 'https://www.facebook.com/video/video.php?v=%s'
@@ -469,65 +464,6 @@ class FacebookIE(InfoExtractor):
         'graphURI': '/api/graphql/',
     }
 
-    def _perform_login(self, username, password):
-        login_page_req = Request(self._LOGIN_URL)
-        self._set_cookie('facebook.com', 'locale', 'en_US')
-        login_page = self._download_webpage(login_page_req, None,
-                                            note='Downloading login page',
-                                            errnote='Unable to download login page')
-        lsd = self._search_regex(
-            r'<input type="hidden" name="lsd" value="([^"]*)"',
-            login_page, 'lsd')
-        lgnrnd = self._search_regex(r'name="lgnrnd" value="([^"]*?)"', login_page, 'lgnrnd')
-
-        login_form = {
-            'email': username,
-            'pass': password,
-            'lsd': lsd,
-            'lgnrnd': lgnrnd,
-            'next': 'http://facebook.com/home.php',
-            'default_persistent': '0',
-            'legacy_return': '1',
-            'timezone': '-60',
-            'trynum': '1',
-        }
-        request = Request(self._LOGIN_URL, urlencode_postdata(login_form))
-        request.headers['Content-Type'] = 'application/x-www-form-urlencoded'
-        try:
-            login_results = self._download_webpage(request, None,
-                                                   note='Logging in', errnote='unable to fetch login page')
-            if re.search(r'<form(.*)name="login"(.*)</form>', login_results) is not None:
-                error = self._html_search_regex(
-                    r'(?s)<div[^>]+class=(["\']).*?login_error_box.*?\1[^>]*><div[^>]*>.*?</div><div[^>]*>(?P<error>.+?)</div>',
-                    login_results, 'login error', default=None, group='error')
-                if error:
-                    raise ExtractorError(f'Unable to login: {error}', expected=True)
-                self.report_warning('unable to log in: bad username/password, or exceeded login rate limit (~3/min). Check credentials or wait.')
-                return
-
-            fb_dtsg = self._search_regex(
-                r'name="fb_dtsg" value="(.+?)"', login_results, 'fb_dtsg', default=None)
-            h = self._search_regex(
-                r'name="h"\s+(?:\w+="[^"]+"\s+)*?value="([^"]+)"', login_results, 'h', default=None)
-
-            if not fb_dtsg or not h:
-                return
-
-            check_form = {
-                'fb_dtsg': fb_dtsg,
-                'h': h,
-                'name_action_selected': 'dont_save',
-            }
-            check_req = Request(self._CHECKPOINT_URL, urlencode_postdata(check_form))
-            check_req.headers['Content-Type'] = 'application/x-www-form-urlencoded'
-            check_response = self._download_webpage(check_req, None,
-                                                    note='Confirming login')
-            if re.search(r'id="checkpointSubmitButton"', check_response) is not None:
-                self.report_warning('Unable to confirm login, you have to login in your browser and authorize the login.')
-        except network_exceptions as err:
-            self.report_warning(f'unable to log in: {err}')
-            return
-
     def _extract_from_url(self, url, video_id):
         webpage = self._download_webpage(
             url.replace('://m.facebook.com/', '://www.facebook.com/'), video_id)

plugins/youtube_download/yt_dlp/extractor/fc2.py

@@ -5,6 +5,7 @@ from .common import InfoExtractor
 from ..networking import Request
 from ..utils import (
     ExtractorError,
+    UserNotLive,
     js_to_json,
     traverse_obj,
     update_url_query,
@@ -205,6 +206,9 @@ class FC2LiveIE(InfoExtractor):
                 'client_app': 'browser_hls',
                 'ipv6': '',
             }), headers={'X-Requested-With': 'XMLHttpRequest'})
+        # A non-zero 'status' indicates the stream is not live, so check truthiness
+        if traverse_obj(control_server, ('status', {int})) and 'control_token' not in control_server:
+            raise UserNotLive(video_id=video_id)
         self._set_cookie('live.fc2.com', 'l_ortkn', control_server['orz_raw'])
 
         ws_url = update_url_query(control_server['url'], {'control_token': control_server['control_token']})

plugins/youtube_download/yt_dlp/extractor/filmarchiv.py

@@ -0,0 +1,52 @@
+from .common import InfoExtractor
+from ..utils import clean_html
+from ..utils.traversal import (
+    find_element,
+    find_elements,
+    traverse_obj,
+)
+
+
+class FilmArchivIE(InfoExtractor):
+    IE_DESC = 'FILMARCHIV ON'
+    _VALID_URL = r'https?://(?:www\.)?filmarchiv\.at/de/filmarchiv-on/video/(?P<id>f_[0-9a-zA-Z]{5,})'
+    _TESTS = [{
+        'url': 'https://www.filmarchiv.at/de/filmarchiv-on/video/f_0305p7xKrXUPBwoNE9x6mh',
+        'md5': '54a6596f6a84624531866008a77fa27a',
+        'info_dict': {
+            'id': 'f_0305p7xKrXUPBwoNE9x6mh',
+            'ext': 'mp4',
+            'title': 'Der Wurstelprater zur Kaiserzeit',
+            'description': 'md5:9843f92df5cc9a4975cee7aabcf6e3b2',
+            'thumbnail': r're:https://cdn\.filmarchiv\.at/f_0305/p7xKrXUPBwoNE9x6mh_v1/poster\.jpg',
+        },
+    }, {
+        'url': 'https://www.filmarchiv.at/de/filmarchiv-on/video/f_0306vI3wO0tJIsfrqYFQXF',
+        'md5': '595385d7f54cb6529140ee8de7d1c3c7',
+        'info_dict': {
+            'id': 'f_0306vI3wO0tJIsfrqYFQXF',
+            'ext': 'mp4',
+            'title': 'Vor 70 Jahren: Wettgehen der Briefträger in Wien',
+            'description': 'md5:b2a2e4230923cd1969d471c552e62811',
+            'thumbnail': r're:https://cdn\.filmarchiv\.at/f_0306/vI3wO0tJIsfrqYFQXF_v1/poster\.jpg',
+        },
+    }]
+
+    def _real_extract(self, url):
+        media_id = self._match_id(url)
+        webpage = self._download_webpage(url, media_id)
+        path = '/'.join((media_id[:6], media_id[6:]))
+        formats, subtitles = self._extract_m3u8_formats_and_subtitles(
+            f'https://cdn.filmarchiv.at/{path}_v1_sv1/playlist.m3u8', media_id)
+
+        return {
+            'id': media_id,
+            'title': traverse_obj(webpage, ({find_element(tag='title-div')}, {clean_html})),
+            'description': traverse_obj(webpage, (
+                {find_elements(tag='div', attr='class', value=r'.*\bborder-base-content\b', regex=True)}, ...,
+                {find_elements(tag='div', attr='class', value=r'.*\bprose\b', html=False, regex=True)}, ...,
+                {clean_html}, any)),
+            'thumbnail': f'https://cdn.filmarchiv.at/{path}_v1/poster.jpg',
+            'formats': formats,
+            'subtitles': subtitles,
+        }

plugins/youtube_download/yt_dlp/extractor/firsttv.py

@@ -10,7 +10,7 @@ from ..utils import (
     unified_strdate,
     url_or_none,
 )
-from ..utils.traversal import traverse_obj
+from ..utils.traversal import require, traverse_obj
 
 
 class FirstTVIE(InfoExtractor):
@@ -129,3 +129,36 @@ class FirstTVIE(InfoExtractor):
         return self.playlist_result(
             self._entries(items), display_id, self._og_search_title(webpage, default=None),
             thumbnail=self._og_search_thumbnail(webpage, default=None))
+
+
+class FirstTVLiveIE(InfoExtractor):
+    IE_NAME = '1tv:live'
+    IE_DESC = 'Первый канал (прямой эфир)'
+    _VALID_URL = r'https?://(?:www\.)?1tv\.ru/live'
+
+    _TESTS = [{
+        'url': 'https://www.1tv.ru/live',
+        'info_dict': {
+            'id': 'live',
+            'ext': 'mp4',
+            'title': r're:ПЕРВЫЙ КАНАЛ ПРЯМОЙ ЭФИР СМОТРЕТЬ ОНЛАЙН \d{4}-\d{2}-\d{2} \d{2}:\d{2}$',
+            'live_status': 'is_live',
+        },
+        'params': {'skip_download': 'livestream'},
+    }]
+
+    def _real_extract(self, url):
+        display_id = 'live'
+        webpage = self._download_webpage(url, display_id, fatal=False)
+
+        streams_list = self._download_json('https://stream.1tv.ru/api/playlist/1tvch-v1_as_array.json', display_id)
+        mpd_url = traverse_obj(streams_list, ('mpd', ..., {url_or_none}, any, {require('mpd url')}))
+        # FFmpeg needs to be passed -re to not seek past live window. This is handled by core
+        formats, _ = self._extract_mpd_formats_and_subtitles(mpd_url, display_id, mpd_id='dash')
+
+        return {
+            'id': display_id,
+            'title': self._html_extract_title(webpage),
+            'formats': formats,
+            'is_live': True,
+        }

plugins/youtube_download/yt_dlp/extractor/floatplane.py

@@ -6,15 +6,15 @@ from ..utils import (
     OnDemandPagedList,
     clean_html,
     determine_ext,
+    float_or_none,
     format_field,
     int_or_none,
     join_nonempty,
-    parse_codecs,
     parse_iso8601,
     url_or_none,
     urljoin,
 )
-from ..utils.traversal import traverse_obj
+from ..utils.traversal import require, traverse_obj
 
 
 class FloatplaneBaseIE(InfoExtractor):
@@ -50,37 +50,31 @@ class FloatplaneBaseIE(InfoExtractor):
             media_id = media['id']
             media_typ = media.get('type') or 'video'
 
-            metadata = self._download_json(
-                f'{self._BASE_URL}/api/v3/content/{media_typ}', media_id, query={'id': media_id},
-                note=f'Downloading {media_typ} metadata', impersonate=self._IMPERSONATE_TARGET)
-
             stream = self._download_json(
-                f'{self._BASE_URL}/api/v2/cdn/delivery', media_id, query={
-                    'type': 'vod' if media_typ == 'video' else 'aod',
-                    'guid': metadata['guid'],
-                }, note=f'Downloading {media_typ} stream data',
+                f'{self._BASE_URL}/api/v3/delivery/info', media_id,
+                query={'scenario': 'onDemand', 'entityId': media_id},
+                note=f'Downloading {media_typ} stream data',
                 impersonate=self._IMPERSONATE_TARGET)
 
-            path_template = traverse_obj(stream, ('resource', 'uri', {str}))
+            metadata = self._download_json(
+                f'{self._BASE_URL}/api/v3/content/{media_typ}', media_id,
+                f'Downloading {media_typ} metadata', query={'id': media_id},
+                fatal=False, impersonate=self._IMPERSONATE_TARGET)
 
-            def format_path(params):
-                path = path_template
-                for i, val in (params or {}).items():
-                    path = path.replace(f'{{qualityLevelParams.{i}}}', val)
-                return path
+            cdn_base_url = traverse_obj(stream, (
+                'groups', 0, 'origins', ..., 'url', {url_or_none}, any, {require('cdn base url')}))
 
             formats = []
-            for quality in traverse_obj(stream, ('resource', 'data', 'qualityLevels', ...)):
-                url = urljoin(stream['cdn'], format_path(traverse_obj(
-                    stream, ('resource', 'data', 'qualityLevelParams', quality['name'], {dict}))))
-                format_id = traverse_obj(quality, ('name', {str}))
+            for variant in traverse_obj(stream, ('groups', 0, 'variants', lambda _, v: v['url'])):
+                format_url = urljoin(cdn_base_url, variant['url'])
+                format_id = traverse_obj(variant, ('name', {str}))
                 hls_aes = {}
                 m3u8_data = None
 
                 # If we need impersonation for the API, then we need it for HLS keys too: extract in advance
                 if self._IMPERSONATE_TARGET is not None:
                     m3u8_data = self._download_webpage(
-                        url, media_id, fatal=False, impersonate=self._IMPERSONATE_TARGET, headers=self._HEADERS,
+                        format_url, media_id, fatal=False, impersonate=self._IMPERSONATE_TARGET, headers=self._HEADERS,
                         note=join_nonempty('Downloading', format_id, 'm3u8 information', delim=' '),
                         errnote=join_nonempty('Failed to download', format_id, 'm3u8 information', delim=' '))
                     if not m3u8_data:
@@ -98,18 +92,34 @@ class FloatplaneBaseIE(InfoExtractor):
                             hls_aes['key'] = urlh.read().hex()
 
                 formats.append({
-                    **traverse_obj(quality, {
+                    **traverse_obj(variant, {
                         'format_note': ('label', {str}),
-                        'width': ('width', {int}),
-                        'height': ('height', {int}),
+                        'width': ('meta', 'video', 'width', {int_or_none}),
+                        'height': ('meta', 'video', 'height', {int_or_none}),
+                        'vcodec': ('meta', 'video', 'codec', {str}),
+                        'acodec': ('meta', 'audio', 'codec', {str}),
+                        'vbr': ('meta', 'video', 'bitrate', 'average', {int_or_none(scale=1000)}),
+                        'abr': ('meta', 'audio', 'bitrate', 'average', {int_or_none(scale=1000)}),
+                        'audio_channels': ('meta', 'audio', 'channelCount', {int_or_none}),
+                        'fps': ('meta', 'video', 'fps', {float_or_none}),
                     }),
-                    **parse_codecs(quality.get('codecs')),
-                    'url': url,
-                    'ext': determine_ext(url.partition('/chunk.m3u8')[0], 'mp4'),
+                    'url': format_url,
+                    'ext': determine_ext(format_url.partition('/chunk.m3u8')[0], 'mp4'),
                     'format_id': format_id,
                     'hls_media_playlist_data': m3u8_data,
                     'hls_aes': hls_aes or None,
                 })
+
+            subtitles = {}
+            automatic_captions = {}
+            for sub_data in traverse_obj(metadata, ('textTracks', lambda _, v: url_or_none(v['src']))):
+                sub_lang = sub_data.get('language') or 'en'
+                sub_entry = {'url': sub_data['src']}
+                if sub_data.get('generated'):
+                    automatic_captions.setdefault(sub_lang, []).append(sub_entry)
+                else:
+                    subtitles.setdefault(sub_lang, []).append(sub_entry)
+
             items.append({
                 **common_info,
                 'id': media_id,
@@ -119,6 +129,8 @@ class FloatplaneBaseIE(InfoExtractor):
                     'thumbnail': ('thumbnail', 'path', {url_or_none}),
                 }),
                 'formats': formats,
+                'subtitles': subtitles,
+                'automatic_captions': automatic_captions,
             })
 
         post_info = {

plugins/youtube_download/yt_dlp/extractor/frontro.py

@@ -0,0 +1,164 @@
+import json
+
+from .common import InfoExtractor
+from ..utils import int_or_none, parse_iso8601, url_or_none
+from ..utils.traversal import traverse_obj
+
+
+class FrontoBaseIE(InfoExtractor):
+    def _get_auth_headers(self, url):
+        return traverse_obj(self._get_cookies(url), {
+            'authorization': ('frAccessToken', 'value', {lambda token: f'Bearer {token}' if token else None}),
+        })
+
+
+class FrontroVideoBaseIE(FrontoBaseIE):
+    _CHANNEL_ID = None
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        metadata = self._download_json(
+            'https://api.frontrow.cc/query', video_id, data=json.dumps({
+                'operationName': 'Video',
+                'variables': {'channelID': self._CHANNEL_ID, 'videoID': video_id},
+                'query': '''query Video($channelID: ID!, $videoID: ID!) {
+                    video(ChannelID: $channelID, VideoID: $videoID) {
+                        ... on Video {title description updatedAt thumbnail createdAt duration likeCount comments views url hasAccess}
+                    }
+                }''',
+            }).encode(), headers={
+                'content-type': 'application/json',
+                **self._get_auth_headers(url),
+            })['data']['video']
+        if not traverse_obj(metadata, 'hasAccess'):
+            self.raise_login_required()
+
+        formats, subtitles = self._extract_m3u8_formats_and_subtitles(metadata['url'], video_id)
+
+        return {
+            'id': video_id,
+            'formats': formats,
+            'subtitles': subtitles,
+            **traverse_obj(metadata, {
+                'title': ('title', {str}),
+                'description': ('description', {str}),
+                'thumbnail': ('thumbnail', {url_or_none}),
+                'timestamp': ('createdAt', {parse_iso8601}),
+                'modified_timestamp': ('updatedAt', {parse_iso8601}),
+                'duration': ('duration', {int_or_none}),
+                'like_count': ('likeCount', {int_or_none}),
+                'comment_count': ('comments', {int_or_none}),
+                'view_count': ('views', {int_or_none}),
+            }),
+        }
+
+
+class FrontroGroupBaseIE(FrontoBaseIE):
+    _CHANNEL_ID = None
+    _VIDEO_EXTRACTOR = None
+    _VIDEO_URL_TMPL = None
+
+    def _real_extract(self, url):
+        group_id = self._match_id(url)
+
+        metadata = self._download_json(
+            'https://api.frontrow.cc/query', group_id, note='Downloading playlist metadata',
+            data=json.dumps({
+                'operationName': 'PaginatedStaticPageContainer',
+                'variables': {'channelID': self._CHANNEL_ID, 'first': 500, 'pageContainerID': group_id},
+                'query': '''query PaginatedStaticPageContainer($channelID: ID!, $pageContainerID: ID!) {
+                              pageContainer(ChannelID: $channelID, PageContainerID: $pageContainerID) {
+                                ... on StaticPageContainer { id title updatedAt createdAt itemRefs {edges {node {
+                                        id contentItem { ... on ItemVideo { videoItem: item {
+                                            id
+                                        }}}
+                                    }}}
+                                }
+                              }
+                            }''',
+            }).encode(), headers={
+                'content-type': 'application/json',
+                **self._get_auth_headers(url),
+            })['data']['pageContainer']
+
+        entries = []
+        for video_id in traverse_obj(metadata, (
+            'itemRefs', 'edges', ..., 'node', 'contentItem', 'videoItem', 'id', {str}),
+        ):
+            entries.append(self.url_result(
+                self._VIDEO_URL_TMPL % video_id, self._VIDEO_EXTRACTOR, video_id))
+
+        return {
+            '_type': 'playlist',
+            'id': group_id,
+            'entries': entries,
+            **traverse_obj(metadata, {
+                'title': ('title', {str}),
+                'timestamp': ('createdAt', {parse_iso8601}),
+                'modified_timestamp': ('updatedAt', {parse_iso8601}),
+            }),
+        }
+
+
+class TheChosenIE(FrontroVideoBaseIE):
+    _CHANNEL_ID = '12884901895'
+
+    _VALID_URL = r'https?://(?:www\.)?watch\.thechosen\.tv/video/(?P<id>[0-9]+)'
+    _TESTS = [{
+        'url': 'https://watch.thechosen.tv/video/184683594325',
+        'md5': '3f878b689588c71b38ec9943c54ff5b0',
+        'info_dict': {
+            'id': '184683594325',
+            'ext': 'mp4',
+            'title': 'Season 3 Episode 2: Two by Two',
+            'description': 'md5:174c373756ecc8df46b403f4fcfbaf8c',
+            'comment_count': int,
+            'view_count': int,
+            'like_count': int,
+            'duration': 4212,
+            'thumbnail': r're:https://fastly\.frontrowcdn\.com/channels/12884901895/VIDEO_THUMBNAIL/184683594325/',
+            'timestamp': 1698954546,
+            'upload_date': '20231102',
+            'modified_timestamp': int,
+            'modified_date': str,
+        },
+    }, {
+        'url': 'https://watch.thechosen.tv/video/184683596189',
+        'md5': 'd581562f9d29ce82f5b7770415334151',
+        'info_dict': {
+            'id': '184683596189',
+            'ext': 'mp4',
+            'title': 'Season 4 Episode 8: Humble',
+            'description': 'md5:20a57bead43da1cf77cd5b0fe29bbc76',
+            'comment_count': int,
+            'view_count': int,
+            'like_count': int,
+            'duration': 5092,
+            'thumbnail': r're:https://fastly\.frontrowcdn\.com/channels/12884901895/VIDEO_THUMBNAIL/184683596189/',
+            'timestamp': 1715019474,
+            'upload_date': '20240506',
+            'modified_timestamp': int,
+            'modified_date': str,
+        },
+    }]
+
+
+class TheChosenGroupIE(FrontroGroupBaseIE):
+    _CHANNEL_ID = '12884901895'
+    _VIDEO_EXTRACTOR = TheChosenIE
+    _VIDEO_URL_TMPL = 'https://watch.thechosen.tv/video/%s'
+
+    _VALID_URL = r'https?://(?:www\.)?watch\.thechosen\.tv/group/(?P<id>[0-9]+)'
+    _TESTS = [{
+        'url': 'https://watch.thechosen.tv/group/309237658592',
+        'info_dict': {
+            'id': '309237658592',
+            'title': 'Season 3',
+            'timestamp': 1746203969,
+            'upload_date': '20250502',
+            'modified_timestamp': int,
+            'modified_date': str,
+        },
+        'playlist_count': 8,
+    }]

plugins/youtube_download/yt_dlp/extractor/generic.py

@@ -821,13 +821,17 @@ class GenericIE(InfoExtractor):
                 'Referer': smuggled_data.get('referer'),
             }), impersonate=impersonate)
         except ExtractorError as e:
-            if not (isinstance(e.cause, HTTPError) and e.cause.status == 403
-                    and e.cause.response.get_header('cf-mitigated') == 'challenge'
-                    and e.cause.response.extensions.get('impersonate') is None):
+            if not isinstance(e.cause, HTTPError) or e.cause.status != 403:
+                raise
+            res = e.cause.response
+            already_impersonating = res.extensions.get('impersonate') is not None
+            if already_impersonating or (
+                res.get_header('cf-mitigated') != 'challenge'
+                and b'<title>Attention Required! | Cloudflare</title>' not in res.read()
+            ):
                 raise
             cf_cookie_domain = traverse_obj(
-                LenientSimpleCookie(e.cause.response.get_header('set-cookie')),
-                ('__cf_bm', 'domain'))
+                LenientSimpleCookie(res.get_header('set-cookie')), ('__cf_bm', 'domain'))
             if cf_cookie_domain:
                 self.write_debug(f'Clearing __cf_bm cookie for {cf_cookie_domain}')
                 self.cookiejar.clear(domain=cf_cookie_domain, path='/', name='__cf_bm')

plugins/youtube_download/yt_dlp/extractor/gofile.py

@@ -46,6 +46,7 @@ class GofileIE(InfoExtractor):
             'videopassword': 'password',
         },
     }]
+    _STATIC_TOKEN = '4fd6sg89d7s6'  # From https://gofile.io/dist/js/config.js
     _TOKEN = None
 
     def _real_initialize(self):
@@ -60,13 +61,16 @@ class GofileIE(InfoExtractor):
         self._set_cookie('.gofile.io', 'accountToken', self._TOKEN)
 
     def _entries(self, file_id):
-        query_params = {'wt': '4fd6sg89d7s6'}  # From https://gofile.io/dist/js/alljs.js
-        password = self.get_param('videopassword')
-        if password:
+        query_params = {}
+        if password := self.get_param('videopassword'):
             query_params['password'] = hashlib.sha256(password.encode()).hexdigest()
+
         files = self._download_json(
             f'https://api.gofile.io/contents/{file_id}', file_id, 'Getting filelist',
-            query=query_params, headers={'Authorization': f'Bearer {self._TOKEN}'})
+            query=query_params, headers={
+                'Authorization': f'Bearer {self._TOKEN}',
+                'X-Website-Token': self._STATIC_TOKEN,
+            })
 
         status = files['status']
         if status == 'error-passwordRequired':

plugins/youtube_download/yt_dlp/extractor/googledrive.py

@@ -1,21 +1,20 @@
 import re
-import urllib.parse
 
 from .common import InfoExtractor
-from .youtube import YoutubeIE
 from ..utils import (
-    ExtractorError,
-    bug_reports_message,
     determine_ext,
     extract_attributes,
+    filter_dict,
     get_element_by_class,
     get_element_html_by_id,
     int_or_none,
-    lowercase_escape,
-    parse_qs,
-    try_get,
+    mimetype2ext,
+    parse_duration,
+    str_or_none,
     update_url_query,
+    url_or_none,
 )
+from ..utils.traversal import traverse_obj, value
 
 
 class GoogleDriveIE(InfoExtractor):
@@ -38,8 +37,8 @@ class GoogleDriveIE(InfoExtractor):
             'id': '0ByeS4oOUV-49Zzh4R1J6R09zazQ',
             'ext': 'mp4',
             'title': 'Big Buck Bunny.mp4',
-            'duration': 45,
-            'thumbnail': 'https://drive.google.com/thumbnail?id=0ByeS4oOUV-49Zzh4R1J6R09zazQ',
+            'duration': 45.069,
+            'thumbnail': r're:https://lh3\.googleusercontent\.com/drive-storage/',
         },
     }, {
         # has itag 50 which is not in YoutubeIE._formats (royalty Free music from 1922)
@@ -49,8 +48,29 @@ class GoogleDriveIE(InfoExtractor):
             'id': '1IP0o8dHcQrIHGgVyp0Ofvx2cGfLzyO1x',
             'ext': 'mp3',
             'title': 'My Buddy - Henry Burr - Gus Kahn - Walter Donaldson.mp3',
-            'duration': 184,
-            'thumbnail': 'https://drive.google.com/thumbnail?id=1IP0o8dHcQrIHGgVyp0Ofvx2cGfLzyO1x',
+            'duration': 184.68,
+        },
+    }, {
+        # Has subtitle track
+        'url': 'https://drive.google.com/file/d/1RAGWRgzn85TXCaCk4gxnwF6TGUaZatzE/view',
+        'md5': '05488c528da6ef737ec8c962bfa9724e',
+        'info_dict': {
+            'id': '1RAGWRgzn85TXCaCk4gxnwF6TGUaZatzE',
+            'ext': 'mp4',
+            'title': 'test.mp4',
+            'duration': 9.999,
+            'thumbnail': r're:https://lh3\.googleusercontent\.com/drive-storage/',
+        },
+    }, {
+        # Has subtitle track with kind 'asr'
+        'url': 'https://drive.google.com/file/d/1Prvv9-mtDDfN_gkJgtt1OFvIULK8c3Ev/view',
+        'md5': 'ccae12d07f18b5988900b2c8b92801fc',
+        'info_dict': {
+            'id': '1Prvv9-mtDDfN_gkJgtt1OFvIULK8c3Ev',
+            'ext': 'mp4',
+            'title': 'LEE NA GYUNG-3410-VOICE_MESSAGE.mp4',
+            'duration': 8.766,
+            'thumbnail': r're:https://lh3\.googleusercontent\.com/drive-storage/',
         },
     }, {
         # video can't be watched anonymously due to view count limit reached,
@@ -71,17 +91,6 @@ class GoogleDriveIE(InfoExtractor):
         'url': 'https://drive.usercontent.google.com/download?id=0ByeS4oOUV-49Zzh4R1J6R09zazQ',
         'only_matching': True,
     }]
-    _FORMATS_EXT = {
-        **{k: v['ext'] for k, v in YoutubeIE._formats.items() if v.get('ext')},
-        '50': 'm4a',
-    }
-    _BASE_URL_CAPTIONS = 'https://drive.google.com/timedtext'
-    _CAPTIONS_ENTRY_TAG = {
-        'subtitles': 'track',
-        'automatic_captions': 'target',
-    }
-    _caption_formats_ext = []
-    _captions_xml = None
 
     @classmethod
     def _extract_embed_urls(cls, url, webpage):
@@ -91,129 +100,73 @@ class GoogleDriveIE(InfoExtractor):
         if mobj:
             yield 'https://drive.google.com/file/d/{}'.format(mobj.group('id'))
 
-    def _download_subtitles_xml(self, video_id, subtitles_id, hl):
-        if self._captions_xml:
-            return
-        self._captions_xml = self._download_xml(
-            self._BASE_URL_CAPTIONS, video_id, query={
-                'id': video_id,
-                'vid': subtitles_id,
-                'hl': hl,
+    @staticmethod
+    def _construct_subtitle_url(base_url, video_id, language, fmt, kind):
+        return update_url_query(
+            base_url, filter_dict({
+                'hl': 'en-US',
                 'v': video_id,
+                'type': 'track',
+                'lang': language,
+                'fmt': fmt,
+                'kind': kind,
+            }))
+
+    def _get_subtitles(self, video_id, video_info):
+        subtitles = {}
+        timed_text_base_url = traverse_obj(video_info, ('timedTextDetails', 'timedTextBaseUrl', {url_or_none}))
+        if not timed_text_base_url:
+            return subtitles
+        subtitle_data = self._download_xml(
+            timed_text_base_url, video_id, 'Downloading subtitles XML', fatal=False, query={
+                'hl': 'en-US',
                 'type': 'list',
-                'tlangs': '1',
-                'fmts': '1',
-                'vssids': '1',
-            }, note='Downloading subtitles XML',
-            errnote='Unable to download subtitles XML', fatal=False)
-        if self._captions_xml:
-            for f in self._captions_xml.findall('format'):
-                if f.attrib.get('fmt_code') and not f.attrib.get('default'):
-                    self._caption_formats_ext.append(f.attrib['fmt_code'])
-
-    def _get_captions_by_type(self, video_id, subtitles_id, caption_type,
-                              origin_lang_code=None, origin_lang_name=None):
-        if not subtitles_id or not caption_type:
-            return
-        captions = {}
-        for caption_entry in self._captions_xml.findall(
-                self._CAPTIONS_ENTRY_TAG[caption_type]):
-            caption_lang_code = caption_entry.attrib.get('lang_code')
-            caption_name = caption_entry.attrib.get('name') or origin_lang_name
-            if not caption_lang_code or not caption_name:
-                self.report_warning(f'Missing necessary caption metadata. '
-                                    f'Need lang_code and name attributes. '
-                                    f'Found: {caption_entry.attrib}')
-                continue
-            caption_format_data = []
-            for caption_format in self._caption_formats_ext:
-                query = {
-                    'vid': subtitles_id,
-                    'v': video_id,
-                    'fmt': caption_format,
-                    'lang': (caption_lang_code if origin_lang_code is None
-                             else origin_lang_code),
-                    'type': 'track',
-                    'name': caption_name,
-                    'kind': '',
-                }
-                if origin_lang_code is not None:
-                    query.update({'tlang': caption_lang_code})
-                caption_format_data.append({
-                    'url': update_url_query(self._BASE_URL_CAPTIONS, query),
-                    'ext': caption_format,
-                })
-            captions[caption_lang_code] = caption_format_data
-        return captions
-
-    def _get_subtitles(self, video_id, subtitles_id, hl):
-        if not subtitles_id or not hl:
-            return
-        self._download_subtitles_xml(video_id, subtitles_id, hl)
-        if not self._captions_xml:
-            return
-        return self._get_captions_by_type(video_id, subtitles_id, 'subtitles')
-
-    def _get_automatic_captions(self, video_id, subtitles_id, hl):
-        if not subtitles_id or not hl:
-            return
-        self._download_subtitles_xml(video_id, subtitles_id, hl)
-        if not self._captions_xml:
-            return
-        track = next((t for t in self._captions_xml.findall('track') if t.attrib.get('cantran') == 'true'), None)
-        if track is None:
-            return
-        origin_lang_code = track.attrib.get('lang_code')
-        origin_lang_name = track.attrib.get('name')
-        if not origin_lang_code or not origin_lang_name:
-            return
-        return self._get_captions_by_type(
-            video_id, subtitles_id, 'automatic_captions', origin_lang_code, origin_lang_name)
+                'tlangs': 1,
+                'v': video_id,
+                'vssids': 1,
+            })
+        subtitle_formats = traverse_obj(subtitle_data, (lambda _, v: v.tag == 'format', {lambda x: x.get('fmt_code')}, {str}))
+        for track in traverse_obj(subtitle_data, (lambda _, v: v.tag == 'track' and v.get('lang_code'))):
+            language = track.get('lang_code')
+            subtitles.setdefault(language, []).extend([{
+                'url': self._construct_subtitle_url(
+                    timed_text_base_url, video_id, language, sub_fmt, track.get('kind')),
+                'name': track.get('lang_original'),
+                'ext': sub_fmt,
+            } for sub_fmt in subtitle_formats])
+        return subtitles
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
-        video_info = urllib.parse.parse_qs(self._download_webpage(
-            'https://drive.google.com/get_video_info',
-            video_id, 'Downloading video webpage', query={'docid': video_id}))
-
-        def get_value(key):
-            return try_get(video_info, lambda x: x[key][0])
-
-        reason = get_value('reason')
-        title = get_value('title')
+        video_info = self._download_json(
+            f'https://content-workspacevideo-pa.googleapis.com/v1/drive/media/{video_id}/playback',
+            video_id, 'Downloading video webpage', query={'key': 'AIzaSyDVQw45DwoYh632gvsP5vPDqEKvb-Ywnb8'},
+            headers={'Referer': 'https://drive.google.com/'})
 
         formats = []
-        fmt_stream_map = (get_value('fmt_stream_map') or '').split(',')
-        fmt_list = (get_value('fmt_list') or '').split(',')
-        if fmt_stream_map and fmt_list:
-            resolutions = {}
-            for fmt in fmt_list:
-                mobj = re.search(
-                    r'^(?P<format_id>\d+)/(?P<width>\d+)[xX](?P<height>\d+)', fmt)
-                if mobj:
-                    resolutions[mobj.group('format_id')] = (
-                        int(mobj.group('width')), int(mobj.group('height')))
+        for fmt in traverse_obj(video_info, (
+                'mediaStreamingData', 'formatStreamingData', ('adaptiveTranscodes', 'progressiveTranscodes'),
+                lambda _, v: url_or_none(v['url']))):
+            formats.append({
+                **traverse_obj(fmt, {
+                    'url': 'url',
+                    'format_id': ('itag', {int}, {str_or_none}),
+                }),
+                **traverse_obj(fmt, ('transcodeMetadata', {
+                    'ext': ('mimeType', {mimetype2ext}),
+                    'width': ('width', {int_or_none}),
+                    'height': ('height', {int_or_none}),
+                    'fps': ('videoFps', {int_or_none}),
+                    'filesize': ('contentLength', {int_or_none}),
+                    'vcodec': ((('videoCodecString', {str}), {value('none')}), any),
+                    'acodec': ((('audioCodecString', {str}), {value('none')}), any),
+                })),
+                'downloader_options': {
+                    'http_chunk_size': 10 << 20,
+                },
+            })
 
-            for fmt_stream in fmt_stream_map:
-                fmt_stream_split = fmt_stream.split('|')
-                if len(fmt_stream_split) < 2:
-                    continue
-                format_id, format_url = fmt_stream_split[:2]
-                ext = self._FORMATS_EXT.get(format_id)
-                if not ext:
-                    self.report_warning(f'Unknown format {format_id}{bug_reports_message()}')
-                f = {
-                    'url': lowercase_escape(format_url),
-                    'format_id': format_id,
-                    'ext': ext,
-                }
-                resolution = resolutions.get(format_id)
-                if resolution:
-                    f.update({
-                        'width': resolution[0],
-                        'height': resolution[1],
-                    })
-                formats.append(f)
+        title = traverse_obj(video_info, ('mediaMetadata', 'title', {str}))
 
         source_url = update_url_query(
             'https://drive.usercontent.google.com/download', {
@@ -264,30 +217,20 @@ class GoogleDriveIE(InfoExtractor):
                             or get_element_by_class('uc-error-caption', confirmation_webpage)
                             or 'unable to extract confirmation code')
 
-        if not formats and reason:
-            if title:
-                self.raise_no_formats(reason, expected=True)
-            else:
-                raise ExtractorError(reason, expected=True)
-
-        hl = get_value('hl')
-        subtitles_id = None
-        ttsurl = get_value('ttsurl')
-        if ttsurl:
-            # the subtitles ID is the vid param of the ttsurl query
-            subtitles_id = parse_qs(ttsurl).get('vid', [None])[-1]
-
-        self.cookiejar.clear(domain='.google.com', path='/', name='NID')
-
         return {
             'id': video_id,
             'title': title,
-            'thumbnail': 'https://drive.google.com/thumbnail?id=' + video_id,
-            'duration': int_or_none(get_value('length_seconds')),
+            **traverse_obj(video_info, {
+                'duration': ('mediaMetadata', 'duration', {parse_duration}),
+                'thumbnails': ('thumbnails', lambda _, v: url_or_none(v['url']), {
+                    'url': 'url',
+                    'ext': ('mimeType', {mimetype2ext}),
+                    'width': ('width', {int}),
+                    'height': ('height', {int}),
+                }),
+            }),
             'formats': formats,
-            'subtitles': self.extract_subtitles(video_id, subtitles_id, hl),
-            'automatic_captions': self.extract_automatic_captions(
-                video_id, subtitles_id, hl),
+            'subtitles': self.extract_subtitles(video_id, video_info),
         }
 
 

plugins/youtube_download/yt_dlp/extractor/goplay.py

@@ -13,12 +13,14 @@ from ..utils.traversal import get_first, traverse_obj
 
 
 class GoPlayIE(InfoExtractor):
-    _VALID_URL = r'https?://(www\.)?goplay\.be/video/([^/?#]+/[^/?#]+/|)(?P<id>[^/#]+)'
+    IE_NAME = 'play.tv'
+    IE_DESC = 'PLAY (formerly goplay.be)'
+    _VALID_URL = r'https?://(www\.)?play\.tv/video/([^/?#]+/[^/?#]+/|)(?P<id>[^/#]+)'
 
     _NETRC_MACHINE = 'goplay'
 
     _TESTS = [{
-        'url': 'https://www.goplay.be/video/de-slimste-mens-ter-wereld/de-slimste-mens-ter-wereld-s22/de-slimste-mens-ter-wereld-s22-aflevering-1',
+        'url': 'https://www.play.tv/video/de-slimste-mens-ter-wereld/de-slimste-mens-ter-wereld-s22/de-slimste-mens-ter-wereld-s22-aflevering-1',
         'info_dict': {
             'id': '2baa4560-87a0-421b-bffc-359914e3c387',
             'ext': 'mp4',
@@ -33,7 +35,7 @@ class GoPlayIE(InfoExtractor):
         'params': {'skip_download': True},
         'skip': 'This video is only available for registered users',
     }, {
-        'url': 'https://www.goplay.be/video/1917',
+        'url': 'https://www.play.tv/video/1917',
         'info_dict': {
             'id': '40cac41d-8d29-4ef5-aa11-75047b9f0907',
             'ext': 'mp4',
@@ -43,7 +45,7 @@ class GoPlayIE(InfoExtractor):
         'params': {'skip_download': True},
         'skip': 'This video is only available for registered users',
     }, {
-        'url': 'https://www.goplay.be/video/de-mol/de-mol-s11/de-mol-s11-aflevering-1#autoplay',
+        'url': 'https://www.play.tv/video/de-mol/de-mol-s11/de-mol-s11-aflevering-1#autoplay',
         'info_dict': {
             'id': 'ecb79672-92b9-4cd9-a0d7-e2f0250681ee',
             'ext': 'mp4',
@@ -101,7 +103,7 @@ class GoPlayIE(InfoExtractor):
                 break
 
         api = self._download_json(
-            f'https://api.goplay.be/web/v1/videos/long-form/{video_id}',
+            f'https://api.play.tv/web/v1/videos/long-form/{video_id}',
             video_id, headers={
                 'Authorization': f'Bearer {self._id_token}',
                 **self.geo_verification_headers(),

plugins/youtube_download/yt_dlp/extractor/hotstar.py

@@ -27,7 +27,7 @@ class HotStarBaseIE(InfoExtractor):
     _TOKEN_NAME = 'userUP'
     _BASE_URL = 'https://www.hotstar.com'
     _API_URL = 'https://api.hotstar.com'
-    _API_URL_V2 = 'https://apix.hotstar.com/v2'
+    _API_URL_V2 = 'https://www.hotstar.com/api/internal/bff/v2'
     _AKAMAI_ENCRYPTION_KEY = b'\x05\xfc\x1a\x01\xca\xc9\x4b\xc4\x12\xfc\x53\x12\x07\x75\xf9\xee'
 
     _FREE_HEADERS = {

plugins/youtube_download/yt_dlp/extractor/iqiyi.py

@@ -9,14 +9,12 @@ from .openload import PhantomJSwrapper
 from ..utils import (
     ExtractorError,
     clean_html,
-    decode_packed_codes,
     float_or_none,
     format_field,
     get_element_by_attribute,
     get_element_by_id,
     int_or_none,
     js_to_json,
-    ohdave_rsa_encrypt,
     parse_age_limit,
     parse_duration,
     parse_iso8601,
@@ -33,143 +31,12 @@ def md5_text(text):
     return hashlib.md5(text.encode()).hexdigest()
 
 
-class IqiyiSDK:
-    def __init__(self, target, ip, timestamp):
-        self.target = target
-        self.ip = ip
-        self.timestamp = timestamp
-
-    @staticmethod
-    def split_sum(data):
-        return str(sum(int(p, 16) for p in data))
-
-    @staticmethod
-    def digit_sum(num):
-        if isinstance(num, int):
-            num = str(num)
-        return str(sum(map(int, num)))
-
-    def even_odd(self):
-        even = self.digit_sum(str(self.timestamp)[::2])
-        odd = self.digit_sum(str(self.timestamp)[1::2])
-        return even, odd
-
-    def preprocess(self, chunksize):
-        self.target = md5_text(self.target)
-        chunks = []
-        for i in range(32 // chunksize):
-            chunks.append(self.target[chunksize * i:chunksize * (i + 1)])
-        if 32 % chunksize:
-            chunks.append(self.target[32 - 32 % chunksize:])
-        return chunks, list(map(int, self.ip.split('.')))
-
-    def mod(self, modulus):
-        chunks, ip = self.preprocess(32)
-        self.target = chunks[0] + ''.join(str(p % modulus) for p in ip)
-
-    def split(self, chunksize):
-        modulus_map = {
-            4: 256,
-            5: 10,
-            8: 100,
-        }
-
-        chunks, ip = self.preprocess(chunksize)
-        ret = ''
-        for i in range(len(chunks)):
-            ip_part = str(ip[i] % modulus_map[chunksize]) if i < 4 else ''
-            if chunksize == 8:
-                ret += ip_part + chunks[i]
-            else:
-                ret += chunks[i] + ip_part
-        self.target = ret
-
-    def handle_input16(self):
-        self.target = md5_text(self.target)
-        self.target = self.split_sum(self.target[:16]) + self.target + self.split_sum(self.target[16:])
-
-    def handle_input8(self):
-        self.target = md5_text(self.target)
-        ret = ''
-        for i in range(4):
-            part = self.target[8 * i:8 * (i + 1)]
-            ret += self.split_sum(part) + part
-        self.target = ret
-
-    def handleSum(self):
-        self.target = md5_text(self.target)
-        self.target = self.split_sum(self.target) + self.target
-
-    def date(self, scheme):
-        self.target = md5_text(self.target)
-        d = time.localtime(self.timestamp)
-        strings = {
-            'y': str(d.tm_year),
-            'm': '%02d' % d.tm_mon,
-            'd': '%02d' % d.tm_mday,
-        }
-        self.target += ''.join(strings[c] for c in scheme)
-
-    def split_time_even_odd(self):
-        even, odd = self.even_odd()
-        self.target = odd + md5_text(self.target) + even
-
-    def split_time_odd_even(self):
-        even, odd = self.even_odd()
-        self.target = even + md5_text(self.target) + odd
-
-    def split_ip_time_sum(self):
-        chunks, ip = self.preprocess(32)
-        self.target = str(sum(ip)) + chunks[0] + self.digit_sum(self.timestamp)
-
-    def split_time_ip_sum(self):
-        chunks, ip = self.preprocess(32)
-        self.target = self.digit_sum(self.timestamp) + chunks[0] + str(sum(ip))
-
-
-class IqiyiSDKInterpreter:
-    def __init__(self, sdk_code):
-        self.sdk_code = sdk_code
-
-    def run(self, target, ip, timestamp):
-        self.sdk_code = decode_packed_codes(self.sdk_code)
-
-        functions = re.findall(r'input=([a-zA-Z0-9]+)\(input', self.sdk_code)
-
-        sdk = IqiyiSDK(target, ip, timestamp)
-
-        other_functions = {
-            'handleSum': sdk.handleSum,
-            'handleInput8': sdk.handle_input8,
-            'handleInput16': sdk.handle_input16,
-            'splitTimeEvenOdd': sdk.split_time_even_odd,
-            'splitTimeOddEven': sdk.split_time_odd_even,
-            'splitIpTimeSum': sdk.split_ip_time_sum,
-            'splitTimeIpSum': sdk.split_time_ip_sum,
-        }
-        for function in functions:
-            if re.match(r'mod\d+', function):
-                sdk.mod(int(function[3:]))
-            elif re.match(r'date[ymd]{3}', function):
-                sdk.date(function[4:])
-            elif re.match(r'split\d+', function):
-                sdk.split(int(function[5:]))
-            elif function in other_functions:
-                other_functions[function]()
-            else:
-                raise ExtractorError(f'Unknown function {function}')
-
-        return sdk.target
-
-
 class IqiyiIE(InfoExtractor):
     IE_NAME = 'iqiyi'
     IE_DESC = '爱奇艺'
 
     _VALID_URL = r'https?://(?:(?:[^.]+\.)?iqiyi\.com|www\.pps\.tv)/.+\.html'
 
-    _NETRC_MACHINE = 'iqiyi'
-
     _TESTS = [{
         'url': 'http://www.iqiyi.com/v_19rrojlavg.html',
         # MD5 checksum differs on my machine and Travis CI
@@ -234,57 +101,6 @@ class IqiyiIE(InfoExtractor):
         '18': 7,    # 1080p
     }
 
-    @staticmethod
-    def _rsa_fun(data):
-        # public key extracted from http://static.iqiyi.com/js/qiyiV2/20160129180840/jobs/i18n/i18nIndex.js
-        N = 0xab86b6371b5318aaa1d3c9e612a9f1264f372323c8c0f19875b5fc3b3fd3afcc1e5bec527aa94bfa85bffc157e4245aebda05389a5357b75115ac94f074aefcd
-        e = 65537
-
-        return ohdave_rsa_encrypt(data, e, N)
-
-    def _perform_login(self, username, password):
-
-        data = self._download_json(
-            'http://kylin.iqiyi.com/get_token', None,
-            note='Get token for logging', errnote='Unable to get token for logging')
-        sdk = data['sdk']
-        timestamp = int(time.time())
-        target = (
-            f'/apis/reglogin/login.action?lang=zh_TW&area_code=null&email={username}'
-            f'&passwd={self._rsa_fun(password.encode())}&agenttype=1&from=undefined&keeplogin=0&piccode=&fromurl=&_pos=1')
-
-        interp = IqiyiSDKInterpreter(sdk)
-        sign = interp.run(target, data['ip'], timestamp)
-
-        validation_params = {
-            'target': target,
-            'server': 'BEA3AA1908656AABCCFF76582C4C6660',
-            'token': data['token'],
-            'bird_src': 'f8d91d57af224da7893dd397d52d811a',
-            'sign': sign,
-            'bird_t': timestamp,
-        }
-        validation_result = self._download_json(
-            'http://kylin.iqiyi.com/validate?' + urllib.parse.urlencode(validation_params), None,
-            note='Validate credentials', errnote='Unable to validate credentials')
-
-        MSG_MAP = {
-            'P00107': 'please login via the web interface and enter the CAPTCHA code',
-            'P00117': 'bad username or password',
-        }
-
-        code = validation_result['code']
-        if code != 'A00000':
-            msg = MSG_MAP.get(code)
-            if not msg:
-                msg = f'error {code}'
-                if validation_result.get('msg'):
-                    msg += ': ' + validation_result['msg']
-            self.report_warning('unable to log in: ' + msg)
-            return False
-
-        return True
-
     def get_raw_data(self, tvid, video_id):
         tm = int(time.time() * 1000)
 

plugins/youtube_download/yt_dlp/extractor/jtbc.py

@@ -98,7 +98,7 @@ class JTBCIE(InfoExtractor):
 
         formats = []
         for stream_url in traverse_obj(playback_data, ('sources', 'HLS', ..., 'file', {url_or_none})):
-            stream_url = re.sub(r'/playlist(?:_pd\d+)?\.m3u8', '/index.m3u8', stream_url)
+            stream_url = re.sub(r'/playlist_pd\d+\.m3u8', '/playlist.m3u8', stream_url)
             formats.extend(self._extract_m3u8_formats(stream_url, video_id, fatal=False))
 
         metadata = self._download_json(

plugins/youtube_download/yt_dlp/extractor/kika.py

@@ -17,57 +17,60 @@ class KikaIE(InfoExtractor):
     _GEO_COUNTRIES = ['DE']
 
     _TESTS = [{
-        'url': 'https://www.kika.de/logo/videos/logo-vom-samstag-einunddreissig-august-zweitausendvierundzwanzig-100',
-        'md5': 'fbfc8da483719ef06f396e5e5b938c69',
+        # Video without season/episode info
+        'url': 'https://www.kika.de/logo/videos/logo-vom-dienstag-achtundzwanzig-oktober-zweitausendfuenfundzwanzig-100',
+        'md5': '4a9f6e0f9c6bfcc82394c294f186d6db',
         'info_dict': {
-            'id': 'logo-vom-samstag-einunddreissig-august-zweitausendvierundzwanzig-100',
+            'id': 'logo-vom-dienstag-achtundzwanzig-oktober-zweitausendfuenfundzwanzig-100',
             'ext': 'mp4',
-            'upload_date': '20240831',
-            'timestamp': 1725126600,
-            'season_number': 2024,
-            'modified_date': '20240831',
-            'episode': 'Episode 476',
-            'episode_number': 476,
-            'season': 'Season 2024',
-            'duration': 634,
-            'title': 'logo! vom Samstag, 31. August 2024',
-            'modified_timestamp': 1725129983,
+            'title': 'logo! vom Dienstag, 28. Oktober 2025',
+            'description': 'md5:4d28b92cef423bec99740ffaa3e7ec04',
+            'duration': 651,
+            'timestamp': 1761678000,
+            'upload_date': '20251028',
+            'modified_timestamp': 1761682624,
+            'modified_date': '20251028',
         },
     }, {
+        # Video with season/episode info
+        # Also: Video with subtitles
         'url': 'https://www.kika.de/kaltstart/videos/video92498',
-        'md5': '710ece827e5055094afeb474beacb7aa',
+        'md5': 'e58073070acb195906c55c4ad31dceb3',
         'info_dict': {
             'id': 'video92498',
             'ext': 'mp4',
             'title': '7. Wo ist Leo?',
             'description': 'md5:fb48396a5b75068bcac1df74f1524920',
             'duration': 436,
+            'season': 'Season 1',
+            'season_number': 1,
+            'episode': 'Episode 7',
+            'episode_number': 7,
             'timestamp': 1702926876,
             'upload_date': '20231218',
-            'episode_number': 7,
-            'modified_date': '20240319',
             'modified_timestamp': 1710880610,
-            'episode': 'Episode 7',
-            'season_number': 1,
-            'season': 'Season 1',
+            'modified_date': '20240319',
+            'subtitles': 'count:1',
         },
     }, {
-        'url': 'https://www.kika.de/bernd-das-brot/astrobrot/videos/video90088',
-        'md5': 'ffd1b700d7de0a6616a1d08544c77294',
+        # Video without subtitles
+        'url': 'https://www.kika.de/die-pfefferkoerner/videos/abgezogen-102',
+        'md5': '62e97961ce5343c19f0f330a1b6dd736',
         'info_dict': {
-            'id': 'video90088',
+            'id': 'abgezogen-102',
             'ext': 'mp4',
-            'upload_date': '20221102',
-            'timestamp': 1667390580,
-            'duration': 197,
-            'modified_timestamp': 1711093771,
-            'episode_number': 8,
-            'title': 'Es ist nicht leicht, ein Astrobrot zu sein',
-            'modified_date': '20240322',
-            'description': 'md5:d3641deaf1b5515a160788b2be4159a9',
-            'season_number': 1,
-            'episode': 'Episode 8',
+            'title': '1. Abgezogen',
+            'description': 'md5:42d87963364391f9f8eba8affcb30bd2',
+            'duration': 1574,
             'season': 'Season 1',
+            'season_number': 1,
+            'episode': 'Episode 1',
+            'episode_number': 1,
+            'timestamp': 1735382700,
+            'upload_date': '20241228',
+            'modified_timestamp': 1757344051,
+            'modified_date': '20250908',
+            'subtitles': 'count:0',
         },
     }]
 
@@ -78,16 +81,19 @@ class KikaIE(InfoExtractor):
         video_assets = self._download_json(doc['assets']['url'], video_id)
 
         subtitles = {}
-        if ttml_resource := url_or_none(video_assets.get('videoSubtitle')):
-            subtitles['de'] = [{
-                'url': ttml_resource,
-                'ext': 'ttml',
-            }]
-        if webvtt_resource := url_or_none(video_assets.get('webvttUrl')):
-            subtitles.setdefault('de', []).append({
-                'url': webvtt_resource,
-                'ext': 'vtt',
-            })
+        # Subtitle API endpoints may be present in the JSON even if there are no subtitles.
+        # They then return HTTP 200 with invalid data. So we must check explicitly.
+        if doc.get('hasSubtitle'):
+            if ttml_resource := url_or_none(video_assets.get('videoSubtitle')):
+                subtitles['de'] = [{
+                    'url': ttml_resource,
+                    'ext': 'ttml',
+                }]
+            if webvtt_resource := url_or_none(video_assets.get('webvttUrl')):
+                subtitles.setdefault('de', []).append({
+                    'url': webvtt_resource,
+                    'ext': 'vtt',
+                })
 
         return {
             'id': video_id,

plugins/youtube_download/yt_dlp/extractor/loom.py

@@ -8,12 +8,10 @@ from ..utils import (
     ExtractorError,
     determine_ext,
     filter_dict,
-    get_first,
     int_or_none,
     parse_iso8601,
     update_url,
     url_or_none,
-    variadic,
 )
 from ..utils.traversal import traverse_obj
 
@@ -51,7 +49,7 @@ class LoomIE(InfoExtractor):
     }, {
         # m3u8 raw-url, mp4 transcoded-url, cdn url == raw-url, vtt sub and json subs
         'url': 'https://www.loom.com/share/9458bcbf79784162aa62ffb8dd66201b',
-        'md5': '51737ec002969dd28344db4d60b9cbbb',
+        'md5': '7b6bfdef8181c4ffc376e18919a4dcc2',
         'info_dict': {
             'id': '9458bcbf79784162aa62ffb8dd66201b',
             'ext': 'mp4',
@@ -71,12 +69,13 @@ class LoomIE(InfoExtractor):
             'ext': 'webm',
             'title': 'OMFG clown',
             'description': 'md5:285c5ee9d62aa087b7e3271b08796815',
-            'uploader': 'MrPumkin B',
+            'uploader': 'Brailey Bragg',
             'upload_date': '20210924',
             'timestamp': 1632519618,
             'duration': 210,
         },
         'params': {'skip_download': 'dash'},
+        'expected_warnings': ['Failed to parse JSON'],  # transcoded-url no longer available
     }, {
         # password-protected
         'url': 'https://www.loom.com/share/50e26e8aeb7940189dff5630f95ce1f4',
@@ -91,10 +90,11 @@ class LoomIE(InfoExtractor):
             'duration': 35,
         },
         'params': {'videopassword': 'seniorinfants2'},
+        'expected_warnings': ['Failed to parse JSON'],  # transcoded-url no longer available
     }, {
         # embed, transcoded-url endpoint sends empty JSON response, split video and audio HLS formats
         'url': 'https://www.loom.com/embed/ddcf1c1ad21f451ea7468b1e33917e4e',
-        'md5': 'b321d261656848c184a94e3b93eae28d',
+        'md5': 'f983a0f02f24331738b2f43aecb05256',
         'info_dict': {
             'id': 'ddcf1c1ad21f451ea7468b1e33917e4e',
             'ext': 'mp4',
@@ -119,11 +119,12 @@ class LoomIE(InfoExtractor):
             'duration': 247,
             'timestamp': 1676274030,
         },
+        'skip': '404 Not Found',
     }]
 
     _GRAPHQL_VARIABLES = {
         'GetVideoSource': {
-            'acceptableMimes': ['DASH', 'M3U8', 'MP4'],
+            'acceptableMimes': ['DASH', 'M3U8', 'MP4', 'WEBM'],
         },
     }
     _GRAPHQL_QUERIES = {
@@ -192,6 +193,12 @@ class LoomIE(InfoExtractor):
                   id
                   nullableRawCdnUrl(acceptableMimes: $acceptableMimes, password: $password) {
                     url
+                    credentials {
+                      Policy
+                      Signature
+                      KeyPairId
+                      __typename
+                    }
                     __typename
                   }
                   __typename
@@ -240,9 +247,9 @@ class LoomIE(InfoExtractor):
               }
             }\n'''),
     }
-    _APOLLO_GRAPHQL_VERSION = '0a1856c'
+    _APOLLO_GRAPHQL_VERSION = '45a5bd4'
 
-    def _call_graphql_api(self, operations, video_id, note=None, errnote=None):
+    def _call_graphql_api(self, operation_name, video_id, note=None, errnote=None, fatal=True):
         password = self.get_param('videopassword')
         return self._download_json(
             'https://www.loom.com/graphql', video_id, note or 'Downloading GraphQL JSON',
@@ -252,7 +259,9 @@ class LoomIE(InfoExtractor):
                 'x-loom-request-source': f'loom_web_{self._APOLLO_GRAPHQL_VERSION}',
                 'apollographql-client-name': 'web',
                 'apollographql-client-version': self._APOLLO_GRAPHQL_VERSION,
-            }, data=json.dumps([{
+                'graphql-operation-name': operation_name,
+                'Origin': 'https://www.loom.com',
+            }, data=json.dumps({
                 'operationName': operation_name,
                 'variables': {
                     'videoId': video_id,
@@ -260,7 +269,7 @@ class LoomIE(InfoExtractor):
                     **self._GRAPHQL_VARIABLES.get(operation_name, {}),
                 },
                 'query': self._GRAPHQL_QUERIES[operation_name],
-            } for operation_name in variadic(operations)], separators=(',', ':')).encode())
+            }, separators=(',', ':')).encode(), fatal=fatal)
 
     def _call_url_api(self, endpoint, video_id):
         response = self._download_json(
@@ -275,7 +284,7 @@ class LoomIE(InfoExtractor):
             }, separators=(',', ':')).encode())
         return traverse_obj(response, ('url', {url_or_none}))
 
-    def _extract_formats(self, video_id, metadata, gql_data):
+    def _extract_formats(self, video_id, metadata, video_data):
         formats = []
         video_properties = traverse_obj(metadata, ('video_properties', {
             'width': ('width', {int_or_none}),
@@ -330,7 +339,7 @@ class LoomIE(InfoExtractor):
         transcoded_url = self._call_url_api('transcoded-url', video_id)
         formats.extend(get_formats(transcoded_url, 'transcoded', quality=-1))  # transcoded quality
 
-        cdn_url = get_first(gql_data, ('data', 'getVideo', 'nullableRawCdnUrl', 'url', {url_or_none}))
+        cdn_url = traverse_obj(video_data, ('data', 'getVideo', 'nullableRawCdnUrl', 'url', {url_or_none}))
         # cdn_url is usually a dupe, but the raw-url/transcoded-url endpoints could return errors
         valid_urls = [update_url(url, query=None) for url in (raw_url, transcoded_url) if url]
         if cdn_url and update_url(cdn_url, query=None) not in valid_urls:
@@ -338,10 +347,21 @@ class LoomIE(InfoExtractor):
 
         return formats
 
+    def _get_subtitles(self, video_id):
+        subs_data = self._call_graphql_api(
+            'FetchVideoTranscript', video_id, 'Downloading GraphQL subtitles JSON', fatal=False)
+        return filter_dict({
+            'en': traverse_obj(subs_data, (
+                'data', 'fetchVideoTranscript',
+                ('source_url', 'captions_source_url'), {
+                    'url': {url_or_none},
+                })) or None,
+        })
+
     def _real_extract(self, url):
         video_id = self._match_id(url)
-        metadata = get_first(
-            self._call_graphql_api('GetVideoSSR', video_id, 'Downloading GraphQL metadata JSON'),
+        metadata = traverse_obj(
+            self._call_graphql_api('GetVideoSSR', video_id, 'Downloading GraphQL metadata JSON', fatal=False),
             ('data', 'getVideo', {dict})) or {}
 
         if metadata.get('__typename') == 'VideoPasswordMissingOrIncorrect':
@@ -350,22 +370,19 @@ class LoomIE(InfoExtractor):
                     'This video is password-protected, use the --video-password option', expected=True)
             raise ExtractorError('Invalid video password', expected=True)
 
-        gql_data = self._call_graphql_api(['FetchChapters', 'FetchVideoTranscript', 'GetVideoSource'], video_id)
+        video_data = self._call_graphql_api(
+            'GetVideoSource', video_id, 'Downloading GraphQL video JSON')
+        chapter_data = self._call_graphql_api(
+            'FetchChapters', video_id, 'Downloading GraphQL chapters JSON', fatal=False)
         duration = traverse_obj(metadata, ('video_properties', 'duration', {int_or_none}))
 
         return {
             'id': video_id,
             'duration': duration,
             'chapters': self._extract_chapters_from_description(
-                get_first(gql_data, ('data', 'fetchVideoChapters', 'content', {str})), duration) or None,
-            'formats': self._extract_formats(video_id, metadata, gql_data),
-            'subtitles': filter_dict({
-                'en': traverse_obj(gql_data, (
-                    ..., 'data', 'fetchVideoTranscript',
-                    ('source_url', 'captions_source_url'), {
-                        'url': {url_or_none},
-                    })) or None,
-            }),
+                traverse_obj(chapter_data, ('data', 'fetchVideoChapters', 'content', {str})), duration) or None,
+            'formats': self._extract_formats(video_id, metadata, video_data),
+            'subtitles': self.extract_subtitles(video_id),
             **traverse_obj(metadata, {
                 'title': ('name', {str}),
                 'description': ('description', {str}),
@@ -376,6 +393,7 @@ class LoomIE(InfoExtractor):
 
 
 class LoomFolderIE(InfoExtractor):
+    _WORKING = False
     IE_NAME = 'loom:folder'
     _VALID_URL = r'https?://(?:www\.)?loom\.com/share/folder/(?P<id>[\da-f]{32})'
     _TESTS = [{

plugins/youtube_download/yt_dlp/extractor/manoto.py

@@ -1,128 +0,0 @@
-from .common import InfoExtractor
-from ..utils import clean_html, int_or_none, traverse_obj
-
-_API_URL = 'https://dak1vd5vmi7x6.cloudfront.net/api/v1/publicrole/{}/{}?id={}'
-
-
-class ManotoTVIE(InfoExtractor):
-    IE_DESC = 'Manoto TV (Episode)'
-    _VALID_URL = r'https?://(?:www\.)?manototv\.com/episode/(?P<id>[0-9]+)'
-    _TESTS = [{
-        'url': 'https://www.manototv.com/episode/8475',
-        'info_dict': {
-            'id': '8475',
-            'series': 'خانه های رویایی با برادران اسکات',
-            'season_number': 7,
-            'episode_number': 25,
-            'episode_id': 'My Dream Home S7: Carol & John',
-            'duration': 3600,
-            'categories': ['سرگرمی'],
-            'title': 'کارول و جان',
-            'description': 'md5:d0fff1f8ba5c6775d312a00165d1a97e',
-            'thumbnail': r're:^https?://.*\.(jpeg|png|jpg)$',
-            'ext': 'mp4',
-        },
-        'params': {
-            'skip_download': 'm3u8',
-        },
-    }, {
-        'url': 'https://www.manototv.com/episode/12576',
-        'info_dict': {
-            'id': '12576',
-            'series': 'فیلم های ایرانی',
-            'episode_id': 'Seh Mah Taatili',
-            'duration': 5400,
-            'view_count': int,
-            'categories': ['سرگرمی'],
-            'title': 'سه ماه تعطیلی',
-            'description': 'سه ماه تعطیلی فیلمی به کارگردانی و نویسندگی شاپور قریب ساختهٔ سال ۱۳۵۶ است.',
-            'thumbnail': r're:^https?://.*\.(jpeg|png|jpg)$',
-            'ext': 'mp4',
-        },
-        'params': {
-            'skip_download': 'm3u8',
-        },
-    }]
-
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-        episode_json = self._download_json(_API_URL.format('showmodule', 'episodedetails', video_id), video_id)
-        details = episode_json.get('details', {})
-        formats = self._extract_m3u8_formats(details.get('videoM3u8Url'), video_id, 'mp4')
-        return {
-            'id': video_id,
-            'series': details.get('showTitle'),
-            'season_number': int_or_none(details.get('analyticsSeasonNumber')),
-            'episode_number': int_or_none(details.get('episodeNumber')),
-            'episode_id': details.get('analyticsEpisodeTitle'),
-            'duration': int_or_none(details.get('durationInMinutes'), invscale=60),
-            'view_count': details.get('viewCount'),
-            'categories': [details.get('videoCategory')],
-            'title': details.get('episodeTitle'),
-            'description': clean_html(details.get('episodeDescription')),
-            'thumbnail': details.get('episodelandscapeImgIxUrl'),
-            'formats': formats,
-        }
-
-
-class ManotoTVShowIE(InfoExtractor):
-    IE_DESC = 'Manoto TV (Show)'
-    _VALID_URL = r'https?://(?:www\.)?manototv\.com/show/(?P<id>[0-9]+)'
-    _TESTS = [{
-        'url': 'https://www.manototv.com/show/2526',
-        'playlist_mincount': 68,
-        'info_dict': {
-            'id': '2526',
-            'title': 'فیلم های ایرانی',
-            'description': 'مجموعه ای از فیلم های سینمای کلاسیک ایران',
-        },
-    }]
-
-    def _real_extract(self, url):
-        show_id = self._match_id(url)
-        show_json = self._download_json(_API_URL.format('showmodule', 'details', show_id), show_id)
-        show_details = show_json.get('details', {})
-        title = show_details.get('showTitle')
-        description = show_details.get('showSynopsis')
-
-        series_json = self._download_json(_API_URL.format('showmodule', 'serieslist', show_id), show_id)
-        playlist_id = str(traverse_obj(series_json, ('details', 'list', 0, 'id')))
-
-        playlist_json = self._download_json(_API_URL.format('showmodule', 'episodelist', playlist_id), playlist_id)
-        playlist = traverse_obj(playlist_json, ('details', 'list')) or []
-
-        entries = [
-            self.url_result(
-                'https://www.manototv.com/episode/{}'.format(item['slideID']), ie=ManotoTVIE.ie_key(), video_id=item['slideID'])
-            for item in playlist]
-        return self.playlist_result(entries, show_id, title, description)
-
-
-class ManotoTVLiveIE(InfoExtractor):
-    IE_DESC = 'Manoto TV (Live)'
-    _VALID_URL = r'https?://(?:www\.)?manototv\.com/live/'
-    _TEST = {
-        'url': 'https://www.manototv.com/live/',
-        'info_dict': {
-            'id': 'live',
-            'title': 'Manoto TV Live',
-            'ext': 'mp4',
-            'is_live': True,
-        },
-        'params': {
-            'skip_download': 'm3u8',
-        },
-    }
-
-    def _real_extract(self, url):
-        video_id = 'live'
-        json = self._download_json(_API_URL.format('livemodule', 'details', ''), video_id)
-        details = json.get('details', {})
-        video_url = details.get('liveUrl')
-        formats = self._extract_m3u8_formats(video_url, video_id, 'mp4', live=True)
-        return {
-            'id': video_id,
-            'title': 'Manoto TV Live',
-            'is_live': True,
-            'formats': formats,
-        }

plugins/youtube_download/yt_dlp/extractor/mave.py

@@ -1,7 +1,9 @@
-import re
+import functools
+import math
 
 from .common import InfoExtractor
 from ..utils import (
+    InAdvancePagedList,
     clean_html,
     int_or_none,
     parse_iso8601,
@@ -10,15 +12,64 @@ from ..utils import (
 from ..utils.traversal import require, traverse_obj
 
 
-class MaveIE(InfoExtractor):
-    _VALID_URL = r'https?://(?P<channel>[\w-]+)\.mave\.digital/(?P<id>ep-\d+)'
+class MaveBaseIE(InfoExtractor):
+    _API_BASE_URL = 'https://api.mave.digital/v1/website'
+    _API_BASE_STORAGE_URL = 'https://store.cloud.mts.ru/mave/'
+
+    def _load_channel_meta(self, channel_id, display_id):
+        return traverse_obj(self._download_json(
+            f'{self._API_BASE_URL}/{channel_id}/', display_id,
+            note='Downloading channel metadata'), 'podcast')
+
+    def _load_episode_meta(self, channel_id, episode_code, display_id):
+        return self._download_json(
+            f'{self._API_BASE_URL}/{channel_id}/episodes/{episode_code}',
+            display_id, note='Downloading episode metadata')
+
+    def _create_entry(self, channel_id, channel_meta, episode_meta):
+        episode_code = traverse_obj(episode_meta, ('code', {int}, {require('episode code')}))
+        return {
+            'display_id': f'{channel_id}-{episode_code}',
+            'extractor_key': MaveIE.ie_key(),
+            'extractor': MaveIE.IE_NAME,
+            'webpage_url': f'https://{channel_id}.mave.digital/ep-{episode_code}',
+            'channel_id': channel_id,
+            'channel_url': f'https://{channel_id}.mave.digital/',
+            'vcodec': 'none',
+            **traverse_obj(episode_meta, {
+                'id': ('id', {str}),
+                'url': ('audio', {urljoin(self._API_BASE_STORAGE_URL)}),
+                'title': ('title', {str}),
+                'description': ('description', {clean_html}),
+                'thumbnail': ('image', {urljoin(self._API_BASE_STORAGE_URL)}),
+                'duration': ('duration', {int_or_none}),
+                'season_number': ('season', {int_or_none}),
+                'episode_number': ('number', {int_or_none}),
+                'view_count': ('listenings', {int_or_none}),
+                'like_count': ('reactions', lambda _, v: v['type'] == 'like', 'count', {int_or_none}, any),
+                'dislike_count': ('reactions', lambda _, v: v['type'] == 'dislike', 'count', {int_or_none}, any),
+                'age_limit': ('is_explicit', {bool}, {lambda x: 18 if x else None}),
+                'timestamp': ('publish_date', {parse_iso8601}),
+            }),
+            **traverse_obj(channel_meta, {
+                'series_id': ('id', {str}),
+                'series': ('title', {str}),
+                'channel': ('title', {str}),
+                'uploader': ('author', {str}),
+            }),
+        }
+
+
+class MaveIE(MaveBaseIE):
+    IE_NAME = 'mave'
+    _VALID_URL = r'https?://(?P<channel_id>[\w-]+)\.mave\.digital/ep-(?P<episode_code>\d+)'
     _TESTS = [{
         'url': 'https://ochenlichnoe.mave.digital/ep-25',
         'md5': 'aa3e513ef588b4366df1520657cbc10c',
         'info_dict': {
             'id': '4035f587-914b-44b6-aa5a-d76685ad9bc2',
             'ext': 'mp3',
-            'display_id': 'ochenlichnoe-ep-25',
+            'display_id': 'ochenlichnoe-25',
             'title': 'Между мной и миром: психология самооценки',
             'description': 'md5:4b7463baaccb6982f326bce5c700382a',
             'uploader': 'Самарский университет',
@@ -45,7 +96,7 @@ class MaveIE(InfoExtractor):
         'info_dict': {
             'id': '41898bb5-ff57-4797-9236-37a8e537aa21',
             'ext': 'mp3',
-            'display_id': 'budem-ep-12',
+            'display_id': 'budem-12',
             'title': 'Екатерина Михайлова: "Горе от ума" не про женщин написана',
             'description': 'md5:fa3bdd59ee829dfaf16e3efcb13f1d19',
             'uploader': 'Полина Цветкова+Евгения Акопова',
@@ -68,40 +119,72 @@ class MaveIE(InfoExtractor):
             'upload_date': '20241230',
         },
     }]
-    _API_BASE_URL = 'https://api.mave.digital/'
 
     def _real_extract(self, url):
-        channel_id, slug = self._match_valid_url(url).group('channel', 'id')
-        display_id = f'{channel_id}-{slug}'
-        webpage = self._download_webpage(url, display_id)
-        data = traverse_obj(
-            self._search_nuxt_json(webpage, display_id),
-            ('data', lambda _, v: v['activeEpisodeData'], any, {require('podcast data')}))
+        channel_id, episode_code = self._match_valid_url(url).group(
+            'channel_id', 'episode_code')
+        display_id = f'{channel_id}-{episode_code}'
+
+        channel_meta = self._load_channel_meta(channel_id, display_id)
+        episode_meta = self._load_episode_meta(channel_id, episode_code, display_id)
+
+        return self._create_entry(channel_id, channel_meta, episode_meta)
+
+
+class MaveChannelIE(MaveBaseIE):
+    IE_NAME = 'mave:channel'
+    _VALID_URL = r'https?://(?P<id>[\w-]+)\.mave\.digital/?(?:$|[?#])'
+    _TESTS = [{
+        'url': 'https://budem.mave.digital/',
+        'info_dict': {
+            'id': 'budem',
+            'title': 'Все там будем',
+            'description': 'md5:f04ae12a42be0f1d765c5e326b41987a',
+        },
+        'playlist_mincount': 15,
+    }, {
+        'url': 'https://ochenlichnoe.mave.digital/',
+        'info_dict': {
+            'id': 'ochenlichnoe',
+            'title': 'Очень личное',
+            'description': 'md5:ee36a6a52546b91b487fe08c552fdbb2',
+        },
+        'playlist_mincount': 20,
+    }, {
+        'url': 'https://geekcity.mave.digital/',
+        'info_dict': {
+            'id': 'geekcity',
+            'title': 'Мужчины в трико',
+            'description': 'md5:4164d425d60a0d97abdce9d1f6f8e049',
+        },
+        'playlist_mincount': 80,
+    }]
+    _PAGE_SIZE = 50
+
+    def _entries(self, channel_id, channel_meta, page_num):
+        page_data = self._download_json(
+            f'{self._API_BASE_URL}/{channel_id}/episodes', channel_id, query={
+                'view': 'all',
+                'page': page_num + 1,
+                'sort': 'newest',
+                'format': 'all',
+            }, note=f'Downloading page {page_num + 1}')
+        for ep in traverse_obj(page_data, ('episodes', lambda _, v: v['audio'] and v['id'])):
+            yield self._create_entry(channel_id, channel_meta, ep)
+
+    def _real_extract(self, url):
+        channel_id = self._match_id(url)
+
+        channel_meta = self._load_channel_meta(channel_id, channel_id)
 
         return {
-            'display_id': display_id,
-            'channel_id': channel_id,
-            'channel_url': f'https://{channel_id}.mave.digital/',
-            'vcodec': 'none',
-            'thumbnail': re.sub(r'_\d+(?=\.(?:jpg|png))', '', self._og_search_thumbnail(webpage, default='')) or None,
-            **traverse_obj(data, ('activeEpisodeData', {
-                'url': ('audio', {urljoin(self._API_BASE_URL)}),
-                'id': ('id', {str}),
+            '_type': 'playlist',
+            'id': channel_id,
+            **traverse_obj(channel_meta, {
                 'title': ('title', {str}),
-                'description': ('description', {clean_html}),
-                'duration': ('duration', {int_or_none}),
-                'season_number': ('season', {int_or_none}),
-                'episode_number': ('number', {int_or_none}),
-                'view_count': ('listenings', {int_or_none}),
-                'like_count': ('reactions', lambda _, v: v['type'] == 'like', 'count', {int_or_none}, any),
-                'dislike_count': ('reactions', lambda _, v: v['type'] == 'dislike', 'count', {int_or_none}, any),
-                'age_limit': ('is_explicit', {bool}, {lambda x: 18 if x else None}),
-                'timestamp': ('publish_date', {parse_iso8601}),
-            })),
-            **traverse_obj(data, ('podcast', 'podcast', {
-                'series_id': ('id', {str}),
-                'series': ('title', {str}),
-                'channel': ('title', {str}),
-                'uploader': ('author', {str}),
-            })),
+                'description': ('description', {str}),
+            }),
+            'entries': InAdvancePagedList(
+                functools.partial(self._entries, channel_id, channel_meta),
+                math.ceil(channel_meta['episodes_count'] / self._PAGE_SIZE), self._PAGE_SIZE),
         }

plugins/youtube_download/yt_dlp/extractor/medaltv.py

@@ -1,14 +1,9 @@
-import re
-
 from .common import InfoExtractor
 from ..utils import (
-    ExtractorError,
-    float_or_none,
-    format_field,
     int_or_none,
-    str_or_none,
-    traverse_obj,
+    url_or_none,
 )
+from ..utils.traversal import traverse_obj
 
 
 class MedalTVIE(InfoExtractor):
@@ -30,25 +25,8 @@ class MedalTVIE(InfoExtractor):
             'view_count': int,
             'like_count': int,
             'duration': 13,
-        },
-    }, {
-        'url': 'https://medal.tv/games/cod-cold-war/clips/2mA60jWAGQCBH',
-        'md5': 'fc7a3e4552ae8993c1c4006db46be447',
-        'info_dict': {
-            'id': '2mA60jWAGQCBH',
-            'ext': 'mp4',
-            'title': 'Quad Cold',
-            'description': 'Medal,https://medal.tv/desktop/',
-            'uploader': 'MowgliSB',
-            'timestamp': 1603165266,
-            'upload_date': '20201020',
-            'uploader_id': '10619174',
-            'thumbnail': 'https://cdn.medal.tv/10619174/thumbnail-34934644-720p.jpg?t=1080p&c=202042&missing',
-            'uploader_url': 'https://medal.tv/users/10619174',
-            'comment_count': int,
-            'view_count': int,
-            'like_count': int,
-            'duration': 23,
+            'thumbnail': r're:https://cdn\.medal\.tv/ugcp/content-thumbnail/.*\.jpg',
+            'tags': ['headshot', 'valorant', '4k', 'clutch', 'mornu'],
         },
     }, {
         'url': 'https://medal.tv/games/cod-cold-war/clips/2um24TWdty0NA',
@@ -57,12 +35,12 @@ class MedalTVIE(InfoExtractor):
             'id': '2um24TWdty0NA',
             'ext': 'mp4',
             'title': 'u tk me i tk u bigger',
-            'description': 'Medal,https://medal.tv/desktop/',
-            'uploader': 'Mimicc',
+            'description': '',
+            'uploader': 'zahl',
             'timestamp': 1605580939,
             'upload_date': '20201117',
             'uploader_id': '5156321',
-            'thumbnail': 'https://cdn.medal.tv/5156321/thumbnail-36787208-360p.jpg?t=1080p&c=202046&missing',
+            'thumbnail': r're:https://cdn\.medal\.tv/source/.*\.png',
             'uploader_url': 'https://medal.tv/users/5156321',
             'comment_count': int,
             'view_count': int,
@@ -70,91 +48,77 @@ class MedalTVIE(InfoExtractor):
             'duration': 9,
         },
     }, {
-        'url': 'https://medal.tv/games/valorant/clips/37rMeFpryCC-9',
-        'only_matching': True,
-    }, {
+        # API requires auth
         'url': 'https://medal.tv/games/valorant/clips/2WRj40tpY_EU9',
+        'md5': '6c6bb6569777fd8b4ef7b33c09de8dcf',
+        'info_dict': {
+            'id': '2WRj40tpY_EU9',
+            'ext': 'mp4',
+            'title': '1v5 clutch',
+            'description': '',
+            'uploader': 'adny',
+            'uploader_id': '6256941',
+            'uploader_url': 'https://medal.tv/users/6256941',
+            'comment_count': int,
+            'view_count': int,
+            'like_count': int,
+            'duration': 25,
+            'thumbnail': r're:https://cdn\.medal\.tv/source/.*\.jpg',
+            'timestamp': 1612896680,
+            'upload_date': '20210209',
+        },
+        'expected_warnings': ['Video formats are not available through API'],
+    }, {
+        'url': 'https://medal.tv/games/valorant/clips/37rMeFpryCC-9',
         'only_matching': True,
     }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
-        webpage = self._download_webpage(url, video_id, query={'mobilebypass': 'true'})
-
-        hydration_data = self._search_json(
-            r'<script[^>]*>[^<]*\bhydrationData\s*=', webpage,
-            'next data', video_id, end_pattern='</script>', fatal=False)
-
-        clip = traverse_obj(hydration_data, ('clips', ...), get_all=False)
-        if not clip:
-            raise ExtractorError(
-                'Could not find video information.', video_id=video_id)
-
-        title = clip['contentTitle']
-
-        source_width = int_or_none(clip.get('sourceWidth'))
-        source_height = int_or_none(clip.get('sourceHeight'))
-
-        aspect_ratio = source_width / source_height if source_width and source_height else 16 / 9
-
-        def add_item(container, item_url, height, id_key='format_id', item_id=None):
-            item_id = item_id or '%dp' % height
-            if item_id not in item_url:
-                return
-            container.append({
-                'url': item_url,
-                id_key: item_id,
-                'width': round(aspect_ratio * height),
-                'height': height,
-            })
+        content_data = self._download_json(
+            f'https://medal.tv/api/content/{video_id}', video_id,
+            headers={'Accept': 'application/json'})
 
         formats = []
-        thumbnails = []
-        for k, v in clip.items():
-            if not (v and isinstance(v, str)):
-                continue
-            mobj = re.match(r'(contentUrl|thumbnail)(?:(\d+)p)?$', k)
-            if not mobj:
-                continue
-            prefix = mobj.group(1)
-            height = int_or_none(mobj.group(2))
-            if prefix == 'contentUrl':
-                add_item(
-                    formats, v, height or source_height,
-                    item_id=None if height else 'source')
-            elif prefix == 'thumbnail':
-                add_item(thumbnails, v, height, 'id')
-
-        error = clip.get('error')
-        if not formats and error:
-            if error == 404:
-                self.raise_no_formats(
-                    'That clip does not exist.',
-                    expected=True, video_id=video_id)
-            else:
-                self.raise_no_formats(
-                    f'An unknown error occurred ({error}).',
-                    video_id=video_id)
-
-        # Necessary because the id of the author is not known in advance.
-        # Won't raise an issue if no profile can be found as this is optional.
-        author = traverse_obj(hydration_data, ('profiles', ...), get_all=False) or {}
-        author_id = str_or_none(author.get('userId'))
-        author_url = format_field(author_id, None, 'https://medal.tv/users/%s')
+        if m3u8_url := url_or_none(content_data.get('contentUrlHls')):
+            formats.extend(self._extract_m3u8_formats(m3u8_url, video_id, 'mp4', m3u8_id='hls'))
+        if http_url := url_or_none(content_data.get('contentUrl')):
+            formats.append({
+                'url': http_url,
+                'format_id': 'http-source',
+                'ext': 'mp4',
+                'quality': 1,
+            })
+        formats = [fmt for fmt in formats if 'video/privacy-protected-guest' not in fmt['url']]
+        if not formats:
+            # Fallback, does not require auth
+            self.report_warning('Video formats are not available through API, falling back to social video URL')
+            urlh = self._request_webpage(
+                f'https://medal.tv/api/content/{video_id}/socialVideoUrl', video_id,
+                note='Checking social video URL')
+            formats.append({
+                'url': urlh.url,
+                'format_id': 'social-video',
+                'ext': 'mp4',
+                'quality': -1,
+            })
 
         return {
             'id': video_id,
-            'title': title,
             'formats': formats,
-            'thumbnails': thumbnails,
-            'description': clip.get('contentDescription'),
-            'uploader': author.get('displayName'),
-            'timestamp': float_or_none(clip.get('created'), 1000),
-            'uploader_id': author_id,
-            'uploader_url': author_url,
-            'duration': int_or_none(clip.get('videoLengthSeconds')),
-            'view_count': int_or_none(clip.get('views')),
-            'like_count': int_or_none(clip.get('likes')),
-            'comment_count': int_or_none(clip.get('comments')),
+            **traverse_obj(content_data, {
+                'title': ('contentTitle', {str}),
+                'description': ('contentDescription', {str}),
+                'timestamp': ('created', {int_or_none(scale=1000)}),
+                'duration': ('videoLengthSeconds', {int_or_none}),
+                'view_count': ('views', {int_or_none}),
+                'like_count': ('likes', {int_or_none}),
+                'comment_count': ('comments', {int_or_none}),
+                'uploader': ('poster', 'displayName', {str}),
+                'uploader_id': ('poster', 'userId', {str}),
+                'uploader_url': ('poster', 'userId', {str}, filter, {lambda x: x and f'https://medal.tv/users/{x}'}),
+                'tags': ('tags', ..., {str}),
+                'thumbnail': ('thumbnailUrl', {url_or_none}),
+            }),
         }

plugins/youtube_download/yt_dlp/extractor/mux.py

@@ -0,0 +1,92 @@
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    extract_attributes,
+    filter_dict,
+    parse_qs,
+    smuggle_url,
+    unsmuggle_url,
+    update_url_query,
+)
+from ..utils.traversal import traverse_obj
+
+
+class MuxIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:stream\.new/v|player\.mux\.com)/(?P<id>[A-Za-z0-9-]+)'
+    _EMBED_REGEX = [r'<iframe\b[^>]+\bsrc=["\'](?P<url>(?:https?:)?//(?:stream\.new/v|player\.mux\.com)/(?P<id>[A-Za-z0-9-]+)[^"\']+)']
+    _TESTS = [{
+        'url': 'https://stream.new/v/OCtRWZiZqKvLbnZ32WSEYiGNvHdAmB01j/embed',
+        'info_dict': {
+            'ext': 'mp4',
+            'id': 'OCtRWZiZqKvLbnZ32WSEYiGNvHdAmB01j',
+            'title': 'OCtRWZiZqKvLbnZ32WSEYiGNvHdAmB01j',
+        },
+    }, {
+        'url': 'https://player.mux.com/OCtRWZiZqKvLbnZ32WSEYiGNvHdAmB01j',
+        'info_dict': {
+            'ext': 'mp4',
+            'id': 'OCtRWZiZqKvLbnZ32WSEYiGNvHdAmB01j',
+            'title': 'OCtRWZiZqKvLbnZ32WSEYiGNvHdAmB01j',
+        },
+    }]
+    _WEBPAGE_TESTS = [{
+        # iframe embed
+        'url': 'https://www.redbrickai.com/blog/2025-07-14-FAST-brush',
+        'info_dict': {
+            'ext': 'mp4',
+            'id': 'cXhzAiW1AmsHY01eRbEYFcTEAn0102aGN8sbt8JprP6Dfw',
+            'title': 'cXhzAiW1AmsHY01eRbEYFcTEAn0102aGN8sbt8JprP6Dfw',
+        },
+    }, {
+        # mux-player embed
+        'url': 'https://muxvideo.2coders.com/download/',
+        'info_dict': {
+            'ext': 'mp4',
+            'id': 'JBuasdg35Hw7tYmTe9k68QLPQKixL300YsWHDz5Flit8',
+            'title': 'JBuasdg35Hw7tYmTe9k68QLPQKixL300YsWHDz5Flit8',
+        },
+    }, {
+        # mux-player with title metadata
+        'url': 'https://datastar-todomvc.cross.stream/',
+        'info_dict': {
+            'ext': 'mp4',
+            'id': 'KX01ZSZ8CXv5SVfVwMZKJTcuBcUQmo1ReS9U5JjoHm4k',
+            'title': 'TodoMVC with Datastar Tutorial',
+        },
+    }]
+
+    @classmethod
+    def _extract_embed_urls(cls, url, webpage):
+        yield from super()._extract_embed_urls(url, webpage)
+        for mux_player in re.findall(r'<mux-(?:player|video)\b[^>]*\bplayback-id=[^>]+>', webpage):
+            attrs = extract_attributes(mux_player)
+            playback_id = attrs.get('playback-id')
+            if not playback_id:
+                continue
+            token = attrs.get('playback-token') or traverse_obj(playback_id, ({parse_qs}, 'token', -1))
+            playback_id = playback_id.partition('?')[0]
+
+            embed_url = update_url_query(
+                f'https://player.mux.com/{playback_id}',
+                filter_dict({'playback-token': token}))
+            if title := attrs.get('metadata-video-title'):
+                embed_url = smuggle_url(embed_url, {'title': title})
+            yield embed_url
+
+    def _real_extract(self, url):
+        url, smuggled_data = unsmuggle_url(url, {})
+        video_id = self._match_id(url)
+
+        token = traverse_obj(parse_qs(url), ('playback-token', -1))
+
+        formats, subtitles = self._extract_m3u8_formats_and_subtitles(
+            f'https://stream.mux.com/{video_id}.m3u8', video_id, 'mp4',
+            query=filter_dict({'token': token}))
+
+        return {
+            'id': video_id,
+            'title': smuggled_data.get('title') or video_id,
+            'formats': formats,
+            'subtitles': subtitles,
+        }

plugins/youtube_download/yt_dlp/extractor/nascar.py

@@ -0,0 +1,60 @@
+from .common import InfoExtractor
+from ..utils import (
+    float_or_none,
+    parse_iso8601,
+    url_or_none,
+)
+from ..utils.traversal import traverse_obj
+
+
+class NascarClassicsIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?classics\.nascar\.com/video/(?P<id>[\w~-]+)'
+    _TESTS = [{
+        'url': 'https://classics.nascar.com/video/Ka5qGuxzZ~SIvJii7uAC~wszPshklHN',
+        'md5': '81d712eccffa7169c328281b8cc28f77',
+        'info_dict': {
+            'id': 'Ka5qGuxzZ~SIvJii7uAC~wszPshklHN',
+            'ext': 'mp4',
+            'title': 'Cook Out 400 2023',
+            'thumbnail': 'https://va.aws.nascar.com/IMAGES/CUP_2023_22_RICHMOND_THUMB_NCD.jpg',
+            'timestamp': 1690732800,
+            'upload_date': '20230730',
+            'tags': ['2023', 'race #22', 'richmond', 'chris buescher', 'cup'],
+            'chapters': 'count:18',
+        },
+    }, {
+        'url': 'https://classics.nascar.com/video/UASvPDOwEha~SIvJii7uAC~wszPshklHN',
+        'md5': 'a5e8d6ec6005da3857d25ba2df5e7133',
+        'info_dict': {
+            'id': 'UASvPDOwEha~SIvJii7uAC~wszPshklHN',
+            'ext': 'mp4',
+            'title': 'I Love New York 355 at the Glen 2017',
+            'thumbnail': 'https://va.aws.nascar.com/IMAGES/CUP_2017_22_WATKINSGLEN_THUMB_NCD.jpg',
+            'timestamp': 1501995600,
+            'upload_date': '20170806',
+            'tags': ['watkins glen', 'race #22', '2017', 'martin truex jr.', 'cup'],
+            'chapters': 'count:13',
+        },
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+        content_data = self._search_nextjs_data(
+            webpage, video_id)['props']['pageProps']['contentData']
+
+        return {
+            'id': video_id,
+            'formats': self._extract_m3u8_formats(content_data['input']['src'], video_id, 'mp4'),
+            **traverse_obj(content_data, {
+                'title': ('input', 'name', {str}),
+                'description': ('input', 'description', {str}, filter),
+                'thumbnail': ('input', 'thumbnail', {url_or_none}),
+                'tags': ('input', 'settings', 'tags', ..., {str}),
+                'timestamp': ('input', 'start_time', {parse_iso8601}),
+                'chapters': ('overlay', 'data', 'timelines', 0, 'events', lambda _, v: float(v['timestamp']) is not None, {
+                    'start_time': ('timestamp', {float_or_none}),
+                    'title': ('name', {str}),
+                }),
+            }),
+        }

plugins/youtube_download/yt_dlp/extractor/nbc.py

@@ -63,7 +63,7 @@ class NBCUniversalBaseIE(ThePlatformBaseIE):
         # formats='mpeg4' will return either a working m3u8 URL or an m3u8 template for non-DRM HLS
         # formats='m3u+none,mpeg4' may return DRM HLS but w/the "folders" needed for non-DRM template
         query['formats'] = 'm3u+none,mpeg4'
-        m3u8_url = self._download_nbcu_smil_and_extract_m3u8_url(tp_path, video_id, query)
+        orig_m3u8_url = m3u8_url = self._download_nbcu_smil_and_extract_m3u8_url(tp_path, video_id, query)
 
         if mobj := re.fullmatch(self._M3U8_RE, m3u8_url):
             query['formats'] = 'mpeg4'
@@ -76,7 +76,17 @@ class NBCUniversalBaseIE(ThePlatformBaseIE):
         if '/mpeg_cenc' in m3u8_url or '/mpeg_cbcs' in m3u8_url:
             self.report_drm(video_id)
 
-        return self._extract_m3u8_formats_and_subtitles(m3u8_url, video_id, 'mp4', m3u8_id='hls')
+        formats, subtitles = self._extract_m3u8_formats_and_subtitles(
+            m3u8_url, video_id, 'mp4', m3u8_id='hls', fatal=False)
+
+        if not formats and m3u8_url != orig_m3u8_url:
+            orig_fmts, subtitles = self._extract_m3u8_formats_and_subtitles(
+                orig_m3u8_url, video_id, 'mp4', m3u8_id='hls', fatal=False)
+            formats = [f for f in orig_fmts if not f.get('has_drm')]
+            if orig_fmts and not formats:
+                self.report_drm(video_id)
+
+        return formats, subtitles
 
     def _extract_nbcu_video(self, url, display_id, old_ie_key=None):
         webpage = self._download_webpage(url, display_id)

plugins/youtube_download/yt_dlp/extractor/nebula.py

@@ -478,3 +478,64 @@ class NebulaChannelIE(NebulaBaseIE):
             playlist_id=collection_slug,
             playlist_title=channel.get('title'),
             playlist_description=channel.get('description'))
+
+
+class NebulaSeasonIE(NebulaBaseIE):
+    IE_NAME = 'nebula:season'
+    _VALID_URL = rf'{_BASE_URL_RE}/(?P<series>[\w-]+)/season/(?P<season_number>[\w-]+)'
+    _TESTS = [{
+        'url': 'https://nebula.tv/jetlag/season/15',
+        'info_dict': {
+            'id': 'jetlag_15',
+            'title': 'Tag: All Stars',
+            'description': 'md5:5aa5b8abf3de71756448dc44ffebb674',
+        },
+        'playlist_count': 8,
+    }, {
+        'url': 'https://nebula.tv/jetlag/season/14',
+        'info_dict': {
+            'id': 'jetlag_14',
+            'title': 'Snake',
+            'description': 'md5:6da9040f1c2ac559579738bfb6919d1e',
+        },
+        'playlist_count': 8,
+    }, {
+        'url': 'https://nebula.tv/jetlag/season/13-5',
+        'info_dict': {
+            'id': 'jetlag_13-5',
+            'title': 'Hide + Seek Across NYC',
+            'description': 'md5:5b87bb9acc6dcdff289bb4c71a2ad59f',
+        },
+        'playlist_count': 3,
+    }]
+
+    def _build_url_result(self, item):
+        url = (
+            traverse_obj(item, ('share_url', {url_or_none}))
+            or urljoin('https://nebula.tv/', item.get('app_path'))
+            or f'https://nebula.tv/videos/{item["slug"]}')
+        return self.url_result(
+            smuggle_url(url, {'id': item['id']}),
+            NebulaIE, url_transparent=True,
+            **self._extract_video_metadata(item))
+
+    def _entries(self, data):
+        for episode in traverse_obj(data, ('episodes', lambda _, v: v['video']['id'], 'video')):
+            yield self._build_url_result(episode)
+        for extra in traverse_obj(data, ('extras', ..., 'items', lambda _, v: v['id'])):
+            yield self._build_url_result(extra)
+        for trailer in traverse_obj(data, ('trailers', lambda _, v: v['id'])):
+            yield self._build_url_result(trailer)
+
+    def _real_extract(self, url):
+        series, season_id = self._match_valid_url(url).group('series', 'season_number')
+        playlist_id = f'{series}_{season_id}'
+        data = self._call_api(
+            f'https://content.api.nebula.app/content/{series}/season/{season_id}', playlist_id)
+
+        return self.playlist_result(
+            self._entries(data), playlist_id,
+            **traverse_obj(data, {
+                'title': ('title', {str}),
+                'description': ('description', {str}),
+            }))

plugins/youtube_download/yt_dlp/extractor/netapp.py

@@ -0,0 +1,79 @@
+from .brightcove import BrightcoveNewIE
+from .common import InfoExtractor
+from ..utils import parse_iso8601
+from ..utils.traversal import require, traverse_obj
+
+
+class NetAppBaseIE(InfoExtractor):
+    _BC_URL = 'https://players.brightcove.net/6255154784001/default_default/index.html?videoId={}'
+
+    @staticmethod
+    def _parse_metadata(item):
+        return traverse_obj(item, {
+            'title': ('name', {str}),
+            'description': ('description', {str}),
+            'timestamp': ('createdAt', {parse_iso8601}),
+        })
+
+
+class NetAppVideoIE(NetAppBaseIE):
+    _VALID_URL = r'https?://media\.netapp\.com/video-detail/(?P<id>[0-9a-f-]+)'
+
+    _TESTS = [{
+        'url': 'https://media.netapp.com/video-detail/da25fc01-82ad-5284-95bc-26920200a222/seamless-storage-for-modern-kubernetes-deployments',
+        'info_dict': {
+            'id': '1843620950167202073',
+            'ext': 'mp4',
+            'title': 'Seamless storage for modern Kubernetes deployments',
+            'description': 'md5:1ee39e315243fe71fb90af2796037248',
+            'uploader_id': '6255154784001',
+            'duration': 2159.41,
+            'thumbnail': r're:https://house-fastly-signed-us-east-1-prod\.brightcovecdn\.com/image/.*\.jpg',
+            'tags': 'count:15',
+            'timestamp': 1758213949,
+            'upload_date': '20250918',
+        },
+    }, {
+        'url': 'https://media.netapp.com/video-detail/45593e5d-cf1c-5996-978c-c9081906e69f/unleash-ai-innovation-with-your-data-with-the-netapp-platform',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        video_uuid = self._match_id(url)
+        metadata = self._download_json(
+            f'https://api.media.netapp.com/client/detail/{video_uuid}', video_uuid)
+
+        brightcove_video_id = traverse_obj(metadata, (
+            'sections', lambda _, v: v['type'] == 'Player', 'video', {str}, any, {require('brightcove video id')}))
+
+        video_item = traverse_obj(metadata, ('sections', lambda _, v: v['type'] == 'VideoDetail', any))
+
+        return self.url_result(
+            self._BC_URL.format(brightcove_video_id), BrightcoveNewIE, brightcove_video_id,
+            url_transparent=True, **self._parse_metadata(video_item))
+
+
+class NetAppCollectionIE(NetAppBaseIE):
+    _VALID_URL = r'https?://media\.netapp\.com/collection/(?P<id>[0-9a-f-]+)'
+    _TESTS = [{
+        'url': 'https://media.netapp.com/collection/9820e190-f2a6-47ac-9c0a-98e5e64234a4',
+        'info_dict': {
+            'title': 'Featured sessions',
+            'id': '9820e190-f2a6-47ac-9c0a-98e5e64234a4',
+        },
+        'playlist_count': 4,
+    }]
+
+    def _entries(self, metadata):
+        for item in traverse_obj(metadata, ('items', lambda _, v: v['brightcoveVideoId'])):
+            brightcove_video_id = item['brightcoveVideoId']
+            yield self.url_result(
+                self._BC_URL.format(brightcove_video_id), BrightcoveNewIE, brightcove_video_id,
+                url_transparent=True, **self._parse_metadata(item))
+
+    def _real_extract(self, url):
+        collection_uuid = self._match_id(url)
+        metadata = self._download_json(
+            f'https://api.media.netapp.com/client/collection/{collection_uuid}', collection_uuid)
+
+        return self.playlist_result(self._entries(metadata), collection_uuid, playlist_title=metadata.get('name'))

plugins/youtube_download/yt_dlp/extractor/neteasemusic.py

@@ -528,7 +528,7 @@ class NetEaseMusicMvIE(NetEaseMusicBaseIE):
 class NetEaseMusicProgramIE(NetEaseMusicBaseIE):
     IE_NAME = 'netease:program'
     IE_DESC = '网易云音乐 - 电台节目'
-    _VALID_URL = r'https?://music\.163\.com/(?:#/)?program\?id=(?P<id>[0-9]+)'
+    _VALID_URL = r'https?://music\.163\.com/(?:#/)?(?:dj|program)\?id=(?P<id>[0-9]+)'
     _TESTS = [{
         'url': 'http://music.163.com/#/program?id=10109055',
         'info_dict': {
@@ -572,6 +572,9 @@ class NetEaseMusicProgramIE(NetEaseMusicBaseIE):
         'params': {
             'noplaylist': True,
         },
+    }, {
+        'url': 'https://music.163.com/#/dj?id=3706179315',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):

plugins/youtube_download/yt_dlp/extractor/netzkino.py

@@ -2,84 +2,59 @@ from .common import InfoExtractor
 from ..utils import (
     clean_html,
     int_or_none,
-    js_to_json,
-    parse_iso8601,
+    url_or_none,
+    urljoin,
 )
+from ..utils.traversal import traverse_obj
 
 
 class NetzkinoIE(InfoExtractor):
-    _WORKING = False
-    _VALID_URL = r'https?://(?:www\.)?netzkino\.de/\#!/[^/]+/(?P<id>[^/]+)'
-
+    _GEO_COUNTRIES = ['DE']
+    _VALID_URL = r'https?://(?:www\.)?netzkino\.de/details/(?P<id>[^/?#]+)'
     _TESTS = [{
-        'url': 'https://www.netzkino.de/#!/scifikino/rakete-zum-mond',
-        'md5': '92a3f8b76f8d7220acce5377ea5d4873',
+        'url': 'https://www.netzkino.de/details/snow-beast',
+        'md5': '1a4c90fe40d3ccabce163287e45e56dd',
         'info_dict': {
-            'id': 'rakete-zum-mond',
+            'id': 'snow-beast',
             'ext': 'mp4',
-            'title': 'Rakete zum Mond \u2013 Jules Verne',
-            'description': 'md5:f0a8024479618ddbfa450ff48ffa6c60',
-            'upload_date': '20120813',
-            'thumbnail': r're:https?://.*\.jpg$',
-            'timestamp': 1344858571,
+            'title': 'Snow Beast',
             'age_limit': 12,
-        },
-        'params': {
-            'skip_download': 'Download only works from Germany',
-        },
-    }, {
-        'url': 'https://www.netzkino.de/#!/filme/dr-jekyll-mrs-hyde-2',
-        'md5': 'c7728b2dadd04ff6727814847a51ef03',
-        'info_dict': {
-            'id': 'dr-jekyll-mrs-hyde-2',
-            'ext': 'mp4',
-            'title': 'Dr. Jekyll & Mrs. Hyde 2',
-            'description': 'md5:c2e9626ebd02de0a794b95407045d186',
-            'upload_date': '20190130',
-            'thumbnail': r're:https?://.*\.jpg$',
-            'timestamp': 1548849437,
-            'age_limit': 18,
-        },
-        'params': {
-            'skip_download': 'Download only works from Germany',
+            'alt_title': 'Snow Beast',
+            'cast': 'count:3',
+            'categories': 'count:7',
+            'creators': 'count:2',
+            'description': 'md5:e604a954a7f827a80e96a3a97d48b269',
+            'location': 'US',
+            'release_year': 2011,
+            'thumbnail': r're:https?://.+\.jpg',
         },
     }]
 
     def _real_extract(self, url):
-        mobj = self._match_valid_url(url)
-        video_id = mobj.group('id')
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+        next_js_data = self._search_nextjs_data(webpage, video_id)
 
-        api_url = f'https://api.netzkino.de.simplecache.net/capi-2.0a/movies/{video_id}.json?d=www'
-        info = self._download_json(api_url, video_id)
-        custom_fields = info['custom_fields']
-
-        production_js = self._download_webpage(
-            'http://www.netzkino.de/beta/dist/production.min.js', video_id,
-            note='Downloading player code')
-        avo_js = self._search_regex(
-            r'var urlTemplate=(\{.*?"\})',
-            production_js, 'URL templates')
-        templates = self._parse_json(
-            avo_js, video_id, transform_source=js_to_json)
-
-        suffix = {
-            'hds': '.mp4/manifest.f4m',
-            'hls': '.mp4/master.m3u8',
-            'pmd': '.mp4',
-        }
-        film_fn = custom_fields['Streaming'][0]
-        formats = [{
-            'format_id': key,
-            'ext': 'mp4',
-            'url': tpl.replace('{}', film_fn) + suffix[key],
-        } for key, tpl in templates.items()]
+        query = traverse_obj(next_js_data, (
+            'props', '__dehydratedState', 'queries', ..., 'state',
+            'data', 'data', lambda _, v: v['__typename'] == 'CmsMovie', any))
+        if 'DRM' in traverse_obj(query, ('licenses', 'nodes', ..., 'properties', {str})):
+            self.report_drm(video_id)
 
         return {
             'id': video_id,
-            'formats': formats,
-            'title': info['title'],
-            'age_limit': int_or_none(custom_fields.get('FSK')[0]),
-            'timestamp': parse_iso8601(info.get('date'), delimiter=' '),
-            'description': clean_html(info.get('content')),
-            'thumbnail': info.get('thumbnail'),
+            **traverse_obj(query, {
+                'title': ('originalTitle', {clean_html}),
+                'age_limit': ('fskRating', {int_or_none}),
+                'alt_title': ('originalTitle', {clean_html}, filter),
+                'cast': ('cast', 'nodes', ..., 'person', 'name', {clean_html}, filter),
+                'creators': (('directors', 'writers'), 'nodes', ..., 'person', 'name', {clean_html}, filter),
+                'categories': ('categories', 'nodes', ..., 'category', 'title', {clean_html}, filter),
+                'description': ('longSynopsis', {clean_html}, filter),
+                'duration': ('runtimeInSeconds', {int_or_none}),
+                'location': ('productionCountry', {clean_html}, filter),
+                'release_year': ('productionYear', {int_or_none}),
+                'thumbnail': ('coverImage', 'masterUrl', {url_or_none}),
+                'url': ('videoSource', 'pmdUrl', {urljoin('https://pmd.netzkino-seite.netzkino.de/')}),
+            }),
         }

plugins/youtube_download/yt_dlp/extractor/nextmedia.py

@@ -1,238 +0,0 @@
-import urllib.parse
-
-from .common import InfoExtractor
-from ..utils import (
-    clean_html,
-    get_element_by_class,
-    int_or_none,
-    parse_iso8601,
-    remove_start,
-    unified_timestamp,
-)
-
-
-class NextMediaIE(InfoExtractor):
-    IE_DESC = '蘋果日報'
-    _VALID_URL = r'https?://hk\.apple\.nextmedia\.com/[^/]+/[^/]+/(?P<date>\d+)/(?P<id>\d+)'
-    _TESTS = [{
-        'url': 'http://hk.apple.nextmedia.com/realtime/news/20141108/53109199',
-        'md5': 'dff9fad7009311c421176d1ac90bfe4f',
-        'info_dict': {
-            'id': '53109199',
-            'ext': 'mp4',
-            'title': '【佔領金鐘】50外國領事議員撐場 讚學生勇敢香港有希望',
-            'thumbnail': r're:^https?://.*\.jpg$',
-            'description': 'md5:28222b9912b6665a21011b034c70fcc7',
-            'timestamp': 1415456273,
-            'upload_date': '20141108',
-        },
-    }]
-
-    _URL_PATTERN = r'\{ url: \'(.+)\' \}'
-
-    def _real_extract(self, url):
-        news_id = self._match_id(url)
-        page = self._download_webpage(url, news_id)
-        return self._extract_from_nextmedia_page(news_id, url, page)
-
-    def _extract_from_nextmedia_page(self, news_id, url, page):
-        redirection_url = self._search_regex(
-            r'window\.location\.href\s*=\s*([\'"])(?P<url>(?!\1).+)\1',
-            page, 'redirection URL', default=None, group='url')
-        if redirection_url:
-            return self.url_result(urllib.parse.urljoin(url, redirection_url))
-
-        title = self._fetch_title(page)
-        video_url = self._search_regex(self._URL_PATTERN, page, 'video url')
-
-        attrs = {
-            'id': news_id,
-            'title': title,
-            'url': video_url,  # ext can be inferred from url
-            'thumbnail': self._fetch_thumbnail(page),
-            'description': self._fetch_description(page),
-        }
-
-        timestamp = self._fetch_timestamp(page)
-        if timestamp:
-            attrs['timestamp'] = timestamp
-        else:
-            attrs['upload_date'] = self._fetch_upload_date(url)
-
-        return attrs
-
-    def _fetch_title(self, page):
-        return self._og_search_title(page)
-
-    def _fetch_thumbnail(self, page):
-        return self._og_search_thumbnail(page)
-
-    def _fetch_timestamp(self, page):
-        date_created = self._search_regex('"dateCreated":"([^"]+)"', page, 'created time')
-        return parse_iso8601(date_created)
-
-    def _fetch_upload_date(self, url):
-        return self._search_regex(self._VALID_URL, url, 'upload date', group='date')
-
-    def _fetch_description(self, page):
-        return self._og_search_property('description', page)
-
-
-class NextMediaActionNewsIE(NextMediaIE):  # XXX: Do not subclass from concrete IE
-    IE_DESC = '蘋果日報 - 動新聞'
-    _VALID_URL = r'https?://hk\.dv\.nextmedia\.com/actionnews/[^/]+/(?P<date>\d+)/(?P<id>\d+)/\d+'
-    _TESTS = [{
-        'url': 'http://hk.dv.nextmedia.com/actionnews/hit/20150121/19009428/20061460',
-        'md5': '05fce8ffeed7a5e00665d4b7cf0f9201',
-        'info_dict': {
-            'id': '19009428',
-            'ext': 'mp4',
-            'title': '【壹週刊】細10年男友偷食　50歲邵美琪再失戀',
-            'thumbnail': r're:^https?://.*\.jpg$',
-            'description': 'md5:cd802fad1f40fd9ea178c1e2af02d659',
-            'timestamp': 1421791200,
-            'upload_date': '20150120',
-        },
-    }]
-
-    def _real_extract(self, url):
-        news_id = self._match_id(url)
-        actionnews_page = self._download_webpage(url, news_id)
-        article_url = self._og_search_url(actionnews_page)
-        article_page = self._download_webpage(article_url, news_id)
-        return self._extract_from_nextmedia_page(news_id, url, article_page)
-
-
-class AppleDailyIE(NextMediaIE):  # XXX: Do not subclass from concrete IE
-    IE_DESC = '臺灣蘋果日報'
-    _VALID_URL = r'https?://(www|ent)\.appledaily\.com\.tw/[^/]+/[^/]+/[^/]+/(?P<date>\d+)/(?P<id>\d+)(/.*)?'
-    _TESTS = [{
-        'url': 'http://ent.appledaily.com.tw/enews/article/entertainment/20150128/36354694',
-        'md5': 'a843ab23d150977cc55ef94f1e2c1e4d',
-        'info_dict': {
-            'id': '36354694',
-            'ext': 'mp4',
-            'title': '周亭羽走過摩鐵陰霾2男陪吃 九把刀孤寒看醫生',
-            'thumbnail': r're:^https?://.*\.jpg$',
-            'description': 'md5:2acd430e59956dc47cd7f67cb3c003f4',
-            'upload_date': '20150128',
-        },
-    }, {
-        'url': 'http://www.appledaily.com.tw/realtimenews/article/strange/20150128/550549/%E4%B8%8D%E6%BB%BF%E8%A2%AB%E8%B8%A9%E8%85%B3%E3%80%80%E5%B1%B1%E6%9D%B1%E5%85%A9%E5%A4%A7%E5%AA%BD%E4%B8%80%E8%B7%AF%E6%89%93%E4%B8%8B%E8%BB%8A',
-        'md5': '86b4e9132d158279c7883822d94ccc49',
-        'info_dict': {
-            'id': '550549',
-            'ext': 'mp4',
-            'title': '不滿被踩腳　山東兩大媽一路打下車',
-            'thumbnail': r're:^https?://.*\.jpg$',
-            'description': 'md5:175b4260c1d7c085993474217e4ab1b4',
-            'upload_date': '20150128',
-        },
-    }, {
-        'url': 'http://www.appledaily.com.tw/animation/realtimenews/new/20150128/5003671',
-        'md5': '03df296d95dedc2d5886debbb80cb43f',
-        'info_dict': {
-            'id': '5003671',
-            'ext': 'mp4',
-            'title': '20正妹熱舞　《刀龍傳說Online》火辣上市',
-            'thumbnail': r're:^https?://.*\.jpg$',
-            'description': 'md5:23c0aac567dc08c9c16a3161a2c2e3cd',
-            'upload_date': '20150128',
-        },
-        'skip': 'redirect to http://www.appledaily.com.tw/animation/',
-    }, {
-        # No thumbnail
-        'url': 'http://www.appledaily.com.tw/animation/realtimenews/new/20150128/5003673/',
-        'md5': 'b06182cd386ea7bc6115ec7ff0f72aeb',
-        'info_dict': {
-            'id': '5003673',
-            'ext': 'mp4',
-            'title': '半夜尿尿　好像會看到___',
-            'description': 'md5:61d2da7fe117fede148706cdb85ac066',
-            'upload_date': '20150128',
-        },
-        'expected_warnings': [
-            'video thumbnail',
-        ],
-        'skip': 'redirect to http://www.appledaily.com.tw/animation/',
-    }, {
-        'url': 'http://www.appledaily.com.tw/appledaily/article/supplement/20140417/35770334/',
-        'md5': 'eaa20e6b9df418c912d7f5dec2ba734d',
-        'info_dict': {
-            'id': '35770334',
-            'ext': 'mp4',
-            'title': '咖啡占卜測 XU裝熟指數',
-            'thumbnail': r're:^https?://.*\.jpg$',
-            'description': 'md5:7b859991a6a4fedbdf3dd3b66545c748',
-            'upload_date': '20140417',
-        },
-    }, {
-        'url': 'http://www.appledaily.com.tw/actionnews/appledaily/7/20161003/960588/',
-        'only_matching': True,
-    }, {
-        # Redirected from http://ent.appledaily.com.tw/enews/article/entertainment/20150128/36354694
-        'url': 'http://ent.appledaily.com.tw/section/article/headline/20150128/36354694',
-        'only_matching': True,
-    }]
-
-    _URL_PATTERN = r'\{url: \'(.+)\'\}'
-
-    def _fetch_title(self, page):
-        return (self._html_search_regex(r'<h1 id="h1">([^<>]+)</h1>', page, 'news title', default=None)
-                or self._html_search_meta('description', page, 'news title'))
-
-    def _fetch_thumbnail(self, page):
-        return self._html_search_regex(r"setInitialImage\(\'([^']+)'\)", page, 'video thumbnail', fatal=False)
-
-    def _fetch_timestamp(self, page):
-        return None
-
-    def _fetch_description(self, page):
-        return self._html_search_meta('description', page, 'news description')
-
-
-class NextTVIE(InfoExtractor):
-    _WORKING = False
-    _ENABLED = None  # XXX: pass through to GenericIE
-    IE_DESC = '壹電視'
-    _VALID_URL = r'https?://(?:www\.)?nexttv\.com\.tw/(?:[^/]+/)+(?P<id>\d+)'
-
-    _TEST = {
-        'url': 'http://www.nexttv.com.tw/news/realtime/politics/11779671',
-        'info_dict': {
-            'id': '11779671',
-            'ext': 'mp4',
-            'title': '「超收稅」近4千億！　藍議員籲發消費券',
-            'thumbnail': r're:^https?://.*\.jpg$',
-            'timestamp': 1484825400,
-            'upload_date': '20170119',
-            'view_count': int,
-        },
-    }
-
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-
-        webpage = self._download_webpage(url, video_id)
-
-        title = self._html_search_regex(
-            r'<h1[^>]*>([^<]+)</h1>', webpage, 'title')
-
-        data = self._hidden_inputs(webpage)
-
-        video_url = data['ntt-vod-src-detailview']
-
-        date_str = get_element_by_class('date', webpage)
-        timestamp = unified_timestamp(date_str + '+0800') if date_str else None
-
-        view_count = int_or_none(remove_start(
-            clean_html(get_element_by_class('click', webpage)), '點閱：'))
-
-        return {
-            'id': video_id,
-            'title': title,
-            'url': video_url,
-            'thumbnail': data.get('ntt-vod-img-src'),
-            'timestamp': timestamp,
-            'view_count': view_count,
-        }

plugins/youtube_download/yt_dlp/extractor/nhk.py

@@ -23,96 +23,38 @@ from ..utils import (
 
 
 class NhkBaseIE(InfoExtractor):
-    _API_URL_TEMPLATE = 'https://nwapi.nhk.jp/nhkworld/%sod%slist/v7b/%s/%s/%s/all%s.json'
+    _API_URL_TEMPLATE = 'https://api.nhkworld.jp/showsapi/v1/{lang}/{content_format}_{page_type}/{m_id}{extra_page}'
     _BASE_URL_REGEX = r'https?://www3\.nhk\.or\.jp/nhkworld/(?P<lang>[a-z]{2})/'
 
     def _call_api(self, m_id, lang, is_video, is_episode, is_clip):
+        content_format = 'video' if is_video else 'audio'
+        content_type = 'clips' if is_clip else 'episodes'
+        if not is_episode:
+            extra_page = f'/{content_format}_{content_type}'
+            page_type = 'programs'
+        else:
+            extra_page = ''
+            page_type = content_type
+
         return self._download_json(
-            self._API_URL_TEMPLATE % (
-                'v' if is_video else 'r',
-                'clip' if is_clip else 'esd',
-                'episode' if is_episode else 'program',
-                m_id, lang, '/all' if is_video else ''),
-            m_id, query={'apikey': 'EJfK8jdS57GqlupFgAfAAwr573q01y6k'})['data']['episodes'] or []
-
-    def _get_api_info(self, refresh=True):
-        if not refresh:
-            return self.cache.load('nhk', 'api_info')
-
-        self.cache.store('nhk', 'api_info', {})
-        movie_player_js = self._download_webpage(
-            'https://movie-a.nhk.or.jp/world/player/js/movie-player.js', None,
-            note='Downloading stream API information')
-        api_info = {
-            'url': self._search_regex(
-                r'prod:[^;]+\bapiUrl:\s*[\'"]([^\'"]+)[\'"]', movie_player_js, None, 'stream API url'),
-            'token': self._search_regex(
-                r'prod:[^;]+\btoken:\s*[\'"]([^\'"]+)[\'"]', movie_player_js, None, 'stream API token'),
-        }
-        self.cache.store('nhk', 'api_info', api_info)
-        return api_info
-
-    def _extract_stream_info(self, vod_id):
-        for refresh in (False, True):
-            api_info = self._get_api_info(refresh)
-            if not api_info:
-                continue
-
-            api_url = api_info.pop('url')
-            meta = traverse_obj(
-                self._download_json(
-                    api_url, vod_id, 'Downloading stream url info', fatal=False, query={
-                        **api_info,
-                        'type': 'json',
-                        'optional_id': vod_id,
-                        'active_flg': 1,
-                    }), ('meta', 0))
-            stream_url = traverse_obj(
-                meta, ('movie_url', ('mb_auto', 'auto_sp', 'auto_pc'), {url_or_none}), get_all=False)
-
-            if stream_url:
-                formats, subtitles = self._extract_m3u8_formats_and_subtitles(stream_url, vod_id)
-                return {
-                    **traverse_obj(meta, {
-                        'duration': ('duration', {int_or_none}),
-                        'timestamp': ('publication_date', {unified_timestamp}),
-                        'release_timestamp': ('insert_date', {unified_timestamp}),
-                        'modified_timestamp': ('update_date', {unified_timestamp}),
-                    }),
-                    'formats': formats,
-                    'subtitles': subtitles,
-                }
-        raise ExtractorError('Unable to extract stream url')
+            self._API_URL_TEMPLATE.format(
+                lang=lang, content_format=content_format, page_type=page_type,
+                m_id=m_id, extra_page=extra_page),
+            join_nonempty(m_id, lang))
 
     def _extract_episode_info(self, url, episode=None):
         fetch_episode = episode is None
         lang, m_type, episode_id = NhkVodIE._match_valid_url(url).group('lang', 'type', 'id')
         is_video = m_type != 'audio'
 
-        if is_video:
-            episode_id = episode_id[:4] + '-' + episode_id[4:]
-
         if fetch_episode:
             episode = self._call_api(
-                episode_id, lang, is_video, True, episode_id[:4] == '9999')[0]
+                episode_id, lang, is_video, is_episode=True, is_clip=episode_id[:4] == '9999')
 
-        def get_clean_field(key):
-            return clean_html(episode.get(key + '_clean') or episode.get(key))
+        video_id = join_nonempty('id', 'lang', from_dict=episode)
 
-        title = get_clean_field('sub_title')
-        series = get_clean_field('title')
-
-        thumbnails = []
-        for s, w, h in [('', 640, 360), ('_l', 1280, 720)]:
-            img_path = episode.get('image' + s)
-            if not img_path:
-                continue
-            thumbnails.append({
-                'id': f'{h}p',
-                'height': h,
-                'width': w,
-                'url': 'https://www3.nhk.or.jp' + img_path,
-            })
+        title = episode.get('title')
+        series = traverse_obj(episode, (('video_program', 'audio_program'), any, 'title'))
 
         episode_name = title
         if series and title:
@@ -125,37 +67,52 @@ class NhkBaseIE(InfoExtractor):
             episode_name = None
 
         info = {
-            'id': episode_id + '-' + lang,
+            'id': video_id,
             'title': title,
-            'description': get_clean_field('description'),
-            'thumbnails': thumbnails,
             'series': series,
             'episode': episode_name,
+            **traverse_obj(episode, {
+                'description': ('description', {str}),
+                'release_timestamp': ('first_broadcasted_at', {unified_timestamp}),
+                'categories': ('categories', ..., 'name', {str}),
+                'tags': ('tags', ..., 'name', {str}),
+                'thumbnails': ('images', lambda _, v: v['url'], {
+                    'url': ('url', {urljoin(url)}),
+                    'width': ('width', {int_or_none}),
+                    'height': ('height', {int_or_none}),
+                }),
+                'webpage_url': ('url', {urljoin(url)}),
+            }),
+            'extractor_key': NhkVodIE.ie_key(),
+            'extractor': NhkVodIE.IE_NAME,
         }
 
-        if is_video:
-            vod_id = episode['vod_id']
-            info.update({
-                **self._extract_stream_info(vod_id),
-                'id': vod_id,
-            })
-
+        # XXX: We are assuming that 'video' and 'audio' are mutually exclusive
+        stream_info = traverse_obj(episode, (('video', 'audio'), {dict}, any)) or {}
+        if not stream_info.get('url'):
+            self.raise_no_formats('Stream not found; it has most likely expired', expected=True)
         else:
-            if fetch_episode:
+            stream_url = stream_info['url']
+            if is_video:
+                formats, subtitles = self._extract_m3u8_formats_and_subtitles(stream_url, video_id)
+                info.update({
+                    'formats': formats,
+                    'subtitles': subtitles,
+                    **traverse_obj(stream_info, ({
+                        'duration': ('duration', {int_or_none}),
+                        'timestamp': ('published_at', {unified_timestamp}),
+                    })),
+                })
+            else:
                 # From https://www3.nhk.or.jp/nhkworld/common/player/radio/inline/rod.html
-                audio_path = remove_end(episode['audio']['audio'], '.m4a')
+                audio_path = remove_end(stream_url, '.m4a')
                 info['formats'] = self._extract_m3u8_formats(
                     f'{urljoin("https://vod-stream.nhk.jp", audio_path)}/index.m3u8',
                     episode_id, 'm4a', entry_protocol='m3u8_native',
                     m3u8_id='hls', fatal=False)
                 for f in info['formats']:
                     f['language'] = lang
-            else:
-                info.update({
-                    '_type': 'url_transparent',
-                    'ie_key': NhkVodIE.ie_key(),
-                    'url': url,
-                })
+
         return info
 
 
@@ -168,29 +125,29 @@ class NhkVodIE(NhkBaseIE):
     # Content available only for a limited period of time. Visit
     # https://www3.nhk.or.jp/nhkworld/en/ondemand/ for working samples.
     _TESTS = [{
-        'url': 'https://www3.nhk.or.jp/nhkworld/en/ondemand/video/2049126/',
+        'url': 'https://www3.nhk.or.jp/nhkworld/en/shows/2049165/',
         'info_dict': {
-            'id': 'nw_vod_v_en_2049_126_20230413233000_01_1681398302',
+            'id': '2049165-en',
             'ext': 'mp4',
-            'title': 'Japan Railway Journal - The Tohoku Shinkansen: Full Speed Ahead',
-            'description': 'md5:49f7c5b206e03868a2fdf0d0814b92f6',
+            'title': 'Japan Railway Journal - Choshi Electric Railway: Fighting to Get Back on Track',
+            'description': 'md5:ab57df2fca7f04245148c2e787bb203d',
             'thumbnail': r're:https://.+/.+\.jpg',
-            'episode': 'The Tohoku Shinkansen: Full Speed Ahead',
+            'episode': 'Choshi Electric Railway: Fighting to Get Back on Track',
             'series': 'Japan Railway Journal',
-            'modified_timestamp': 1707217907,
-            'timestamp': 1681428600,
-            'release_timestamp': 1693883728,
-            'duration': 1679,
-            'upload_date': '20230413',
-            'modified_date': '20240206',
-            'release_date': '20230905',
+            'duration': 1680,
+            'categories': ['Biz & Tech'],
+            'tags': ['Akita', 'Chiba', 'Trains', 'Transcript', 'All (Japan Navigator)'],
+            'timestamp': 1759055880,
+            'upload_date': '20250928',
+            'release_timestamp': 1758810600,
+            'release_date': '20250925',
         },
     }, {
         # video clip
         'url': 'https://www3.nhk.or.jp/nhkworld/en/ondemand/video/9999011/',
         'md5': '153c3016dfd252ba09726588149cf0e7',
         'info_dict': {
-            'id': 'lpZXIwaDE6_Z-976CPsFdxyICyWUzlT5',
+            'id': '9999011-en',
             'ext': 'mp4',
             'title': 'Dining with the Chef - Chef Saito\'s Family recipe: MENCHI-KATSU',
             'description': 'md5:5aee4a9f9d81c26281862382103b0ea5',
@@ -198,24 +155,23 @@ class NhkVodIE(NhkBaseIE):
             'series': 'Dining with the Chef',
             'episode': 'Chef Saito\'s Family recipe: MENCHI-KATSU',
             'duration': 148,
-            'upload_date': '20190816',
-            'release_date': '20230902',
-            'release_timestamp': 1693619292,
-            'modified_timestamp': 1707217907,
-            'modified_date': '20240206',
-            'timestamp': 1565997540,
+            'categories': ['Food'],
+            'tags': ['Washoku'],
+            'timestamp': 1548212400,
+            'upload_date': '20190123',
         },
     }, {
         # radio
-        'url': 'https://www3.nhk.or.jp/nhkworld/en/ondemand/audio/livinginjapan-20231001-1/',
+        'url': 'https://www3.nhk.or.jp/nhkworld/en/shows/audio/livinginjapan-20240901-1/',
         'info_dict': {
-            'id': 'livinginjapan-20231001-1-en',
+            'id': 'livinginjapan-20240901-1-en',
             'ext': 'm4a',
-            'title': 'Living in Japan - Tips for Travelers to Japan / Ramen Vending Machines',
+            'title': 'Living in Japan - Weekend Hiking / Self-protection from crime',
             'series': 'Living in Japan',
-            'description': 'md5:0a0e2077d8f07a03071e990a6f51bfab',
+            'description': 'md5:4d0e14ab73bdbfedb60a53b093954ed6',
             'thumbnail': r're:https://.+/.+\.jpg',
-            'episode': 'Tips for Travelers to Japan / Ramen Vending Machines',
+            'episode': 'Weekend Hiking / Self-protection from crime',
+            'categories': ['Interactive'],
         },
     }, {
         'url': 'https://www3.nhk.or.jp/nhkworld/en/ondemand/video/2015173/',
@@ -256,96 +212,51 @@ class NhkVodIE(NhkBaseIE):
         },
         'skip': 'expires 2023-10-15',
     }, {
-        # a one-off (single-episode series). title from the api is just '<p></p>'
-        'url': 'https://www3.nhk.or.jp/nhkworld/en/ondemand/video/3004952/',
+        # a one-off (single-episode series). title from the api is just null
+        'url': 'https://www3.nhk.or.jp/nhkworld/en/shows/3026036/',
         'info_dict': {
-            'id': 'nw_vod_v_en_3004_952_20230723091000_01_1690074552',
+            'id': '3026036-en',
             'ext': 'mp4',
-            'title': 'Barakan Discovers - AMAMI OSHIMA: Isson\'s Treasure Isla',
-            'description': 'md5:5db620c46a0698451cc59add8816b797',
-            'thumbnail': r're:https://.+/.+\.jpg',
-            'release_date': '20230905',
-            'timestamp': 1690103400,
-            'duration': 2939,
-            'release_timestamp': 1693898699,
-            'upload_date': '20230723',
-            'modified_timestamp': 1707217907,
-            'modified_date': '20240206',
-            'episode': 'AMAMI OSHIMA: Isson\'s Treasure Isla',
-            'series': 'Barakan Discovers',
+            'title': 'STATELESS: The Japanese Left Behind in the Philippines',
+            'description': 'md5:9a2fd51cdfa9f52baae28569e0053786',
+            'duration': 2955,
+            'thumbnail': 'https://www3.nhk.or.jp/nhkworld/en/shows/3026036/images/wide_l_QPtWpt4lzVhm3NzPAMIIF35MCg4CdNwcikPaTS5Q.jpg',
+            'categories': ['Documentary', 'Culture & Lifestyle'],
+            'tags': ['Transcript', 'Documentary 360', 'The Pursuit of PEACE'],
+            'timestamp': 1758931800,
+            'upload_date': '20250927',
+            'release_timestamp': 1758931800,
+            'release_date': '20250927',
         },
     }, {
         # /ondemand/video/ url with alphabetical character in 5th position of id
         'url': 'https://www3.nhk.or.jp/nhkworld/en/ondemand/video/9999a07/',
         'info_dict': {
-            'id': 'nw_c_en_9999-a07',
+            'id': '9999a07-en',
             'ext': 'mp4',
             'episode': 'Mini-Dramas on SDGs: Ep 1 Close the Gender Gap [Director\'s Cut]',
             'series': 'Mini-Dramas on SDGs',
-            'modified_date': '20240206',
             'title': 'Mini-Dramas on SDGs - Mini-Dramas on SDGs: Ep 1 Close the Gender Gap [Director\'s Cut]',
             'description': 'md5:3f9dcb4db22fceb675d90448a040d3f6',
-            'timestamp': 1621962360,
-            'duration': 189,
-            'release_date': '20230903',
-            'modified_timestamp': 1707217907,
+            'timestamp': 1621911600,
+            'duration': 190,
             'upload_date': '20210525',
             'thumbnail': r're:https://.+/.+\.jpg',
-            'release_timestamp': 1693713487,
+            'categories': ['Current Affairs', 'Entertainment'],
         },
     }, {
         'url': 'https://www3.nhk.or.jp/nhkworld/en/ondemand/video/9999d17/',
         'info_dict': {
-            'id': 'nw_c_en_9999-d17',
+            'id': '9999d17-en',
             'ext': 'mp4',
             'title': 'Flowers of snow blossom - The 72 Pentads of Yamato',
             'description': 'Today’s focus: Snow',
-            'release_timestamp': 1693792402,
-            'release_date': '20230904',
-            'upload_date': '20220128',
-            'timestamp': 1643370960,
             'thumbnail': r're:https://.+/.+\.jpg',
             'duration': 136,
-            'series': '',
-            'modified_date': '20240206',
-            'modified_timestamp': 1707217907,
-        },
-    }, {
-        # new /shows/ url format
-        'url': 'https://www3.nhk.or.jp/nhkworld/en/shows/2032307/',
-        'info_dict': {
-            'id': 'nw_vod_v_en_2032_307_20240321113000_01_1710990282',
-            'ext': 'mp4',
-            'title': 'Japanology Plus - 20th Anniversary Special Part 1',
-            'description': 'md5:817d41fc8e54339ad2a916161ea24faf',
-            'episode': '20th Anniversary Special Part 1',
-            'series': 'Japanology Plus',
-            'thumbnail': r're:https://.+/.+\.jpg',
-            'duration': 1680,
-            'timestamp': 1711020600,
-            'upload_date': '20240321',
-            'release_timestamp': 1711022683,
-            'release_date': '20240321',
-            'modified_timestamp': 1711031012,
-            'modified_date': '20240321',
-        },
-    }, {
-        'url': 'https://www3.nhk.or.jp/nhkworld/en/shows/3020025/',
-        'info_dict': {
-            'id': 'nw_vod_v_en_3020_025_20230325144000_01_1679723944',
-            'ext': 'mp4',
-            'title': '100 Ideas to Save the World - Working Styles Evolve',
-            'description': 'md5:9e6c7778eaaf4f7b4af83569649f84d9',
-            'episode': 'Working Styles Evolve',
-            'series': '100 Ideas to Save the World',
-            'thumbnail': r're:https://.+/.+\.jpg',
-            'duration': 899,
-            'upload_date': '20230325',
-            'timestamp': 1679755200,
-            'release_date': '20230905',
-            'release_timestamp': 1693880540,
-            'modified_date': '20240206',
-            'modified_timestamp': 1707217907,
+            'categories': ['Culture & Lifestyle', 'Science & Nature'],
+            'tags': ['Nara', 'Temples & Shrines', 'Winter', 'Snow'],
+            'timestamp': 1643339040,
+            'upload_date': '20220128',
         },
     }, {
         # new /shows/audio/ url format
@@ -373,6 +284,7 @@ class NhkVodProgramIE(NhkBaseIE):
             'id': 'sumo',
             'title': 'GRAND SUMO Highlights',
             'description': 'md5:fc20d02dc6ce85e4b72e0273aa52fdbf',
+            'series': 'GRAND SUMO Highlights',
         },
         'playlist_mincount': 1,
     }, {
@@ -381,6 +293,7 @@ class NhkVodProgramIE(NhkBaseIE):
             'id': 'japanrailway',
             'title': 'Japan Railway Journal',
             'description': 'md5:ea39d93af7d05835baadf10d1aae0e3f',
+            'series': 'Japan Railway Journal',
         },
         'playlist_mincount': 12,
     }, {
@@ -390,6 +303,7 @@ class NhkVodProgramIE(NhkBaseIE):
             'id': 'japanrailway',
             'title': 'Japan Railway Journal',
             'description': 'md5:ea39d93af7d05835baadf10d1aae0e3f',
+            'series': 'Japan Railway Journal',
         },
         'playlist_mincount': 12,
     }, {
@@ -399,17 +313,9 @@ class NhkVodProgramIE(NhkBaseIE):
             'id': 'livinginjapan',
             'title': 'Living in Japan',
             'description': 'md5:665bb36ec2a12c5a7f598ee713fc2b54',
+            'series': 'Living in Japan',
         },
-        'playlist_mincount': 12,
-    }, {
-        # /tv/ program url
-        'url': 'https://www3.nhk.or.jp/nhkworld/en/tv/designtalksplus/',
-        'info_dict': {
-            'id': 'designtalksplus',
-            'title': 'DESIGN TALKS plus',
-            'description': 'md5:47b3b3a9f10d4ac7b33b53b70a7d2837',
-        },
-        'playlist_mincount': 20,
+        'playlist_mincount': 11,
     }, {
         'url': 'https://www3.nhk.or.jp/nhkworld/en/shows/10yearshayaomiyazaki/',
         'only_matching': True,
@@ -430,9 +336,8 @@ class NhkVodProgramIE(NhkBaseIE):
             program_id, lang, m_type != 'audio', False, episode_type == 'clip')
 
         def entries():
-            for episode in episodes:
-                if episode_path := episode.get('url'):
-                    yield self._extract_episode_info(urljoin(url, episode_path), episode)
+            for episode in traverse_obj(episodes, ('items', lambda _, v: v['url'])):
+                yield self._extract_episode_info(urljoin(url, episode['url']), episode)
 
         html = self._download_webpage(url, program_id)
         program_title = self._extract_meta_from_class_elements([
@@ -446,7 +351,7 @@ class NhkVodProgramIE(NhkBaseIE):
             'tAudioProgramMain__info',  # /shows/audio/programs/
             'p-program-description'], html)  # /tv/
 
-        return self.playlist_result(entries(), program_id, program_title, program_description)
+        return self.playlist_result(entries(), program_id, program_title, program_description, series=program_title)
 
 
 class NhkForSchoolBangumiIE(InfoExtractor):

plugins/youtube_download/yt_dlp/extractor/nowcanal.py

@@ -0,0 +1,37 @@
+from .brightcove import BrightcoveNewIE
+from .common import InfoExtractor
+
+
+class NowCanalIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?nowcanal\.pt(?:/[\w-]+)+/detalhe/(?P<id>[\w-]+)'
+    _TESTS = [{
+        'url': 'https://www.nowcanal.pt/ultimas/detalhe/pedro-sousa-hjulmand-pode-ter-uma-saida-limpa-do-sporting-daqui-a-um-ano',
+        'md5': '047f17cb783e66e467d703e704bbc95d',
+        'info_dict': {
+            'id': '6376598467112',
+            'ext': 'mp4',
+            'title': 'Pedro Sousa «Hjulmand pode ter uma saída limpa do Sporting daqui a um ano»',
+            'description': '',
+            'uploader_id': '6108484330001',
+            'duration': 65.237,
+            'thumbnail': r're:^https://.+\.jpg',
+            'timestamp': 1754440620,
+            'upload_date': '20250806',
+            'tags': ['now'],
+        },
+    }, {
+        'url': 'https://www.nowcanal.pt/programas/frente-a-frente/detalhe/frente-a-frente-eva-cruzeiro-ps-e-rita-matias-chega',
+        'only_matching': True,
+    }]
+
+    _BC_URL_TMPL = 'https://players.brightcove.net/6108484330001/chhIqzukMq_default/index.html?videoId={}'
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_id)
+
+        video_id = self._search_json(
+            r'videoHandler\.addBrightcoveVideoWithJson\(\[',
+            webpage, 'video data', display_id)['brightcoveVideoId']
+
+        return self.url_result(self._BC_URL_TMPL.format(video_id), BrightcoveNewIE)

plugins/youtube_download/yt_dlp/extractor/ntvru.py

@@ -1,17 +1,40 @@
 from .common import InfoExtractor
 from ..utils import (
     int_or_none,
-    strip_or_none,
+    parse_iso8601,
     unescapeHTML,
+    url_or_none,
     xpath_text,
 )
+from ..utils.traversal import traverse_obj
 
 
 class NTVRuIE(InfoExtractor):
     IE_NAME = 'ntv.ru'
-    _VALID_URL = r'https?://(?:www\.)?ntv\.ru/(?:[^/]+/)*(?P<id>[^/?#&]+)'
+    _VALID_URL = r'https?://(?:www\.)?ntv\.ru/(?:[^/#?]+/)*(?P<id>[^/?#&]+)'
 
     _TESTS = [{
+        # JSON Api is geo restricted
+        'url': 'https://www.ntv.ru/peredacha/svoya_igra/m58980/o818800',
+        'md5': '818962a1b52747d446db7cd5be43e142',
+        'info_dict': {
+            'id': '2520563',
+            'ext': 'mp4',
+            'title': 'Участники: Ирина Петрова, Сергей Коновалов, Кристина Кораблина',
+            'description': 'md5:fcbd21cd45238a940b95550f9e178e3e',
+            'thumbnail': r're:^http://.*\.jpg',
+            'duration': 2462,
+            'view_count': int,
+            'comment_count': int,
+            'tags': ['игры и игрушки'],
+            'timestamp': 1761821096,
+            'upload_date': '20251030',
+            'release_timestamp': 1761821096,
+            'release_date': '20251030',
+            'modified_timestamp': 1761821096,
+            'modified_date': '20251030',
+        },
+    }, {
         'url': 'http://www.ntv.ru/novosti/863142/',
         'md5': 'ba7ea172a91cb83eb734cad18c10e723',
         'info_dict': {
@@ -22,31 +45,35 @@ class NTVRuIE(InfoExtractor):
             'thumbnail': r're:^http://.*\.jpg',
             'duration': 136,
             'view_count': int,
+            'comment_count': int,
+            'tags': ['ВМС', 'захват', 'митинги', 'Севастополь', 'Украина'],
+            'timestamp': 1395222013,
+            'upload_date': '20140319',
+            'release_timestamp': 1395222013,
+            'release_date': '20140319',
+            'modified_timestamp': 1395222013,
+            'modified_date': '20140319',
         },
     }, {
-        'url': 'http://www.ntv.ru/video/novosti/750370/',
-        'md5': 'adecff79691b4d71e25220a191477124',
-        'info_dict': {
-            'id': '750370',
-            'ext': 'mp4',
-            'title': 'Родные пассажиров пропавшего Boeing не верят в трагический исход',
-            'description': 'Родные пассажиров пропавшего Boeing не верят в трагический исход',
-            'thumbnail': r're:^http://.*\.jpg',
-            'duration': 172,
-            'view_count': int,
-        },
-        'skip': '404 Not Found',
-    }, {
+        # Requires unescapeHTML
         'url': 'http://www.ntv.ru/peredacha/segodnya/m23700/o232416',
         'md5': '82dbd49b38e3af1d00df16acbeab260c',
         'info_dict': {
             'id': '747480',
             'ext': 'mp4',
-            'title': '«Сегодня». 21 марта 2014 года. 16:00',
-            'description': '«Сегодня». 21 марта 2014 года. 16:00',
+            'title': '"Сегодня". 21 марта 2014 года. 16:00 ',
+            'description': 'md5:bed80745ca72af557433195f51a02785',
             'thumbnail': r're:^http://.*\.jpg',
             'duration': 1496,
             'view_count': int,
+            'comment_count': int,
+            'tags': ['Брюссель', 'гражданство', 'ЕС', 'Крым', 'ОСАГО', 'саммит', 'санкции', 'события', 'чиновники', 'рейтинг'],
+            'timestamp': 1395406951,
+            'upload_date': '20140321',
+            'release_timestamp': 1395406951,
+            'release_date': '20140321',
+            'modified_timestamp': 1395406951,
+            'modified_date': '20140321',
         },
     }, {
         'url': 'https://www.ntv.ru/kino/Koma_film/m70281/o336036/video/',
@@ -54,11 +81,19 @@ class NTVRuIE(InfoExtractor):
         'info_dict': {
             'id': '1126480',
             'ext': 'mp4',
-            'title': 'Остросюжетный фильм «Кома»',
-            'description': 'Остросюжетный фильм «Кома»',
+            'title': 'Остросюжетный фильм "Кома"',
+            'description': 'md5:e79ffd0887425a0f05a58885c408d7d8',
             'thumbnail': r're:^http://.*\.jpg',
-            'duration': 5592,
+            'duration': 5608,
             'view_count': int,
+            'comment_count': int,
+            'tags': ['кино'],
+            'timestamp': 1432868572,
+            'upload_date': '20150529',
+            'release_timestamp': 1432868572,
+            'release_date': '20150529',
+            'modified_timestamp': 1432868572,
+            'modified_date': '20150529',
         },
     }, {
         'url': 'http://www.ntv.ru/serial/Delo_vrachey/m31760/o233916/',
@@ -66,11 +101,19 @@ class NTVRuIE(InfoExtractor):
         'info_dict': {
             'id': '751482',
             'ext': 'mp4',
-            'title': '«Дело врачей»: «Деревце жизни»',
-            'description': '«Дело врачей»: «Деревце жизни»',
+            'title': '"Дело врачей": "Деревце жизни"',
+            'description': 'md5:d6fbf9193f880f50d9cbfbcc954161c1',
             'thumbnail': r're:^http://.*\.jpg',
             'duration': 2590,
             'view_count': int,
+            'comment_count': int,
+            'tags': ['врачи', 'больницы'],
+            'timestamp': 1395882300,
+            'upload_date': '20140327',
+            'release_timestamp': 1395882300,
+            'release_date': '20140327',
+            'modified_timestamp': 1395882300,
+            'modified_date': '20140327',
         },
     }, {
         # Schemeless file URL
@@ -78,48 +121,26 @@ class NTVRuIE(InfoExtractor):
         'only_matching': True,
     }]
 
-    _VIDEO_ID_REGEXES = [
-        r'<meta property="og:url" content="https?://www\.ntv\.ru/video/(\d+)',
-        r'<meta property="og:video:(?:url|iframe)" content="https?://www\.ntv\.ru/embed/(\d+)',
-        r'<video embed=[^>]+><id>(\d+)</id>',
-        r'<video restriction[^>]+><key>(\d+)</key>',
-    ]
-
     def _real_extract(self, url):
-        video_id = self._match_id(url)
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_id)
 
-        webpage = self._download_webpage(url, video_id)
-
-        video_url = self._og_search_property(
-            ('video', 'video:iframe'), webpage, default=None)
-        if video_url:
-            video_id = self._search_regex(
-                r'https?://(?:www\.)?ntv\.ru/video/(?:embed/)?(\d+)',
-                video_url, 'video id', default=None)
-
-        if not video_id:
-            video_id = self._html_search_regex(
-                self._VIDEO_ID_REGEXES, webpage, 'video id')
+        video_id = self._html_search_regex(
+            r'<meta property="ya:ovs:feed_url" content="https?://www\.ntv\.ru/(?:exp/)?video/(\d+)', webpage, 'video id')
 
         player = self._download_xml(
             f'http://www.ntv.ru/vi{video_id}/',
             video_id, 'Downloading video XML')
 
-        title = strip_or_none(unescapeHTML(xpath_text(player, './data/title', 'title', fatal=True)))
-
         video = player.find('./data/video')
 
         formats = []
         for format_id in ['', 'hi', 'webm']:
-            file_ = xpath_text(video, f'./{format_id}file')
-            if not file_:
+            video_url = url_or_none(xpath_text(video, f'./{format_id}file'))
+            if not video_url:
                 continue
-            if file_.startswith('//'):
-                file_ = self._proto_relative_url(file_)
-            elif not file_.startswith('http'):
-                file_ = 'http://media.ntv.ru/vod/' + file_
             formats.append({
-                'url': file_,
+                'url': video_url,
                 'filesize': int_or_none(xpath_text(video, f'./{format_id}size')),
             })
         hls_manifest = xpath_text(video, './playback/hls')
@@ -131,12 +152,28 @@ class NTVRuIE(InfoExtractor):
             formats.extend(self._extract_mpd_formats(
                 dash_manifest, video_id, mpd_id='dash', fatal=False))
 
+        metadata = self._download_xml(
+            f'https://www.ntv.ru/exp/video/{video_id}', video_id, 'Downloading XML metadata', fatal=False)
+
         return {
-            'id': xpath_text(video, './id'),
-            'title': title,
-            'description': strip_or_none(unescapeHTML(xpath_text(player, './data/description'))),
-            'thumbnail': xpath_text(video, './splash'),
-            'duration': int_or_none(xpath_text(video, './totaltime')),
-            'view_count': int_or_none(xpath_text(video, './views')),
+            'id': video_id,
             'formats': formats,
+            **traverse_obj(player, {
+                'title': ('data/title/text()', ..., {str}, {unescapeHTML}, any),
+                'description': ('data/description/text()', ..., {str}, {unescapeHTML}, any),
+                'duration': ('data/video/totaltime/text()', ..., {int_or_none}, any),
+                'view_count': ('data/video/views/text()', ..., {int_or_none}, any),
+                'thumbnail': ('data/video/splash/text()', ..., {url_or_none}, any),
+            }),
+            **traverse_obj(metadata, {
+                'title': ('{*}title/text()', ..., {str}, {unescapeHTML}, any),
+                'description': ('{*}description/text()', ..., {str}, {unescapeHTML}, any),
+                'duration': ('{*}duration/text()', ..., {int_or_none}, any),
+                'timestamp': ('{*}create_date/text()', ..., {parse_iso8601}, any),
+                'release_timestamp': ('{*}upload_date/text()', ..., {parse_iso8601}, any),
+                'modified_timestamp': ('{*}modify_date/text()', ..., {parse_iso8601}, any),
+                'tags': ('{*}tag/text()', ..., {str}, {lambda x: x.split(',')}, ..., {str.strip}, filter),
+                'view_count': ('{*}stats/views_total/text()', ..., {int_or_none}, any),
+                'comment_count': ('{*}stats/comments/text()', ..., {int_or_none}, any),
+            }),
         }

plugins/youtube_download/yt_dlp/extractor/pandatv.py

@@ -0,0 +1,83 @@
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+    UserNotLive,
+    filter_dict,
+    int_or_none,
+    join_nonempty,
+    parse_iso8601,
+    url_or_none,
+    urlencode_postdata,
+)
+from ..utils.traversal import traverse_obj
+
+
+class PandaTvIE(InfoExtractor):
+    IE_DESC = 'pandalive.co.kr (팬더티비)'
+    _VALID_URL = r'https?://(?:www\.|m\.)?pandalive\.co\.kr/play/(?P<id>\w+)'
+    _TESTS = [{
+        'url': 'https://www.pandalive.co.kr/play/bebenim',
+        'info_dict': {
+            'id': 'bebenim',
+            'ext': 'mp4',
+            'channel': '릴리ෆ',
+            'title': r're:앙앙❤ \d{4}-\d{2}-\d{2} \d{2}:\d{2}',
+            'thumbnail': r're:https://cdn\.pandalive\.co\.kr/ivs/v1/.+/thumb\.jpg',
+            'concurrent_view_count': int,
+            'like_count': int,
+            'live_status': 'is_live',
+            'upload_date': str,
+        },
+        'skip': 'The channel is not currently live',
+    }]
+
+    def _real_extract(self, url):
+        channel_id = self._match_id(url)
+        video_meta = self._download_json(
+            'https://api.pandalive.co.kr/v1/live/play', channel_id,
+            'Downloading video meta data', 'Unable to download video meta data',
+            data=urlencode_postdata(filter_dict({
+                'action': 'watch',
+                'userId': channel_id,
+                'password': self.get_param('videopassword'),
+            })), expected_status=400)
+
+        if error_code := traverse_obj(video_meta, ('errorData', 'code', {str})):
+            if error_code == 'castEnd':
+                raise UserNotLive(video_id=channel_id)
+            elif error_code == 'needAdult':
+                self.raise_login_required('Adult verification is required for this stream')
+            elif error_code == 'needLogin':
+                self.raise_login_required('Login is required for this stream')
+            elif error_code == 'needCoinPurchase':
+                raise ExtractorError('Coin purchase is required for this stream', expected=True)
+            elif error_code == 'needUnlimitItem':
+                raise ExtractorError('Ticket purchase is required for this stream', expected=True)
+            elif error_code == 'needPw':
+                raise ExtractorError('Password protected video, use --video-password <password>', expected=True)
+            elif error_code == 'wrongPw':
+                raise ExtractorError('Wrong password', expected=True)
+            else:
+                error_msg = video_meta.get('message')
+                raise ExtractorError(join_nonempty(
+                    'API returned error code', error_code,
+                    error_msg and 'with error message:', error_msg,
+                    delim=' '))
+
+        http_headers = {'Origin': 'https://www.pandalive.co.kr'}
+
+        return {
+            'id': channel_id,
+            'is_live': True,
+            'formats': self._extract_m3u8_formats(
+                video_meta['PlayList']['hls'][0]['url'], channel_id, 'mp4', headers=http_headers, live=True),
+            'http_headers': http_headers,
+            **traverse_obj(video_meta, ('media', {
+                'title': ('title', {str}),
+                'release_timestamp': ('startTime', {parse_iso8601(delim=' ')}),
+                'thumbnail': ('ivsThumbnail', {url_or_none}),
+                'channel': ('userNick', {str}),
+                'concurrent_view_count': ('user', {int_or_none}),
+                'like_count': ('likeCnt', {int_or_none}),
+            })),
+        }

plugins/youtube_download/yt_dlp/extractor/parti.py

@@ -6,7 +6,10 @@ from ..utils.traversal import traverse_obj
 class PartiBaseIE(InfoExtractor):
     def _call_api(self, path, video_id, note=None):
         return self._download_json(
-            f'https://api-backend.parti.com/parti_v2/profile/{path}', video_id, note)
+            f'https://prod-api.parti.com/parti_v2/profile/{path}', video_id, note, headers={
+                'Origin': 'https://parti.com',
+                'Referer': 'https://parti.com/',
+            })
 
 
 class PartiVideoIE(PartiBaseIE):
@@ -20,7 +23,7 @@ class PartiVideoIE(PartiBaseIE):
             'title': 'NOW LIVE ',
             'upload_date': '20250327',
             'categories': ['Gaming'],
-            'thumbnail': 'https://assets.parti.com/351424_eb9e5250-2821-484a-9c5f-ca99aa666c87.png',
+            'thumbnail': 'https://media.parti.com/351424_eb9e5250-2821-484a-9c5f-ca99aa666c87.png',
             'channel': 'ItZTMGG',
             'timestamp': 1743044379,
         },
@@ -34,7 +37,7 @@ class PartiVideoIE(PartiBaseIE):
         return {
             'id': video_id,
             'formats': self._extract_m3u8_formats(
-                urljoin('https://watch.parti.com', data['livestream_recording']), video_id, 'mp4'),
+                urljoin('https://media.parti.com/', data['livestream_recording']), video_id, 'mp4'),
             **traverse_obj(data, {
                 'title': ('event_title', {str}),
                 'channel': ('user_name', {str}),
@@ -47,32 +50,27 @@ class PartiVideoIE(PartiBaseIE):
 
 class PartiLivestreamIE(PartiBaseIE):
     IE_NAME = 'parti:livestream'
-    _VALID_URL = r'https?://(?:www\.)?parti\.com/creator/(?P<service>[\w]+)/(?P<id>[\w/-]+)'
+    _VALID_URL = r'https?://(?:www\.)?parti\.com/(?!video/)(?P<id>[\w/-]+)'
     _TESTS = [{
-        'url': 'https://parti.com/creator/parti/Capt_Robs_Adventures',
+        'url': 'https://parti.com/247CryptoTracker',
         'info_dict': {
-            'id': 'Capt_Robs_Adventures',
             'ext': 'mp4',
+            'id': '247CryptoTracker',
+            'description': 'md5:a78051f3d7e66e6a64c6b1eaf59fd364',
             'title': r"re:I'm Live on Parti \d{4}-\d{2}-\d{2} \d{2}:\d{2}",
-            'view_count': int,
-            'thumbnail': r're:https://assets\.parti\.com/.+\.png',
-            'timestamp': 1743879776,
-            'upload_date': '20250405',
+            'thumbnail': r're:https://media\.parti\.com/stream-screenshots/.+\.png',
             'live_status': 'is_live',
         },
         'params': {'skip_download': 'm3u8'},
-    }, {
-        'url': 'https://parti.com/creator/discord/sazboxgaming/0',
-        'only_matching': True,
     }]
 
     def _real_extract(self, url):
-        service, creator_slug = self._match_valid_url(url).group('service', 'id')
+        creator_slug = self._match_id(url)
 
         encoded_creator_slug = creator_slug.replace('/', '%23')
         creator_id = self._call_api(
-            f'get_user_by_social_media/{service}/{encoded_creator_slug}',
-            creator_slug, note='Fetching user ID')
+            f'user_id_from_name/{encoded_creator_slug}',
+            creator_slug, note='Fetching user ID')['user_id']
 
         data = self._call_api(
             f'get_livestream_channel_info/{creator_id}', creator_id,
@@ -85,11 +83,7 @@ class PartiLivestreamIE(PartiBaseIE):
 
         return {
             'id': creator_slug,
-            'formats': self._extract_m3u8_formats(
-                channel_info['playback_url'], creator_slug, live=True, query={
-                    'token': channel_info['playback_auth_token'],
-                    'player_version': '1.17.0',
-                }),
+            'formats': self._extract_m3u8_formats(channel_info['playback_url'], creator_slug, live=True),
             'is_live': True,
             **traverse_obj(data, {
                 'title': ('livestream_event_info', 'event_name', {str}),

plugins/youtube_download/yt_dlp/extractor/patreon.py

@@ -598,7 +598,8 @@ class PatreonCampaignIE(PatreonBaseIE):
                 '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')}))
+                    ((..., 'value', 'campaign', 'data'), lambda _, v: v['type'] == 'campaign'),
+                    'id', {str}, any, {require('campaign ID')}))
 
         params = {
             'json-api-use-default-includes': 'false',

plugins/youtube_download/yt_dlp/extractor/picarto.py

@@ -4,6 +4,7 @@ from .common import InfoExtractor
 from ..utils import (
     ExtractorError,
     str_or_none,
+    strip_or_none,
     traverse_obj,
     update_url,
 )
@@ -50,7 +51,6 @@ class PicartoIE(InfoExtractor):
 
         if metadata.get('online') == 0:
             raise ExtractorError('Stream is offline', expected=True)
-        title = metadata['title']
 
         cdn_data = self._download_json(''.join((
             update_url(data['getLoadBalancerUrl']['url'], scheme='https'),
@@ -79,7 +79,7 @@ class PicartoIE(InfoExtractor):
 
         return {
             'id': channel_id,
-            'title': title.strip(),
+            'title': strip_or_none(metadata.get('title')),
             'is_live': True,
             'channel': channel_id,
             'channel_id': metadata.get('id'),
@@ -159,7 +159,7 @@ class PicartoVodIE(InfoExtractor):
             'id': video_id,
             **traverse_obj(data, {
                 'id': ('id', {str_or_none}),
-                'title': ('title', {str}),
+                'title': ('title', {str.strip}),
                 'thumbnail': 'video_recording_image_url',
                 'channel': ('channel', 'name', {str}),
                 'age_limit': ('adult', {lambda x: 18 if x else 0}),

plugins/youtube_download/yt_dlp/extractor/pornhub.py

@@ -24,6 +24,7 @@ from ..utils import (
     url_or_none,
     urlencode_postdata,
 )
+from ..utils.traversal import find_elements, traverse_obj
 
 
 class PornHubBaseIE(InfoExtractor):
@@ -137,23 +138,24 @@ class PornHubIE(PornHubBaseIE):
     _EMBED_REGEX = [r'<iframe[^>]+?src=["\'](?P<url>(?:https?:)?//(?:www\.)?pornhub(?:premium)?\.(?:com|net|org)/embed/[\da-z]+)']
     _TESTS = [{
         'url': 'http://www.pornhub.com/view_video.php?viewkey=648719015',
-        'md5': 'a6391306d050e4547f62b3f485dd9ba9',
+        'md5': '4d4a4e9178b655776f86cf89ecaf0edf',
         'info_dict': {
             'id': '648719015',
             'ext': 'mp4',
             'title': 'Seductive Indian beauty strips down and fingers her pink pussy',
-            'uploader': 'Babes',
+            'uploader': 'BABES-COM',
+            'uploader_id': '/users/babes-com',
             'upload_date': '20130628',
             'timestamp': 1372447216,
             'duration': 361,
             'view_count': int,
             'like_count': int,
-            'dislike_count': int,
             'comment_count': int,
             'age_limit': 18,
             'tags': list,
             'categories': list,
             'cast': list,
+            'thumbnail': r're:https?://.+',
         },
     }, {
         # non-ASCII title
@@ -480,13 +482,6 @@ class PornHubIE(PornHubBaseIE):
         comment_count = self._extract_count(
             r'All Comments\s*<span>\(([\d,.]+)\)', webpage, 'comment')
 
-        def extract_list(meta_key):
-            div = self._search_regex(
-                rf'(?s)<div[^>]+\bclass=["\'].*?\b{meta_key}Wrapper[^>]*>(.+?)</div>',
-                webpage, meta_key, default=None)
-            if div:
-                return [clean_html(x).strip() for x in re.findall(r'(?s)<a[^>]+\bhref=[^>]+>.+?</a>', div)]
-
         info = self._search_json_ld(webpage, video_id, default={})
         # description provided in JSON-LD is irrelevant
         info['description'] = None
@@ -505,9 +500,11 @@ class PornHubIE(PornHubBaseIE):
             'comment_count': comment_count,
             'formats': formats,
             'age_limit': 18,
-            'tags': extract_list('tags'),
-            'categories': extract_list('categories'),
-            'cast': extract_list('pornstars'),
+            **traverse_obj(webpage, {
+                'tags': ({find_elements(attr='data-label', value='tag')}, ..., {clean_html}),
+                'categories': ({find_elements(attr='data-label', value='category')}, ..., {clean_html}),
+                'cast': ({find_elements(attr='data-label', value='pornstar')}, ..., {clean_html}),
+            }),
             'subtitles': subtitles,
         }, info)
 

plugins/youtube_download/yt_dlp/extractor/rinsefm.py

@@ -3,12 +3,14 @@ from ..utils import (
     MEDIA_EXTENSIONS,
     determine_ext,
     parse_iso8601,
-    traverse_obj,
     url_or_none,
 )
+from ..utils.traversal import traverse_obj
 
 
 class RinseFMBaseIE(InfoExtractor):
+    _API_BASE = 'https://rinse.fm/api/query/v1'
+
     @staticmethod
     def _parse_entry(entry):
         return {
@@ -45,8 +47,10 @@ class RinseFMIE(RinseFMBaseIE):
 
     def _real_extract(self, url):
         display_id = self._match_id(url)
-        webpage = self._download_webpage(url, display_id)
-        entry = self._search_nextjs_data(webpage, display_id)['props']['pageProps']['entry']
+
+        entry = self._download_json(
+            f'{self._API_BASE}/episodes/{display_id}', display_id,
+            note='Downloading episode data from API')['entry']
 
         return self._parse_entry(entry)
 
@@ -58,32 +62,35 @@ class RinseFMArtistPlaylistIE(RinseFMBaseIE):
         'info_dict': {
             'id': 'resources',
             'title': '[re]sources',
-            'description': '[re]sources est un label parisien piloté par le DJ et producteur Tommy Kid.',
+            'description': 'md5:fd6a7254e8273510e6d49fbf50edf392',
         },
         'playlist_mincount': 40,
     }, {
-        'url': 'https://rinse.fm/shows/ivy/',
+        'url': 'https://www.rinse.fm/shows/esk',
         'info_dict': {
-            'id': 'ivy',
-            'title': '[IVY]',
-            'description': 'A dedicated space for DNB/Turbo House and 4x4.',
+            'id': 'esk',
+            'title': 'Esk',
+            'description': 'md5:5893d7c1d411ae8dea7fba12f109aa98',
         },
-        'playlist_mincount': 7,
+        'playlist_mincount': 139,
     }]
 
     def _entries(self, data):
         for episode in traverse_obj(data, (
-            'props', 'pageProps', 'episodes', lambda _, v: determine_ext(v['fileUrl']) in MEDIA_EXTENSIONS.audio),
+            'episodes', lambda _, v: determine_ext(v['fileUrl']) in MEDIA_EXTENSIONS.audio),
         ):
             yield self._parse_entry(episode)
 
     def _real_extract(self, url):
         playlist_id = self._match_id(url)
-        webpage = self._download_webpage(url, playlist_id)
-        title = self._og_search_title(webpage) or self._html_search_meta('title', webpage)
-        description = self._og_search_description(webpage) or self._html_search_meta(
-            'description', webpage)
-        data = self._search_nextjs_data(webpage, playlist_id)
+
+        api_data = self._download_json(
+            f'{self._API_BASE}/shows/{playlist_id}', playlist_id,
+            note='Downloading show data from API')
 
         return self.playlist_result(
-            self._entries(data), playlist_id, title, description=description)
+            self._entries(api_data), playlist_id,
+            **traverse_obj(api_data, ('entry', {
+                'title': ('title', {str}),
+                'description': ('description', {str}),
+            })))

plugins/youtube_download/yt_dlp/extractor/s4c.py

@@ -15,14 +15,15 @@ class S4CIE(InfoExtractor):
             'thumbnail': 'https://www.s4c.cymru/amg/1920x1080/Y_Swn_2023S4C_099_ii.jpg',
         },
     }, {
-        'url': 'https://www.s4c.cymru/clic/programme/856636948',
+        # Geo restricted to the UK
+        'url': 'https://www.s4c.cymru/clic/programme/886303048',
         'info_dict': {
-            'id': '856636948',
+            'id': '886303048',
             'ext': 'mp4',
-            'title': 'Am Dro',
+            'title': 'Pennod 1',
+            'description': 'md5:7e3f364b70f61fcdaa8b4cb4a3eb3e7a',
             'duration': 2880,
-            'description': 'md5:100d8686fc9a632a0cb2db52a3433ffe',
-            'thumbnail': 'https://www.s4c.cymru/amg/1920x1080/Am_Dro_2022-23S4C_P6_4005.jpg',
+            'thumbnail': 'https://www.s4c.cymru/amg/1920x1080/Stad_2025S4C_P1_210053.jpg',
         },
     }]
 
@@ -51,7 +52,7 @@ class S4CIE(InfoExtractor):
             'https://player-api.s4c-cdn.co.uk/streaming-urls/prod', video_id, query={
                 'mode': 'od',
                 'application': 'clic',
-                'region': 'WW',
+                'region': 'UK' if player_config.get('application') == 's4chttpl' else 'WW',
                 'extra': 'false',
                 'thirdParty': 'false',
                 'filename': player_config['filename'],

plugins/youtube_download/yt_dlp/extractor/scte.py

@@ -1,137 +0,0 @@
-import re
-
-from .common import InfoExtractor
-from ..utils import (
-    ExtractorError,
-    decode_packed_codes,
-    urlencode_postdata,
-)
-
-
-class SCTEBaseIE(InfoExtractor):
-    _LOGIN_URL = 'https://www.scte.org/SCTE/Sign_In.aspx'
-    _NETRC_MACHINE = 'scte'
-
-    def _perform_login(self, username, password):
-        login_popup = self._download_webpage(
-            self._LOGIN_URL, None, 'Downloading login popup')
-
-        def is_logged(webpage):
-            return any(re.search(p, webpage) for p in (
-                r'class=["\']welcome\b', r'>Sign Out<'))
-
-        # already logged in
-        if is_logged(login_popup):
-            return
-
-        login_form = self._hidden_inputs(login_popup)
-
-        login_form.update({
-            'ctl01$TemplateBody$WebPartManager1$gwpciNewContactSignInCommon$ciNewContactSignInCommon$signInUserName': username,
-            'ctl01$TemplateBody$WebPartManager1$gwpciNewContactSignInCommon$ciNewContactSignInCommon$signInPassword': password,
-            'ctl01$TemplateBody$WebPartManager1$gwpciNewContactSignInCommon$ciNewContactSignInCommon$RememberMe': 'on',
-        })
-
-        response = self._download_webpage(
-            self._LOGIN_URL, None, 'Logging in',
-            data=urlencode_postdata(login_form))
-
-        if '|pageRedirect|' not in response and not is_logged(response):
-            error = self._html_search_regex(
-                r'(?s)<[^>]+class=["\']AsiError["\'][^>]*>(.+?)</',
-                response, 'error message', default=None)
-            if error:
-                raise ExtractorError(f'Unable to login: {error}', expected=True)
-            raise ExtractorError('Unable to log in')
-
-
-class SCTEIE(SCTEBaseIE):
-    _WORKING = False
-    _VALID_URL = r'https?://learning\.scte\.org/mod/scorm/view\.php?.*?\bid=(?P<id>\d+)'
-    _TESTS = [{
-        'url': 'https://learning.scte.org/mod/scorm/view.php?id=31484',
-        'info_dict': {
-            'title': 'Introduction to DOCSIS Engineering Professional',
-            'id': '31484',
-        },
-        'playlist_count': 5,
-        'skip': 'Requires account credentials',
-    }]
-
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-
-        webpage = self._download_webpage(url, video_id)
-
-        title = self._search_regex(r'<h1>(.+?)</h1>', webpage, 'title')
-
-        context_id = self._search_regex(r'context-(\d+)', webpage, video_id)
-        content_base = f'https://learning.scte.org/pluginfile.php/{context_id}/mod_scorm/content/8/'
-        context = decode_packed_codes(self._download_webpage(
-            f'{content_base}mobile/data.js', video_id))
-
-        data = self._parse_xml(
-            self._search_regex(
-                r'CreateData\(\s*"(.+?)"', context, 'data').replace(r"\'", "'"),
-            video_id)
-
-        entries = []
-        for asset in data.findall('.//asset'):
-            asset_url = asset.get('url')
-            if not asset_url or not asset_url.endswith('.mp4'):
-                continue
-            asset_id = self._search_regex(
-                r'video_([^_]+)_', asset_url, 'asset id', default=None)
-            if not asset_id:
-                continue
-            entries.append({
-                'id': asset_id,
-                'title': title,
-                'url': content_base + asset_url,
-            })
-
-        return self.playlist_result(entries, video_id, title)
-
-
-class SCTECourseIE(SCTEBaseIE):
-    _WORKING = False
-    _VALID_URL = r'https?://learning\.scte\.org/(?:mod/sub)?course/view\.php?.*?\bid=(?P<id>\d+)'
-    _TESTS = [{
-        'url': 'https://learning.scte.org/mod/subcourse/view.php?id=31491',
-        'only_matching': True,
-    }, {
-        'url': 'https://learning.scte.org/course/view.php?id=3639',
-        'only_matching': True,
-    }, {
-        'url': 'https://learning.scte.org/course/view.php?id=3073',
-        'only_matching': True,
-    }]
-
-    def _real_extract(self, url):
-        course_id = self._match_id(url)
-
-        webpage = self._download_webpage(url, course_id)
-
-        title = self._search_regex(
-            r'<h1>(.+?)</h1>', webpage, 'title', default=None)
-
-        entries = []
-        for mobj in re.finditer(
-                r'''(?x)
-                    <a[^>]+
-                        href=(["\'])
-                        (?P<url>
-                            https?://learning\.scte\.org/mod/
-                            (?P<kind>scorm|subcourse)/view\.php?(?:(?!\1).)*?
-                            \bid=\d+
-                        )
-                    ''',
-                webpage):
-            item_url = mobj.group('url')
-            if item_url == url:
-                continue
-            ie = (SCTEIE.ie_key() if mobj.group('kind') == 'scorm'
-                  else SCTECourseIE.ie_key())
-            entries.append(self.url_result(item_url, ie=ie))
-
-        return self.playlist_result(entries, course_id, title)

plugins/youtube_download/yt_dlp/extractor/soundcloud.py

@@ -1064,7 +1064,7 @@ class SoundcloudRelatedIE(SoundcloudPagedPlaylistBaseIE):
 
 
 class SoundcloudPlaylistIE(SoundcloudPlaylistBaseIE):
-    _VALID_URL = r'https?://api(?:-v2)?\.soundcloud\.com/playlists/(?P<id>[0-9]+)(?:/?\?secret_token=(?P<token>[^&]+?))?$'
+    _VALID_URL = r'https?://api(?:-v2)?\.soundcloud\.com/playlists/(?:soundcloud(?:%3A|:)playlists(?:%3A|:))?(?P<id>[0-9]+)(?:/?\?secret_token=(?P<token>[^&]+?))?$'
     IE_NAME = 'soundcloud:playlist'
     _TESTS = [{
         'url': 'https://api.soundcloud.com/playlists/4110309',
@@ -1079,6 +1079,12 @@ class SoundcloudPlaylistIE(SoundcloudPlaylistBaseIE):
             'album': 'TILT Brass - Bowery Poetry Club, August \'03 [Non-Site SCR 02]',
         },
         'playlist_count': 6,
+    }, {
+        'url': 'https://api.soundcloud.com/playlists/soundcloud%3Aplaylists%3A1759227795',
+        'only_matching': True,
+    }, {
+        'url': 'https://api.soundcloud.com/playlists/soundcloud:playlists:2104769627?secret_token=s-wmpCLuExeYX',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):

plugins/youtube_download/yt_dlp/extractor/sportdeutschland.py

@@ -8,10 +8,11 @@ from ..utils import (
 
 
 class SportDeutschlandIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:player\.)?sportdeutschland\.tv/(?P<id>(?:[^/?#]+/)?[^?#/&]+)'
+    IE_NAME = 'sporteurope'
+    _VALID_URL = r'https?://(?:player\.)?sporteurope\.tv/(?P<id>(?:[^/?#]+/)?[^?#/&]+)'
     _TESTS = [{
         # Single-part video, direct link
-        'url': 'https://sportdeutschland.tv/rostock-griffins/gfl2-rostock-griffins-vs-elmshorn-fighting-pirates',
+        'url': 'https://sporteurope.tv/rostock-griffins/gfl2-rostock-griffins-vs-elmshorn-fighting-pirates',
         'md5': '35c11a19395c938cdd076b93bda54cde',
         'info_dict': {
             'id': '9f27a97d-1544-4d0b-aa03-48d92d17a03a',
@@ -19,9 +20,9 @@ class SportDeutschlandIE(InfoExtractor):
             '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',
+            'channel_url': 'https://sporteurope.tv/rostock-griffins',
             'live_status': 'was_live',
-            'description': 'md5:60cb00067e55dafa27b0933a43d72862',
+            'description': r're:Video-Livestream des Spiels Rostock Griffins vs\. Elmshorn Fighting Pirates.+',
             'channel_id': '9635f21c-3f67-4584-9ce4-796e9a47276b',
             'timestamp': 1749913117,
             'upload_date': '20250614',
@@ -29,16 +30,16 @@ class SportDeutschlandIE(InfoExtractor):
         },
     }, {
         # Single-part video, embedded player link
-        'url': 'https://player.sportdeutschland.tv/9e9619c4-7d77-43c4-926d-49fb57dc06dc',
+        'url': 'https://player.sporteurope.tv/9e9619c4-7d77-43c4-926d-49fb57dc06dc',
         'info_dict': {
             'id': '9f27a97d-1544-4d0b-aa03-48d92d17a03a',
             'ext': 'mp4',
             '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',
+            'channel_url': 'https://sporteurope.tv/rostock-griffins',
             'live_status': 'was_live',
-            'description': 'md5:60cb00067e55dafa27b0933a43d72862',
+            'description': r're:Video-Livestream des Spiels Rostock Griffins vs\. Elmshorn Fighting Pirates.+',
             'channel_id': '9635f21c-3f67-4584-9ce4-796e9a47276b',
             'timestamp': 1749913117,
             'upload_date': '20250614',
@@ -47,7 +48,7 @@ class SportDeutschlandIE(InfoExtractor):
         'params': {'skip_download': True},
     }, {
         # Multi-part video
-        'url': 'https://sportdeutschland.tv/rhine-ruhr-2025-fisu-world-university-games/volleyball-w-japan-vs-brasilien-halbfinale-2',
+        'url': 'https://sporteurope.tv/rhine-ruhr-2025-fisu-world-university-games/volleyball-w-japan-vs-brasilien-halbfinale-2',
         'info_dict': {
             'id': '9f63d737-2444-4e3a-a1ea-840df73fd481',
             'display_id': 'rhine-ruhr-2025-fisu-world-university-games/volleyball-w-japan-vs-brasilien-halbfinale-2',
@@ -55,7 +56,7 @@ class SportDeutschlandIE(InfoExtractor):
             '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',
+            'channel_url': 'https://sporteurope.tv/rhine-ruhr-2025-fisu-world-university-games',
             'live_status': 'was_live',
         },
         'playlist_count': 2,
@@ -66,7 +67,7 @@ class SportDeutschlandIE(InfoExtractor):
                 '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',
+                'channel_url': 'https://sporteurope.tv/rhine-ruhr-2025-fisu-world-university-games',
                 'duration': 14773.0,
                 'timestamp': 1753085197,
                 'upload_date': '20250721',
@@ -79,16 +80,17 @@ class SportDeutschlandIE(InfoExtractor):
                 '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',
+                'channel_url': 'https://sporteurope.tv/rhine-ruhr-2025-fisu-world-university-games',
                 'duration': 14773.0,
                 'timestamp': 1753128421,
                 'upload_date': '20250721',
                 'live_status': 'was_live',
             },
         }],
+        'skip': '404 Not Found',
     }, {
         # Livestream
-        'url': 'https://sportdeutschland.tv/dtb/gymnastik-international-tag-1',
+        'url': 'https://sporteurope.tv/dtb/gymnastik-international-tag-1',
         'info_dict': {
             'id': '95d71b8a-370a-4b87-ad16-94680da18528',
             'ext': 'mp4',
@@ -96,7 +98,7 @@ class SportDeutschlandIE(InfoExtractor):
             'display_id': 'dtb/gymnastik-international-tag-1',
             'channel_id': '936ecef1-2f4a-4e08-be2f-68073cb7ecab',
             'channel': 'Deutscher Turner-Bund',
-            'channel_url': 'https://sportdeutschland.tv/dtb',
+            'channel_url': 'https://sporteurope.tv/dtb',
             'description': 'md5:07a885dde5838a6f0796ee21dc3b0c52',
             'live_status': 'is_live',
         },
@@ -106,9 +108,9 @@ 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/web/personal/asset-token/{asset_id}',
+            f'https://api.sporteurope.tv/api/web/personal/asset-token/{asset_id}',
             video['id'], query={'type': video['type'], 'playback_id': video['src']},
-            headers={'Referer': 'https://sportdeutschland.tv/'})['token']
+            headers={'Referer': 'https://sporteurope.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)
 
@@ -126,7 +128,7 @@ class SportDeutschlandIE(InfoExtractor):
     def _real_extract(self, url):
         display_id = self._match_id(url)
         meta = self._download_json(
-            f'https://api.sportdeutschland.tv/api/stateless/frontend/assets/{display_id}',
+            f'https://api.sporteurope.tv/api/stateless/frontend/assets/{display_id}',
             display_id, query={'access_token': 'true'})
 
         info = {
@@ -139,7 +141,7 @@ class SportDeutschlandIE(InfoExtractor):
                 'channel_id': ('profile', 'id'),
                 'is_live': 'currently_live',
                 'was_live': 'was_live',
-                'channel_url': ('profile', 'slug', {lambda x: f'https://sportdeutschland.tv/{x}'}),
+                'channel_url': ('profile', 'slug', {lambda x: f'https://sporteurope.tv/{x}'}),
             }, get_all=False),
         }
 

plugins/youtube_download/yt_dlp/extractor/sproutvideo.py

@@ -101,8 +101,8 @@ class SproutVideoIE(InfoExtractor):
         webpage = self._download_webpage(
             url, video_id, headers=traverse_obj(smuggled_data, {'Referer': 'referer'}))
         data = self._search_json(
-            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'["\'];',
+            r'(?:window\.|(?: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]

plugins/youtube_download/yt_dlp/extractor/tarangplus.py

@@ -0,0 +1,243 @@
+import base64
+import binascii
+import functools
+import re
+import urllib.parse
+
+from .common import InfoExtractor
+from ..dependencies import Cryptodome
+from ..utils import (
+    ExtractorError,
+    OnDemandPagedList,
+    clean_html,
+    extract_attributes,
+    urljoin,
+)
+from ..utils.traversal import (
+    find_element,
+    find_elements,
+    require,
+    traverse_obj,
+)
+
+
+class TarangPlusBaseIE(InfoExtractor):
+    _BASE_URL = 'https://tarangplus.in'
+
+
+class TarangPlusVideoIE(TarangPlusBaseIE):
+    IE_NAME = 'tarangplus:video'
+    _VALID_URL = r'https?://(?:www\.)?tarangplus\.in/(?:movies|[^#?/]+/[^#?/]+)/(?!episodes)(?P<id>[^#?/]+)'
+    _TESTS = [{
+        'url': 'https://tarangplus.in/tarangaplus-originals/khitpit/khitpit-ep-10',
+        'md5': '78ce056cee755687b8a48199909ecf53',
+        'info_dict': {
+            'id': '67b8206719521d054c0059b7',
+            'display_id': 'khitpit-ep-10',
+            'ext': 'mp4',
+            'title': 'Khitpit Ep-10',
+            'description': 'md5:a45b805cb628e15c853d78b0406eab48',
+            'thumbnail': r're:https?://.+/.+\.jpg',
+            'duration': 756.0,
+            'timestamp': 1740355200,
+            'upload_date': '20250224',
+            'media_type': 'episode',
+            'categories': ['Originals'],
+        },
+    }, {
+        'url': 'https://tarangplus.in/tarang-serials/bada-bohu/bada-bohu-ep-233',
+        'md5': 'b4f9beb15172559bb362203b4f48382e',
+        'info_dict': {
+            'id': '680b9d6c19521d054c007782',
+            'display_id': 'bada-bohu-ep-233',
+            'ext': 'mp4',
+            'title': 'Bada Bohu  | Ep -233',
+            'description': 'md5:e6b8e7edc9e60b92c1b390f8789ecd69',
+            'thumbnail': r're:https?://.+/.+\.jpg',
+            'duration': 1392.0,
+            'timestamp': 1745539200,
+            'upload_date': '20250425',
+            'media_type': 'episode',
+            'categories': ['Prime'],
+        },
+    }, {
+        # Decrypted m3u8 URL has trailing control characters that need to be stripped
+        'url': 'https://tarangplus.in/tarangaplus-originals/ichha/ichha-teaser-1',
+        'md5': '16ee43fe21ad8b6e652ec65eba38a64e',
+        'info_dict': {
+            'id': '5f0f252d3326af0720000342',
+            'ext': 'mp4',
+            'display_id': 'ichha-teaser-1',
+            'title': 'Ichha Teaser',
+            'description': 'md5:c724b0b0669a2cefdada3711cec792e6',
+            'media_type': 'episode',
+            'duration': 21.0,
+            'thumbnail': r're:https?://.+/.+\.jpg',
+            'categories': ['Originals'],
+            'timestamp': 1758153600,
+            'upload_date': '20250918',
+        },
+    }, {
+        'url': 'https://tarangplus.in/short/ai-maa/ai-maa',
+        'only_matching': True,
+    }, {
+        'url': 'https://tarangplus.in/shows/tarang-cine-utsav-2024/tarang-cine-utsav-2024-seg-1',
+        'only_matching': True,
+    }, {
+        'url': 'https://tarangplus.in/music-videos/chori-chori-bohu-chori-songs/nijara-laguchu-dhire-dhire',
+        'only_matching': True,
+    }, {
+        'url': 'https://tarangplus.in/kids-shows/chhota-jaga/chhota-jaga-ep-33-jamidar-ra-khajana-adaya',
+        'only_matching': True,
+    }, {
+        'url': 'https://tarangplus.in/movies/swayambara',
+        'only_matching': True,
+    }]
+
+    def decrypt(self, data, key):
+        if not Cryptodome.AES:
+            raise ExtractorError('pycryptodomex not found. Please install', expected=True)
+        iv = binascii.unhexlify('00000000000000000000000000000000')
+        cipher = Cryptodome.AES.new(base64.b64decode(key), Cryptodome.AES.MODE_CBC, iv)
+        return cipher.decrypt(base64.b64decode(data)).decode('utf-8')
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_id)
+        hidden_inputs_data = self._hidden_inputs(webpage)
+        json_ld_data = self._search_json_ld(webpage, display_id)
+        json_ld_data.pop('url', None)
+
+        iframe_url = traverse_obj(webpage, (
+            {find_element(tag='iframe', attr='src', value=r'.+[?&]contenturl=.+', html=True, regex=True)},
+            {extract_attributes}, 'src', {require('iframe URL')}))
+        # Can't use parse_qs here since it would decode the encrypted base64 `+` chars to spaces
+        content = self._search_regex(r'[?&]contenturl=(.+)', iframe_url, 'content')
+        encrypted_data, _, attrs = content.partition('|')
+        metadata = {
+            m.group('k'): m.group('v')
+            for m in re.finditer(r'(?:^|\|)(?P<k>[a-z_]+)=(?P<v>(?:(?!\|[a-z_]+=).)+)', attrs)
+        }
+        m3u8_url = urllib.parse.unquote(
+            self.decrypt(encrypted_data, metadata['key'])).rstrip('\x0e\x0f')
+
+        return {
+            'id': display_id,  # Fallback
+            'display_id': display_id,
+            **json_ld_data,
+            **traverse_obj(metadata, {
+                'id': ('content_id', {str}),
+                'title': ('title', {str}),
+                'thumbnail': ('image', {str}),
+            }),
+            **traverse_obj(hidden_inputs_data, {
+                'id': ('content_id', {str}),
+                'media_type': ('theme_type', {str}),
+                'categories': ('genre', {str}, filter, all, filter),
+            }),
+            'formats': self._extract_m3u8_formats(m3u8_url, display_id),
+        }
+
+
+class TarangPlusEpisodesIE(TarangPlusBaseIE):
+    IE_NAME = 'tarangplus:episodes'
+    _VALID_URL = r'https?://(?:www\.)?tarangplus\.in/(?P<type>[^#?/]+)/(?P<id>[^#?/]+)/episodes/?(?:$|[?#])'
+    _TESTS = [{
+        'url': 'https://tarangplus.in/tarangaplus-originals/balijatra/episodes',
+        'info_dict': {
+            'id': 'balijatra',
+            'title': 'Balijatra',
+        },
+        'playlist_mincount': 7,
+    }, {
+        'url': 'https://tarangplus.in/tarang-serials/bada-bohu/episodes',
+        'info_dict': {
+            'id': 'bada-bohu',
+            'title': 'Bada Bohu',
+        },
+        'playlist_mincount': 236,
+    }, {
+        'url': 'https://tarangplus.in/shows/dr-nonsense/episodes',
+        'info_dict': {
+            'id': 'dr-nonsense',
+            'title': 'Dr. Nonsense',
+        },
+        'playlist_mincount': 15,
+    }]
+    _PAGE_SIZE = 20
+
+    def _entries(self, playlist_url, playlist_id, page):
+        data = self._download_json(
+            playlist_url, playlist_id, f'Downloading playlist JSON page {page + 1}',
+            query={'page_no': page})
+        for item in traverse_obj(data, ('items', ..., {str})):
+            yield self.url_result(
+                urljoin(self._BASE_URL, item.split('$')[3]), TarangPlusVideoIE)
+
+    def _real_extract(self, url):
+        url_type, display_id = self._match_valid_url(url).group('type', 'id')
+        series_url = f'{self._BASE_URL}/{url_type}/{display_id}'
+        webpage = self._download_webpage(series_url, display_id)
+
+        entries = OnDemandPagedList(
+            functools.partial(self._entries, f'{series_url}/episodes', display_id),
+            self._PAGE_SIZE)
+        return self.playlist_result(
+            entries, display_id, self._hidden_inputs(webpage).get('title'))
+
+
+class TarangPlusPlaylistIE(TarangPlusBaseIE):
+    IE_NAME = 'tarangplus:playlist'
+    _VALID_URL = r'https?://(?:www\.)?tarangplus\.in/(?P<id>[^#?/]+)/all/?(?:$|[?#])'
+    _TESTS = [{
+        'url': 'https://tarangplus.in/chhota-jaga/all',
+        'info_dict': {
+            'id': 'chhota-jaga',
+            'title': 'Chhota Jaga',
+        },
+        'playlist_mincount': 33,
+    }, {
+        'url': 'https://tarangplus.in/kids-yali-show/all',
+        'info_dict': {
+            'id': 'kids-yali-show',
+            'title': 'Yali',
+        },
+        'playlist_mincount': 10,
+    }, {
+        'url': 'https://tarangplus.in/trailer/all',
+        'info_dict': {
+            'id': 'trailer',
+            'title': 'Trailer',
+        },
+        'playlist_mincount': 57,
+    }, {
+        'url': 'https://tarangplus.in/latest-songs/all',
+        'info_dict': {
+            'id': 'latest-songs',
+            'title': 'Latest Songs',
+        },
+        'playlist_mincount': 46,
+    }, {
+        'url': 'https://tarangplus.in/premium-serials-episodes/all',
+        'info_dict': {
+            'id': 'premium-serials-episodes',
+            'title': 'Primetime Latest Episodes',
+        },
+        'playlist_mincount': 100,
+    }]
+
+    def _entries(self, webpage):
+        for url_path in traverse_obj(webpage, (
+            {find_elements(cls='item')}, ...,
+            {find_elements(tag='a', attr='href', value='/.+', html=True, regex=True)},
+            ..., {extract_attributes}, 'href',
+        )):
+            yield self.url_result(urljoin(self._BASE_URL, url_path), TarangPlusVideoIE)
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_id)
+
+        return self.playlist_result(
+            self._entries(webpage), display_id,
+            traverse_obj(webpage, ({find_element(id='al_title')}, {clean_html})))

plugins/youtube_download/yt_dlp/extractor/telecinco.py

@@ -6,20 +6,21 @@ from ..networking.exceptions import HTTPError
 from ..utils import (
     ExtractorError,
     clean_html,
+    extract_attributes,
     int_or_none,
     join_nonempty,
     str_or_none,
-    traverse_obj,
     update_url,
     url_or_none,
 )
+from ..utils.traversal import traverse_obj
 
 
 class TelecincoBaseIE(InfoExtractor):
     def _parse_content(self, content, url):
-        video_id = content['dataMediaId']
+        video_id = content['dataMediaId'][1]
         config = self._download_json(
-            content['dataConfig'], video_id, 'Downloading config JSON')
+            content['dataConfig'][1], video_id, 'Downloading config JSON')
         services = config['services']
         caronte = self._download_json(services['caronte'], video_id)
         if traverse_obj(caronte, ('dls', 0, 'drm', {bool})):
@@ -57,9 +58,9 @@ class TelecincoBaseIE(InfoExtractor):
             'id': video_id,
             'title': traverse_obj(config, ('info', 'title', {str})),
             'formats': formats,
-            'thumbnail': (traverse_obj(content, ('dataPoster', {url_or_none}))
+            'thumbnail': (traverse_obj(content, ('dataPoster', 1, {url_or_none}))
                           or traverse_obj(config, 'poster', 'imageUrl', expected_type=url_or_none)),
-            'duration': traverse_obj(content, ('dataDuration', {int_or_none})),
+            'duration': traverse_obj(content, ('dataDuration', 1, {int_or_none})),
             'http_headers': headers,
         }
 
@@ -137,30 +138,45 @@ class TelecincoIE(TelecincoBaseIE):
         'url': 'http://www.cuatro.com/chesterinlove/a-carta/chester-chester_in_love-chester_edu_2_2331030022.html',
         'only_matching': True,
     }]
+    _ASTRO_ISLAND_RE = re.compile(r'<astro-island\b[^>]+>')
 
     def _real_extract(self, url):
         display_id = self._match_id(url)
         webpage = self._download_webpage(url, display_id, impersonate=True)
-        article = self._search_json(
-            r'window\.\$REACTBASE_STATE\.article(?:_multisite)?\s*=',
-            webpage, 'article', display_id)['article']
-        description = traverse_obj(article, ('leadParagraph', {clean_html}, filter))
 
-        if article.get('editorialType') != 'VID':
+        props_list = traverse_obj(webpage, (
+            {self._ASTRO_ISLAND_RE.findall}, ...,
+            {extract_attributes}, 'props', {json.loads}))
+
+        description = traverse_obj(props_list, (..., 'leadParagraph', 1, {clean_html}, any, filter))
+        main_content = traverse_obj(props_list, (..., ('content', ('articleData', 1, 'opening')), 1, {dict}, any))
+
+        if traverse_obj(props_list, (..., 'editorialType', 1, {str}, any)) != 'VID':  # e.g. 'ART'
             entries = []
 
-            for p in traverse_obj(article, ((('opening', all), 'body'), lambda _, v: v['content'])):
-                content = p['content']
-                type_ = p.get('type')
-                if type_ == 'paragraph' and isinstance(content, str):
+            for p in traverse_obj(props_list, (..., 'articleData', 1, ('opening', ('body', 1, ...)), 1, {dict})):
+                type_ = traverse_obj(p, ('type', 1, {str}))
+                content = traverse_obj(p, ('content', 1, {str} if type_ == 'paragraph' else {dict}))
+                if not content:
+                    continue
+                if type_ == 'paragraph':
                     description = join_nonempty(description, content, delim='')
-                elif type_ == 'video' and isinstance(content, dict):
+                elif type_ == 'video':
                     entries.append(self._parse_content(content, url))
+                else:
+                    self.report_warning(
+                        f'Skipping unsupported content type "{type_}"', display_id, only_once=True)
 
             return self.playlist_result(
-                entries, str_or_none(article.get('id')),
-                traverse_obj(article, ('title', {str})), clean_html(description))
+                entries,
+                traverse_obj(props_list, (..., 'id', 1, {int}, {str_or_none}, any)) or display_id,
+                traverse_obj(main_content, ('dataTitle', 1, {str})),
+                clean_html(description))
 
-        info = self._parse_content(article['opening']['content'], url)
+        if not main_content:
+            raise ExtractorError('Unable to extract main content from webpage')
+
+        info = self._parse_content(main_content, url)
         info['description'] = description
+
         return info

plugins/youtube_download/yt_dlp/extractor/thisoldhouse.py

@@ -1,18 +1,17 @@
-import json
+import urllib.parse
 
 from .brightcove import BrightcoveNewIE
 from .common import InfoExtractor
 from .zype import ZypeIE
 from ..networking import HEADRequest
-from ..networking.exceptions import HTTPError
 from ..utils import (
     ExtractorError,
     filter_dict,
     parse_qs,
     smuggle_url,
-    try_call,
     urlencode_postdata,
 )
+from ..utils.traversal import traverse_obj
 
 
 class ThisOldHouseIE(InfoExtractor):
@@ -77,46 +76,43 @@ class ThisOldHouseIE(InfoExtractor):
         'only_matching': True,
     }]
 
-    _LOGIN_URL = 'https://login.thisoldhouse.com/usernamepassword/login'
-
     def _perform_login(self, username, password):
-        self._request_webpage(
-            HEADRequest('https://www.thisoldhouse.com/insider'), None, 'Requesting session cookies')
-        urlh = self._request_webpage(
-            'https://www.thisoldhouse.com/wp-login.php', None, 'Requesting login info',
-            errnote='Unable to login', query={'redirect_to': 'https://www.thisoldhouse.com/insider'})
+        login_page = self._download_webpage(
+            'https://www.thisoldhouse.com/insider-login', None, 'Downloading login page')
+        hidden_inputs = self._hidden_inputs(login_page)
+        response = self._download_json(
+            'https://www.thisoldhouse.com/wp-admin/admin-ajax.php', None, 'Logging in',
+            headers={
+                'Accept': 'application/json',
+                'X-Requested-With': 'XMLHttpRequest',
+            }, data=urlencode_postdata(filter_dict({
+                'action': 'onebill_subscriber_login',
+                'email': username,
+                'password': password,
+                'pricingPlanTerm': hidden_inputs['pricing_plan_term'],
+                'utm_parameters': hidden_inputs.get('utm_parameters'),
+                'nonce': hidden_inputs['mdcr_onebill_login_nonce'],
+            })))
 
-        try:
-            auth_form = self._download_webpage(
-                self._LOGIN_URL, None, 'Submitting credentials', headers={
-                    'Content-Type': 'application/json',
-                    'Referer': urlh.url,
-                }, data=json.dumps(filter_dict({
-                    **{('client_id' if k == 'client' else k): v[0] for k, v in parse_qs(urlh.url).items()},
-                    'tenant': 'thisoldhouse',
-                    'username': username,
-                    'password': password,
-                    'popup_options': {},
-                    'sso': True,
-                    '_csrf': try_call(lambda: self._get_cookies(self._LOGIN_URL)['_csrf'].value),
-                    '_intstate': 'deprecated',
-                }), separators=(',', ':')).encode())
-        except ExtractorError as e:
-            if isinstance(e.cause, HTTPError) and e.cause.status == 401:
+        message = traverse_obj(response, ('data', 'message', {str}))
+        if not response['success']:
+            if message and 'Something went wrong' in message:
                 raise ExtractorError('Invalid username or password', expected=True)
-            raise
-
-        self._request_webpage(
-            'https://login.thisoldhouse.com/login/callback', None, 'Completing login',
-            data=urlencode_postdata(self._hidden_inputs(auth_form)))
+            raise ExtractorError(message or 'Login was unsuccessful')
+        if message and 'Your subscription is not active' in message:
+            self.report_warning(
+                f'{self.IE_NAME} said your subscription is not active. '
+                f'If your subscription is active, this could be caused by too many sign-ins, '
+                f'and you should instead try using {self._login_hint(method="cookies")[4:]}')
+        else:
+            self.write_debug(f'{self.IE_NAME} said: {message}')
 
     def _real_extract(self, url):
         display_id = self._match_id(url)
-        webpage = self._download_webpage(url, display_id)
-        if 'To Unlock This content' in webpage:
-            self.raise_login_required(
-                'This video is only available for subscribers. '
-                'Note that --cookies-from-browser may not work due to this site using session cookies')
+        webpage, urlh = self._download_webpage_handle(url, display_id)
+        # If login response says inactive subscription, site redirects to frontpage for Insider content
+        if 'To Unlock This content' in webpage or urllib.parse.urlparse(urlh.url).path in ('', '/'):
+            self.raise_login_required('This video is only available for subscribers')
 
         video_url, video_id = self._search_regex(
             r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?thisoldhouse\.(?:chorus\.build|com)/videos/zype/([0-9a-f]{24})[^\'"]*)[\'"]',

plugins/youtube_download/yt_dlp/extractor/tiktok.py

@@ -454,6 +454,7 @@ class TikTokBaseIE(InfoExtractor):
                 'like_count': 'digg_count',
                 'repost_count': 'share_count',
                 'comment_count': 'comment_count',
+                'save_count': 'collect_count',
             }, expected_type=int_or_none),
             **author_info,
             'channel_url': format_field(author_info, 'channel_id', self._UPLOADER_URL_FORMAT, default=None),
@@ -607,6 +608,7 @@ class TikTokBaseIE(InfoExtractor):
                 'like_count': 'diggCount',
                 'repost_count': 'shareCount',
                 'comment_count': 'commentCount',
+                'save_count': 'collectCount',
             }), expected_type=int_or_none),
             'thumbnails': [
                 {
@@ -646,6 +648,7 @@ class TikTokIE(TikTokBaseIE):
             'like_count': int,
             'repost_count': int,
             'comment_count': int,
+            'save_count': int,
             'artist': 'Ysrbeats',
             'album': 'Lehanga',
             'track': 'Lehanga',
@@ -675,6 +678,7 @@ class TikTokIE(TikTokBaseIE):
             'like_count': int,
             'repost_count': int,
             'comment_count': int,
+            'save_count': int,
             'artists': ['Evan Todd', 'Jessica Keenan Wynn', 'Alice Lee', 'Barrett Wilbert Weed', 'Jon Eidson'],
             'track': 'Big Fun',
         },
@@ -702,6 +706,7 @@ class TikTokIE(TikTokBaseIE):
             'like_count': int,
             'repost_count': int,
             'comment_count': int,
+            'save_count': int,
         },
     }, {
         # Sponsored video, only available with feed workaround
@@ -725,6 +730,7 @@ class TikTokIE(TikTokBaseIE):
             'like_count': int,
             'repost_count': int,
             'comment_count': int,
+            'save_count': int,
         },
         'skip': 'This video is unavailable',
     }, {
@@ -751,6 +757,7 @@ class TikTokIE(TikTokBaseIE):
             'like_count': int,
             'repost_count': int,
             'comment_count': int,
+            'save_count': int,
         },
     }, {
         # hydration JSON is sent in a <script> element
@@ -773,6 +780,7 @@ class TikTokIE(TikTokBaseIE):
             'like_count': int,
             'repost_count': int,
             'comment_count': int,
+            'save_count': int,
         },
         'skip': 'This video is unavailable',
     }, {
@@ -798,6 +806,7 @@ class TikTokIE(TikTokBaseIE):
             'like_count': int,
             'repost_count': int,
             'comment_count': int,
+            'save_count': int,
             'thumbnail': r're:^https://.+\.(?:webp|jpe?g)',
         },
     }, {
@@ -824,6 +833,7 @@ class TikTokIE(TikTokBaseIE):
             'like_count': int,
             'repost_count': int,
             'comment_count': int,
+            'save_count': int,
             'thumbnail': r're:^https://.+',
             'thumbnails': 'count:3',
         },
@@ -851,6 +861,7 @@ class TikTokIE(TikTokBaseIE):
             'like_count': int,
             'repost_count': int,
             'comment_count': int,
+            'save_count': int,
             'thumbnail': r're:^https://.+\.webp',
         },
         'skip': 'Unavailable via feed API, only audio available via web',
@@ -879,6 +890,7 @@ class TikTokIE(TikTokBaseIE):
             'like_count': int,
             'comment_count': int,
             'repost_count': int,
+            'save_count': int,
             'thumbnail': r're:^https://.+\.(?:webp|jpe?g)',
         },
     }, {
@@ -1288,6 +1300,7 @@ class DouyinIE(TikTokBaseIE):
             'like_count': int,
             'repost_count': int,
             'comment_count': int,
+            'save_count': int,
             'thumbnail': r're:https?://.+\.jpe?g',
         },
     }, {
@@ -1312,6 +1325,7 @@ class DouyinIE(TikTokBaseIE):
             'like_count': int,
             'repost_count': int,
             'comment_count': int,
+            'save_count': int,
             'thumbnail': r're:https?://.+\.jpe?g',
         },
     }, {
@@ -1336,6 +1350,7 @@ class DouyinIE(TikTokBaseIE):
             'like_count': int,
             'repost_count': int,
             'comment_count': int,
+            'save_count': int,
             'thumbnail': r're:https?://.+\.jpe?g',
         },
     }, {
@@ -1353,6 +1368,7 @@ class DouyinIE(TikTokBaseIE):
             'like_count': int,
             'repost_count': int,
             'comment_count': int,
+            'save_count': int,
         },
         'skip': 'No longer available',
     }, {
@@ -1377,6 +1393,7 @@ class DouyinIE(TikTokBaseIE):
             'like_count': int,
             'repost_count': int,
             'comment_count': int,
+            'save_count': int,
             'thumbnail': r're:https?://.+\.jpe?g',
         },
     }]
@@ -1437,6 +1454,7 @@ class TikTokVMIE(InfoExtractor):
             'view_count': int,
             'like_count': int,
             'comment_count': int,
+            'save_count': int,
             'thumbnail': r're:https://.+\.webp.*',
             'uploader_url': 'https://www.tiktok.com/@MS4wLjABAAAAdZ_NcPPgMneaGrW0hN8O_J_bwLshwNNERRF5DxOw2HKIzk0kdlLrR8RkVl1ksrMO',
             'duration': 29,

plugins/youtube_download/yt_dlp/extractor/tubetugraz.py

@@ -136,8 +136,10 @@ class TubeTuGrazIE(TubeTuGrazBaseIE):
     IE_DESC = 'tube.tugraz.at'
 
     _VALID_URL = r'''(?x)
-        https?://tube\.tugraz\.at/paella/ui/watch.html\?id=
-        (?P<id>[0-9a-fA-F]{8}-(?:[0-9a-fA-F]{4}-){3}[0-9a-fA-F]{12})
+        https?://tube\.tugraz\.at/(?:
+            paella/ui/watch\.html\?(?:[^#]*&)?id=|
+            portal/watch/
+        )(?P<id>[0-9a-fA-F]{8}-(?:[0-9a-fA-F]{4}-){3}[0-9a-fA-F]{12})
     '''
     _TESTS = [
         {
@@ -149,9 +151,9 @@ class TubeTuGrazIE(TubeTuGrazBaseIE):
                 'title': '#6 (23.11.2017)',
                 'episode': '#6 (23.11.2017)',
                 'series': '[INB03001UF] Einführung in die strukturierte Programmierung',
-                'creator': 'Safran C',
                 'duration': 3295818,
                 'series_id': 'b1192fff-2aa7-4bf0-a5cf-7b15c3bd3b34',
+                'creators': ['Safran C'],
             },
         }, {
             'url': 'https://tube.tugraz.at/paella/ui/watch.html?id=2df6d787-e56a-428d-8ef4-d57f07eef238',
@@ -162,6 +164,10 @@ class TubeTuGrazIE(TubeTuGrazBaseIE):
                 'ext': 'mp4',
             },
             'expected_warnings': ['Extractor failed to obtain "title"'],
+        }, {
+            # Portal URL format
+            'url': 'https://tube.tugraz.at/portal/watch/ab28ec60-8cbe-4f1a-9b96-a95add56c612',
+            'only_matching': True,
         },
     ]
 

plugins/youtube_download/yt_dlp/extractor/tubitv.py

@@ -15,7 +15,7 @@ from ..utils import (
 
 class TubiTvIE(InfoExtractor):
     IE_NAME = 'tubitv'
-    _VALID_URL = r'https?://(?:www\.)?tubitv\.com/(?P<type>video|movies|tv-shows)/(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:www\.)?tubitv\.com/(?:[a-z]{2}-[a-z]{2}/)?(?P<type>video|movies|tv-shows)/(?P<id>\d+)'
     _LOGIN_URL = 'http://tubitv.com/login'
     _NETRC_MACHINE = 'tubitv'
     _TESTS = [{
@@ -73,6 +73,9 @@ class TubiTvIE(InfoExtractor):
             'release_year': 1979,
         },
         'skip': 'Content Unavailable',
+    }, {
+        'url': 'https://tubitv.com/es-mx/tv-shows/477363/s01-e03-jacob-dos-dos-y-la-tarjets-de-hockey-robada',
+        'only_matching': True,
     }]
 
     # DRM formats are included only to raise appropriate error
@@ -182,13 +185,13 @@ class TubiTvShowIE(InfoExtractor):
         webpage = self._download_webpage(show_url, playlist_id)
 
         data = self._search_json(
-            r'window\.__data\s*=', webpage, 'data', playlist_id,
-            transform_source=js_to_json)['video']
+            r'window\.__REACT_QUERY_STATE__\s*=', webpage, 'data', playlist_id,
+            transform_source=js_to_json)['queries'][0]['state']['data']
 
         # v['number'] is already a decimal string, but stringify to protect against API changes
         path = [lambda _, v: str(v['number']) == selected_season] if selected_season else [..., {dict}]
 
-        for season in traverse_obj(data, ('byId', lambda _, v: v['type'] == 's', 'seasons', *path)):
+        for season in traverse_obj(data, ('seasons', *path)):
             season_number = int_or_none(season.get('number'))
             for episode in traverse_obj(season, ('episodes', lambda _, v: v['id'])):
                 episode_id = episode['id']

plugins/youtube_download/yt_dlp/extractor/tumblr.py

@@ -20,6 +20,8 @@ class TumblrIE(InfoExtractor):
             'id': '54196191430',
             'ext': 'mp4',
             'title': 'md5:dfac39636969fe6bf1caa2d50405f069',
+            'timestamp': 1372531260,
+            'upload_date': '20130629',
             'description': 'md5:390ab77358960235b6937ab3b8528956',
             'uploader_id': 'tatianamaslanydaily',
             'uploader_url': 'https://tatianamaslanydaily.tumblr.com/',
@@ -39,6 +41,8 @@ class TumblrIE(InfoExtractor):
             'ext': 'mp4',
             'title': 'Mona\xa0“talking” in\xa0“english”',
             'description': 'md5:082a3a621530cb786ad2b7592a6d9e2c',
+            'timestamp': 1597865276,
+            'upload_date': '20200819',
             'uploader_id': 'maskofthedragon',
             'uploader_url': 'https://maskofthedragon.tumblr.com/',
             'thumbnail': r're:^https?://.*\.jpg',
@@ -76,6 +80,8 @@ class TumblrIE(InfoExtractor):
             'id': '159704441298',
             'ext': 'mp4',
             'title': 'md5:ba79365861101f4911452728d2950561',
+            'timestamp': 1492489550,
+            'upload_date': '20170418',
             'description': 'md5:773738196cea76b6996ec71e285bdabc',
             'uploader_id': 'jujanon',
             'uploader_url': 'https://jujanon.tumblr.com/',
@@ -93,6 +99,8 @@ class TumblrIE(InfoExtractor):
             'id': '180294460076',
             'ext': 'mp4',
             'title': 'duality of bird',
+            'timestamp': 1542651819,
+            'upload_date': '20181119',
             'description': 'duality of bird',
             'uploader_id': 'todaysbird',
             'uploader_url': 'https://todaysbird.tumblr.com/',
@@ -238,6 +246,8 @@ class TumblrIE(InfoExtractor):
         'info_dict': {
             'id': '730460905855467520',
             'uploader_id': 'felixcosm',
+            'upload_date': '20231006',
+            'timestamp': 1696621805,
             'repost_count': int,
             'tags': 'count:15',
             'description': 'md5:2eb3482a3c6987280cbefb6839068f32',
@@ -327,6 +337,8 @@ class TumblrIE(InfoExtractor):
         'url': 'https://www.tumblr.com/anyaboz/765332564457209856/my-music-video-for-selkie-by-nobodys-wolf-child',
         'info_dict': {
             'id': '765332564457209856',
+            'timestamp': 1729878010,
+            'upload_date': '20241025',
             'uploader_id': 'anyaboz',
             'repost_count': int,
             'age_limit': 0,
@@ -445,6 +457,8 @@ class TumblrIE(InfoExtractor):
             'uploader_id': uploader_id,
             'uploader_url': f'https://{uploader_id}.tumblr.com/' if uploader_id else None,
             **traverse_obj(post_json, {
+                # Try oldest post in reblog chain, fall back to timestamp of the post itself
+                'timestamp': ((('trail', 0, 'post'), None), 'timestamp', {int_or_none}, any),
                 'like_count': ('like_count', {int_or_none}),
                 'repost_count': ('reblog_count', {int_or_none}),
                 'tags': ('tags', ..., {str}),

plugins/youtube_download/yt_dlp/extractor/tv5unis.py

@@ -1,14 +1,18 @@
 from .common import InfoExtractor
 from ..utils import (
+    ExtractorError,
     int_or_none,
+    join_nonempty,
+    make_archive_id,
     parse_age_limit,
-    smuggle_url,
-    try_get,
+    remove_end,
 )
+from ..utils.traversal import traverse_obj
 
 
 class TV5UnisBaseIE(InfoExtractor):
     _GEO_COUNTRIES = ['CA']
+    _GEO_BYPASS = False
 
     def _real_extract(self, url):
         groups = self._match_valid_url(url).groups()
@@ -16,96 +20,136 @@ class TV5UnisBaseIE(InfoExtractor):
             'https://api.tv5unis.ca/graphql', groups[0], query={
                 'query': '''{
   %s(%s) {
+    title
+    summary
+    tags
+    duration
+    seasonNumber
+    episodeNumber
     collection {
       title
     }
-    episodeNumber
     rating {
       name
     }
-    seasonNumber
-    tags
-    title
     videoElement {
+      __typename
       ... on Video {
         mediaId
+        encodings {
+          hls {
+            url
+          }
+        }
+      }
+      ... on RestrictedVideo {
+        code
+        reason
       }
     }
   }
 }''' % (self._GQL_QUERY_NAME, self._gql_args(groups)),  # noqa: UP031
             })['data'][self._GQL_QUERY_NAME]
-        media_id = product['videoElement']['mediaId']
+
+        video = product['videoElement']
+        if video is None:
+            raise ExtractorError('This content is no longer available', expected=True)
+
+        if video.get('__typename') == 'RestrictedVideo':
+            code = video.get('code')
+            if code == 1001:
+                self.raise_geo_restricted(countries=self._GEO_COUNTRIES)
+            reason = video.get('reason')
+            raise ExtractorError(join_nonempty(
+                'This video is restricted',
+                code is not None and f', error code {code}',
+                reason and f': {remove_end(reason, ".")}',
+                delim=''))
+
+        media_id = video['mediaId']
+        formats, subtitles = self._extract_m3u8_formats_and_subtitles(
+            video['encodings']['hls']['url'], media_id, 'mp4')
 
         return {
-            '_type': 'url_transparent',
             'id': media_id,
-            'title': product.get('title'),
-            'url': smuggle_url('limelight:media:' + media_id, {'geo_countries': self._GEO_COUNTRIES}),
-            'age_limit': parse_age_limit(try_get(product, lambda x: x['rating']['name'])),
-            'tags': product.get('tags'),
-            'series': try_get(product, lambda x: x['collection']['title']),
-            'season_number': int_or_none(product.get('seasonNumber')),
-            'episode_number': int_or_none(product.get('episodeNumber')),
-            'ie_key': 'LimelightMedia',
+            '_old_archive_ids': [make_archive_id('LimelightMedia', media_id)],
+            'formats': formats,
+            'subtitles': subtitles,
+            **traverse_obj(product, {
+                'title': ('title', {str}),
+                'description': ('summary', {str}),
+                'tags': ('tags', ..., {str}),
+                'duration': ('duration', {int_or_none}),
+                'season_number': ('seasonNumber', {int_or_none}),
+                'episode_number': ('episodeNumber', {int_or_none}),
+                'series': ('collection', 'title', {str}),
+                'age_limit': ('rating', 'name', {parse_age_limit}),
+            }),
         }
 
 
 class TV5UnisVideoIE(TV5UnisBaseIE):
-    _WORKING = False
     IE_NAME = 'tv5unis:video'
-    _VALID_URL = r'https?://(?:www\.)?tv5unis\.ca/videos/[^/]+/(?P<id>\d+)'
-    _TEST = {
-        'url': 'https://www.tv5unis.ca/videos/bande-annonces/71843',
-        'md5': '3d794164928bda97fb87a17e89923d9b',
+    _VALID_URL = r'https?://(?:www\.)?tv5unis\.ca/videos/[^/?#]+/(?P<id>\d+)'
+    _TESTS = [{
+        'url': 'https://www.tv5unis.ca/videos/bande-annonces/144041',
+        'md5': '24a247c96119d77fe1bae8b440457dfa',
         'info_dict': {
-            'id': 'a883684aecb2486cad9bdc7bbe17f861',
+            'id': '56862325352147149dce0ae139afced6',
+            '_old_archive_ids': ['limelightmedia 56862325352147149dce0ae139afced6'],
             'ext': 'mp4',
-            'title': 'Watatatow',
-            'duration': 10.01,
+            'title': 'Antigone',
+            'description': r"re:En aidant son frère .+ dicté par l'amour et la solidarité.",
+            'duration': 61,
         },
-    }
+    }]
     _GQL_QUERY_NAME = 'productById'
 
     @staticmethod
     def _gql_args(groups):
-        return f'id: {groups}'
+        return f'id: {groups[0]}'
 
 
 class TV5UnisIE(TV5UnisBaseIE):
-    _WORKING = False
     IE_NAME = 'tv5unis'
-    _VALID_URL = r'https?://(?:www\.)?tv5unis\.ca/videos/(?P<id>[^/]+)(?:/saisons/(?P<season_number>\d+)/episodes/(?P<episode_number>\d+))?/?(?:[?#&]|$)'
+    _VALID_URL = r'https?://(?:www\.)?tv5unis\.ca/videos/(?P<id>[^/?#]+)(?:/saisons/(?P<season_number>\d+)/episodes/(?P<episode_number>\d+))?/?(?:[?#&]|$)'
     _TESTS = [{
-        'url': 'https://www.tv5unis.ca/videos/watatatow/saisons/6/episodes/1',
-        'md5': 'a479907d2e531a73e1f8dc48d6388d02',
+        # geo-restricted to Canada; xff is ineffective
+        'url': 'https://www.tv5unis.ca/videos/watatatow/saisons/11/episodes/1',
+        'md5': '43beebd47eefb1c5caf9a47a3fc35589',
         'info_dict': {
-            'id': 'e5ee23a586c44612a56aad61accf16ef',
+            'id': '2c06e4af20f0417b86c2536825287690',
+            '_old_archive_ids': ['limelightmedia 2c06e4af20f0417b86c2536825287690'],
             'ext': 'mp4',
-            'title': 'Je ne peux pas lui résister',
-            'description': "Atys, le nouveau concierge de l'école, a réussi à ébranler la confiance de Mado en affirmant qu'une médaille, ce n'est que du métal. Comme Mado essaie de lui prouver que ses valeurs sont solides, il veut la mettre à l'épreuve...",
+            'title': "L'homme éléphant",
+            'description': r're:Paul-André et Jean-Yves, .+ quand elle parle du feu au Spot.',
             'subtitles': {
                 'fr': 'count:1',
             },
-            'duration': 1370,
+            'duration': 1440,
             'age_limit': 8,
-            'tags': 'count:3',
+            'tags': 'count:4',
             'series': 'Watatatow',
-            'season_number': 6,
+            'season': 'Season 11',
+            'season_number': 11,
+            'episode': 'Episode 1',
             'episode_number': 1,
         },
     }, {
-        'url': 'https://www.tv5unis.ca/videos/le-voyage-de-fanny',
-        'md5': '9ca80ebb575c681d10cae1adff3d4774',
+        # geo-restricted to Canada; xff is ineffective
+        'url': 'https://www.tv5unis.ca/videos/boite-a-savon',
+        'md5': '7898e868e8c540f03844660e0aab6bbe',
         'info_dict': {
-            'id': '726188eefe094d8faefb13381d42bc06',
+            'id': '4de6d0c6467b4511a0c04b92037a9f15',
+            '_old_archive_ids': ['limelightmedia 4de6d0c6467b4511a0c04b92037a9f15'],
             'ext': 'mp4',
-            'title': 'Le voyage de Fanny',
-            'description': "Fanny, 12 ans, cachée dans un foyer loin de ses parents, s'occupe de ses deux soeurs. Devant fuir, Fanny prend la tête d'un groupe de huit enfants et s'engage dans un dangereux périple à travers la France occupée pour rejoindre la frontière suisse.",
+            'title': 'Boîte à savon',
+            'description': r're:Dans le petit village de Broche-à-foin, .+ celle qui fait battre son coeur.',
             'subtitles': {
                 'fr': 'count:1',
             },
-            'duration': 5587.034,
-            'tags': 'count:4',
+            'duration': 1200,
+            'tags': 'count:5',
         },
     }]
     _GQL_QUERY_NAME = 'productByRootProductSlug'

plugins/youtube_download/yt_dlp/extractor/twitch.py

@@ -41,16 +41,16 @@ class TwitchBaseIE(InfoExtractor):
     _NETRC_MACHINE = 'twitch'
 
     _OPERATION_HASHES = {
-        'CollectionSideBar': '27111f1b382effad0b6def325caef1909c733fe6a4fbabf54f8d491ef2cf2f14',
-        'FilterableVideoTower_Videos': 'a937f1d22e269e39a03b509f65a7490f9fc247d7f83d6ac1421523e3b68042cb',
-        'ClipsCards__User': 'b73ad2bfaecfd30a9e6c28fada15bd97032c83ec77a0440766a56fe0bd632777',
-        'ShareClipRenderStatus': 'e0a46b287d760c6890a39d1ccd736af5ec9479a267d02c710e9ac33326b651d2',
-        'ChannelCollectionsContent': '447aec6a0cc1e8d0a8d7732d47eb0762c336a2294fdb009e9c9d854e49d484b9',
-        'StreamMetadata': 'a647c2a13599e5991e175155f798ca7f1ecddde73f7f341f39009c14dbf59962',
+        'CollectionSideBar': '016e1e4ccee0eb4698eb3bf1a04dc1c077fb746c78c82bac9a8f0289658fbd1a',
+        'FilterableVideoTower_Videos': '67004f7881e65c297936f32c75246470629557a393788fb5a69d6d9a25a8fd5f',
+        'ClipsCards__User': '90c33f5e6465122fba8f9371e2a97076f9ed06c6fed3788d002ab9eba8f91d88',
+        'ShareClipRenderStatus': '1844261bb449fa51e6167040311da4a7a5f1c34fe71c71a3e0c4f551bc30c698',
+        'ChannelCollectionsContent': '5247910a19b1cd2b760939bf4cba4dcbd3d13bdf8c266decd16956f6ef814077',
+        'StreamMetadata': 'b57f9b910f8cd1a4659d894fe7550ccc81ec9052c01e438b290fd66a040b9b93',
         'ComscoreStreamingQuery': 'e1edae8122517d013405f237ffcc124515dc6ded82480a88daef69c83b53ac01',
-        'VideoPreviewOverlay': '3006e77e51b128d838fa4e835723ca4dc9a05c5efd4466c1085215c6e437e65c',
-        'VideoMetadata': '49b5b8f268cdeb259d75b58dcb0c1a748e3b575003448a2333dc5cdafd49adad',
-        'VideoPlayer_ChapterSelectButtonVideo': '8d2793384aac3773beab5e59bd5d6f585aedb923d292800119e03d40cd0f9b41',
+        'VideoPreviewOverlay': '9515480dee68a77e667cb19de634739d33f243572b007e98e67184b1a5d8369f',
+        'VideoMetadata': '45111672eea2e507f8ba44d101a61862f9c56b11dee09a15634cb75cb9b9084d',
+        'VideoPlayer_ChapterSelectButtonVideo': '71835d5ef425e154bf282453a926d99b328cdc5e32f36d3a209d0f4778b41203',
         'VideoPlayer_VODSeekbarPreviewVideo': '07e99e4d56c5a7c67117a154777b0baf85a5ffefa393b213f4bc712ccaf85dd6',
     }
 
@@ -621,15 +621,15 @@ def _make_video_result(node):
 
 
 class TwitchCollectionIE(TwitchBaseIE):
+    IE_NAME = 'twitch:collection'
     _VALID_URL = r'https?://(?:(?:www|go|m)\.)?twitch\.tv/collections/(?P<id>[^/]+)'
-
     _TESTS = [{
-        'url': 'https://www.twitch.tv/collections/wlDCoH0zEBZZbQ',
+        'url': 'https://www.twitch.tv/collections/o9zZer3IQBhTJw',
         'info_dict': {
-            'id': 'wlDCoH0zEBZZbQ',
-            'title': 'Overthrow Nook, capitalism for children',
+            'id': 'o9zZer3IQBhTJw',
+            'title': 'Playthrough Archives',
         },
-        'playlist_mincount': 13,
+        'playlist_mincount': 21,
     }]
 
     _OPERATION_NAME = 'CollectionSideBar'
@@ -680,6 +680,10 @@ class TwitchPlaylistBaseIE(TwitchBaseIE):
                 }],
                 f'Downloading {self._NODE_KIND}s GraphQL page {page_num}',
                 fatal=False)
+            # Avoid extracting random/unrelated entries when channel_name doesn't exist
+            # See https://github.com/yt-dlp/yt-dlp/issues/15450
+            if traverse_obj(page, (0, 'data', 'user', 'id', {str})) == '':
+                raise ExtractorError(f'Channel "{channel_name}" not found', expected=True)
             if not page:
                 break
             edges = try_get(
@@ -720,8 +724,8 @@ class TwitchVideosBaseIE(TwitchPlaylistBaseIE):
 
 
 class TwitchVideosIE(TwitchVideosBaseIE):
+    IE_NAME = 'twitch:videos'
     _VALID_URL = r'https?://(?:(?:www|go|m)\.)?twitch\.tv/(?P<id>[^/]+)/(?:videos|profile)'
-
     _TESTS = [{
         # All Videos sorted by Date
         'url': 'https://www.twitch.tv/spamfish/videos?filter=all',
@@ -729,7 +733,7 @@ class TwitchVideosIE(TwitchVideosBaseIE):
             'id': 'spamfish',
             'title': 'spamfish - All Videos sorted by Date',
         },
-        'playlist_mincount': 924,
+        'playlist_mincount': 751,
     }, {
         # All Videos sorted by Popular
         'url': 'https://www.twitch.tv/spamfish/videos?filter=all&sort=views',
@@ -737,8 +741,9 @@ class TwitchVideosIE(TwitchVideosBaseIE):
             'id': 'spamfish',
             'title': 'spamfish - All Videos sorted by Popular',
         },
-        'playlist_mincount': 931,
+        'playlist_mincount': 754,
     }, {
+        # TODO: Investigate why we get 0 entries
         # Past Broadcasts sorted by Date
         'url': 'https://www.twitch.tv/spamfish/videos?filter=archives',
         'info_dict': {
@@ -753,8 +758,9 @@ class TwitchVideosIE(TwitchVideosBaseIE):
             'id': 'spamfish',
             'title': 'spamfish - Highlights sorted by Date',
         },
-        'playlist_mincount': 901,
+        'playlist_mincount': 751,
     }, {
+        # TODO: Investigate why we get 0 entries
         # Uploads sorted by Date
         'url': 'https://www.twitch.tv/esl_csgo/videos?filter=uploads&sort=time',
         'info_dict': {
@@ -763,6 +769,7 @@ class TwitchVideosIE(TwitchVideosBaseIE):
         },
         'playlist_mincount': 5,
     }, {
+        # TODO: Investigate why we get 0 entries
         # Past Premieres sorted by Date
         'url': 'https://www.twitch.tv/spamfish/videos?filter=past_premieres',
         'info_dict': {
@@ -825,8 +832,8 @@ class TwitchVideosIE(TwitchVideosBaseIE):
 
 
 class TwitchVideosClipsIE(TwitchPlaylistBaseIE):
+    IE_NAME = 'twitch:videos:clips'
     _VALID_URL = r'https?://(?:(?:www|go|m)\.)?twitch\.tv/(?P<id>[^/]+)/(?:clips|videos/*?\?.*?\bfilter=clips)'
-
     _TESTS = [{
         # Clips
         'url': 'https://www.twitch.tv/vanillatv/clips?filter=clips&range=all',
@@ -898,8 +905,8 @@ class TwitchVideosClipsIE(TwitchPlaylistBaseIE):
 
 
 class TwitchVideosCollectionsIE(TwitchPlaylistBaseIE):
+    IE_NAME = 'twitch:videos:collections'
     _VALID_URL = r'https?://(?:(?:www|go|m)\.)?twitch\.tv/(?P<id>[^/]+)/videos/*?\?.*?\bfilter=collections'
-
     _TESTS = [{
         # Collections
         'url': 'https://www.twitch.tv/spamfish/videos?filter=collections',
@@ -1050,7 +1057,10 @@ class TwitchStreamIE(TwitchVideosBaseIE):
         gql = self._download_gql(
             channel_name, [{
                 'operationName': 'StreamMetadata',
-                'variables': {'channelLogin': channel_name},
+                'variables': {
+                    'channelLogin': channel_name,
+                    'includeIsDJ': True,
+                },
             }, {
                 'operationName': 'ComscoreStreamingQuery',
                 'variables': {

plugins/youtube_download/yt_dlp/extractor/twitter.py

@@ -32,67 +32,11 @@ from ..utils.traversal import require, traverse_obj
 
 
 class TwitterBaseIE(InfoExtractor):
-    _NETRC_MACHINE = 'twitter'
     _API_BASE = 'https://api.x.com/1.1/'
     _GRAPHQL_API_BASE = 'https://x.com/i/api/graphql/'
     _BASE_REGEX = r'https?://(?:(?:www|m(?:obile)?)\.)?(?:(?:twitter|x)\.com|twitter3e4tixl4xyajtrzo62zg5vztmjuricljdp2c5kshju4avyoid\.onion)/'
     _AUTH = 'AAAAAAAAAAAAAAAAAAAAANRILgAAAAAAnNwIzUejRCOuH5E6I8xnZz4puTs%3D1Zv7ttfk8LF81IUq16cHjhLTvJu4FA33AGWWjCpTnA'
     _LEGACY_AUTH = 'AAAAAAAAAAAAAAAAAAAAAIK1zgAAAAAA2tUWuhGZ2JceoId5GwYWU5GspY4%3DUq7gzFoCZs1QfwGoVdvSac3IniczZEYXIcDyumCauIXpcAPorE'
-    _flow_token = None
-
-    _LOGIN_INIT_DATA = json.dumps({
-        'input_flow_data': {
-            'flow_context': {
-                'debug_overrides': {},
-                'start_location': {
-                    'location': 'unknown',
-                },
-            },
-        },
-        'subtask_versions': {
-            'action_list': 2,
-            'alert_dialog': 1,
-            'app_download_cta': 1,
-            'check_logged_in_account': 1,
-            'choice_selection': 3,
-            'contacts_live_sync_permission_prompt': 0,
-            'cta': 7,
-            'email_verification': 2,
-            'end_flow': 1,
-            'enter_date': 1,
-            'enter_email': 2,
-            'enter_password': 5,
-            'enter_phone': 2,
-            'enter_recaptcha': 1,
-            'enter_text': 5,
-            'enter_username': 2,
-            'generic_urt': 3,
-            'in_app_notification': 1,
-            'interest_picker': 3,
-            'js_instrumentation': 1,
-            'menu_dialog': 1,
-            'notifications_permission_prompt': 2,
-            'open_account': 2,
-            'open_home_timeline': 1,
-            'open_link': 1,
-            'phone_verification': 4,
-            'privacy_options': 1,
-            'security_key': 3,
-            'select_avatar': 4,
-            'select_banner': 2,
-            'settings_list': 7,
-            'show_code': 1,
-            'sign_up': 2,
-            'sign_up_review': 4,
-            'tweet_selection_urt': 1,
-            'update_users': 1,
-            'upload_media': 1,
-            'user_recommendations_list': 4,
-            'user_recommendations_urt': 1,
-            'wait_spinner': 3,
-            'web_modal': 1,
-        },
-    }, separators=(',', ':')).encode()
 
     def _extract_variant_formats(self, variant, video_id):
         variant_url = variant.get('url')
@@ -172,135 +116,6 @@ class TwitterBaseIE(InfoExtractor):
             'x-csrf-token': try_call(lambda: self._get_cookies(self._API_BASE)['ct0'].value),
         })
 
-    def _call_login_api(self, note, headers, query={}, data=None):
-        response = self._download_json(
-            f'{self._API_BASE}onboarding/task.json', None, note,
-            headers=headers, query=query, data=data, expected_status=400)
-        error = traverse_obj(response, ('errors', 0, 'message', {str}))
-        if error:
-            raise ExtractorError(f'Login failed, Twitter API says: {error}', expected=True)
-        elif traverse_obj(response, 'status') != 'success':
-            raise ExtractorError('Login was unsuccessful')
-
-        subtask = traverse_obj(
-            response, ('subtasks', ..., 'subtask_id', {str}), get_all=False)
-        if not subtask:
-            raise ExtractorError('Twitter API did not return next login subtask')
-
-        self._flow_token = response['flow_token']
-
-        return subtask
-
-    def _perform_login(self, username, password):
-        if self.is_logged_in:
-            return
-
-        guest_token = self._fetch_guest_token(None)
-        headers = {
-            **self._set_base_headers(),
-            'content-type': 'application/json',
-            'x-guest-token': guest_token,
-            'x-twitter-client-language': 'en',
-            'x-twitter-active-user': 'yes',
-            'Referer': 'https://x.com/',
-            'Origin': 'https://x.com',
-        }
-
-        def build_login_json(*subtask_inputs):
-            return json.dumps({
-                'flow_token': self._flow_token,
-                'subtask_inputs': subtask_inputs,
-            }, separators=(',', ':')).encode()
-
-        def input_dict(subtask_id, text):
-            return {
-                'subtask_id': subtask_id,
-                'enter_text': {
-                    'text': text,
-                    'link': 'next_link',
-                },
-            }
-
-        next_subtask = self._call_login_api(
-            'Downloading flow token', headers, query={'flow_name': 'login'}, data=self._LOGIN_INIT_DATA)
-
-        while not self.is_logged_in:
-            if next_subtask == 'LoginJsInstrumentationSubtask':
-                next_subtask = self._call_login_api(
-                    'Submitting JS instrumentation response', headers, data=build_login_json({
-                        'subtask_id': next_subtask,
-                        'js_instrumentation': {
-                            'response': '{}',
-                            'link': 'next_link',
-                        },
-                    }))
-
-            elif next_subtask == 'LoginEnterUserIdentifierSSO':
-                next_subtask = self._call_login_api(
-                    'Submitting username', headers, data=build_login_json({
-                        'subtask_id': next_subtask,
-                        'settings_list': {
-                            'setting_responses': [{
-                                'key': 'user_identifier',
-                                'response_data': {
-                                    'text_data': {
-                                        'result': username,
-                                    },
-                                },
-                            }],
-                            'link': 'next_link',
-                        },
-                    }))
-
-            elif next_subtask == 'LoginEnterAlternateIdentifierSubtask':
-                next_subtask = self._call_login_api(
-                    'Submitting alternate identifier', headers,
-                    data=build_login_json(input_dict(next_subtask, self._get_tfa_info(
-                        'one of username, phone number or email that was not used as --username'))))
-
-            elif next_subtask == 'LoginEnterPassword':
-                next_subtask = self._call_login_api(
-                    'Submitting password', headers, data=build_login_json({
-                        'subtask_id': next_subtask,
-                        'enter_password': {
-                            'password': password,
-                            'link': 'next_link',
-                        },
-                    }))
-
-            elif next_subtask == 'AccountDuplicationCheck':
-                next_subtask = self._call_login_api(
-                    'Submitting account duplication check', headers, data=build_login_json({
-                        'subtask_id': next_subtask,
-                        'check_logged_in_account': {
-                            'link': 'AccountDuplicationCheck_false',
-                        },
-                    }))
-
-            elif next_subtask == 'LoginTwoFactorAuthChallenge':
-                next_subtask = self._call_login_api(
-                    'Submitting 2FA token', headers, data=build_login_json(input_dict(
-                        next_subtask, self._get_tfa_info('two-factor authentication token'))))
-
-            elif next_subtask == 'LoginAcid':
-                next_subtask = self._call_login_api(
-                    'Submitting confirmation code', headers, data=build_login_json(input_dict(
-                        next_subtask, self._get_tfa_info('confirmation code sent to your email or phone'))))
-
-            elif next_subtask == 'ArkoseLogin':
-                self.raise_login_required('Twitter is requiring captcha for this login attempt', method='cookies')
-
-            elif next_subtask == 'DenyLoginSubtask':
-                self.raise_login_required('Twitter rejected this login attempt as suspicious', method='cookies')
-
-            elif next_subtask == 'LoginSuccessSubtask':
-                raise ExtractorError('Twitter API did not grant auth token cookie')
-
-            else:
-                raise ExtractorError(f'Unrecognized subtask ID "{next_subtask}"')
-
-        self.report_login()
-
     def _call_api(self, path, video_id, query={}, graphql=False):
         headers = self._set_base_headers(legacy=not graphql and self._selected_api == 'legacy')
         headers.update({
@@ -416,6 +231,7 @@ class TwitterCardIE(InfoExtractor):
                 'live_status': 'not_live',
             },
             'add_ie': ['Youtube'],
+            'skip': 'The page does not exist',
         },
         {
             'url': 'https://twitter.com/i/videos/tweet/705235433198714880',
@@ -617,6 +433,7 @@ class TwitterIE(TwitterBaseIE):
             'comment_count': int,
             '_old_archive_ids': ['twitter 852138619213144067'],
         },
+        'skip': 'Suspended',
     }, {
         'url': 'https://twitter.com/i/web/status/910031516746514432',
         'info_dict': {
@@ -763,10 +580,10 @@ class TwitterIE(TwitterBaseIE):
         'url': 'https://twitter.com/UltimaShadowX/status/1577719286659006464',
         'info_dict': {
             'id': '1577719286659006464',
-            'title': 'Ultima - Test',
+            'title': r're:Ultima.* - Test$',
             'description': 'Test https://t.co/Y3KEZD7Dad',
             'channel_id': '168922496',
-            'uploader': 'Ultima',
+            'uploader': r're:Ultima.*',
             'uploader_id': 'UltimaShadowX',
             'uploader_url': 'https://twitter.com/UltimaShadowX',
             'upload_date': '20221005',
@@ -895,11 +712,12 @@ class TwitterIE(TwitterBaseIE):
             'uploader': r're:Monique Camarra.+?',
             'uploader_id': 'MoniqueCamarra',
             'live_status': 'was_live',
-            'release_timestamp': 1658417414,
+            'release_timestamp': 1658417305,
             'description': r're:Twitter Space participated by Sergej Sumlenny.+',
             'timestamp': 1658407771,
             'release_date': '20220721',
             'upload_date': '20220721',
+            'thumbnail': 'https://pbs.twimg.com/profile_images/1920514378006188033/xQs6J_yI_400x400.jpg',
         },
         'add_ie': ['TwitterSpaces'],
         'params': {'skip_download': 'm3u8'},
@@ -1010,10 +828,10 @@ class TwitterIE(TwitterBaseIE):
             'description': 'This is a genius ad by Apple. \U0001f525\U0001f525\U0001f525\U0001f525\U0001f525 https://t.co/cNsA0MoOml',
             'thumbnail': 'https://pbs.twimg.com/ext_tw_video_thumb/1600009362759733248/pu/img/XVhFQivj75H_YxxV.jpg?name=orig',
             'age_limit': 0,
-            'uploader': 'Boy Called Mün',
+            'uploader': 'D U N I Y A',
             'repost_count': int,
             'upload_date': '20221206',
-            'title': 'Boy Called Mün - This is a genius ad by Apple. \U0001f525\U0001f525\U0001f525\U0001f525\U0001f525',
+            'title': 'D U N I Y A - This is a genius ad by Apple. \U0001f525\U0001f525\U0001f525\U0001f525\U0001f525',
             'comment_count': int,
             'like_count': int,
             'tags': [],
@@ -1068,6 +886,7 @@ class TwitterIE(TwitterBaseIE):
             'comment_count': int,
             '_old_archive_ids': ['twitter 1695424220702888009'],
         },
+        'skip': 'Suspended',
     }, {
         # retweeted_status w/ legacy API
         'url': 'https://twitter.com/playstrumpcard/status/1695424220702888009',
@@ -1092,6 +911,7 @@ class TwitterIE(TwitterBaseIE):
             '_old_archive_ids': ['twitter 1695424220702888009'],
         },
         'params': {'extractor_args': {'twitter': {'api': ['legacy']}}},
+        'skip': 'Suspended',
     }, {
         # Broadcast embedded in tweet
         'url': 'https://twitter.com/JessicaDobsonWX/status/1731121063248175384',
@@ -1135,7 +955,6 @@ class TwitterIE(TwitterBaseIE):
     }, {
         # "stale tweet" with typename "TweetWithVisibilityResults"
         'url': 'https://twitter.com/RobertKennedyJr/status/1724884212803834154',
-        'md5': '511377ff8dfa7545307084dca4dce319',
         'info_dict': {
             'id': '1724883339285544960',
             'ext': 'mp4',
@@ -1182,6 +1001,30 @@ class TwitterIE(TwitterBaseIE):
             'age_limit': 0,
             '_old_archive_ids': ['twitter 1790637656616943991'],
         },
+    }, {
+        # unified_card with 2 items of type video and photo
+        'url': 'https://x.com/TopHeroes_/status/2001950365332455490',
+        'info_dict': {
+            'id': '2001841416071450628',
+            'ext': 'mp4',
+            'display_id': '2001950365332455490',
+            'title': 'Top Heroes - Forgot to close My heroes solo level up in my phone  ✨Unlock the fog,...',
+            'description': r're:Forgot to close My heroes solo level up in my phone  ✨Unlock the fog.+',
+            'uploader': 'Top Heroes',
+            'uploader_id': 'TopHeroes_',
+            'uploader_url': 'https://twitter.com/TopHeroes_',
+            'channel_id': '1737324725620326400',
+            'comment_count': int,
+            'like_count': int,
+            'repost_count': int,
+            'age_limit': 0,
+            'duration': 30.278,
+            'thumbnail': 'https://pbs.twimg.com/amplify_video_thumb/2001841416071450628/img/hpy5KpJh4pO17b65.jpg?name=orig',
+            'tags': [],
+            'timestamp': 1766137136,
+            'upload_date': '20251219',
+            '_old_archive_ids': ['twitter 2001950365332455490'],
+        },
     }, {
         # onion route
         'url': 'https://twitter3e4tixl4xyajtrzo62zg5vztmjuricljdp2c5kshju4avyoid.onion/TwitterBlue/status/1484226494708662273',
@@ -1422,14 +1265,14 @@ class TwitterIE(TwitterBaseIE):
             if not card:
                 return
 
-            self.write_debug(f'Extracting from card info: {card.get("url")}')
+            card_name = card['name'].split(':')[-1]
+            self.write_debug(f'Extracting from {card_name} card info: {card.get("url")}')
             binding_values = card['binding_values']
 
             def get_binding_value(k):
                 o = binding_values.get(k) or {}
                 return try_get(o, lambda x: x[x['type'].lower() + '_value'])
 
-            card_name = card['name'].split(':')[-1]
             if card_name == 'player':
                 yield {
                     '_type': 'url',
@@ -1461,7 +1304,7 @@ class TwitterIE(TwitterBaseIE):
             elif card_name == 'unified_card':
                 unified_card = self._parse_json(get_binding_value('unified_card'), twid)
                 yield from map(extract_from_video_info, traverse_obj(
-                    unified_card, ('media_entities', ...), expected_type=dict))
+                    unified_card, ('media_entities', lambda _, v: v['type'] == 'video')))
             # amplify, promo_video_website, promo_video_convo, appplayer,
             # video_direct_message, poll2choice_video, poll3choice_video,
             # poll4choice_video, ...

plugins/youtube_download/yt_dlp/extractor/urplay.py

@@ -7,14 +7,15 @@ from ..utils import (
     parse_age_limit,
     try_get,
     unified_timestamp,
+    url_or_none,
 )
+from ..utils.traversal import require, traverse_obj
 
 
 class URPlayIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?ur(?:play|skola)\.se/(?:program|Produkter)/(?P<id>[0-9]+)'
     _TESTS = [{
         'url': 'https://urplay.se/program/203704-ur-samtiden-livet-universum-och-rymdens-markliga-musik-om-vetenskap-kritiskt-tankande-och-motstand',
-        'md5': '5ba36643c77cc3d34ffeadad89937d1e',
         'info_dict': {
             'id': '203704',
             'ext': 'mp4',
@@ -25,11 +26,12 @@ class URPlayIE(InfoExtractor):
             'upload_date': '20171214',
             'series': 'UR Samtiden - Livet, universum och rymdens märkliga musik',
             'duration': 2269,
-            'categories': ['Vetenskap & teknik'],
+            'categories': ['Kultur & historia'],
             'tags': ['Kritiskt tänkande', 'Vetenskap', 'Vetenskaplig verksamhet'],
             'episode': 'Om vetenskap, kritiskt tänkande och motstånd',
             'age_limit': 15,
         },
+        'params': {'skip_download': 'm3u8'},
     }, {
         'url': 'https://urplay.se/program/222967-en-foralders-dagbok-mitt-barn-skadar-sig-sjalv',
         'info_dict': {
@@ -48,6 +50,7 @@ class URPlayIE(InfoExtractor):
             'tags': 'count:7',
             'episode': 'Mitt barn skadar sig själv',
         },
+        'params': {'skip_download': 'm3u8'},
     }, {
         'url': 'https://urskola.se/Produkter/190031-Tripp-Trapp-Trad-Sovkudde',
         'info_dict': {
@@ -67,6 +70,27 @@ class URPlayIE(InfoExtractor):
             'episode': 'Sovkudde',
             'season': 'Säsong 1',
         },
+        'params': {'skip_download': 'm3u8'},
+    }, {
+        # Only accessible through new media api
+        'url': 'https://urplay.se/program/242932-vulkanernas-krafter-fran-kraftfull-till-forgorande',
+        'info_dict': {
+            'id': '242932',
+            'ext': 'mp4',
+            'title': 'Vulkanernas krafter : Från kraftfull till förgörande',
+            'description': 'md5:742bb87048e7d5a7f209d28f9bb70ab1',
+            'age_limit': 15,
+            'duration': 2613,
+            'thumbnail': 'https://assets.ur.se/id/242932/images/1_hd.jpg',
+            'categories': ['Vetenskap & teknik'],
+            'tags': ['Geofysik', 'Naturvetenskap', 'Vulkaner', 'Vulkanutbrott'],
+            'series': 'Vulkanernas krafter',
+            'episode': 'Från kraftfull till förgörande',
+            'episode_number': 2,
+            'timestamp': 1763514000,
+            'upload_date': '20251119',
+        },
+        'params': {'skip_download': 'm3u8'},
     }, {
         'url': 'http://urskola.se/Produkter/155794-Smasagor-meankieli-Grodan-i-vida-varlden',
         'only_matching': True,
@@ -78,7 +102,7 @@ class URPlayIE(InfoExtractor):
         webpage = self._download_webpage(url, video_id)
         urplayer_data = self._search_nextjs_data(webpage, video_id, fatal=False) or {}
         if urplayer_data:
-            urplayer_data = try_get(urplayer_data, lambda x: x['props']['pageProps']['program'], dict)
+            urplayer_data = traverse_obj(urplayer_data, ('props', 'pageProps', 'productData', {dict}))
             if not urplayer_data:
                 raise ExtractorError('Unable to parse __NEXT_DATA__')
         else:
@@ -87,21 +111,12 @@ class URPlayIE(InfoExtractor):
                 webpage, 'urplayer data'), video_id)['accessibleEpisodes']
             urplayer_data = next(e for e in accessible_episodes if e.get('id') == int_or_none(video_id))
         episode = urplayer_data['title']
-
-        host = self._download_json('http://streaming-loadbalancer.ur.se/loadbalancer.json', video_id)['redirect']
-        formats = []
-        urplayer_streams = urplayer_data.get('streamingInfo', {})
-
-        for k, v in urplayer_streams.get('raw', {}).items():
-            if not (k in ('sd', 'hd', 'mp3', 'm4a') and isinstance(v, dict)):
-                continue
-            file_http = v.get('location')
-            if file_http:
-                formats.extend(self._extract_wowza_formats(
-                    f'http://{host}/{file_http}playlist.m3u8',
-                    video_id, skip_protocols=['f4m', 'rtmp', 'rtsp']))
-
-        subtitles = {}
+        sources = self._download_json(
+            f'https://media-api.urplay.se/config-streaming/v1/urplay/sources/{video_id}', video_id,
+            note='Downloading streaming information')
+        hls_url = traverse_obj(sources, ('sources', 'hls', {url_or_none}, {require('HLS URL')}))
+        formats, subtitles = self._extract_m3u8_formats_and_subtitles(
+            hls_url, video_id, 'mp4', m3u8_id='hls')
 
         def parse_lang_code(code):
             "3-character language code or None (utils candidate)"

plugins/youtube_download/yt_dlp/extractor/wistia.py

@@ -339,11 +339,20 @@ class WistiaChannelIE(WistiaBaseIE):
             'title': 'The Roof S2: The Modern CRO',
             'thumbnail': r're:https?://embed(?:-ssl)?\.wistia\.com/.+\.(?:jpg|png)',
             'duration': 86.487,
-            'description': 'A sales leader on The Roof? Man, they really must be letting anyone up here this season.\n',
+            'description': 'A sales leader on The Roof? Man, they really must be letting anyone up here this season. ',
             'timestamp': 1619790290,
             'upload_date': '20210430',
         },
         'params': {'noplaylist': True, 'skip_download': True},
+    }, {
+        # Channel with episodes structure instead of videos
+        'url': 'https://fast.wistia.net/embed/channel/sapab9p6qd',
+        'info_dict': {
+            'id': 'sapab9p6qd',
+            'title': 'Credo: An RCIA Program',
+            'description': '\n',
+        },
+        'playlist_mincount': 80,
     }]
     _WEBPAGE_TESTS = [{
         'url': 'https://www.profitwell.com/recur/boxed-out',
@@ -399,8 +408,7 @@ class WistiaChannelIE(WistiaBaseIE):
 
         entries = [
             self.url_result(f'wistia:{video["hashedId"]}', WistiaIE, title=video.get('name'))
-            for video in traverse_obj(series, ('sections', ..., 'videos', ...)) or []
-            if video.get('hashedId')
+            for video in traverse_obj(series, ('sections', ..., ('videos', 'episodes'), lambda _, v: v['hashedId']))
         ]
 
         return self.playlist_result(

plugins/youtube_download/yt_dlp/extractor/xhamster.py

@@ -1,8 +1,6 @@
-import base64
-import codecs
 import itertools
 import re
-import string
+import urllib.parse
 
 from .common import InfoExtractor
 from ..utils import (
@@ -16,7 +14,6 @@ from ..utils import (
     join_nonempty,
     parse_duration,
     str_or_none,
-    try_call,
     try_get,
     unified_strdate,
     url_or_none,
@@ -32,7 +29,7 @@ class _ByteGenerator:
         try:
             self._algorithm = getattr(self, f'_algo{algo_id}')
         except AttributeError:
-            raise ExtractorError(f'Unknown algorithm ID: {algo_id}')
+            raise ExtractorError(f'Unknown algorithm ID "{algo_id}"')
         self._s = to_signed_32(seed)
 
     def _algo1(self, s):
@@ -60,6 +57,37 @@ class _ByteGenerator:
         s = to_signed_32(s * to_signed_32(0xc2b2ae3d))
         return to_signed_32(s ^ ((s & 0xFFFFFFFF) >> 16))
 
+    def _algo4(self, s):
+        # Custom scrambling function involving a left rotation (ROL)
+        s = self._s = to_signed_32(s + 0x6d2b79f5)
+        s = to_signed_32((s << 7) | ((s & 0xFFFFFFFF) >> 25))  # ROL 7
+        s = to_signed_32(s + 0x9e3779b9)
+        s = to_signed_32(s ^ ((s & 0xFFFFFFFF) >> 11))
+        return to_signed_32(s * 0x27d4eb2d)
+
+    def _algo5(self, s):
+        # xorshift variant with a final addition
+        s = to_signed_32(s ^ (s << 7))
+        s = to_signed_32(s ^ ((s & 0xFFFFFFFF) >> 9))
+        s = to_signed_32(s ^ (s << 8))
+        s = self._s = to_signed_32(s + 0xa5a5a5a5)
+        return s
+
+    def _algo6(self, s):
+        # LCG (a=0x2c9277b5, c=0xac564b05) with a variable right shift scrambler
+        s = self._s = to_signed_32(s * to_signed_32(0x2c9277b5) + to_signed_32(0xac564b05))
+        s2 = to_signed_32(s ^ ((s & 0xFFFFFFFF) >> 18))
+        shift = (s & 0xFFFFFFFF) >> 27 & 31
+        return to_signed_32((s2 & 0xFFFFFFFF) >> shift)
+
+    def _algo7(self, s):
+        # Weyl Sequence (k=0x9e3779b9) + custom multiply-xor-shift mixing function
+        s = self._s = to_signed_32(s + to_signed_32(0x9e3779b9))
+        e = to_signed_32(s ^ (s << 5))
+        e = to_signed_32(e * to_signed_32(0x7feb352d))
+        e = to_signed_32(e ^ ((e & 0xFFFFFFFF) >> 15))
+        return to_signed_32(e * to_signed_32(0x846ca68b))
+
     def __next__(self):
         return self._algorithm(self._s) & 0xFF
 
@@ -185,32 +213,28 @@ class XHamsterIE(InfoExtractor):
         'only_matching': True,
     }]
 
-    _XOR_KEY = b'xh7999'
-
     def _decipher_format_url(self, format_url, format_id):
-        if all(char in string.hexdigits for char in format_url):
-            byte_data = bytes.fromhex(format_url)
-            seed = int.from_bytes(byte_data[1:5], byteorder='little', signed=True)
-            byte_gen = _ByteGenerator(byte_data[0], seed)
-            return bytearray(byte ^ next(byte_gen) for byte in byte_data[5:]).decode('latin-1')
+        parsed_url = urllib.parse.urlparse(format_url)
 
-        cipher_type, _, ciphertext = try_call(
-            lambda: base64.b64decode(format_url).decode().partition('_')) or [None] * 3
-
-        if not cipher_type or not ciphertext:
-            self.report_warning(f'Skipping format "{format_id}": failed to decipher URL')
+        hex_string, path_remainder = self._search_regex(
+            r'^/(?P<hex>[0-9a-fA-F]{12,})(?P<rem>[/,].+)$', parsed_url.path, 'url components',
+            default=(None, None), group=('hex', 'rem'))
+        if not hex_string:
+            self.report_warning(f'Skipping format "{format_id}": unsupported URL format')
             return None
 
-        if cipher_type == 'xor':
-            return bytes(
-                a ^ b for a, b in
-                zip(ciphertext.encode(), itertools.cycle(self._XOR_KEY))).decode()
+        byte_data = bytes.fromhex(hex_string)
+        seed = int.from_bytes(byte_data[1:5], byteorder='little', signed=True)
 
-        if cipher_type == 'rot13':
-            return codecs.decode(ciphertext, cipher_type)
+        try:
+            byte_gen = _ByteGenerator(byte_data[0], seed)
+        except ExtractorError as e:
+            self.report_warning(f'Skipping format "{format_id}": {e.msg}')
+            return None
 
-        self.report_warning(f'Skipping format "{format_id}": unsupported cipher type "{cipher_type}"')
-        return None
+        deciphered = bytearray(byte ^ next(byte_gen) for byte in byte_data[5:]).decode('latin-1')
+
+        return parsed_url._replace(path=f'/{deciphered}{path_remainder}').geturl()
 
     def _fixup_formats(self, formats):
         for f in formats:
@@ -333,8 +357,11 @@ class XHamsterIE(InfoExtractor):
                                     'height': get_height(quality),
                                     'filesize': format_sizes.get(quality),
                                     'http_headers': {
-                                        'Referer': standard_url,
+                                        'Referer': urlh.url,
                                     },
+                                    # HTTP formats return "Wrong key" error even when deciphered by site JS
+                                    # TODO: Remove this when resolved on the site's end
+                                    '__needs_testing': True,
                                 })
 
             categories_list = video.get('categories')
@@ -371,7 +398,8 @@ class XHamsterIE(InfoExtractor):
                 'age_limit': age_limit if age_limit is not None else 18,
                 'categories': categories,
                 'formats': self._fixup_formats(formats),
-                '_format_sort_fields': ('res', 'proto', 'tbr'),
+                # TODO: Revert to ('res', 'proto', 'tbr') when HTTP formats problem is resolved
+                '_format_sort_fields': ('res', 'proto:m3u8', 'tbr'),
             }
 
         # Old layout fallback

plugins/youtube_download/yt_dlp/extractor/yahoo.py

@@ -13,55 +13,16 @@ from ..utils import (
     parse_iso8601,
     traverse_obj,
     try_get,
+    update_url,
     url_or_none,
 )
 
 
 class YahooIE(InfoExtractor):
-    IE_DESC = 'Yahoo screen and movies'
+    IE_NAME = 'yahoo'
     _VALID_URL = r'(?P<url>https?://(?:(?P<country>[a-zA-Z]{2}(?:-[a-zA-Z]{2})?|malaysia)\.)?(?:[\da-zA-Z_-]+\.)?yahoo\.com/(?:[^/]+/)*(?P<id>[^?&#]*-[0-9]+(?:-[a-z]+)?)\.html)'
-    _EMBED_REGEX = [r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1']
-
     _TESTS = [{
-        'url': 'http://screen.yahoo.com/julian-smith-travis-legg-watch-214727115.html',
-        'info_dict': {
-            'id': '2d25e626-2378-391f-ada0-ddaf1417e588',
-            'ext': 'mp4',
-            'title': 'Julian Smith & Travis Legg Watch Julian Smith',
-            'description': 'Julian and Travis watch Julian Smith',
-            'duration': 6863,
-            'timestamp': 1369812016,
-            'upload_date': '20130529',
-        },
-        'skip': 'No longer exists',
-    }, {
-        'url': 'https://screen.yahoo.com/community/community-sizzle-reel-203225340.html?format=embed',
-        'md5': '7993e572fac98e044588d0b5260f4352',
-        'info_dict': {
-            'id': '4fe78544-8d48-39d8-97cd-13f205d9fcdb',
-            'ext': 'mp4',
-            'title': "Yahoo Saves 'Community'",
-            'description': 'md5:4d4145af2fd3de00cbb6c1d664105053',
-            'duration': 170,
-            'timestamp': 1406838636,
-            'upload_date': '20140731',
-        },
-        'skip': 'Unfortunately, this video is not available in your region',
-    }, {
-        'url': 'https://uk.screen.yahoo.com/editor-picks/cute-raccoon-freed-drain-using-091756545.html',
-        'md5': '71298482f7c64cbb7fa064e4553ff1c1',
-        'info_dict': {
-            'id': 'b3affa53-2e14-3590-852b-0e0db6cd1a58',
-            'ext': 'webm',
-            'title': 'Cute Raccoon Freed From Drain\u00a0Using Angle Grinder',
-            'description': 'md5:f66c890e1490f4910a9953c941dee944',
-            'duration': 97,
-            'timestamp': 1414489862,
-            'upload_date': '20141028',
-        },
-        'skip': 'No longer exists',
-    }, {
-        'url': 'http://news.yahoo.com/video/china-moses-crazy-blues-104538833.html',
+        'url': 'https://news.yahoo.com/video/china-moses-crazy-blues-104538833.html',
         'md5': '88e209b417f173d86186bef6e4d1f160',
         'info_dict': {
             'id': 'f885cf7f-43d4-3450-9fac-46ac30ece521',
@@ -69,27 +30,33 @@ class YahooIE(InfoExtractor):
             'title': 'China Moses Is Crazy About the Blues',
             'description': 'md5:9900ab8cd5808175c7b3fe55b979bed0',
             'duration': 128,
-            'timestamp': 1385722202,
+            'timestamp': 1385721938,
             'upload_date': '20131129',
+            'display_id': 'china-moses-crazy-blues-104538833',
+            'view_count': int,
+            'thumbnail': r're:https://media\.zenfs\.com/.+',
         },
     }, {
         'url': 'https://www.yahoo.com/movies/v/true-story-trailer-173000497.html',
-        'md5': '2a9752f74cb898af5d1083ea9f661b58',
+        # 'md5': '989396ae73d20c6f057746fb226aa215',  # varies between this and 'b17ac378b1134fa44370fb27db09a744'
         'info_dict': {
             'id': '071c4013-ce30-3a93-a5b2-e0413cd4a9d1',
             'ext': 'mp4',
             'title': '\'True Story\' Trailer',
             'description': 'True Story',
             'duration': 150,
-            'timestamp': 1418919206,
+            'timestamp': 1418923800,
             'upload_date': '20141218',
+            'display_id': 'true-story-trailer-173000497',
+            'view_count': int,
+            'thumbnail': r're:https://media\.zenfs\.com/.+\.jpg',
         },
     }, {
         'url': 'https://gma.yahoo.com/pizza-delivery-man-surprised-huge-tip-college-kids-195200785.html',
         'only_matching': True,
     }, {
         'note': 'NBC Sports embeds',
-        'url': 'http://sports.yahoo.com/blogs/ncaab-the-dagger/tyler-kalinoski-s-buzzer-beater-caps-davidson-s-comeback-win-185609842.html?guid=nbc_cbk_davidsonbuzzerbeater_150313',
+        'url': 'https://sports.yahoo.com/blogs/ncaab-the-dagger/tyler-kalinoski-s-buzzer-beater-caps-davidson-s-comeback-win-185609842.html?guid=nbc_cbk_davidsonbuzzerbeater_150313',
         'info_dict': {
             'id': '9CsDKds0kvHI',
             'ext': 'flv',
@@ -99,26 +66,10 @@ class YahooIE(InfoExtractor):
             'uploader': 'NBCU-SPORTS',
             'timestamp': 1426270238,
         },
+        'skip': 'Page no longer has video',
     }, {
         'url': 'https://tw.news.yahoo.com/-100120367.html',
         'only_matching': True,
-    }, {
-        # Query result is embedded in webpage, but explicit request to video API fails with geo restriction
-        'url': 'https://screen.yahoo.com/community/communitary-community-episode-1-ladders-154501237.html',
-        'md5': '4fbafb9c9b6f07aa8f870629f6671b35',
-        'info_dict': {
-            'id': '1f32853c-a271-3eef-8cb6-f6d6872cb504',
-            'ext': 'mp4',
-            'title': 'Communitary - Community Episode 1: Ladders',
-            'description': 'md5:8fc39608213295748e1e289807838c97',
-            'duration': 1646,
-            'timestamp': 1440436550,
-            'upload_date': '20150824',
-            'series': 'Communitary',
-            'season_number': 6,
-            'episode_number': 1,
-        },
-        'skip': 'No longer exists',
     }, {
         # ytwnews://cavideo/
         'url': 'https://tw.video.yahoo.com/movie-tw/單車天使-中文版預-092316541.html',
@@ -129,12 +80,16 @@ class YahooIE(InfoExtractor):
             'description': '中文版預',
             'timestamp': 1476696196,
             'upload_date': '20161017',
+            'view_count': int,
+            'duration': 141,
+            'thumbnail': r're:https://media\.zenfs\.com/.+\.jpg',
+            'series': '電影',
+            'display_id': '單車天使-中文版預-092316541',
         },
         'params': {
             'skip_download': True,
         },
     }, {
-        # Contains both a Yahoo hosted video and multiple Youtube embeds
         'url': 'https://www.yahoo.com/entertainment/gwen-stefani-reveals-the-pop-hit-she-passed-on-assigns-it-to-her-voice-contestant-instead-033045672.html',
         'info_dict': {
             'id': '46c5d95a-528f-3d03-b732-732fcadd51de',
@@ -147,24 +102,29 @@ class YahooIE(InfoExtractor):
                 'ext': 'mp4',
                 'title': 'Gwen Stefani reveals she turned down one of Sia\'s best songs',
                 'description': 'On "The Voice" Tuesday, Gwen Stefani told Taylor Swift which Sia hit was almost hers.',
-                'timestamp': 1572406500,
+                'timestamp': 1572406499,
                 'upload_date': '20191030',
-            },
-        }, {
-            'info_dict': {
-                'id': '352CFDOQrKg',
-                'ext': 'mp4',
-                'title': 'Kyndal Inskeep "Performs the Hell Out of" Sia\'s "Elastic Heart" - The Voice Knockouts 2019',
-                'description': 'md5:7fe8e3d5806f96002e55f190d1d94479',
-                'uploader': 'The Voice',
-                'uploader_id': 'NBCTheVoice',
-                'upload_date': '20191029',
+                'display_id': 'gwen-stefani-reveals-she-turned-033459311',
+                'view_count': int,
+                'duration': 97,
+                'thumbnail': 'https://s.yimg.com/os/creatr-uploaded-images/2019-10/348bb330-fac6-11e9-8d27-38e85d573702',
+                'series': 'Last Night Now',
             },
         }],
-        'params': {
-            'playlistend': 2,
+    }, {
+        'url': 'https://sports.yahoo.com/video/rams-lose-grip-nfcs-top-174614409.html',
+        'info_dict': {
+            'id': '6b15f100-cf5c-3ad0-9c96-87cbd2f72d4a',
+            'ext': 'mp4',
+            'display_id': 'rams-lose-grip-nfcs-top-174614409',
+            'title': 'Rams lose their grip on NFC\'s top seed — can they still secure the bye?',
+            'description': 'md5:5f4f98ab3c4de80e54c105b6bbb1d024',
+            'view_count': int,
+            'duration': 85,
+            'thumbnail': 'https://s.yimg.com/os/creatr-uploaded-images/2025-12/94fc4840-dd02-11f0-beff-38ba3a4992e3',
+            'timestamp': 1766166374,
+            'upload_date': '20251219',
         },
-        'expected_warnings': ['HTTP Error 404', 'Ignoring subtitle tracks'],
     }, {
         'url': 'https://malaysia.news.yahoo.com/video/bystanders-help-ontario-policeman-bust-190932818.html',
         'only_matching': True,
@@ -178,14 +138,12 @@ class YahooIE(InfoExtractor):
 
     def _extract_yahoo_video(self, video_id, country):
         video = self._download_json(
-            f'https://{country}.yahoo.com/_td/api/resource/VideoService.videos;view=full;video_ids=["{video_id}"]',
-            video_id, 'Downloading video JSON metadata')[0]
-        title = video['title']
-
+            f'https://video-api.yql.yahoo.com/v1/video/sapi/streams/{video_id}',
+            video_id, 'Downloading video JSON metadata')['query']['results']['mediaObj'][0]['meta']
         if country == 'malaysia':
             country = 'my'
 
-        is_live = video.get('live_state') == 'live'
+        is_live = traverse_obj(video, ('uplynk_live', {bool})) is True
         fmts = ('m3u8',) if is_live else ('webm', 'mp4')
 
         urls = []
@@ -231,43 +189,23 @@ class YahooIE(InfoExtractor):
                     'ext': mimetype2ext(cc.get('content_type')),
                 })
 
-        streaming_url = video.get('streaming_url')
-        if streaming_url and not is_live:
-            formats.extend(self._extract_m3u8_formats(
-                streaming_url, video_id, 'mp4',
-                'm3u8_native', m3u8_id='hls', fatal=False))
-
         if not formats and msg == 'geo restricted':
             self.raise_geo_restricted(metadata_available=True)
 
-        thumbnails = []
-        for thumb in video.get('thumbnails', []):
-            thumb_url = thumb.get('url')
-            if not thumb_url:
-                continue
-            thumbnails.append({
-                'id': thumb.get('tag'),
-                'url': thumb.get('url'),
-                'width': int_or_none(thumb.get('width')),
-                'height': int_or_none(thumb.get('height')),
-            })
-
-        series_info = video.get('series_info') or {}
-
         return {
             'id': video_id,
-            'title': title,
             'formats': formats,
-            'thumbnails': thumbnails,
-            'description': clean_html(video.get('description')),
-            'timestamp': parse_iso8601(video.get('publish_time')),
             'subtitles': subtitles,
-            'duration': int_or_none(video.get('duration')),
-            'view_count': int_or_none(video.get('view_count')),
             'is_live': is_live,
-            'series': video.get('show_name'),
-            'season_number': int_or_none(series_info.get('season_number')),
-            'episode_number': int_or_none(series_info.get('episode_number')),
+            **traverse_obj(video, {
+                'title': ('title', {clean_html}),
+                'description': ('description', {clean_html}),
+                'thumbnail': ('thumbnail', {url_or_none}, {update_url(scheme='https')}),
+                'timestamp': ('publish_time', {parse_iso8601}),
+                'duration': ('duration', {int_or_none}),
+                'view_count': ('view_count', {int_or_none}),
+                'series': ('show_name', {str}, filter),
+            }),
         }
 
     def _real_extract(self, url):
@@ -321,14 +259,13 @@ class YahooIE(InfoExtractor):
 
 
 class YahooSearchIE(SearchInfoExtractor):
-    IE_DESC = 'Yahoo screen search'
     _MAX_RESULTS = 1000
-    IE_NAME = 'screen.yahoo:search'
+    IE_NAME = 'yahoo:search'
     _SEARCH_KEY = 'yvsearch'
 
     def _search_results(self, query):
         for pagenum in itertools.count(0):
-            result_url = f'http://video.search.yahoo.com/search/?p={urllib.parse.quote_plus(query)}&fr=screen&o=js&gs=0&b={pagenum * 30}'
+            result_url = f'https://video.search.yahoo.com/search/?p={urllib.parse.quote_plus(query)}&fr=screen&o=js&gs=0&b={pagenum * 30}'
             info = self._download_json(result_url, query,
                                        note='Downloading results page ' + str(pagenum + 1))
             yield from (self.url_result(result['rurl']) for result in info['results'])

plugins/youtube_download/yt_dlp/extractor/yfanefa.py

@@ -0,0 +1,67 @@
+from .common import InfoExtractor
+from ..utils import (
+    determine_ext,
+    int_or_none,
+    join_nonempty,
+    remove_end,
+    url_or_none,
+)
+from ..utils.traversal import traverse_obj
+
+
+class YfanefaIE(InfoExtractor):
+    IE_NAME = 'yfanefa'
+    _VALID_URL = r'https?://(?:www\.)?yfanefa\.com/(?P<id>[^?#]+)'
+    _TESTS = [{
+        'url': 'https://www.yfanefa.com/record/2717',
+        'info_dict': {
+            'id': 'record-2717',
+            'ext': 'mp4',
+            'title': 'THE HALLAMSHIRE RIFLES LEAVING SHEFFIELD, 1914',
+            'duration': 5239,
+            'thumbnail': r're:https://media\.yfanefa\.com/storage/v1/file/',
+        },
+    }, {
+        'url': 'https://www.yfanefa.com/news/53',
+        'info_dict': {
+            'id': 'news-53',
+            'ext': 'mp4',
+            'title': 'Memory Bank:  Bradford Launch',
+            'thumbnail': r're:https://media\.yfanefa\.com/storage/v1/file/',
+        },
+    }, {
+        'url': 'https://www.yfanefa.com/evaluating_nature_matters',
+        'info_dict': {
+            'id': 'evaluating_nature_matters',
+            'ext': 'mp4',
+            'title': 'Evaluating Nature Matters',
+            'thumbnail': r're:https://media\.yfanefa\.com/storage/v1/file/',
+        },
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+        player_data = self._search_json(
+            r'iwPlayer\.options\["[\w.]+"\]\s*=', webpage, 'player options', video_id)
+
+        formats = []
+        video_url = join_nonempty(player_data['url'], player_data.get('signature'), delim='')
+        if determine_ext(video_url) == 'm3u8':
+            formats = self._extract_m3u8_formats(
+                video_url, video_id, 'mp4', m3u8_id='hls')
+        else:
+            formats = [{'url': video_url, 'ext': 'mp4'}]
+
+        return {
+            'id': video_id.strip('/').replace('/', '-'),
+            'title':
+                self._og_search_title(webpage, default=None)
+                or remove_end(self._html_extract_title(webpage), ' | Yorkshire Film Archive'),
+            'formats': formats,
+            **traverse_obj(player_data, {
+                'thumbnail': ('preview', {url_or_none}),
+                'duration': ('duration', {int_or_none}),
+            }),
+        }

plugins/youtube_download/yt_dlp/extractor/youtube/_base.py

@@ -104,6 +104,7 @@ INNERTUBE_CLIENTS = {
         },
         'INNERTUBE_CONTEXT_CLIENT_NAME': 1,
         'SUPPORTS_COOKIES': True,
+        'SUPPORTS_AD_PLAYBACK_CONTEXT': True,
         **WEB_PO_TOKEN_POLICIES,
     },
     # Safari UA returns pre-merged video+audio 144p/240p/360p/720p/1080p HLS formats
@@ -117,6 +118,7 @@ INNERTUBE_CLIENTS = {
         },
         'INNERTUBE_CONTEXT_CLIENT_NAME': 1,
         'SUPPORTS_COOKIES': True,
+        'SUPPORTS_AD_PLAYBACK_CONTEXT': True,
         **WEB_PO_TOKEN_POLICIES,
     },
     'web_embedded': {
@@ -157,6 +159,7 @@ INNERTUBE_CLIENTS = {
             ),
         },
         'SUPPORTS_COOKIES': True,
+        'SUPPORTS_AD_PLAYBACK_CONTEXT': True,
     },
     # This client now requires sign-in for every video
     'web_creator': {
@@ -313,6 +316,7 @@ INNERTUBE_CLIENTS = {
             ),
         },
         'SUPPORTS_COOKIES': True,
+        'SUPPORTS_AD_PLAYBACK_CONTEXT': True,
     },
     'tv': {
         'INNERTUBE_CONTEXT': {
@@ -327,6 +331,17 @@ INNERTUBE_CLIENTS = {
         # See: https://github.com/youtube/cobalt/blob/main/cobalt/browser/user_agent/user_agent_platform_info.cc#L506
         'AUTHENTICATED_USER_AGENT': 'Mozilla/5.0 (ChromiumStylePlatform) Cobalt/25.lts.30.1034943-gold (unlike Gecko), Unknown_TV_Unknown_0/Unknown (Unknown, Unknown)',
     },
+    'tv_downgraded': {
+        'INNERTUBE_CONTEXT': {
+            'client': {
+                'clientName': 'TVHTML5',
+                'clientVersion': '5.20251105',
+                'userAgent': 'Mozilla/5.0 (ChromiumStylePlatform) Cobalt/Version',
+            },
+        },
+        'INNERTUBE_CONTEXT_CLIENT_NAME': 7,
+        'SUPPORTS_COOKIES': True,
+    },
     'tv_simply': {
         'INNERTUBE_CONTEXT': {
             'client': {
@@ -380,11 +395,15 @@ def short_client_name(client_name):
     return join_nonempty(main[:4], ''.join(x[0] for x in parts)).upper()
 
 
-def build_innertube_clients():
-    THIRD_PARTY = {
+def _fix_embedded_ytcfg(ytcfg):
+    ytcfg['INNERTUBE_CONTEXT'].setdefault('thirdParty', {}).update({
         'embedUrl': 'https://www.youtube.com/',  # Can be any valid URL
-    }
-    BASE_CLIENTS = ('ios', 'web', 'tv', 'mweb', 'android')
+    })
+
+
+def build_innertube_clients():
+    # From highest to lowest priority
+    BASE_CLIENTS = ('tv', 'web', 'mweb', 'android', 'ios')
     priority = qualities(BASE_CLIENTS[::-1])
 
     for client, ytcfg in tuple(INNERTUBE_CLIENTS.items()):
@@ -397,6 +416,7 @@ def build_innertube_clients():
         ytcfg.setdefault('SUBS_PO_TOKEN_POLICY', SubsPoTokenPolicy())
         ytcfg.setdefault('REQUIRE_AUTH', False)
         ytcfg.setdefault('SUPPORTS_COOKIES', False)
+        ytcfg.setdefault('SUPPORTS_AD_PLAYBACK_CONTEXT', False)
         ytcfg.setdefault('PLAYER_PARAMS', None)
         ytcfg.setdefault('AUTHENTICATED_USER_AGENT', None)
         ytcfg['INNERTUBE_CONTEXT']['client'].setdefault('hl', 'en')
@@ -405,10 +425,7 @@ def build_innertube_clients():
         ytcfg['priority'] = 10 * priority(base_client)
 
         if variant == 'embedded':
-            ytcfg['INNERTUBE_CONTEXT']['thirdParty'] = THIRD_PARTY
-            ytcfg['priority'] -= 2
-        elif variant:
-            ytcfg['priority'] -= 3
+            _fix_embedded_ytcfg(ytcfg)
 
 
 build_innertube_clients()
@@ -991,6 +1008,10 @@ class YoutubeBaseInfoExtractor(InfoExtractor):
 
         ytcfg = self.extract_ytcfg(video_id, webpage) or {}
 
+        # See https://github.com/yt-dlp/yt-dlp/issues/14826
+        if _split_innertube_client(client)[2] == 'embedded':
+            _fix_embedded_ytcfg(ytcfg)
+
         # Workaround for https://github.com/yt-dlp/yt-dlp/issues/12563
         # But it's not effective when logged-in
         if client == 'tv' and not self.is_authenticated:
@@ -1044,7 +1065,7 @@ class YoutubeBaseInfoExtractor(InfoExtractor):
             return next_continuation
 
         return traverse_obj(renderer, (
-            ('contents', 'items', 'rows'), ..., 'continuationItemRenderer',
+            ('contents', 'items', 'rows', 'subThreads'), ..., 'continuationItemRenderer',
             ('continuationEndpoint', ('button', 'buttonRenderer', 'command')),
         ), get_all=False, expected_type=cls._extract_continuation_ep_data)
 

plugins/youtube_download/yt_dlp/extractor/youtube/_tab.py

@@ -340,8 +340,9 @@ class YoutubeTabBaseInfoExtractor(YoutubeBaseInfoExtractor):
             thumbnails=self._extract_thumbnails(view_model, (
                 'contentImage', *thumb_keys, 'thumbnailViewModel', 'image'), final_key='sources'),
             duration=traverse_obj(view_model, (
-                'contentImage', 'thumbnailViewModel', 'overlays', ..., 'thumbnailOverlayBadgeViewModel',
-                'thumbnailBadges', ..., 'thumbnailBadgeViewModel', 'text', {parse_duration}, any)),
+                'contentImage', 'thumbnailViewModel', 'overlays', ...,
+                (('thumbnailBottomOverlayViewModel', 'badges'), ('thumbnailOverlayBadgeViewModel', 'thumbnailBadges')),
+                ..., 'thumbnailBadgeViewModel', 'text', {parse_duration}, any)),
             timestamp=(traverse_obj(view_model, (
                 'metadata', 'lockupMetadataViewModel', 'metadata', 'contentMetadataViewModel', 'metadataRows',
                 ..., 'metadataParts', ..., 'text', 'content', {lambda t: self._parse_time_text(t, report_failure=False)}, any))
@@ -381,7 +382,8 @@ class YoutubeTabBaseInfoExtractor(YoutubeBaseInfoExtractor):
                         ('accessibilityText', {lambda x: re.fullmatch(r'(.+), (?:[\d,.]+(?:[KM]| million)?|No) views? - play Short', x)}, 1)), any),
                     'view_count': ('overlayMetadata', 'secondaryText', 'content', {parse_count}),
                 }),
-                thumbnails=self._extract_thumbnails(renderer, 'thumbnail', final_key='sources'))
+                thumbnails=self._extract_thumbnails(
+                    renderer, ('thumbnailViewModel', 'thumbnailViewModel', 'image'), final_key='sources'))
             return
 
     def _video_entry(self, video_renderer):
@@ -1584,7 +1586,6 @@ class YoutubeTabIE(YoutubeTabBaseInfoExtractor):
         'playlist_count': 50,
         'expected_warnings': ['YouTube Music is not directly supported'],
     }, {
-        # TODO: fix test suite, 208163447408c78673b08c172beafe5c310fb167 broke this test
         'note': 'unlisted single video playlist',
         'url': 'https://www.youtube.com/playlist?list=PLt5yu3-wZAlQLfIN0MMgp0wVV6MP3bM4_',
         'info_dict': {
@@ -1884,8 +1885,6 @@ class YoutubeTabIE(YoutubeTabBaseInfoExtractor):
         'playlist_mincount': 30,
     }, {
         # Shorts url result in shorts tab
-        # TODO: Fix channel id extraction
-        # TODO: fix test suite, 208163447408c78673b08c172beafe5c310fb167 broke this test
         'url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA/shorts',
         'info_dict': {
             'id': 'UCiu-3thuViMebBjw_5nWYrA',
@@ -1914,7 +1913,6 @@ class YoutubeTabIE(YoutubeTabBaseInfoExtractor):
         'params': {'extract_flat': True},
     }, {
         # Live video status should be extracted
-        # TODO: fix test suite, 208163447408c78673b08c172beafe5c310fb167 broke this test
         'url': 'https://www.youtube.com/channel/UCQvWX73GQygcwXOTSf_VDVg/live',
         'info_dict': {
             'id': 'UCQvWX73GQygcwXOTSf_VDVg',

plugins/youtube_download/yt_dlp/extractor/youtube/jsc/README.md

@@ -0,0 +1,132 @@
+# YoutubeIE JS Challenge Provider Framework
+
+As part of the YouTube extractor, we have a framework for solving n/sig JS Challenges programmatically. This can be used by plugins.
+
+> [!TIP]
+> If publishing a JS Challenge Provider plugin to GitHub, add the [yt-dlp-jsc-provider](https://github.com/topics/yt-dlp-jsc-provider) topic to your repository to help users find it.
+
+
+## Public APIs
+
+- `yt_dlp.extractor.youtube.jsc.provider`
+
+Everything else is **internal-only** and no guarantees are made about the API stability.
+
+> [!WARNING]
+> We will try our best to maintain stability with the public APIs.
+> However, due to the nature of extractors and YouTube, we may need to remove or change APIs in the future.
+> If you are using these APIs outside yt-dlp plugins, please account for this by importing them safely.
+
+## JS Challenge Provider
+
+`yt_dlp.extractor.youtube.jsc.provider`
+
+```python
+from yt_dlp.extractor.youtube.jsc.provider import (
+    register_provider,
+    register_preference,
+    JsChallengeProvider,
+    JsChallengeRequest,
+    JsChallengeResponse,
+    JsChallengeProviderError,
+    JsChallengeProviderRejectedRequest,
+    JsChallengeType, 
+    JsChallengeProviderResponse,
+    NChallengeOutput,
+)
+from yt_dlp.utils import traverse_obj, Popen
+import json
+import subprocess
+import typing
+
+@register_provider
+class MyJsChallengeProviderJCP(JsChallengeProvider):  # Provider class name must end with "JCP"
+    PROVIDER_VERSION = '0.2.1'
+    # Define a unique display name for the provider
+    PROVIDER_NAME = 'my-provider'
+    BUG_REPORT_LOCATION = 'https://issues.example.com/report'
+    
+    # Set supported challenge types.
+    # If None, the provider will handle all types.
+    _SUPPORTED_TYPES = [JsChallengeType.N]
+
+    def is_available(self) -> bool:
+        """
+        Check if the provider is available (e.g. all required dependencies are available)
+        This is used to determine if the provider should be used and to provide debug information.
+
+        IMPORTANT: This method SHOULD NOT make any network requests or perform any expensive operations.
+
+        Since this is called multiple times, we recommend caching the result.
+        """
+        return True
+
+    def close(self):
+        # Optional close hook, called when YoutubeDL is closed.
+        pass
+
+    def _real_bulk_solve(self, requests: list[JsChallengeRequest]) -> typing.Generator[JsChallengeProviderResponse, None, None]:
+        # ℹ️ If you need to do additional validation on the requests.
+        # Raise yt_dlp.extractor.youtube.jsc.provider.JsChallengeProviderRejectedRequest if the request is not supported.
+        if len("something") > 255:
+            raise JsChallengeProviderRejectedRequest('Challenges longer than 255 are not supported', expected=True)
+            
+
+        # ℹ️ Settings are pulled from extractor args passed to yt-dlp with the key `youtubejsc-<PROVIDER_KEY>`.
+        # For this example, the extractor arg would be:
+        # `--extractor-args "youtubejsc-myjschallengeprovider:bin_path=/path/to/bin"`
+        bin_path = self._configuration_arg(
+            'bin_path', default=['/path/to/bin'])[0]
+        
+        # See below for logging guidelines
+        self.logger.trace(f'Using bin path: {bin_path}')
+        
+        for request in requests:
+            # You can use the _get_player method to get the player JS code if needed.
+            # This shares the same caching as the YouTube extractor, so it will not make unnecessary requests.
+            player_js = self._get_player(request.video_id, request.input.player_url)
+            cmd = f'{bin_path} {request.input.challenges} {player_js}'
+            self.logger.info(f'Executing command: {cmd}')
+            stdout, _, ret = Popen.run(cmd, text=True, shell=True, stdout=subprocess.PIPE)
+            if ret != 0:
+                # ℹ️ If there is an error, raise JsChallengeProviderError.
+                # The request will be sent to the next provider if there is one.
+                # You can specify whether it is expected or not. If it is unexpected, 
+                #  the log will include a link to the bug report location (BUG_REPORT_LOCATION).
+                
+                # raise JsChallengeProviderError(f'Command returned error code {ret}', expected=False)
+                
+                # You can also only fail this specific request by returning a JsChallengeProviderResponse with the error.
+                # This will allow other requests to be processed by this provider.
+                yield JsChallengeProviderResponse(
+                    request=request, 
+                    error=JsChallengeProviderError(f'Command returned error code {ret}', expected=False)
+                )
+                
+            yield JsChallengeProviderResponse(
+                request=request, 
+                response=JsChallengeResponse(
+                    type=JsChallengeType.N,
+                    output=NChallengeOutput(results=traverse_obj(json.loads(stdout))),
+            ))
+        
+
+# If there are multiple JS Challenge Providers that can handle the same JsChallengeRequest(s),
+# you can define a preference function to increase/decrease the priority of providers.
+
+@register_preference(MyJsChallengeProviderJCP)
+def my_provider_preference(provider: JsChallengeProvider, requests: list[JsChallengeRequest]) -> int:
+    return 50
+```
+
+## Logging Guidelines
+
+- Use the `self.logger` object to log messages.
+- When making HTTP requests or any other time-expensive operation, use `self.logger.info` to log a message to standard non-verbose output.
+  - This lets users know what is happening when a time-expensive operation is taking place.
+- Technical information such as a command being executed should be logged to `self.logger.debug`
+- Use `self.logger.trace` for very detailed information that is only useful for debugging to avoid cluttering the debug log.
+
+## Debugging
+
+- Use `-v --extractor-args "youtube:jsc_trace=true"` to enable JS Challenge debug output.

plugins/youtube_download/yt_dlp/extractor/youtube/jsc/__init__.py

@@ -0,0 +1,5 @@
+# Trigger import of built-in providers
+from ._builtin.bun import BunJCP as _BunJCP  # noqa: F401
+from ._builtin.deno import DenoJCP as _DenoJCP  # noqa: F401
+from ._builtin.node import NodeJCP as _NodeJCP  # noqa: F401
+from ._builtin.quickjs import QuickJSJCP as _QuickJSJCP  # noqa: F401

plugins/youtube_download/yt_dlp/extractor/youtube/jsc/_builtin/bun.py

@@ -0,0 +1,150 @@
+from __future__ import annotations
+
+import os
+import re
+import shlex
+import subprocess
+import urllib.parse
+
+from yt_dlp.extractor.youtube.jsc._builtin.ejs import (
+    _EJS_WIKI_URL,
+    EJSBaseJCP,
+    Script,
+    ScriptSource,
+    ScriptType,
+    ScriptVariant,
+)
+from yt_dlp.extractor.youtube.jsc._builtin.vendor import load_script
+from yt_dlp.extractor.youtube.jsc.provider import (
+    JsChallengeProvider,
+    JsChallengeProviderError,
+    JsChallengeRequest,
+    register_preference,
+    register_provider,
+)
+from yt_dlp.extractor.youtube.pot._provider import BuiltinIEContentProvider
+from yt_dlp.extractor.youtube.pot.provider import provider_bug_report_message
+from yt_dlp.utils import Popen
+from yt_dlp.utils.networking import HTTPHeaderDict, clean_proxies
+
+# KNOWN ISSUES:
+# - If node_modules is present and includes a requested lib, the version we request is ignored
+#   and whatever installed in node_modules is used.
+# - No way to ignore existing node_modules, lock files, etc.
+# - No sandboxing options available
+# - Cannot detect if npm packages are cached without potentially downloading them.
+#   `--no-install` appears to disable the cache.
+# - npm auto-install may fail with an integrity error when using HTTP proxies
+# - npm auto-install HTTP proxy support may be limited on older Bun versions
+# - Cannot disable the transpiler / specify lang for stdin
+
+
+@register_provider
+class BunJCP(EJSBaseJCP, BuiltinIEContentProvider):
+    PROVIDER_NAME = 'bun'
+    JS_RUNTIME_NAME = 'bun'
+    BUN_NPM_LIB_FILENAME = 'yt.solver.bun.lib.js'
+    SUPPORTED_PROXY_SCHEMES = ['http', 'https']
+
+    def _iter_script_sources(self):
+        yield from super()._iter_script_sources()
+        yield ScriptSource.BUILTIN, self._bun_npm_source
+
+    def _bun_npm_source(self, script_type: ScriptType, /):
+        if script_type != ScriptType.LIB:
+            return None
+        if 'ejs:npm' not in self.ie.get_param('remote_components', []):
+            return self._skip_component('ejs:npm')
+
+        # Check to see if the environment proxies are compatible with Bun npm source
+        if unsupported_scheme := self._check_env_proxies(self._get_env_options()):
+            self.logger.warning(
+                f'Bun NPM package downloads only support HTTP/HTTPS proxies; skipping remote NPM package downloads. '
+                f'Provide another distribution of the challenge solver script or use '
+                f'another JS runtime that supports "{unsupported_scheme}" proxies. '
+                f'For more information and alternatives, refer to  {_EJS_WIKI_URL}')
+            return None
+
+        # Bun-specific lib scripts that uses Bun autoimport
+        # https://bun.com/docs/runtime/autoimport
+        error_hook = lambda e: self.logger.warning(
+            f'Failed to read bun challenge solver lib script: {e}{provider_bug_report_message(self)}')
+        code = load_script(
+            self.BUN_NPM_LIB_FILENAME, error_hook=error_hook)
+        if code:
+            return Script(script_type, ScriptVariant.BUN_NPM, ScriptSource.BUILTIN, self._SCRIPT_VERSION, code)
+        return None
+
+    def _check_env_proxies(self, env):
+        # check that the schemes of both HTTP_PROXY and HTTPS_PROXY are supported
+        for key in ('HTTP_PROXY', 'HTTPS_PROXY'):
+            proxy = env.get(key)
+            if not proxy:
+                continue
+            scheme = urllib.parse.urlparse(proxy).scheme.lower()
+            if scheme not in self.SUPPORTED_PROXY_SCHEMES:
+                return scheme
+        return None
+
+    def _get_env_options(self) -> dict[str, str]:
+        options = os.environ.copy()  # pass through existing bun env vars
+        request_proxies = self.ie._downloader.proxies.copy()
+        clean_proxies(request_proxies, HTTPHeaderDict())
+
+        # Apply 'all' proxy first, then allow per-scheme overrides
+        if request_proxies.get('all') is not None:
+            options['HTTP_PROXY'] = options['HTTPS_PROXY'] = request_proxies['all']
+        for key, env in (('http', 'HTTP_PROXY'), ('https', 'HTTPS_PROXY')):
+            val = request_proxies.get(key)
+            if val is not None:
+                options[env] = val
+        if self.ie.get_param('nocheckcertificate'):
+            options['NODE_TLS_REJECT_UNAUTHORIZED'] = '0'
+
+        # Disable Bun transpiler cache
+        options['BUN_RUNTIME_TRANSPILER_CACHE_PATH'] = '0'
+
+        # Prevent segfault: <https://github.com/oven-sh/bun/issues/22901>
+        options.pop('JSC_useJIT', None)
+        if self.ejs_setting('jitless', ['false']) != ['false']:
+            options['BUN_JSC_useJIT'] = '0'
+
+        return options
+
+    def _run_js_runtime(self, stdin: str, /) -> str:
+        # https://bun.com/docs/cli/run
+        options = ['--no-addons', '--prefer-offline']
+        if self._lib_script.variant == ScriptVariant.BUN_NPM:
+            # Enable auto-install even if node_modules is present
+            options.append('--install=fallback')
+        else:
+            options.append('--no-install')
+        cmd = [self.runtime_info.path, '--bun', 'run', *options, '-']
+        self.logger.debug(f'Running bun: {shlex.join(cmd)}')
+
+        with Popen(
+            cmd,
+            text=True,
+            stdin=subprocess.PIPE,
+            stdout=subprocess.PIPE,
+            stderr=subprocess.PIPE,
+            env=self._get_env_options(),
+        ) as proc:
+            stdout, stderr = proc.communicate_or_kill(stdin)
+            stderr = self._clean_stderr(stderr)
+            if proc.returncode or stderr:
+                msg = f'Error running bun process (returncode: {proc.returncode})'
+                if stderr:
+                    msg = f'{msg}: {stderr.strip()}'
+                raise JsChallengeProviderError(msg)
+        return stdout
+
+    def _clean_stderr(self, stderr):
+        return '\n'.join(
+            line for line in stderr.splitlines()
+            if not re.match(r'^Bun v\d+\.\d+\.\d+ \([\w\s]+\)$', line))
+
+
+@register_preference(BunJCP)
+def preference(provider: JsChallengeProvider, requests: list[JsChallengeRequest]) -> int:
+    return 800

plugins/youtube_download/yt_dlp/extractor/youtube/jsc/_builtin/deno.py

@@ -0,0 +1,131 @@
+from __future__ import annotations
+
+import os
+import re
+import shlex
+import subprocess
+
+from yt_dlp.extractor.youtube.jsc._builtin.ejs import (
+    EJSBaseJCP,
+    Script,
+    ScriptSource,
+    ScriptType,
+    ScriptVariant,
+)
+from yt_dlp.extractor.youtube.jsc._builtin.vendor import load_script
+from yt_dlp.extractor.youtube.jsc.provider import (
+    JsChallengeProvider,
+    JsChallengeProviderError,
+    JsChallengeRequest,
+    register_preference,
+    register_provider,
+)
+from yt_dlp.extractor.youtube.pot._provider import BuiltinIEContentProvider
+from yt_dlp.extractor.youtube.pot.provider import provider_bug_report_message
+from yt_dlp.utils import Popen, remove_terminal_sequences
+from yt_dlp.utils.networking import HTTPHeaderDict, clean_proxies
+
+# KNOWN ISSUES:
+# - Can't avoid analysis cache: https://github.com/yt-dlp/yt-dlp/pull/14849#issuecomment-3475840821
+
+
+@register_provider
+class DenoJCP(EJSBaseJCP, BuiltinIEContentProvider):
+    PROVIDER_NAME = 'deno'
+    JS_RUNTIME_NAME = 'deno'
+
+    _DENO_BASE_OPTIONS = [
+        '--ext=js', '--no-code-cache', '--no-prompt', '--no-remote',
+        '--no-lock', '--node-modules-dir=none', '--no-config',
+    ]
+    DENO_NPM_LIB_FILENAME = 'yt.solver.deno.lib.js'
+    _NPM_PACKAGES_CACHED = False
+
+    def _iter_script_sources(self):
+        yield from super()._iter_script_sources()
+        yield ScriptSource.BUILTIN, self._deno_npm_source
+
+    def _deno_npm_source(self, script_type: ScriptType, /):
+        if script_type != ScriptType.LIB:
+            return None
+        # Deno-specific lib scripts that use Deno NPM imports
+        error_hook = lambda e: self.logger.warning(
+            f'Failed to read deno challenge solver lib script: {e}{provider_bug_report_message(self)}')
+        code = load_script(
+            self.DENO_NPM_LIB_FILENAME, error_hook=error_hook)
+        if not code:
+            return None
+        if 'ejs:npm' not in self.ie.get_param('remote_components', []):
+            # We may still be able to continue if the npm packages are available/cached
+            self._NPM_PACKAGES_CACHED = self._npm_packages_cached(code)
+            if not self._NPM_PACKAGES_CACHED:
+                return self._skip_component('ejs:npm')
+        return Script(script_type, ScriptVariant.DENO_NPM, ScriptSource.BUILTIN, self._SCRIPT_VERSION, code)
+
+    def _npm_packages_cached(self, stdin: str) -> bool:
+        # Check if npm packages are cached, so we can run without --remote-components ejs:npm
+        self.logger.debug('Checking if npm packages are cached')
+        try:
+            self._run_deno(stdin, [*self._DENO_BASE_OPTIONS, '--cached-only'])
+        except JsChallengeProviderError as e:
+            self.logger.trace(f'Deno npm packages not cached: {e}')
+            return False
+        return True
+
+    def _run_js_runtime(self, stdin: str, /) -> str:
+        options = [*self._DENO_BASE_OPTIONS]
+        if self._lib_script.variant == ScriptVariant.DENO_NPM and self._NPM_PACKAGES_CACHED:
+            options.append('--cached-only')
+        elif self._lib_script.variant != ScriptVariant.DENO_NPM:
+            options.append('--no-npm')
+            options.append('--cached-only')
+        if self.ie.get_param('nocheckcertificate'):
+            options.append('--unsafely-ignore-certificate-errors')
+        # XXX: Convert this extractor-arg into a general option if/when a JSI framework is implemented
+        if self.ejs_setting('jitless', ['false']) != ['false']:
+            options.append('--v8-flags=--jitless')
+        return self._run_deno(stdin, options)
+
+    def _get_env_options(self) -> dict[str, str]:
+        options = os.environ.copy()  # pass through existing deno env vars
+        request_proxies = self.ie._downloader.proxies.copy()
+        clean_proxies(request_proxies, HTTPHeaderDict())
+        # Apply 'all' proxy first, then allow per-scheme overrides
+        if 'all' in request_proxies and request_proxies['all'] is not None:
+            options['HTTP_PROXY'] = options['HTTPS_PROXY'] = request_proxies['all']
+        for key, env in (('http', 'HTTP_PROXY'), ('https', 'HTTPS_PROXY'), ('no', 'NO_PROXY')):
+            if key in request_proxies and request_proxies[key] is not None:
+                options[env] = request_proxies[key]
+        return options
+
+    def _run_deno(self, stdin, options) -> str:
+        cmd = [self.runtime_info.path, 'run', *options, '-']
+        self.logger.debug(f'Running deno: {shlex.join(cmd)}')
+        with Popen(
+            cmd,
+            text=True,
+            stdin=subprocess.PIPE,
+            stdout=subprocess.PIPE,
+            stderr=subprocess.PIPE,
+            env=self._get_env_options(),
+        ) as proc:
+            stdout, stderr = proc.communicate_or_kill(stdin)
+            stderr = self._clean_stderr(stderr)
+            if proc.returncode or stderr:
+                msg = f'Error running deno process (returncode: {proc.returncode})'
+                if stderr:
+                    msg = f'{msg}: {stderr.strip()}'
+                raise JsChallengeProviderError(msg)
+        return stdout
+
+    def _clean_stderr(self, stderr):
+        return '\n'.join(
+            line for line in stderr.splitlines()
+            if not (
+                re.match(r'^Download\s+https\S+$', remove_terminal_sequences(line))
+                or re.match(r'DANGER: TLS certificate validation is disabled for all hostnames', remove_terminal_sequences(line))))
+
+
+@register_preference(DenoJCP)
+def preference(provider: JsChallengeProvider, requests: list[JsChallengeRequest]) -> int:
+    return 1000

plugins/youtube_download/yt_dlp/extractor/youtube/jsc/_builtin/ejs.py

@@ -0,0 +1,328 @@
+from __future__ import annotations
+
+import collections
+import dataclasses
+import enum
+import functools
+import hashlib
+import json
+
+from yt_dlp.dependencies import yt_dlp_ejs as _has_ejs
+from yt_dlp.extractor.youtube.jsc._builtin import vendor
+from yt_dlp.extractor.youtube.jsc.provider import (
+    JsChallengeProvider,
+    JsChallengeProviderError,
+    JsChallengeProviderRejectedRequest,
+    JsChallengeProviderResponse,
+    JsChallengeResponse,
+    JsChallengeType,
+    NChallengeOutput,
+    SigChallengeOutput,
+)
+from yt_dlp.extractor.youtube.pot._provider import configuration_arg
+from yt_dlp.extractor.youtube.pot.provider import provider_bug_report_message
+from yt_dlp.utils import version_tuple
+from yt_dlp.utils._jsruntime import JsRuntimeInfo
+
+if _has_ejs:
+    import yt_dlp_ejs.yt.solver
+
+TYPE_CHECKING = False
+if TYPE_CHECKING:
+    from collections.abc import Callable, Generator
+
+    from yt_dlp.extractor.youtube.jsc.provider import JsChallengeRequest
+
+_EJS_WIKI_URL = 'https://github.com/yt-dlp/yt-dlp/wiki/EJS'
+
+
+class ScriptType(enum.Enum):
+    LIB = 'lib'
+    CORE = 'core'
+
+
+class ScriptVariant(enum.Enum):
+    UNKNOWN = 'unknown'
+    MINIFIED = 'minified'
+    UNMINIFIED = 'unminified'
+    DENO_NPM = 'deno_npm'
+    BUN_NPM = 'bun_npm'
+
+
+class ScriptSource(enum.Enum):
+    PYPACKAGE = 'python package'  # PyPI, PyInstaller exe, zipimport binary, etc
+    CACHE = 'cache'  # GitHub release assets (cached)
+    WEB = 'web'  # GitHub release assets (downloaded)
+    BUILTIN = 'builtin'  # vendored (full core script; import-only lib script + NPM cache)
+
+
+@dataclasses.dataclass
+class Script:
+    type: ScriptType
+    variant: ScriptVariant
+    source: ScriptSource
+    version: str
+    code: str
+
+    @functools.cached_property
+    def hash(self, /) -> str:
+        return hashlib.sha3_512(self.code.encode()).hexdigest()
+
+    def __str__(self, /):
+        return f'<Script {self.type.value!r} v{self.version} (source: {self.source.value}) variant={self.variant.value!r} size={len(self.code)} hash={self.hash[:7]}...>'
+
+
+class EJSBaseJCP(JsChallengeProvider):
+    JS_RUNTIME_NAME: str
+    _CACHE_SECTION = 'challenge-solver'
+
+    _REPOSITORY = 'yt-dlp/ejs'
+    _SUPPORTED_TYPES = [JsChallengeType.N, JsChallengeType.SIG]
+    _SCRIPT_VERSION = vendor.VERSION
+    # TODO: Integration tests for each kind of scripts source
+    _ALLOWED_HASHES = {
+        ScriptType.LIB: {
+            ScriptVariant.UNMINIFIED: vendor.HASHES['yt.solver.lib.js'],
+            ScriptVariant.MINIFIED: vendor.HASHES['yt.solver.lib.min.js'],
+            ScriptVariant.DENO_NPM: vendor.HASHES['yt.solver.deno.lib.js'],
+            ScriptVariant.BUN_NPM: vendor.HASHES['yt.solver.bun.lib.js'],
+        },
+        ScriptType.CORE: {
+            ScriptVariant.MINIFIED: vendor.HASHES['yt.solver.core.min.js'],
+            ScriptVariant.UNMINIFIED: vendor.HASHES['yt.solver.core.js'],
+        },
+    }
+
+    _SCRIPT_FILENAMES = {
+        ScriptType.LIB: 'yt.solver.lib.js',
+        ScriptType.CORE: 'yt.solver.core.js',
+    }
+
+    _MIN_SCRIPT_FILENAMES = {
+        ScriptType.LIB: 'yt.solver.lib.min.js',
+        ScriptType.CORE: 'yt.solver.core.min.js',
+    }
+
+    # currently disabled as files are large and we do not support rotation
+    _ENABLE_PREPROCESSED_PLAYER_CACHE = False
+
+    def __init__(self, *args, **kwargs):
+        super().__init__(*args, **kwargs)
+        self._available = True
+        self.ejs_settings = self.ie.get_param('extractor_args', {}).get('youtube-ejs', {})
+
+        # Note: The following 3 args are for developer use only & intentionally not documented.
+        # - dev: bypasses verification of script hashes and versions.
+        # - repo: use a custom GitHub repository to fetch web script from.
+        # - script_version: use a custom script version.
+        # E.g. --extractor-args "youtube-ejs:dev=true;script_version=0.1.4"
+
+        self.is_dev = self.ejs_setting('dev', ['false'])[0] == 'true'
+        if self.is_dev:
+            self.report_dev_option('You have enabled dev mode for EJS JCP Providers.')
+
+        custom_repo = self.ejs_setting('repo', [None])[0]
+        if custom_repo:
+            self.report_dev_option(f'You have set a custom GitHub repository for EJS JCP Providers ({custom_repo}).')
+            self._REPOSITORY = custom_repo
+
+        custom_version = self.ejs_setting('script_version', [None])[0]
+        if custom_version:
+            self.report_dev_option(f'You have set a custom EJS script version for EJS JCP Providers ({custom_version}).')
+            self._SCRIPT_VERSION = custom_version
+
+    def ejs_setting(self, key, *args, **kwargs):
+        return configuration_arg(self.ejs_settings, key, *args, **kwargs)
+
+    def report_dev_option(self, message: str):
+        self.ie.report_warning(
+            f'{message} '
+            f'This is a developer option intended for debugging. \n'
+            '         If you experience any issues while using this option, '
+            f'{self.ie._downloader._format_err("DO NOT", self.ie._downloader.Styles.ERROR)} open a bug report', only_once=True)
+
+    def _run_js_runtime(self, stdin: str, /) -> str:
+        """To be implemented by subclasses"""
+        raise NotImplementedError
+
+    def _real_bulk_solve(self, /, requests: list[JsChallengeRequest]):
+        grouped: dict[str, list[JsChallengeRequest]] = collections.defaultdict(list)
+        for request in requests:
+            grouped[request.input.player_url].append(request)
+
+        for player_url, grouped_requests in grouped.items():
+            player = None
+            if self._ENABLE_PREPROCESSED_PLAYER_CACHE:
+                player = self.ie.cache.load(self._CACHE_SECTION, f'player:{player_url}')
+
+            if player:
+                cached = True
+            else:
+                cached = False
+                video_id = next((request.video_id for request in grouped_requests), None)
+                player = self._get_player(video_id, player_url)
+
+            # NB: This output belongs after the player request
+            self.logger.info(f'Solving JS challenges using {self.JS_RUNTIME_NAME}')
+
+            stdin = self._construct_stdin(player, cached, grouped_requests)
+            stdout = self._run_js_runtime(stdin)
+            output = json.loads(stdout)
+            if output['type'] == 'error':
+                raise JsChallengeProviderError(output['error'])
+
+            if self._ENABLE_PREPROCESSED_PLAYER_CACHE and (preprocessed := output.get('preprocessed_player')):
+                self.ie.cache.store(self._CACHE_SECTION, f'player:{player_url}', preprocessed)
+
+            for request, response_data in zip(grouped_requests, output['responses'], strict=True):
+                if response_data['type'] == 'error':
+                    yield JsChallengeProviderResponse(request, None, response_data['error'])
+                else:
+                    yield JsChallengeProviderResponse(request, JsChallengeResponse(request.type, (
+                        NChallengeOutput(response_data['data']) if request.type is JsChallengeType.N
+                        else SigChallengeOutput(response_data['data']))))
+
+    def _construct_stdin(self, player: str, preprocessed: bool, requests: list[JsChallengeRequest], /) -> str:
+        json_requests = [{
+            'type': request.type.value,
+            'challenges': request.input.challenges,
+        } for request in requests]
+        data = {
+            'type': 'preprocessed',
+            'preprocessed_player': player,
+            'requests': json_requests,
+        } if preprocessed else {
+            'type': 'player',
+            'player': player,
+            'requests': json_requests,
+            'output_preprocessed': True,
+        }
+        return f'''\
+        {self._lib_script.code}
+        Object.assign(globalThis, lib);
+        {self._core_script.code}
+        console.log(JSON.stringify(jsc({json.dumps(data)})));
+        '''
+
+    # region: challenge solver script
+
+    @functools.cached_property
+    def _lib_script(self, /):
+        return self._get_script(ScriptType.LIB)
+
+    @functools.cached_property
+    def _core_script(self, /):
+        return self._get_script(ScriptType.CORE)
+
+    def _get_script(self, script_type: ScriptType, /) -> Script:
+        skipped_components: list[_SkippedComponent] = []
+        for _, from_source in self._iter_script_sources():
+            script = from_source(script_type)
+            if not script:
+                continue
+            if isinstance(script, _SkippedComponent):
+                skipped_components.append(script)
+                continue
+            if not self.is_dev:
+                # Matching patch version is expected to have same hash
+                if version_tuple(script.version, lenient=True)[:2] != version_tuple(self._SCRIPT_VERSION, lenient=True)[:2]:
+                    self.logger.warning(
+                        f'Challenge solver {script_type.value} script version {script.version} '
+                        f'is not supported (source: {script.source.value}, variant: {script.variant}, supported version: {self._SCRIPT_VERSION})')
+                    if script.source is ScriptSource.CACHE:
+                        self.logger.debug('Clearing outdated cached script')
+                        self.ie.cache.store(self._CACHE_SECTION, script_type.value, None)
+                    continue
+                script_hashes = self._ALLOWED_HASHES[script.type].get(script.variant, [])
+                if script_hashes and script.hash not in script_hashes:
+                    self.logger.warning(
+                        f'Hash mismatch on challenge solver {script.type.value} script '
+                        f'(source: {script.source.value}, variant: {script.variant}, hash: {script.hash})!{provider_bug_report_message(self)}')
+                    if script.source is ScriptSource.CACHE:
+                        self.logger.debug('Clearing invalid cached script')
+                        self.ie.cache.store(self._CACHE_SECTION, script_type.value, None)
+                    continue
+            self.logger.debug(
+                f'Using challenge solver {script.type.value} script v{script.version} '
+                f'(source: {script.source.value}, variant: {script.variant.value})')
+            break
+
+        else:
+            self._available = False
+            raise JsChallengeProviderRejectedRequest(
+                f'No usable challenge solver {script_type.value} script available',
+                _skipped_components=skipped_components or None,
+            )
+
+        return script
+
+    def _iter_script_sources(self) -> Generator[tuple[ScriptSource, Callable[[ScriptType], Script | None]]]:
+        yield from [
+            (ScriptSource.PYPACKAGE, self._pypackage_source),
+            (ScriptSource.CACHE, self._cached_source),
+            (ScriptSource.BUILTIN, self._builtin_source),
+            (ScriptSource.WEB, self._web_release_source)]
+
+    def _pypackage_source(self, script_type: ScriptType, /) -> Script | None:
+        if not _has_ejs:
+            return None
+        try:
+            code = yt_dlp_ejs.yt.solver.core() if script_type is ScriptType.CORE else yt_dlp_ejs.yt.solver.lib()
+        except Exception as e:
+            self.logger.warning(
+                f'Failed to load challenge solver {script_type.value} script from python package: {e}{provider_bug_report_message(self)}')
+            return None
+        return Script(script_type, ScriptVariant.MINIFIED, ScriptSource.PYPACKAGE, yt_dlp_ejs.version, code)
+
+    def _cached_source(self, script_type: ScriptType, /) -> Script | None:
+        if data := self.ie.cache.load(self._CACHE_SECTION, script_type.value):
+            return Script(script_type, ScriptVariant(data['variant']), ScriptSource.CACHE, data['version'], data['code'])
+        return None
+
+    def _builtin_source(self, script_type: ScriptType, /) -> Script | None:
+        error_hook = lambda _: self.logger.warning(
+            f'Failed to read builtin challenge solver {script_type.value} script{provider_bug_report_message(self)}')
+        code = vendor.load_script(
+            self._SCRIPT_FILENAMES[script_type], error_hook=error_hook)
+        if code:
+            return Script(script_type, ScriptVariant.UNMINIFIED, ScriptSource.BUILTIN, self._SCRIPT_VERSION, code)
+        return None
+
+    def _web_release_source(self, script_type: ScriptType, /):
+        if 'ejs:github' not in (self.ie.get_param('remote_components') or ()):
+            return self._skip_component('ejs:github')
+        url = f'https://github.com/{self._REPOSITORY}/releases/download/{self._SCRIPT_VERSION}/{self._MIN_SCRIPT_FILENAMES[script_type]}'
+        if code := self.ie._download_webpage_with_retries(
+            url, None, f'[{self.logger.prefix}] Downloading challenge solver {script_type.value} script from  {url}',
+            f'[{self.logger.prefix}] Failed to download challenge solver {script_type.value} script', fatal=False,
+        ):
+            self.ie.cache.store(self._CACHE_SECTION, script_type.value, {
+                'version': self._SCRIPT_VERSION,
+                'variant': ScriptVariant.MINIFIED.value,
+                'code': code,
+            })
+            return Script(script_type, ScriptVariant.MINIFIED, ScriptSource.WEB, self._SCRIPT_VERSION, code)
+        return None
+
+    # endregion: challenge solver script
+
+    @property
+    def runtime_info(self) -> JsRuntimeInfo | None:
+        runtime = self.ie._downloader._js_runtimes.get(self.JS_RUNTIME_NAME)
+        if not runtime or not runtime.info or not runtime.info.supported:
+            return None
+        return runtime.info
+
+    def is_available(self, /) -> bool:
+        if not self.runtime_info:
+            return False
+        return self._available
+
+    def _skip_component(self, component: str, /):
+        return _SkippedComponent(component, self.JS_RUNTIME_NAME)
+
+
+@dataclasses.dataclass
+class _SkippedComponent:
+    component: str
+    runtime: str

plugins/youtube_download/yt_dlp/extractor/youtube/jsc/_builtin/node.py

@@ -0,0 +1,70 @@
+from __future__ import annotations
+
+import re
+import shlex
+import subprocess
+
+from yt_dlp.extractor.youtube.jsc._builtin.ejs import EJSBaseJCP
+from yt_dlp.extractor.youtube.jsc.provider import (
+    JsChallengeProvider,
+    JsChallengeProviderError,
+    JsChallengeRequest,
+    register_preference,
+    register_provider,
+)
+from yt_dlp.extractor.youtube.pot._provider import BuiltinIEContentProvider
+from yt_dlp.utils import Popen
+
+
+@register_provider
+class NodeJCP(EJSBaseJCP, BuiltinIEContentProvider):
+    PROVIDER_NAME = 'node'
+    JS_RUNTIME_NAME = 'node'
+
+    _ARGS = ['-']
+
+    def _run_js_runtime(self, stdin: str, /) -> str:
+        args = []
+
+        if self.ejs_setting('jitless', ['false']) != ['false']:
+            args.append('--v8-flags=--jitless')
+
+        # Node permission flag changed from experimental to stable in v23.5.0
+        if self.runtime_info.version_tuple < (23, 5, 0):
+            args.append('--experimental-permission')
+            args.append('--no-warnings=ExperimentalWarning')
+        else:
+            args.append('--permission')
+
+        cmd = [self.runtime_info.path, *args, *self._ARGS]
+        self.logger.debug(f'Running node: {shlex.join(cmd)}')
+        with Popen(
+            cmd,
+            text=True,
+            stdin=subprocess.PIPE,
+            stdout=subprocess.PIPE,
+            stderr=subprocess.PIPE,
+        ) as proc:
+            stdout, stderr = proc.communicate_or_kill(stdin)
+            stderr = self._clean_stderr(stderr)
+            if proc.returncode or stderr:
+                msg = f'Error running node process (returncode: {proc.returncode})'
+                if stderr:
+                    msg = f'{msg}: {stderr.strip()}'
+                raise JsChallengeProviderError(msg)
+
+        return stdout
+
+    def _clean_stderr(self, stderr):
+        return '\n'.join(
+            line for line in stderr.splitlines()
+            if not (
+                re.match(r'^\[stdin\]:', line)
+                or re.match(r'^var jsc', line)
+                or '(Use `node --trace-uncaught ...` to show where the exception was thrown)' == line
+                or re.match(r'^Node\.js v\d+\.\d+\.\d+$', line)))
+
+
+@register_preference(NodeJCP)
+def preference(provider: JsChallengeProvider, requests: list[JsChallengeRequest]) -> int:
+    return 900

plugins/youtube_download/yt_dlp/extractor/youtube/jsc/_builtin/quickjs.py

@@ -0,0 +1,59 @@
+from __future__ import annotations
+
+import pathlib
+import shlex
+import subprocess
+import tempfile
+
+from yt_dlp.extractor.youtube.jsc._builtin.ejs import EJSBaseJCP
+from yt_dlp.extractor.youtube.jsc.provider import (
+    JsChallengeProvider,
+    JsChallengeProviderError,
+    JsChallengeRequest,
+    register_preference,
+    register_provider,
+)
+from yt_dlp.extractor.youtube.pot._provider import BuiltinIEContentProvider
+from yt_dlp.utils import Popen
+
+
+@register_provider
+class QuickJSJCP(EJSBaseJCP, BuiltinIEContentProvider):
+    PROVIDER_NAME = 'quickjs'
+    JS_RUNTIME_NAME = 'quickjs'
+
+    def _run_js_runtime(self, stdin: str, /) -> str:
+        if self.runtime_info.name == 'quickjs-ng':
+            self.logger.warning('QuickJS-NG is missing some optimizations making this very slow. Consider using upstream QuickJS instead.')
+        elif self.runtime_info.version_tuple < (2025, 4, 26):
+            self.logger.warning('Older QuickJS versions are missing optimizations making this very slow. Consider upgrading.')
+
+        # QuickJS does not support reading from stdin, so we have to use a temp file
+        temp_file = tempfile.NamedTemporaryFile(mode='w', suffix='.js', delete=False, encoding='utf-8')
+        try:
+            temp_file.write(stdin)
+            temp_file.close()
+            cmd = [self.runtime_info.path, '--script', temp_file.name]
+            self.logger.debug(f'Running QuickJS: {shlex.join(cmd)}')
+            with Popen(
+                cmd,
+                text=True,
+                stdin=subprocess.PIPE,
+                stdout=subprocess.PIPE,
+                stderr=subprocess.PIPE,
+            ) as proc:
+                stdout, stderr = proc.communicate_or_kill()
+                if proc.returncode or stderr:
+                    msg = f'Error running QuickJS process (returncode: {proc.returncode})'
+                    if stderr:
+                        msg = f'{msg}: {stderr.strip()}'
+                    raise JsChallengeProviderError(msg)
+        finally:
+            pathlib.Path(temp_file.name).unlink(missing_ok=True)
+
+        return stdout
+
+
+@register_preference(QuickJSJCP)
+def preference(provider: JsChallengeProvider, requests: list[JsChallengeRequest]) -> int:
+    return 850

plugins/youtube_download/yt_dlp/extractor/youtube/jsc/_builtin/vendor/__init__.py

@@ -0,0 +1,17 @@
+import importlib.resources
+
+from yt_dlp.extractor.youtube.jsc._builtin.vendor._info import HASHES, VERSION
+
+__all__ = ['HASHES', 'VERSION', 'load_script']
+
+
+def load_script(filename, error_hook=None):
+    file = importlib.resources.files(__package__) / filename
+    if file.is_file():
+        try:
+            return file.read_text(encoding='utf-8')
+        except (OSError, FileNotFoundError, ModuleNotFoundError) as e:
+            if error_hook:
+                error_hook(e)
+            return None
+    return None

plugins/youtube_download/yt_dlp/extractor/youtube/jsc/_builtin/vendor/_info.py

@@ -0,0 +1,11 @@
+# This file is generated by devscripts/update_ejs.py. DO NOT MODIFY!
+
+VERSION = '0.3.2'
+HASHES = {
+    'yt.solver.bun.lib.js': '6ff45e94de9f0ea936a183c48173cfa9ce526ee4b7544cd556428427c1dd53c8073ef0174e79b320252bf0e7c64b0032cc1cf9c4358f3fda59033b7caa01c241',
+    'yt.solver.core.js': '0cd96b2d3f319dfa62cae689efa7d930ef1706e95f5921794db5089b2262957ec0a17d73938d8975ea35d0309cbfb4c8e4418d5e219837215eee242890c8b64d',
+    'yt.solver.core.min.js': '370d627703002b4a73b10027702734a3de9484f6b56b739942be1dc2b60fee49dee2aa86ed117d1c8ae1ac55181d326481f1fe2e2e8d5211154d48e2a55dac51',
+    'yt.solver.deno.lib.js': '9c8ee3ab6c23e443a5a951e3ac73c6b8c1c8fb34335e7058a07bf99d349be5573611de00536dcd03ecd3cf34014c4e9b536081de37af3637c5390c6a6fd6a0f0',
+    'yt.solver.lib.js': '1ee3753a8222fc855f5c39db30a9ccbb7967dbe1fb810e86dc9a89aa073a0907f294c720e9b65427d560a35aa1ce6af19ef854d9126a05ca00afe03f72047733',
+    'yt.solver.lib.min.js': '8420c259ad16e99ce004e4651ac1bcabb53b4457bf5668a97a9359be9a998a789fee8ab124ee17f91a2ea8fd84e0f2b2fc8eabcaf0b16a186ba734cf422ad053',
+}

plugins/youtube_download/yt_dlp/extractor/youtube/jsc/_builtin/vendor/yt.solver.bun.lib.js

@@ -0,0 +1,9 @@
+/*!
+ * SPDX-License-Identifier: Unlicense
+ * This file was automatically generated by https://github.com/yt-dlp/ejs
+ */
+const lib = {
+  meriyah: await import('[email protected]'),
+  astring: await import('[email protected]'),
+};
+export { lib };

plugins/youtube_download/yt_dlp/extractor/youtube/jsc/_builtin/vendor/yt.solver.core.js

@@ -0,0 +1,550 @@
+/*!
+ * SPDX-License-Identifier: Unlicense
+ * This file was automatically generated by https://github.com/yt-dlp/ejs
+ */
+var jsc = (function (meriyah, astring) {
+  'use strict';
+  function matchesStructure(obj, structure) {
+    if (Array.isArray(structure)) {
+      if (!Array.isArray(obj)) {
+        return false;
+      }
+      return (
+        structure.length === obj.length &&
+        structure.every((value, index) => matchesStructure(obj[index], value))
+      );
+    }
+    if (typeof structure === 'object') {
+      if (!obj) {
+        return !structure;
+      }
+      if ('or' in structure) {
+        return structure.or.some((node) => matchesStructure(obj, node));
+      }
+      if ('anykey' in structure && Array.isArray(structure.anykey)) {
+        const haystack = Array.isArray(obj) ? obj : Object.values(obj);
+        return structure.anykey.every((value) =>
+          haystack.some((el) => matchesStructure(el, value)),
+        );
+      }
+      for (const [key, value] of Object.entries(structure)) {
+        if (!matchesStructure(obj[key], value)) {
+          return false;
+        }
+      }
+      return true;
+    }
+    return structure === obj;
+  }
+  function isOneOf(value, ...of) {
+    return of.includes(value);
+  }
+  function _optionalChain$2(ops) {
+    let lastAccessLHS = undefined;
+    let value = ops[0];
+    let i = 1;
+    while (i < ops.length) {
+      const op = ops[i];
+      const fn = ops[i + 1];
+      i += 2;
+      if ((op === 'optionalAccess' || op === 'optionalCall') && value == null) {
+        return undefined;
+      }
+      if (op === 'access' || op === 'optionalAccess') {
+        lastAccessLHS = value;
+        value = fn(value);
+      } else if (op === 'call' || op === 'optionalCall') {
+        value = fn((...args) => value.call(lastAccessLHS, ...args));
+        lastAccessLHS = undefined;
+      }
+    }
+    return value;
+  }
+  const logicalExpression = {
+    type: 'ExpressionStatement',
+    expression: {
+      type: 'LogicalExpression',
+      left: { type: 'Identifier' },
+      right: {
+        type: 'SequenceExpression',
+        expressions: [
+          {
+            type: 'AssignmentExpression',
+            left: { type: 'Identifier' },
+            operator: '=',
+            right: {
+              type: 'CallExpression',
+              callee: { type: 'Identifier' },
+              arguments: {
+                or: [
+                  [
+                    { type: 'Literal' },
+                    {
+                      type: 'CallExpression',
+                      callee: {
+                        type: 'Identifier',
+                        name: 'decodeURIComponent',
+                      },
+                      arguments: [{ type: 'Identifier' }],
+                      optional: false,
+                    },
+                  ],
+                  [
+                    {
+                      type: 'CallExpression',
+                      callee: {
+                        type: 'Identifier',
+                        name: 'decodeURIComponent',
+                      },
+                      arguments: [{ type: 'Identifier' }],
+                      optional: false,
+                    },
+                  ],
+                ],
+              },
+              optional: false,
+            },
+          },
+          { type: 'CallExpression' },
+        ],
+      },
+      operator: '&&',
+    },
+  };
+  const identifier$1 = {
+    or: [
+      {
+        type: 'ExpressionStatement',
+        expression: {
+          type: 'AssignmentExpression',
+          operator: '=',
+          left: { type: 'Identifier' },
+          right: { type: 'FunctionExpression', params: [{}, {}, {}] },
+        },
+      },
+      { type: 'FunctionDeclaration', params: [{}, {}, {}] },
+      {
+        type: 'VariableDeclaration',
+        declarations: {
+          anykey: [
+            {
+              type: 'VariableDeclarator',
+              init: { type: 'FunctionExpression', params: [{}, {}, {}] },
+            },
+          ],
+        },
+      },
+    ],
+  };
+  function extract$1(node) {
+    if (!matchesStructure(node, identifier$1)) {
+      return null;
+    }
+    let block;
+    if (
+      node.type === 'ExpressionStatement' &&
+      node.expression.type === 'AssignmentExpression' &&
+      node.expression.right.type === 'FunctionExpression'
+    ) {
+      block = node.expression.right.body;
+    } else if (node.type === 'VariableDeclaration') {
+      for (const decl of node.declarations) {
+        if (
+          decl.type === 'VariableDeclarator' &&
+          _optionalChain$2([
+            decl,
+            'access',
+            (_) => _.init,
+            'optionalAccess',
+            (_2) => _2.type,
+          ]) === 'FunctionExpression' &&
+          _optionalChain$2([
+            decl,
+            'access',
+            (_3) => _3.init,
+            'optionalAccess',
+            (_4) => _4.params,
+            'access',
+            (_5) => _5.length,
+          ]) === 3
+        ) {
+          block = decl.init.body;
+          break;
+        }
+      }
+    } else if (node.type === 'FunctionDeclaration') {
+      block = node.body;
+    } else {
+      return null;
+    }
+    const relevantExpression = _optionalChain$2([
+      block,
+      'optionalAccess',
+      (_6) => _6.body,
+      'access',
+      (_7) => _7.at,
+      'call',
+      (_8) => _8(-2),
+    ]);
+    if (!matchesStructure(relevantExpression, logicalExpression)) {
+      return null;
+    }
+    if (
+      _optionalChain$2([
+        relevantExpression,
+        'optionalAccess',
+        (_9) => _9.type,
+      ]) !== 'ExpressionStatement' ||
+      relevantExpression.expression.type !== 'LogicalExpression' ||
+      relevantExpression.expression.right.type !== 'SequenceExpression' ||
+      relevantExpression.expression.right.expressions[0].type !==
+        'AssignmentExpression'
+    ) {
+      return null;
+    }
+    const call = relevantExpression.expression.right.expressions[0].right;
+    if (call.type !== 'CallExpression' || call.callee.type !== 'Identifier') {
+      return null;
+    }
+    return {
+      type: 'ArrowFunctionExpression',
+      params: [{ type: 'Identifier', name: 'sig' }],
+      body: {
+        type: 'CallExpression',
+        callee: { type: 'Identifier', name: call.callee.name },
+        arguments:
+          call.arguments.length === 1
+            ? [{ type: 'Identifier', name: 'sig' }]
+            : [call.arguments[0], { type: 'Identifier', name: 'sig' }],
+        optional: false,
+      },
+      async: false,
+      expression: false,
+      generator: false,
+    };
+  }
+  function _optionalChain$1(ops) {
+    let lastAccessLHS = undefined;
+    let value = ops[0];
+    let i = 1;
+    while (i < ops.length) {
+      const op = ops[i];
+      const fn = ops[i + 1];
+      i += 2;
+      if ((op === 'optionalAccess' || op === 'optionalCall') && value == null) {
+        return undefined;
+      }
+      if (op === 'access' || op === 'optionalAccess') {
+        lastAccessLHS = value;
+        value = fn(value);
+      } else if (op === 'call' || op === 'optionalCall') {
+        value = fn((...args) => value.call(lastAccessLHS, ...args));
+        lastAccessLHS = undefined;
+      }
+    }
+    return value;
+  }
+  const identifier = {
+    or: [
+      {
+        type: 'VariableDeclaration',
+        kind: 'var',
+        declarations: {
+          anykey: [
+            {
+              type: 'VariableDeclarator',
+              id: { type: 'Identifier' },
+              init: {
+                type: 'ArrayExpression',
+                elements: [{ type: 'Identifier' }],
+              },
+            },
+          ],
+        },
+      },
+      {
+        type: 'ExpressionStatement',
+        expression: {
+          type: 'AssignmentExpression',
+          left: { type: 'Identifier' },
+          operator: '=',
+          right: {
+            type: 'ArrayExpression',
+            elements: [{ type: 'Identifier' }],
+          },
+        },
+      },
+    ],
+  };
+  const catchBlockBody = [
+    {
+      type: 'ReturnStatement',
+      argument: {
+        type: 'BinaryExpression',
+        left: {
+          type: 'MemberExpression',
+          object: { type: 'Identifier' },
+          computed: true,
+          property: { type: 'Literal' },
+          optional: false,
+        },
+        right: { type: 'Identifier' },
+        operator: '+',
+      },
+    },
+  ];
+  function extract(node) {
+    if (!matchesStructure(node, identifier)) {
+      let name = null;
+      let block = null;
+      switch (node.type) {
+        case 'ExpressionStatement': {
+          if (
+            node.expression.type === 'AssignmentExpression' &&
+            node.expression.left.type === 'Identifier' &&
+            node.expression.right.type === 'FunctionExpression' &&
+            node.expression.right.params.length === 1
+          ) {
+            name = node.expression.left.name;
+            block = node.expression.right.body;
+          }
+          break;
+        }
+        case 'FunctionDeclaration': {
+          if (node.params.length === 1) {
+            name = _optionalChain$1([
+              node,
+              'access',
+              (_) => _.id,
+              'optionalAccess',
+              (_2) => _2.name,
+            ]);
+            block = node.body;
+          }
+          break;
+        }
+      }
+      if (!block || !name) {
+        return null;
+      }
+      const tryNode = block.body.at(-2);
+      if (
+        _optionalChain$1([tryNode, 'optionalAccess', (_3) => _3.type]) !==
+          'TryStatement' ||
+        _optionalChain$1([
+          tryNode,
+          'access',
+          (_4) => _4.handler,
+          'optionalAccess',
+          (_5) => _5.type,
+        ]) !== 'CatchClause'
+      ) {
+        return null;
+      }
+      const catchBody = tryNode.handler.body.body;
+      if (matchesStructure(catchBody, catchBlockBody)) {
+        return makeSolverFuncFromName(name);
+      }
+      return null;
+    }
+    if (node.type === 'VariableDeclaration') {
+      for (const declaration of node.declarations) {
+        if (
+          declaration.type !== 'VariableDeclarator' ||
+          !declaration.init ||
+          declaration.init.type !== 'ArrayExpression' ||
+          declaration.init.elements.length !== 1
+        ) {
+          continue;
+        }
+        const [firstElement] = declaration.init.elements;
+        if (firstElement && firstElement.type === 'Identifier') {
+          return makeSolverFuncFromName(firstElement.name);
+        }
+      }
+    } else if (node.type === 'ExpressionStatement') {
+      const expr = node.expression;
+      if (
+        expr.type === 'AssignmentExpression' &&
+        expr.left.type === 'Identifier' &&
+        expr.operator === '=' &&
+        expr.right.type === 'ArrayExpression' &&
+        expr.right.elements.length === 1
+      ) {
+        const [firstElement] = expr.right.elements;
+        if (firstElement && firstElement.type === 'Identifier') {
+          return makeSolverFuncFromName(firstElement.name);
+        }
+      }
+    }
+    return null;
+  }
+  function makeSolverFuncFromName(name) {
+    return {
+      type: 'ArrowFunctionExpression',
+      params: [{ type: 'Identifier', name: 'n' }],
+      body: {
+        type: 'CallExpression',
+        callee: { type: 'Identifier', name: name },
+        arguments: [{ type: 'Identifier', name: 'n' }],
+        optional: false,
+      },
+      async: false,
+      expression: false,
+      generator: false,
+    };
+  }
+  const setupNodes = meriyah.parse(
+    `\nif (typeof globalThis.XMLHttpRequest === "undefined") {\n    globalThis.XMLHttpRequest = { prototype: {} };\n}\nconst window = Object.create(null);\nif (typeof URL === "undefined") {\n    window.location = {\n        hash: "",\n        host: "www.youtube.com",\n        hostname: "www.youtube.com",\n        href: "https://www.youtube.com/watch?v=yt-dlp-wins",\n        origin: "https://www.youtube.com",\n        password: "",\n        pathname: "/watch",\n        port: "",\n        protocol: "https:",\n        search: "?v=yt-dlp-wins",\n        username: "",\n    };\n} else {\n    window.location = new URL("https://www.youtube.com/watch?v=yt-dlp-wins");\n}\nif (typeof globalThis.document === "undefined") {\n    globalThis.document = Object.create(null);\n}\nif (typeof globalThis.navigator === "undefined") {\n    globalThis.navigator = Object.create(null);\n}\nif (typeof globalThis.self === "undefined") {\n    globalThis.self = globalThis;\n}\n`,
+  ).body;
+  function _optionalChain(ops) {
+    let lastAccessLHS = undefined;
+    let value = ops[0];
+    let i = 1;
+    while (i < ops.length) {
+      const op = ops[i];
+      const fn = ops[i + 1];
+      i += 2;
+      if ((op === 'optionalAccess' || op === 'optionalCall') && value == null) {
+        return undefined;
+      }
+      if (op === 'access' || op === 'optionalAccess') {
+        lastAccessLHS = value;
+        value = fn(value);
+      } else if (op === 'call' || op === 'optionalCall') {
+        value = fn((...args) => value.call(lastAccessLHS, ...args));
+        lastAccessLHS = undefined;
+      }
+    }
+    return value;
+  }
+  function preprocessPlayer(data) {
+    const ast = meriyah.parse(data);
+    const body = ast.body;
+    const block = (() => {
+      switch (body.length) {
+        case 1: {
+          const func = body[0];
+          if (
+            _optionalChain([func, 'optionalAccess', (_) => _.type]) ===
+              'ExpressionStatement' &&
+            func.expression.type === 'CallExpression' &&
+            func.expression.callee.type === 'MemberExpression' &&
+            func.expression.callee.object.type === 'FunctionExpression'
+          ) {
+            return func.expression.callee.object.body;
+          }
+          break;
+        }
+        case 2: {
+          const func = body[1];
+          if (
+            _optionalChain([func, 'optionalAccess', (_2) => _2.type]) ===
+              'ExpressionStatement' &&
+            func.expression.type === 'CallExpression' &&
+            func.expression.callee.type === 'FunctionExpression'
+          ) {
+            const block = func.expression.callee.body;
+            block.body.splice(0, 1);
+            return block;
+          }
+          break;
+        }
+      }
+      throw 'unexpected structure';
+    })();
+    const found = { n: [], sig: [] };
+    const plainExpressions = block.body.filter((node) => {
+      const n = extract(node);
+      if (n) {
+        found.n.push(n);
+      }
+      const sig = extract$1(node);
+      if (sig) {
+        found.sig.push(sig);
+      }
+      if (node.type === 'ExpressionStatement') {
+        if (node.expression.type === 'AssignmentExpression') {
+          return true;
+        }
+        return node.expression.type === 'Literal';
+      }
+      return true;
+    });
+    block.body = plainExpressions;
+    for (const [name, options] of Object.entries(found)) {
+      const unique = new Set(options.map((x) => JSON.stringify(x)));
+      if (unique.size !== 1) {
+        const message = `found ${unique.size} ${name} function possibilities`;
+        throw (
+          message +
+          (unique.size
+            ? `: ${options.map((x) => astring.generate(x)).join(', ')}`
+            : '')
+        );
+      }
+      plainExpressions.push({
+        type: 'ExpressionStatement',
+        expression: {
+          type: 'AssignmentExpression',
+          operator: '=',
+          left: {
+            type: 'MemberExpression',
+            computed: false,
+            object: { type: 'Identifier', name: '_result' },
+            property: { type: 'Identifier', name: name },
+          },
+          right: options[0],
+        },
+      });
+    }
+    ast.body.splice(0, 0, ...setupNodes);
+    return astring.generate(ast);
+  }
+  function getFromPrepared(code) {
+    const resultObj = { n: null, sig: null };
+    Function('_result', code)(resultObj);
+    return resultObj;
+  }
+  function main(input) {
+    const preprocessedPlayer =
+      input.type === 'player'
+        ? preprocessPlayer(input.player)
+        : input.preprocessed_player;
+    const solvers = getFromPrepared(preprocessedPlayer);
+    const responses = input.requests.map((input) => {
+      if (!isOneOf(input.type, 'n', 'sig')) {
+        return { type: 'error', error: `Unknown request type: ${input.type}` };
+      }
+      const solver = solvers[input.type];
+      if (!solver) {
+        return {
+          type: 'error',
+          error: `Failed to extract ${input.type} function`,
+        };
+      }
+      try {
+        return {
+          type: 'result',
+          data: Object.fromEntries(
+            input.challenges.map((challenge) => [challenge, solver(challenge)]),
+          ),
+        };
+      } catch (error) {
+        return {
+          type: 'error',
+          error:
+            error instanceof Error
+              ? `${error.message}\n${error.stack}`
+              : `${error}`,
+        };
+      }
+    });
+    const output = { type: 'result', responses: responses };
+    if (input.type === 'player' && input.output_preprocessed) {
+      output.preprocessed_player = preprocessedPlayer;
+    }
+    return output;
+  }
+  return main;
+})(meriyah, astring);

plugins/youtube_download/yt_dlp/extractor/youtube/jsc/_builtin/vendor/yt.solver.deno.lib.js

@@ -0,0 +1,9 @@
+/*!
+ * SPDX-License-Identifier: Unlicense
+ * This file was automatically generated by https://github.com/yt-dlp/ejs
+ */
+const lib = {
+  meriyah: await import('npm:[email protected]'),
+  astring: await import('npm:[email protected]'),
+};
+export { lib };

plugins/youtube_download/yt_dlp/extractor/youtube/jsc/_director.py

@@ -0,0 +1,287 @@
+from __future__ import annotations
+
+import collections
+import dataclasses
+import typing
+
+from yt_dlp.extractor.youtube.jsc._builtin.ejs import _EJS_WIKI_URL
+from yt_dlp.extractor.youtube.jsc._registry import (
+    _jsc_preferences,
+    _jsc_providers,
+)
+from yt_dlp.extractor.youtube.jsc.provider import (
+    JsChallengeProvider,
+    JsChallengeProviderError,
+    JsChallengeProviderRejectedRequest,
+    JsChallengeProviderResponse,
+    JsChallengeRequest,
+    JsChallengeResponse,
+    JsChallengeType,
+    NChallengeInput,
+    NChallengeOutput,
+    SigChallengeInput,
+    SigChallengeOutput,
+)
+from yt_dlp.extractor.youtube.pot._director import YoutubeIEContentProviderLogger, provider_display_list
+from yt_dlp.extractor.youtube.pot._provider import (
+    IEContentProviderLogger,
+)
+from yt_dlp.extractor.youtube.pot.provider import (
+    provider_bug_report_message,
+)
+
+if typing.TYPE_CHECKING:
+    from collections.abc import Iterable
+
+    from yt_dlp.extractor.youtube.jsc._builtin.ejs import _SkippedComponent
+    from yt_dlp.extractor.youtube.jsc.provider import Preference as JsChallengePreference
+
+
+class JsChallengeRequestDirector:
+
+    def __init__(self, logger: IEContentProviderLogger):
+        self.providers: dict[str, JsChallengeProvider] = {}
+        self.preferences: list[JsChallengePreference] = []
+        self.logger = logger
+
+    def register_provider(self, provider: JsChallengeProvider):
+        self.providers[provider.PROVIDER_KEY] = provider
+
+    def register_preference(self, preference: JsChallengePreference):
+        self.preferences.append(preference)
+
+    def _get_providers(self, requests: list[JsChallengeRequest]) -> Iterable[JsChallengeProvider]:
+        """Sorts available providers by preference, given a request"""
+        preferences = {
+            provider: sum(pref(provider, requests) for pref in self.preferences)
+            for provider in self.providers.values()
+        }
+        if self.logger.log_level <= self.logger.LogLevel.TRACE:
+            # calling is_available() for every JS Challenge provider upfront may have some overhead
+            self.logger.trace(f'JS Challenge Providers: {provider_display_list(self.providers.values())}')
+            self.logger.trace('JS Challenge Provider preferences for this request: {}'.format(', '.join(
+                f'{provider.PROVIDER_NAME}={pref}' for provider, pref in preferences.items())))
+
+        return (
+            provider for provider in sorted(
+                self.providers.values(), key=preferences.get, reverse=True)
+            if provider.is_available()
+        )
+
+    def _handle_error(self, e: Exception, provider: JsChallengeProvider, requests: list[JsChallengeRequest]):
+        if isinstance(e, JsChallengeProviderRejectedRequest):
+            self.logger.trace(
+                f'JS Challenge Provider "{provider.PROVIDER_NAME}" rejected '
+                f'{"this request" if len(requests) == 1 else f"{len(requests)} requests"}, '
+                f'trying next available provider. Reason: {e}',
+            )
+        elif isinstance(e, JsChallengeProviderError):
+            if len(requests) == 1:
+                self.logger.warning(
+                    f'Error solving {requests[0].type.value} challenge request using "{provider.PROVIDER_NAME}" provider: {e}.\n'
+                    f'         input = {requests[0].input}\n'
+                    f'         {(provider_bug_report_message(provider, before="") if not e.expected else "")}')
+            else:
+                self.logger.warning(
+                    f'Error solving {len(requests)} challenge requests using "{provider.PROVIDER_NAME}" provider: {e}.\n'
+                    f'         requests = {requests}\n'
+                    f'         {(provider_bug_report_message(provider, before="") if not e.expected else "")}')
+        else:
+            self.logger.error(
+                f'Unexpected error solving {len(requests)} challenge request(s) using "{provider.PROVIDER_NAME}" provider: {e!r}\n'
+                f'         requests = {requests}\n'
+                f'         {provider_bug_report_message(provider, before="")}', cause=e)
+
+    def bulk_solve(self, requests: list[JsChallengeRequest]) -> list[tuple[JsChallengeRequest, JsChallengeResponse]]:
+        """Solves multiple JS Challenges in bulk, returning a list of responses"""
+        if not self.providers:
+            self.logger.trace('No JS Challenge providers registered')
+            return []
+
+        results = []
+        next_requests = requests[:]
+
+        skipped_components = []
+        for provider in self._get_providers(next_requests):
+            if not next_requests:
+                break
+            self.logger.trace(
+                f'Attempting to solve {len(next_requests)} challenges using "{provider.PROVIDER_NAME}" provider')
+            try:
+                for response in provider.bulk_solve([dataclasses.replace(request) for request in next_requests]):
+                    if not validate_provider_response(response):
+                        self.logger.warning(
+                            f'JS Challenge Provider "{provider.PROVIDER_NAME}" returned an invalid response:'
+                            f'         response = {response!r}\n'
+                            f'         {provider_bug_report_message(provider, before="")}')
+                        continue
+                    if response.error:
+                        self._handle_error(response.error, provider, [response.request])
+                        continue
+                    if (vr_msg := validate_response(response.response, response.request)) is not True:
+                        self.logger.warning(
+                            f'Invalid JS Challenge response received from "{provider.PROVIDER_NAME}" provider: {vr_msg or ""}\n'
+                            f'         response = {response.response}\n'
+                            f'         request = {response.request}\n'
+                            f'         {provider_bug_report_message(provider, before="")}')
+                        continue
+                    try:
+                        next_requests.remove(response.request)
+                    except ValueError:
+                        self.logger.warning(
+                            f'JS Challenge Provider "{provider.PROVIDER_NAME}" returned a response for an unknown request:\n'
+                            f'         request = {response.request}\n'
+                            f'         {provider_bug_report_message(provider, before="")}')
+                        continue
+                    results.append((response.request, response.response))
+            except Exception as e:
+                if isinstance(e, JsChallengeProviderRejectedRequest) and e._skipped_components:
+                    skipped_components.extend(e._skipped_components)
+                self._handle_error(e, provider, next_requests)
+                continue
+
+        if skipped_components:
+            self.__report_skipped_components(skipped_components)
+
+        if len(results) != len(requests):
+            self.logger.trace(
+                f'Not all JS Challenges were solved, expected {len(requests)} responses, got {len(results)}')
+            self.logger.trace(f'Unsolved requests: {next_requests}')
+        else:
+            self.logger.trace(f'Solved all {len(requests)} requested JS Challenges')
+        return results
+
+    def __report_skipped_components(self, components: list[_SkippedComponent], /):
+        runtime_components = collections.defaultdict(list)
+        for component in components:
+            runtime_components[component.component].append(component.runtime)
+        for runtimes in runtime_components.values():
+            runtimes.sort()
+
+        description_lookup = {
+            'ejs:npm': 'NPM package',
+            'ejs:github': 'challenge solver script',
+        }
+
+        descriptions = [
+            f'{description_lookup.get(component, component)} ({", ".join(runtimes)})'
+            for component, runtimes in runtime_components.items()
+            if runtimes
+        ]
+        flags = [
+            f' --remote-components {f"{component}  (recommended)" if component == "ejs:github" else f"{component} "}'
+            for component, runtimes in runtime_components.items()
+            if runtimes
+        ]
+
+        def join_parts(parts, joiner):
+            if not parts:
+                return ''
+            if len(parts) == 1:
+                return parts[0]
+            return f'{", ".join(parts[:-1])} {joiner} {parts[-1]}'
+
+        if len(descriptions) == 1:
+            msg = (
+                f'Remote component {descriptions[0]} was skipped. '
+                f'It may be required to solve JS challenges. '
+                f'You can enable the download with {flags[0]}')
+        else:
+            msg = (
+                f'Remote components {join_parts(descriptions, "and")} were skipped. '
+                f'These may be required to solve JS challenges. '
+                f'You can enable these downloads with {join_parts(flags, "or")}, respectively')
+
+        self.logger.warning(f'{msg}. For more information and alternatives, refer to  {_EJS_WIKI_URL}')
+
+    def close(self):
+        for provider in self.providers.values():
+            provider.close()
+
+
+EXTRACTOR_ARG_PREFIX = 'youtubejsc'
+
+
+def initialize_jsc_director(ie):
+    assert ie._downloader is not None, 'Downloader not set'
+
+    enable_trace = ie._configuration_arg(
+        'jsc_trace', ['false'], ie_key='youtube', casesense=False)[0] == 'true'
+
+    if enable_trace:
+        log_level = IEContentProviderLogger.LogLevel.TRACE
+    elif ie.get_param('verbose', False):
+        log_level = IEContentProviderLogger.LogLevel.DEBUG
+    else:
+        log_level = IEContentProviderLogger.LogLevel.INFO
+
+    def get_provider_logger_and_settings(provider, logger_key):
+        logger_prefix = f'{logger_key}:{provider.PROVIDER_NAME}'
+        extractor_key = f'{EXTRACTOR_ARG_PREFIX}-{provider.PROVIDER_KEY.lower()}'
+        return (
+            YoutubeIEContentProviderLogger(ie, logger_prefix, log_level=log_level),
+            ie.get_param('extractor_args', {}).get(extractor_key, {}))
+
+    director = JsChallengeRequestDirector(
+        logger=YoutubeIEContentProviderLogger(ie, 'jsc', log_level=log_level),
+    )
+
+    ie._downloader.add_close_hook(director.close)
+
+    for provider in _jsc_providers.value.values():
+        logger, settings = get_provider_logger_and_settings(provider, 'jsc')
+        director.register_provider(provider(ie, logger, settings))
+
+    for preference in _jsc_preferences.value:
+        director.register_preference(preference)
+
+    if director.logger.log_level <= director.logger.LogLevel.DEBUG:
+        # calling is_available() for every JS Challenge provider upfront may have some overhead
+        director.logger.debug(f'JS Challenge Providers: {provider_display_list(director.providers.values())}')
+        director.logger.trace(f'Registered {len(director.preferences)} JS Challenge provider preferences')
+
+    return director
+
+
+def validate_provider_response(response: JsChallengeProviderResponse) -> bool:
+    return (
+        isinstance(response, JsChallengeProviderResponse)
+        and isinstance(response.request, JsChallengeRequest)
+        and (
+            isinstance(response.response, JsChallengeResponse)
+            or (response.error is not None and isinstance(response.error, Exception)))
+    )
+
+
+def validate_response(response: JsChallengeResponse, request: JsChallengeRequest) -> bool | str:
+    if not isinstance(response, JsChallengeResponse):
+        return 'Response is not a JsChallengeResponse'
+    if request.type == JsChallengeType.N:
+        return validate_nsig_challenge_output(response.output, request.input)
+    else:
+        return validate_sig_challenge_output(response.output, request.input)
+
+
+def validate_nsig_challenge_output(challenge_output: NChallengeOutput, challenge_input: NChallengeInput) -> bool | str:
+    if not (
+        isinstance(challenge_output, NChallengeOutput)
+        and len(challenge_output.results) == len(challenge_input.challenges)
+        and all(isinstance(k, str) and isinstance(v, str) for k, v in challenge_output.results.items())
+        and all(challenge in challenge_output.results for challenge in challenge_input.challenges)
+    ):
+        return 'Invalid NChallengeOutput'
+
+    # Validate n results are valid - if they end with the input challenge then the js function returned with an exception.
+    for challenge, result in challenge_output.results.items():
+        if result.endswith(challenge):
+            return f'n result is invalid for {challenge!r}: {result!r}'
+    return True
+
+
+def validate_sig_challenge_output(challenge_output: SigChallengeOutput, challenge_input: SigChallengeInput) -> bool:
+    return (
+        isinstance(challenge_output, SigChallengeOutput)
+        and len(challenge_output.results) == len(challenge_input.challenges)
+        and all(isinstance(k, str) and isinstance(v, str) for k, v in challenge_output.results.items())
+        and all(challenge in challenge_output.results for challenge in challenge_input.challenges)
+    ) or 'Invalid SigChallengeOutput'

plugins/youtube_download/yt_dlp/extractor/youtube/jsc/_registry.py

@@ -0,0 +1,4 @@
+from yt_dlp.globals import Indirect
+
+_jsc_providers = Indirect({})
+_jsc_preferences = Indirect(set())

plugins/youtube_download/yt_dlp/extractor/youtube/jsc/provider.py

@@ -0,0 +1,161 @@
+"""PUBLIC API"""
+
+from __future__ import annotations
+
+import abc
+import dataclasses
+import enum
+import typing
+
+from yt_dlp.extractor.youtube.jsc._registry import _jsc_preferences, _jsc_providers
+from yt_dlp.extractor.youtube.pot._provider import (
+    IEContentProvider,
+    IEContentProviderError,
+    register_preference_generic,
+    register_provider_generic,
+)
+from yt_dlp.utils import ExtractorError
+
+__all__ = [
+    'JsChallengeProvider',
+    'JsChallengeProviderError',
+    'JsChallengeProviderRejectedRequest',
+    'JsChallengeProviderResponse',
+    'JsChallengeRequest',
+    'JsChallengeResponse',
+    'JsChallengeType',
+    'NChallengeInput',
+    'NChallengeOutput',
+    'SigChallengeInput',
+    'SigChallengeOutput',
+    'register_preference',
+    'register_provider',
+]
+
+
+class JsChallengeType(enum.Enum):
+    N = 'n'
+    SIG = 'sig'
+
+
+@dataclasses.dataclass(frozen=True)
+class JsChallengeRequest:
+    type: JsChallengeType
+    input: NChallengeInput | SigChallengeInput
+    video_id: str | None = None
+
+
+@dataclasses.dataclass(frozen=True)
+class NChallengeInput:
+    player_url: str
+    challenges: list[str] = dataclasses.field(default_factory=list)
+
+
+@dataclasses.dataclass(frozen=True)
+class SigChallengeInput:
+    player_url: str
+    challenges: list[str] = dataclasses.field(default_factory=list)
+
+
+@dataclasses.dataclass(frozen=True)
+class NChallengeOutput:
+    results: dict[str, str] = dataclasses.field(default_factory=dict)
+
+
+@dataclasses.dataclass(frozen=True)
+class SigChallengeOutput:
+    results: dict[str, str] = dataclasses.field(default_factory=dict)
+
+
+@dataclasses.dataclass
+class JsChallengeProviderResponse:
+    request: JsChallengeRequest
+    response: JsChallengeResponse | None = None
+    error: Exception | None = None
+
+
+@dataclasses.dataclass
+class JsChallengeResponse:
+    type: JsChallengeType
+    output: NChallengeOutput | SigChallengeOutput
+
+
+class JsChallengeProviderRejectedRequest(IEContentProviderError):
+    """Reject the JsChallengeRequest (cannot handle the request)"""
+
+    def __init__(self, msg=None, expected: bool = False, *, _skipped_components=None):
+        super().__init__(msg, expected)
+        self._skipped_components = _skipped_components
+
+
+class JsChallengeProviderError(IEContentProviderError):
+    """An error occurred while solving the challenge"""
+
+
+class JsChallengeProvider(IEContentProvider, abc.ABC, suffix='JCP'):
+
+    # Set to None to disable the check
+    _SUPPORTED_TYPES: tuple[JsChallengeType] | None = ()
+
+    def __validate_request(self, request: JsChallengeRequest):
+        if not self.is_available():
+            raise JsChallengeProviderRejectedRequest(f'{self.PROVIDER_NAME} is not available')
+
+        # Validate request using built-in settings
+        if (
+            self._SUPPORTED_TYPES is not None
+            and request.type not in self._SUPPORTED_TYPES
+        ):
+            raise JsChallengeProviderRejectedRequest(
+                f'JS Challenge type "{request.type}" is not supported by {self.PROVIDER_NAME}')
+
+    def bulk_solve(self, requests: list[JsChallengeRequest]) -> typing.Generator[JsChallengeProviderResponse, None, None]:
+        """Solve multiple JS challenges and return the results"""
+        validated_requests = []
+        for request in requests:
+            try:
+                self.__validate_request(request)
+                validated_requests.append(request)
+            except JsChallengeProviderRejectedRequest as e:
+                yield JsChallengeProviderResponse(request=request, error=e)
+                continue
+        yield from self._real_bulk_solve(validated_requests)
+
+    @abc.abstractmethod
+    def _real_bulk_solve(self, requests: list[JsChallengeRequest]) -> typing.Generator[JsChallengeProviderResponse, None, None]:
+        """Subclasses can override this method to handle bulk solving"""
+        raise NotImplementedError(f'{self.PROVIDER_NAME} does not implement bulk solving')
+
+    def _get_player(self, video_id, player_url):
+        try:
+            return self.ie._load_player(
+                video_id=video_id,
+                player_url=player_url,
+                fatal=True,
+            )
+        except ExtractorError as e:
+            raise JsChallengeProviderError(
+                f'Failed to load player for JS challenge: {e}') from e
+
+
+def register_provider(provider: type[JsChallengeProvider]):
+    """Register a JsChallengeProvider class"""
+    return register_provider_generic(
+        provider=provider,
+        base_class=JsChallengeProvider,
+        registry=_jsc_providers.value,
+    )
+
+
+def register_preference(*providers: type[JsChallengeProvider]) -> typing.Callable[[Preference], Preference]:
+    """Register a preference for a JsChallengeProvider class."""
+    return register_preference_generic(
+        JsChallengeProvider,
+        _jsc_preferences.value,
+        *providers,
+    )
+
+
+if typing.TYPE_CHECKING:
+    Preference = typing.Callable[[JsChallengeProvider, list[JsChallengeRequest]], int]
+    __all__.append('Preference')

plugins/youtube_download/yt_dlp/extractor/youtube/pot/_director.py

@@ -6,6 +6,7 @@ import dataclasses
 import datetime as dt
 import hashlib
 import json
+import traceback
 import typing
 import urllib.parse
 from collections.abc import Iterable
@@ -58,9 +59,9 @@ class YoutubeIEContentProviderLogger(IEContentProviderLogger):
         if self.log_level <= self.LogLevel.TRACE:
             self.__ie.write_debug(self._format_msg('TRACE: ' + message))
 
-    def debug(self, message: str):
+    def debug(self, message: str, *, once=False):
         if self.log_level <= self.LogLevel.DEBUG:
-            self.__ie.write_debug(self._format_msg(message))
+            self.__ie.write_debug(self._format_msg(message), only_once=once)
 
     def info(self, message: str):
         if self.log_level <= self.LogLevel.INFO:
@@ -70,9 +71,11 @@ class YoutubeIEContentProviderLogger(IEContentProviderLogger):
         if self.log_level <= self.LogLevel.WARNING:
             self.__ie.report_warning(self._format_msg(message), only_once=once)
 
-    def error(self, message: str):
+    def error(self, message: str, cause=None):
         if self.log_level <= self.LogLevel.ERROR:
-            self.__ie._downloader.report_error(self._format_msg(message), is_error=False)
+            self.__ie._downloader.report_error(
+                self._format_msg(message), is_error=False,
+                tb=''.join(traceback.format_exception(None, cause, cause.__traceback__)) if cause else None)
 
 
 class PoTokenCache:

plugins/youtube_download/yt_dlp/extractor/youtube/pot/_provider.py

@@ -36,7 +36,7 @@ class IEContentProviderLogger(abc.ABC):
         pass
 
     @abc.abstractmethod
-    def debug(self, message: str):
+    def debug(self, message: str, *, once=False):
         pass
 
     @abc.abstractmethod
@@ -48,7 +48,7 @@ class IEContentProviderLogger(abc.ABC):
         pass
 
     @abc.abstractmethod
-    def error(self, message: str):
+    def error(self, message: str, cause=None):
         pass
 
 
@@ -90,7 +90,7 @@ class IEContentProvider(abc.ABC):
     @classproperty
     def PROVIDER_KEY(cls) -> str:
         assert hasattr(cls, '_PROVIDER_KEY_SUFFIX'), 'Content Provider implementation must define a suffix for the provider key'
-        assert cls.__name__.endswith(cls._PROVIDER_KEY_SUFFIX), f'PoTokenProvider class names must end with "{cls._PROVIDER_KEY_SUFFIX}"'
+        assert cls.__name__.endswith(cls._PROVIDER_KEY_SUFFIX), f'Class name must end with "{cls._PROVIDER_KEY_SUFFIX}"'
         return cls.__name__[:-len(cls._PROVIDER_KEY_SUFFIX)]
 
     @abc.abstractmethod
@@ -114,10 +114,7 @@ class IEContentProvider(abc.ABC):
         @param default      The default value to return when the key is not present (default: [])
         @param casesense    When false, the values are converted to lower case
         """
-        val = traverse_obj(self.settings, key)
-        if val is None:
-            return [] if default is NO_DEFAULT else default
-        return list(val) if casesense else [x.lower() for x in val]
+        return configuration_arg(self.settings, key, default=default, casesense=casesense)
 
 
 class BuiltinIEContentProvider(IEContentProvider, abc.ABC):
@@ -125,6 +122,20 @@ class BuiltinIEContentProvider(IEContentProvider, abc.ABC):
     BUG_REPORT_MESSAGE = bug_reports_message(before='')
 
 
+def configuration_arg(config, key, default=NO_DEFAULT, *, casesense=False):
+    """
+    @returns            A list of values for the setting given by "key"
+                        or "default" if no such key is present
+    @param config       The configuration dictionary
+    @param default      The default value to return when the key is not present (default: [])
+    @param casesense    When false, the values are converted to lower case
+    """
+    val = traverse_obj(config, key)
+    if val is None:
+        return [] if default is NO_DEFAULT else default
+    return list(val) if casesense else [x.lower() for x in val]
+
+
 def register_provider_generic(
     provider,
     base_class,

plugins/youtube_download/yt_dlp/extractor/zdf.py

@@ -127,6 +127,7 @@ class ZDFBaseIE(InfoExtractor):
                                 **parse_codecs(quality.get('mimeCodec')),
                                 'height': height,
                                 'width': width,
+                                'filesize': int_or_none(variant.get('filesize')),
                                 'format_id': join_nonempty('http', stream.get('type')),
                                 'tbr': int_or_none(self._search_regex(r'_(\d+)k_', format_url, 'tbr', default=None)),
                             }]
@@ -193,8 +194,10 @@ class ZDFBaseIE(InfoExtractor):
 class ZDFIE(ZDFBaseIE):
     _VALID_URL = [
         r'https?://(?:www\.)?zdf\.de/(?:video|play)/(?:[^/?#]+/)*(?P<id>[^/?#]+)',
-        # /nachrichten/ sub-site URLs and legacy redirects from before the redesign in 2025-03
+        # Legacy redirects from before the redesign in 2025-03 or from before sister sites moved to their own domains
         r'https?://(?:www\.)?zdf\.de/(?:[^/?#]+/)*(?P<id>[^/?#]+)\.html',
+        # Sister sites
+        r'https?://(?:www\.)?(?:zdfheute|logo)\.de/(?:[^/?#]+/)*(?P<id>[^/?#]+)\.html',
     ]
     IE_NAME = 'zdf'
     _TESTS = [{
@@ -206,7 +209,7 @@ class ZDFIE(ZDFBaseIE):
             'title': 'Sylt - Deutschlands edles Nordlicht',
             'description': 'md5:35407b810c2e1e33efbe15ef6e4c06c3',
             'duration': 810.0,
-            'thumbnail': 'https://www.zdf.de/assets/sylt-118~original?cb=1613992485011',
+            'thumbnail': r're:https://www\.zdf\.de/assets/sylt-118~original\?cb=\d+',
             'series': 'Sylt - Deutschlands edles Nordlicht',
             'series_id': 'sylt---deutschlands-edles-nordlicht-movie-100',
             'timestamp': 1612462500,
@@ -222,7 +225,7 @@ class ZDFIE(ZDFBaseIE):
             'title': 'Sylt - Deutschlands edles Nordlicht',
             'description': 'md5:35407b810c2e1e33efbe15ef6e4c06c3',
             'duration': 810.0,
-            'thumbnail': 'https://www.zdf.de/assets/sylt-118~original?cb=1613992485011',
+            'thumbnail': r're:https://www\.zdf\.de/assets/sylt-118~original\?cb=\d+',
             'series': 'Sylt - Deutschlands edles Nordlicht',
             'series_id': 'sylt---deutschlands-edles-nordlicht-movie-100',
             'timestamp': 1612462500,
@@ -239,7 +242,7 @@ class ZDFIE(ZDFBaseIE):
             'title': 'Sylt - Deutschlands edles Nordlicht',
             'description': 'md5:35407b810c2e1e33efbe15ef6e4c06c3',
             'duration': 810.0,
-            'thumbnail': 'https://www.zdf.de/assets/sylt-118~original?cb=1613992485011',
+            'thumbnail': r're:https://www\.zdf\.de/assets/sylt-118~original\?cb=\d+',
             'series': 'Sylt - Deutschlands edles Nordlicht',
             'series_id': 'sylt---deutschlands-edles-nordlicht-movie-100',
             'timestamp': 1612462500,
@@ -249,67 +252,66 @@ class ZDFIE(ZDFBaseIE):
         'params': {'skip_download': True},
     }, {
         # Video belongs to a playlist, video URL
-        'url': 'https://www.zdf.de/video/dokus/die-magie-der-farben-116/die-magie-der-farben-von-koenigspurpur-und-jeansblau-100',
-        'md5': '1eda17eb40a9ead3046326e10b9c5973',
+        # Also: video mirrored from ARD Mediathek
+        'url': 'https://www.zdf.de/video/dokus/collection-index-page-ard-collection-ard-dxjuomfyzdpzag93ojy2mzhhmmq3mzk2ztq4nda-132/page-video-ard-gelb-vom-hellen-glanz-zu-finsteren-abgruenden-102',
+        'md5': '84980c1a0148da6cd94de58333d7e1ee',
         'info_dict': {
-            'id': 'die-magie-der-farben-von-koenigspurpur-und-jeansblau-100',
+            'id': 'page-video-ard-gelb-vom-hellen-glanz-zu-finsteren-abgruenden-102',
             'ext': 'mp4',
-            'title': 'Von Königspurpur bis Jeansblau',
-            'description': 'md5:a89da10c928c6235401066b60a6d5c1a',
-            'duration': 2615.0,
-            'thumbnail': 'https://www.zdf.de/assets/koenigspurpur-bis-jeansblau-100~original?cb=1741857765971',
+            'title': 'Gelb: Vom hellen Glanz zu finsteren Abgründen',
+            'description': 'md5:9aad4806b4c8ea152ab21e70c9d516be',
+            'duration': 895.0,
+            'thumbnail': r're:https://www\.zdf\.de/assets/image-ard-gelb-vom-hellen-glanz-zu-finsteren-abgruenden-102~original\?cb=\d+',
             'series': 'Die Magie der Farben',
-            'series_id': 'die-magie-der-farben-116',
-            'season': 'Season 1',
-            'season_number': 1,
-            'episode': 'Episode 2',
-            'episode_number': 2,
-            'timestamp': 1445797800,
-            'upload_date': '20151025',
-            '_old_archive_ids': ['zdf 151025_magie_farben2_tex'],
+            'series_id': 'collection-index-page-ard-collection-ard-dxjuomfyzdpzag93ojy2mzhhmmq3mzk2ztq4nda-132',
+            'season': 'Season 2023',
+            'season_number': 2023,
+            'episode': 'Episode 5',
+            'episode_number': 5,
+            'timestamp': 1690902120,
+            'upload_date': '20230801',
+            '_old_archive_ids': ['zdf video_ard_dXJuOmFyZDpwdWJsaWNhdGlvbjo0YTYyOTJjM2Q0ZThlNmY1'],
         },
     }, {
         # Video belongs to a playlist, play URL
-        'url': 'https://www.zdf.de/play/dokus/die-magie-der-farben-116/die-magie-der-farben-von-koenigspurpur-und-jeansblau-100',
-        'md5': '1eda17eb40a9ead3046326e10b9c5973',
+        'url': 'https://www.zdf.de/play/dokus/collection-index-page-ard-collection-ard-dxjuomfyzdpzag93ojy2mzhhmmq3mzk2ztq4nda-132/page-video-ard-gelb-vom-hellen-glanz-zu-finsteren-abgruenden-102',
         'info_dict': {
-            'id': 'die-magie-der-farben-von-koenigspurpur-und-jeansblau-100',
+            'id': 'page-video-ard-gelb-vom-hellen-glanz-zu-finsteren-abgruenden-102',
             'ext': 'mp4',
-            'title': 'Von Königspurpur bis Jeansblau',
-            'description': 'md5:a89da10c928c6235401066b60a6d5c1a',
-            'duration': 2615.0,
-            'thumbnail': 'https://www.zdf.de/assets/koenigspurpur-bis-jeansblau-100~original?cb=1741857765971',
+            'title': 'Gelb: Vom hellen Glanz zu finsteren Abgründen',
+            'description': 'md5:9aad4806b4c8ea152ab21e70c9d516be',
+            'duration': 895.0,
+            'thumbnail': r're:https://www\.zdf\.de/assets/image-ard-gelb-vom-hellen-glanz-zu-finsteren-abgruenden-102~original\?cb=\d+',
             'series': 'Die Magie der Farben',
-            'series_id': 'die-magie-der-farben-116',
-            'season': 'Season 1',
-            'season_number': 1,
-            'episode': 'Episode 2',
-            'episode_number': 2,
-            'timestamp': 1445797800,
-            'upload_date': '20151025',
-            '_old_archive_ids': ['zdf 151025_magie_farben2_tex'],
+            'series_id': 'collection-index-page-ard-collection-ard-dxjuomfyzdpzag93ojy2mzhhmmq3mzk2ztq4nda-132',
+            'season': 'Season 2023',
+            'season_number': 2023,
+            'episode': 'Episode 5',
+            'episode_number': 5,
+            'timestamp': 1690902120,
+            'upload_date': '20230801',
+            '_old_archive_ids': ['zdf video_ard_dXJuOmFyZDpwdWJsaWNhdGlvbjo0YTYyOTJjM2Q0ZThlNmY1'],
         },
         'params': {'skip_download': True},
     }, {
         # Video belongs to a playlist, legacy URL before website redesign in 2025-03
-        'url': 'https://www.zdf.de/dokumentation/terra-x/die-magie-der-farben-von-koenigspurpur-und-jeansblau-100.html',
-        'md5': '1eda17eb40a9ead3046326e10b9c5973',
+        'url': 'https://www.zdf.de/dokus/collection-index-page-ard-collection-ard-dxjuomfyzdpzag93ojy2mzhhmmq3mzk2ztq4nda-132/page-video-ard-gelb-vom-hellen-glanz-zu-finsteren-abgruenden-102.html',
         'info_dict': {
-            'id': 'die-magie-der-farben-von-koenigspurpur-und-jeansblau-100',
+            'id': 'page-video-ard-gelb-vom-hellen-glanz-zu-finsteren-abgruenden-102',
             'ext': 'mp4',
-            'title': 'Von Königspurpur bis Jeansblau',
-            'description': 'md5:a89da10c928c6235401066b60a6d5c1a',
-            'duration': 2615.0,
-            'thumbnail': 'https://www.zdf.de/assets/koenigspurpur-bis-jeansblau-100~original?cb=1741857765971',
+            'title': 'Gelb: Vom hellen Glanz zu finsteren Abgründen',
+            'description': 'md5:9aad4806b4c8ea152ab21e70c9d516be',
+            'duration': 895.0,
+            'thumbnail': r're:https://www\.zdf\.de/assets/image-ard-gelb-vom-hellen-glanz-zu-finsteren-abgruenden-102~original\?cb=\d+',
             'series': 'Die Magie der Farben',
-            'series_id': 'die-magie-der-farben-116',
-            'season': 'Season 1',
-            'season_number': 1,
-            'episode': 'Episode 2',
-            'episode_number': 2,
-            'timestamp': 1445797800,
-            'upload_date': '20151025',
-            '_old_archive_ids': ['zdf 151025_magie_farben2_tex'],
+            'series_id': 'collection-index-page-ard-collection-ard-dxjuomfyzdpzag93ojy2mzhhmmq3mzk2ztq4nda-132',
+            'season': 'Season 2023',
+            'season_number': 2023,
+            'episode': 'Episode 5',
+            'episode_number': 5,
+            'timestamp': 1690902120,
+            'upload_date': '20230801',
+            '_old_archive_ids': ['zdf video_ard_dXJuOmFyZDpwdWJsaWNhdGlvbjo0YTYyOTJjM2Q0ZThlNmY1'],
         },
         'params': {'skip_download': True},
     }, {
@@ -337,7 +339,50 @@ class ZDFIE(ZDFBaseIE):
             '_old_archive_ids': ['zdf 211219_sendung_hjo'],
         },
     }, {
-        # Video that requires fallback extraction
+        # FUNK video (hosted on a different CDN, has atypical PTMD and HLS files)
+        'url': 'https://www.zdf.de/video/serien/funk-collection-funk-11790-1596/funk-alles-ist-verzaubert-102',
+        'md5': '57af4423db0455a3975d2dc4578536bc',
+        'info_dict': {
+            'id': 'funk-alles-ist-verzaubert-102',
+            'ext': 'mp4',
+            'title': 'Alles ist verzaubert',
+            'description': 'Die Neue an der Schule verdreht Ismail den Kopf.',
+            'duration': 1278.0,
+            'thumbnail': r're:https://www\.zdf\.de/assets/teaser-funk-alles-ist-verzaubert-102~original\?cb=\d+',
+            'series': 'DRUCK',
+            'series_id': 'funk-collection-funk-11790-1596',
+            'season': 'Season 2021',
+            'season_number': 2021,
+            'episode': 'Episode 50',
+            'episode_number': 50,
+            'timestamp': 1635520560,
+            'upload_date': '20211029',
+            '_old_archive_ids': ['zdf video_funk_1770473'],
+        },
+    }, {
+        # zdfheute video, also available on zdf.de
+        'url': 'https://www.zdfheute.de/video/heute-journal/heute-journal-vom-19-dezember-2025-100.html',
+        'md5': '47af8c2cfa30abf74501170f62754c63',
+        'info_dict': {
+            'id': 'heute-journal-vom-19-dezember-2025-100',
+            'ext': 'mp4',
+            'title': 'heute journal vom 19. Dezember 2025',
+            'description': 'md5:fd0dfbce0783486db839ff9140a8074b',
+            'duration': 1780.0,
+            'thumbnail': 'https://epg-image.zdf.de/fotobase-webdelivery/images/273e5545-16e7-4ca3-898e-52fe9e06d964?layout=2400x1350',
+            'chapters': 'count:10',
+            'series': 'heute journal',
+            'series_id': 'heute-journal-104',
+            'season': 'Season 2025',
+            'season_number': 2025,
+            'episode': 'Episode 365',
+            'episode_number': 365,
+            'timestamp': 1766178000,
+            'upload_date': '20251219',
+            '_old_archive_ids': ['zdf 251219_2200_sendung_hjo'],
+        },
+    }, {
+        # zdfheute video, not available on zdf.de (uses the fallback extraction path)
         'url': 'https://www.zdf.de/nachrichten/politik/deutschland/koalitionsverhandlungen-spd-cdu-csu-dobrindt-100.html',
         'md5': 'c3a78514dd993a5781aa3afe50db51e2',
         'info_dict': {
@@ -346,71 +391,50 @@ class ZDFIE(ZDFBaseIE):
             'title': 'Dobrindt schließt Steuererhöhungen aus',
             'description': 'md5:9a117646d7b8df6bc902eb543a9c9023',
             'duration': 325,
-            'thumbnail': 'https://www.zdfheute.de/assets/dobrindt-csu-berlin-direkt-100~1920x1080?cb=1743357653736',
+            'thumbnail': r're:https://www\.zdfheute\.de/assets/dobrindt-csu-berlin-direkt-100~1920x1080\?cb=\d+',
             'timestamp': 1743374520,
             'upload_date': '20250330',
             '_old_archive_ids': ['zdf 250330_clip_2_bdi'],
         },
     }, {
-        # FUNK video (hosted on a different CDN, has atypical PTMD and HLS files)
-        'url': 'https://www.zdf.de/funk/druck-11790/funk-alles-ist-verzaubert-102.html',
-        'md5': '57af4423db0455a3975d2dc4578536bc',
+        # logo! video, also available on zdf.de
+        'url': 'https://www.logo.de/logo-vom-freitag-19-dezember-2025-102.html',
+        'md5': 'cfb1a0988b1249f052a437a55851134b',
         'info_dict': {
-            'id': 'funk-alles-ist-verzaubert-102',
+            'id': 'logo-vom-freitag-19-dezember-2025-102',
             'ext': 'mp4',
-            'title': 'Alles ist verzaubert',
-            'description': 'Die Neue an der Schule verdreht Ismail den Kopf.',
-            'duration': 1278.0,
-            'thumbnail': 'https://www.zdf.de/assets/teaser-funk-alles-ist-verzaubert-102~original?cb=1663848412907',
-            'series': 'DRUCK',
-            'series_id': 'funk-collection-funk-11790-1590',
-            'season': 'Season 7',
-            'season_number': 7,
-            'episode': 'Episode 1',
-            'episode_number': 1,
-            'timestamp': 1635520560,
-            'upload_date': '20211029',
-            '_old_archive_ids': ['zdf video_funk_1770473'],
+            'title': 'logo! vom Freitag, 19. Dezember 2025',
+            'description': 'md5:971428cb563e924c153580f23870c613',
+            'duration': 490.0,
+            'thumbnail': r're:https://www\.zdf\.de/assets/iran-rote-erde-sendung-19-dezember-2025-100~original\?cb=\d+',
+            'chapters': 'count:7',
+            'series': 'logo!',
+            'series_id': 'logo-154',
+            'season': 'Season 2025',
+            'season_number': 2025,
+            'episode': 'Episode 382',
+            'episode_number': 382,
+            'timestamp': 1766168700,
+            'upload_date': '20251219',
+            '_old_archive_ids': ['zdf 251219_1925_sendung_log'],
         },
     }, {
-        'url': 'https://www.zdf.de/serien/soko-stuttgart/das-geld-anderer-leute-100.html',
+        # logo! video, not available on zdf.de (uses the fallback extraction path)
+        'url': 'https://www.logo.de/kinderreporter-vivaan-trifft-alina-grijseels-100.html',
+        'md5': '094cea026babb67aa25fd0108400bc12',
         'info_dict': {
-            'id': 'das-geld-anderer-leute-100',
+            'id': 'kinderreporter-vivaan-trifft-alina-grijseels-100',
             'ext': 'mp4',
-            'title': 'Das Geld anderer Leute',
-            'description': 'md5:cb6f660850dc5eb7d1ab776ea094959d',
-            'duration': 2581.0,
-            'thumbnail': 'https://epg-image.zdf.de/fotobase-webdelivery/images/e2d7e55a-09f0-424e-ac73-6cac4dd65f35?layout=1920x1080',
-            'series': 'SOKO Stuttgart',
-            'series_id': 'soko-stuttgart-104',
-            'season': 'Season 11',
-            'season_number': 11,
-            'episode': 'Episode 10',
-            'episode_number': 10,
-            'timestamp': 1728983700,
-            'upload_date': '20241015',
-            '_old_archive_ids': ['zdf 191205_1800_sendung_sok8'],
+            'title': 'Vivaan trifft Handballerin Alina Grijseels',
+            'description': 'md5:9572e7f4340dda823ea4091a76624da6',
+            'duration': 166.0,
+            'thumbnail': r're:https://www\.zdf\.de/assets/vivaan-alina-grijseels-100~original\?cb=\d+',
+            'series': 'logo!',
+            'series_id': 'logo-154',
+            'timestamp': 1766236320,
+            'upload_date': '20251220',
+            '_old_archive_ids': ['zdf 251219_kr_alina_grijseels_neu_log'],
         },
-    }, {
-        'url': 'https://www.zdf.de/serien/northern-lights/begegnung-auf-der-bruecke-100.html',
-        'info_dict': {
-            'id': 'begegnung-auf-der-bruecke-100',
-            'ext': 'webm',
-            'title': 'Begegnung auf der Brücke',
-            'description': 'md5:e53a555da87447f7f1207f10353f8e45',
-            'duration': 3083.0,
-            'thumbnail': 'https://epg-image.zdf.de/fotobase-webdelivery/images/c5ff1d1f-f5c8-4468-86ac-1b2f1dbecc76?layout=1920x1080',
-            'series': 'Northern Lights',
-            'series_id': 'northern-lights-100',
-            'season': 'Season 1',
-            'season_number': 1,
-            'episode': 'Episode 1',
-            'episode_number': 1,
-            'timestamp': 1738546500,
-            'upload_date': '20250203',
-            '_old_archive_ids': ['zdf 240319_2310_sendung_not'],
-        },
-        'params': {'skip_download': 'geo-restricted http format'},
     }, {
         # Same as https://www.phoenix.de/sendungen/ereignisse/corona-nachgehakt/wohin-fuehrt-der-protest-in-der-pandemie-a-2050630.html
         'url': 'https://www.zdf.de/politik/phoenix-sendungen/wohin-fuehrt-der-protest-in-der-pandemie-100.html',
@@ -617,7 +641,7 @@ class ZDFChannelIE(ZDFBaseIE):
             'title': 'Sylt - Deutschlands edles Nordlicht',
             'description': 'md5:35407b810c2e1e33efbe15ef6e4c06c3',
             'duration': 810.0,
-            'thumbnail': 'https://www.zdf.de/assets/sylt-118~original?cb=1613992485011',
+            'thumbnail': r're:https://www\.zdf\.de/assets/sylt-118~original\?cb=\d+',
             'series': 'Sylt - Deutschlands edles Nordlicht',
             'series_id': 'sylt---deutschlands-edles-nordlicht-movie-100',
             'timestamp': 1612462500,
@@ -634,38 +658,24 @@ class ZDFChannelIE(ZDFBaseIE):
         },
         'playlist_mincount': 2,
     }, {
-        'url': 'https://www.zdf.de/serien/taunuskrimi/',
-        'info_dict': {
-            'id': 'taunuskrimi-100',
-            'title': 'Taunuskrimi',
-            'description': 'md5:ee7204e9c625c3b611d1274f9d0e3070',
-        },
-        'playlist_mincount': 8,
-    }, {
-        'url': 'https://www.zdf.de/serien/taunuskrimi/?staffel=1',
-        'info_dict': {
-            'id': 'taunuskrimi-100-s1',
-            'title': 'Taunuskrimi - Season 1',
-            'description': 'md5:ee7204e9c625c3b611d1274f9d0e3070',
-        },
-        'playlist_count': 7,
-    }, {
+        # All seasons of playlist
         'url': 'https://www.zdf.de/magazine/heute-journal-104',
         'info_dict': {
             'id': 'heute-journal-104',
             'title': 'heute journal',
             'description': 'md5:6edad39189abf8431795d3d6d7f986b3',
         },
-        'playlist_mincount': 500,
+        'playlist_mincount': 366,
     }, {
-        'url': 'https://www.zdf.de/magazine/heute-journal-104?staffel=2024',
+        # Only selected season
+        'url': 'https://www.zdf.de/magazine/heute-journal-104?staffel=2025',
         'info_dict': {
-            'id': 'heute-journal-104-s2024',
-            'title': 'heute journal - Season 2024',
+            'id': 'heute-journal-104-s2025',
+            'title': 'heute journal - Season 2025',
             'description': 'md5:6edad39189abf8431795d3d6d7f986b3',
         },
-        'playlist_count': 242,
-        'skip': 'Video count changes daily, needs support for playlist_maxcount',
+        'playlist_mincount': 1,
+        'playlist_maxcount': 365,
     }]
 
     _PAGE_SIZE = 24