[extractor/foxnews] Add FoxNewsVideo extractor

Closes #5133

README.md

@@ -12,7 +12,7 @@
 [![License: Unlicense](https://img.shields.io/badge/-Unlicense-blue.svg?style=for-the-badge)](LICENSE "License")
 [![CI Status](https://img.shields.io/github/workflow/status/yt-dlp/yt-dlp/Core%20Tests/master?label=Tests&style=for-the-badge)](https://github.com/yt-dlp/yt-dlp/actions "CI Status")
 [![Commits](https://img.shields.io/github/commit-activity/m/yt-dlp/yt-dlp?label=commits&style=for-the-badge)](https://github.com/yt-dlp/yt-dlp/commits "Commit History")
-[![Last Commit](https://img.shields.io/github/last-commit/yt-dlp/yt-dlp/master?label=&style=for-the-badge)](https://github.com/yt-dlp/yt-dlp/commits "Commit History")
+[![Last Commit](https://img.shields.io/github/last-commit/yt-dlp/yt-dlp/master?label=&style=for-the-badge&display_timestamp=committer)](https://github.com/yt-dlp/yt-dlp/commits "Commit History")
 
 </div>
 <!-- MANPAGE: END EXCLUDED SECTION -->
@@ -1642,9 +1642,9 @@ # MODIFYING METADATA
 
 `--replace-in-metadata FIELDS REGEX REPLACE` is used to replace text in any metadata field using [python regular expression](https://docs.python.org/3/library/re.html#regular-expression-syntax). [Backreferences](https://docs.python.org/3/library/re.html?highlight=backreferences#re.sub) can be used in the replace string for advanced use.
 
-The general syntax of `--parse-metadata FROM:TO` is to give the name of a field or an [output template](#output-template) to extract data from, and the format to interpret it as, separated by a colon `:`. Either a [python regular expression](https://docs.python.org/3/library/re.html#regular-expression-syntax) with named capture groups or a similar syntax to the [output template](#output-template) (only `%(field)s` formatting is supported) can be used for `TO`. The option can be used multiple times to parse and modify various fields.
+The general syntax of `--parse-metadata FROM:TO` is to give the name of a field or an [output template](#output-template) to extract data from, and the format to interpret it as, separated by a colon `:`. Either a [python regular expression](https://docs.python.org/3/library/re.html#regular-expression-syntax) with named capture groups, a single field name, or a similar syntax to the [output template](#output-template) (only `%(field)s` formatting is supported) can be used for `TO`. The option can be used multiple times to parse and modify various fields.
 
-Note that any field created by this can be used in the [output template](#output-template) and will also affect the media file's metadata added when using `--embed-metadata`.
+Note that these options preserve their relative order, allowing replacements to be made in parsed fields and viceversa. Also, any field thus created can be used in the [output template](#output-template) and will also affect the media file's metadata added when using `--embed-metadata`.
 
 This option also has a few special uses:
 
@@ -1733,11 +1733,7 @@ #### funimation
 * `language`: Audio languages to extract, e.g. `funimation:language=english,japanese`
 * `version`: The video version to extract - `uncut` or `simulcast`
 
-#### crunchyroll
-* `language`: Audio languages to extract, e.g. `crunchyroll:language=jaJp`
-* `hardsub`: Which hard-sub versions to extract, e.g. `crunchyroll:hardsub=None,enUS`
-
-#### crunchyrollbeta
+#### crunchyrollbeta (Crunchyroll)
 * `format`: Which stream type(s) to extract (default: `adaptive_hls`). Potentially useful values include `adaptive_hls`, `adaptive_dash`, `vo_adaptive_hls`, `vo_adaptive_dash`, `download_hls`, `download_dash`, `multitrack_adaptive_hls_v2`
 * `hardsub`: Preference order for which hardsub versions to extract, or `all` (default: `None` = no hardsubs), e.g. `crunchyrollbeta:hardsub=en-US,None`
 

supportedsites.md

@@ -23,7 +23,7 @@ # Supported sites
  - **9now.com.au**
  - **abc.net.au**
  - **abc.net.au:iview**
- - **abc.net.au:iview:showseries**
+ - **abc.net.au:​iview:showseries**
  - **abcnews**
  - **abcnews:video**
  - **abcotvs**: ABC Owned Television Stations
@@ -124,8 +124,8 @@ # Supported sites
  - **bbc**: [<abbr title="netrc machine"><em>bbc</em></abbr>] BBC
  - **bbc.co.uk**: [<abbr title="netrc machine"><em>bbc</em></abbr>] BBC iPlayer
  - **bbc.co.uk:article**: BBC articles
- - **bbc.co.uk:iplayer:episodes**
- - **bbc.co.uk:iplayer:group**
+ - **bbc.co.uk:​iplayer:episodes**
+ - **bbc.co.uk:​iplayer:group**
  - **bbc.co.uk:playlist**
  - **BBVTV**: [<abbr title="netrc machine"><em>bbvtv</em></abbr>]
  - **BBVTVLive**: [<abbr title="netrc machine"><em>bbvtv</em></abbr>]
@@ -274,7 +274,7 @@ # Supported sites
  - **crunchyroll**: [<abbr title="netrc machine"><em>crunchyroll</em></abbr>]
  - **crunchyroll:beta**: [<abbr title="netrc machine"><em>crunchyroll</em></abbr>]
  - **crunchyroll:playlist**: [<abbr title="netrc machine"><em>crunchyroll</em></abbr>]
- - **crunchyroll:playlist:beta**: [<abbr title="netrc machine"><em>crunchyroll</em></abbr>]
+ - **crunchyroll:​playlist:beta**: [<abbr title="netrc machine"><em>crunchyroll</em></abbr>]
  - **CSpan**: C-SPAN
  - **CSpanCongress**
  - **CtsNews**: 華視新聞
@@ -483,7 +483,7 @@ # Supported sites
  - **Golem**
  - **goodgame:stream**
  - **google:podcasts**
- - **google:podcasts:feed**
+ - **google:​podcasts:feed**
  - **GoogleDrive**
  - **GoogleDrive:Folder**
  - **GoPlay**: [<abbr title="netrc machine"><em>goplay</em></abbr>]
@@ -618,7 +618,7 @@ # Supported sites
  - **kuwo:singer**: 酷我音乐 - 歌手
  - **kuwo:song**: 酷我音乐
  - **la7.it**
- - **la7.it:pod:episode**
+ - **la7.it:​pod:episode**
  - **la7.it:podcast**
  - **laola1tv**
  - **laola1tv:embed**
@@ -652,7 +652,7 @@ # Supported sites
  - **LineLiveChannel**
  - **LinkedIn**: [<abbr title="netrc machine"><em>linkedin</em></abbr>]
  - **linkedin:learning**: [<abbr title="netrc machine"><em>linkedin</em></abbr>]
- - **linkedin:learning:course**: [<abbr title="netrc machine"><em>linkedin</em></abbr>]
+ - **linkedin:​learning:course**: [<abbr title="netrc machine"><em>linkedin</em></abbr>]
  - **LinuxAcademy**: [<abbr title="netrc machine"><em>linuxacademy</em></abbr>]
  - **Liputan6**
  - **LiTV**
@@ -673,7 +673,7 @@ # Supported sites
  - **MagentaMusik360**
  - **mailru**: Видео@Mail.Ru
  - **mailru:music**: Музыка@Mail.Ru
- - **mailru:music:search**: Музыка@Mail.Ru
+ - **mailru:​music:search**: Музыка@Mail.Ru
  - **MainStreaming**: MainStreaming Player
  - **MallTV**
  - **mangomolo:live**
@@ -718,7 +718,7 @@ # Supported sites
  - **microsoftstream**: Microsoft Stream
  - **mildom**: Record ongoing live by specific user in Mildom
  - **mildom:clip**: Clip in Mildom
- - **mildom:user:vod**: Download all VODs from specific user in Mildom
+ - **mildom:​user:vod**: Download all VODs from specific user in Mildom
  - **mildom:vod**: VOD in Mildom
  - **minds**
  - **minds:channel**
@@ -803,7 +803,7 @@ # Supported sites
  - **navernow**
  - **NBA**
  - **nba:watch**
- - **nba:watch:collection**
+ - **nba:​watch:collection**
  - **NBAChannel**
  - **NBAEmbed**
  - **NBAWatchEmbed**
@@ -817,7 +817,7 @@ # Supported sites
  - **NBCStations**
  - **ndr**: NDR.de - Norddeutscher Rundfunk
  - **ndr:embed**
- - **ndr:embed:base**
+ - **ndr:​embed:base**
  - **NDTV**
  - **Nebula**: [<abbr title="netrc machine"><em>watchnebula</em></abbr>]
  - **nebula:channel**: [<abbr title="netrc machine"><em>watchnebula</em></abbr>]
@@ -869,7 +869,7 @@ # Supported sites
  - **niconico:tag**: NicoNico video tag URLs
  - **NiconicoUser**
  - **nicovideo:search**: Nico video search; "nicosearch:" prefix
- - **nicovideo:search:date**: Nico video search, newest first; "nicosearchdate:" prefix
+ - **nicovideo:​search:date**: Nico video search, newest first; "nicosearchdate:" prefix
  - **nicovideo:search_url**: Nico video search URLs
  - **Nintendo**
  - **Nitter**
@@ -892,7 +892,7 @@ # Supported sites
  - **npo**: npo.nl, ntr.nl, omroepwnl.nl, zapp.nl and npo3.nl
  - **npo.nl:live**
  - **npo.nl:radio**
- - **npo.nl:radio:fragment**
+ - **npo.nl:​radio:fragment**
  - **Npr**
  - **NRK**
  - **NRKPlaylist**
@@ -933,7 +933,7 @@ # Supported sites
  - **openrec:capture**
  - **openrec:movie**
  - **OraTV**
- - **orf:fm4:story**: fm4.orf.at stories
+ - **orf:​fm4:story**: fm4.orf.at stories
  - **orf:iptv**: iptv.ORF.at
  - **orf:radio**
  - **orf:tvthek**: ORF TVthek
@@ -981,7 +981,7 @@ # Supported sites
  - **Pinterest**
  - **PinterestCollection**
  - **pixiv:sketch**
- - **pixiv:sketch:user**
+ - **pixiv:​sketch:user**
  - **Pladform**
  - **PlanetMarathi**
  - **Platzi**: [<abbr title="netrc machine"><em>platzi</em></abbr>]
@@ -1010,7 +1010,7 @@ # Supported sites
  - **polskieradio:kierowcow**
  - **polskieradio:player**
  - **polskieradio:podcast**
- - **polskieradio:podcast:list**
+ - **polskieradio:​podcast:list**
  - **PolskieRadioCategory**
  - **Popcorntimes**
  - **PopcornTV**
@@ -1122,7 +1122,7 @@ # Supported sites
  - **rtl.nl**: rtl.nl and rtlxl.nl
  - **rtl2**
  - **rtl2:you**
- - **rtl2:you:series**
+ - **rtl2:​you:series**
  - **RTLLuLive**
  - **RTLLuRadio**
  - **RTNews**
@@ -1198,9 +1198,9 @@ # Supported sites
  - **Skeb**
  - **sky.it**
  - **sky:news**
- - **sky:news:story**
+ - **sky:​news:story**
  - **sky:sports**
- - **sky:sports:news**
+ - **sky:​sports:news**
  - **skyacademy.it**
  - **SkylineWebcams**
  - **skynewsarabia:article**
@@ -1289,7 +1289,7 @@ # Supported sites
  - **Teachable**: [<abbr title="netrc machine"><em>teachable</em></abbr>]
  - **TeachableCourse**: [<abbr title="netrc machine"><em>teachable</em></abbr>]
  - **teachertube**: teachertube.com videos
- - **teachertube:user:collection**: teachertube.com user and collection videos
+ - **teachertube:​user:collection**: teachertube.com user and collection videos
  - **TeachingChannel**
  - **Teamcoco**
  - **TeamTreeHouse**: [<abbr title="netrc machine"><em>teamtreehouse</em></abbr>]
@@ -1614,12 +1614,12 @@ # Supported sites
  - **XXXYMovies**
  - **Yahoo**: Yahoo screen and movies
  - **yahoo:gyao**
- - **yahoo:gyao:player**
+ - **yahoo:​gyao:player**
  - **yahoo:japannews**: Yahoo! Japan News
  - **YandexDisk**
  - **yandexmusic:album**: Яндекс.Музыка - Альбом
- - **yandexmusic:artist:albums**: Яндекс.Музыка - Артист - Альбомы
- - **yandexmusic:artist:tracks**: Яндекс.Музыка - Артист - Треки
+ - **yandexmusic:​artist:albums**: Яндекс.Музыка - Артист - Альбомы
+ - **yandexmusic:​artist:tracks**: Яндекс.Музыка - Артист - Треки
  - **yandexmusic:playlist**: Яндекс.Музыка - Плейлист
  - **yandexmusic:track**: Яндекс.Музыка - Трек
  - **YandexVideo**
@@ -1641,14 +1641,14 @@ # Supported sites
  - **youtube:clip**
  - **youtube:favorites**: YouTube liked videos; ":ytfav" keyword (requires cookies)
  - **youtube:history**: Youtube watch history; ":ythis" keyword (requires cookies)
- - **youtube:music:search_url**: YouTube music search URLs with selectable sections, e.g. #songs
+ - **youtube:​music:search_url**: YouTube music search URLs with selectable sections, e.g. #songs
  - **youtube:notif**: YouTube notifications; ":ytnotif" keyword (requires cookies)
  - **youtube:playlist**: YouTube playlists
  - **youtube:recommended**: YouTube recommended videos; ":ytrec" keyword
  - **youtube:search**: YouTube search; "ytsearch:" prefix
- - **youtube:search:date**: YouTube search, newest videos first; "ytsearchdate:" prefix
+ - **youtube:​search:date**: YouTube search, newest videos first; "ytsearchdate:" prefix
  - **youtube:search_url**: YouTube search URLs with sorting and filter support
- - **youtube:shorts:pivot:audio**: YouTube Shorts audio pivot (Shorts using audio of a given video)
+ - **youtube:​shorts:pivot:audio**: YouTube Shorts audio pivot (Shorts using audio of a given video)
  - **youtube:stories**: YouTube channel stories; "ytstories:" prefix
  - **youtube:subscriptions**: YouTube subscriptions feed; ":ytsubs" keyword (requires cookies)
  - **youtube:tab**: YouTube Tabs

test/helper.py

@@ -260,8 +260,8 @@ def _repr(v):
         info_dict_str += ''.join(
             f'    {_repr(k)}: {_repr(test_info_dict[k])},\n'
             for k in missing_keys)
-        write_string(
-            '\n\'info_dict\': {\n' + info_dict_str + '},\n', out=sys.stderr)
+        info_dict_str = '\n\'info_dict\': {\n' + info_dict_str + '},\n'
+        write_string(info_dict_str.replace('\n', '\n        '), out=sys.stderr)
         self.assertFalse(
             missing_keys,
             'Missing keys in test definition: %s' % (

test/test_aes.py

@@ -11,7 +11,6 @@
 import base64
 
 from yt_dlp.aes import (
-    BLOCK_SIZE_BYTES,
     aes_cbc_decrypt,
     aes_cbc_decrypt_bytes,
     aes_cbc_encrypt,
@@ -103,8 +102,7 @@ def test_decrypt_text(self):
 
     def test_ecb_encrypt(self):
         data = bytes_to_intlist(self.secret_msg)
-        data += [0x08] * (BLOCK_SIZE_BYTES - len(data) % BLOCK_SIZE_BYTES)
-        encrypted = intlist_to_bytes(aes_ecb_encrypt(data, self.key, self.iv))
+        encrypted = intlist_to_bytes(aes_ecb_encrypt(data, self.key))
         self.assertEqual(
             encrypted,
             b'\xaa\x86]\x81\x97>\x02\x92\x9d\x1bR[[L/u\xd3&\xd1(h\xde{\x81\x94\xba\x02\xae\xbd\xa6\xd0:')

yt_dlp/aes.py

@@ -28,11 +28,23 @@ def aes_cbc_encrypt_bytes(data, key, iv, **kwargs):
     return intlist_to_bytes(aes_cbc_encrypt(*map(bytes_to_intlist, (data, key, iv)), **kwargs))
 
 
+BLOCK_SIZE_BYTES = 16
+
+
 def unpad_pkcs7(data):
     return data[:-compat_ord(data[-1])]
 
 
-BLOCK_SIZE_BYTES = 16
+def pkcs7_padding(data):
+    """
+    PKCS#7 padding
+
+    @param {int[]} data        cleartext
+    @returns {int[]}           padding data
+    """
+
+    remaining_length = BLOCK_SIZE_BYTES - len(data) % BLOCK_SIZE_BYTES
+    return data + [remaining_length] * remaining_length
 
 
 def pad_block(block, padding_mode):
@@ -64,7 +76,7 @@ def pad_block(block, padding_mode):
 
 def aes_ecb_encrypt(data, key, iv=None):
     """
-    Encrypt with aes in ECB mode
+    Encrypt with aes in ECB mode. Using PKCS#7 padding
 
     @param {int[]} data        cleartext
     @param {int[]} key         16/24/32-Byte cipher key
@@ -77,8 +89,7 @@ def aes_ecb_encrypt(data, key, iv=None):
     encrypted_data = []
     for i in range(block_count):
         block = data[i * BLOCK_SIZE_BYTES: (i + 1) * BLOCK_SIZE_BYTES]
-        encrypted_data += aes_encrypt(block, expanded_key)
-    encrypted_data = encrypted_data[:len(data)]
+        encrypted_data += aes_encrypt(pkcs7_padding(block), expanded_key)
 
     return encrypted_data
 
@@ -551,5 +562,6 @@ def ghash(subkey, data):
 
     'key_expansion',
     'pad_block',
+    'pkcs7_padding',
     'unpad_pkcs7',
 ]

yt_dlp/compat/__init__.py

@@ -14,7 +14,7 @@
 # HTMLParseError has been deprecated in Python 3.3 and removed in
 # Python 3.5. Introducing dummy exception for Python >3.5 for compatible
 # and uniform cross-version exception handling
-class compat_HTMLParseError(Exception):
+class compat_HTMLParseError(ValueError):
     pass
 
 

yt_dlp/compat/_legacy.py

@@ -48,6 +48,7 @@ def compat_setenv(key, value, env=os.environ):
 
 
 compat_basestring = str
+compat_casefold = str.casefold
 compat_chr = chr
 compat_collections_abc = collections.abc
 compat_cookiejar = http.cookiejar

yt_dlp/extractor/_extractors.py

@@ -372,8 +372,6 @@
     CrowdBunkerChannelIE,
 )
 from .crunchyroll import (
-    CrunchyrollIE,
-    CrunchyrollShowPlaylistIE,
     CrunchyrollBetaIE,
     CrunchyrollBetaShowIE,
 )
@@ -470,6 +468,10 @@
 )
 from .dumpert import DumpertIE
 from .defense import DefenseGouvFrIE
+from .deuxm import (
+    DeuxMIE,
+    DeuxMNewsIE
+)
 from .digitalconcerthall import DigitalConcertHallIE
 from .discovery import DiscoveryIE
 from .disney import DisneyIE
@@ -586,6 +588,7 @@
 from .foxnews import (
     FoxNewsIE,
     FoxNewsArticleIE,
+    FoxNewsVideoIE,
 )
 from .foxsports import FoxSportsIE
 from .fptplay import FptplayIE
@@ -908,6 +911,7 @@
 )
 from .linuxacademy import LinuxAcademyIE
 from .liputan6 import Liputan6IE
+from .listennotes import ListenNotesIE
 from .litv import LiTVIE
 from .livejournal import LiveJournalIE
 from .livestream import (
@@ -1427,6 +1431,7 @@
 )
 from .puls4 import Puls4IE
 from .pyvideo import PyvideoIE
+from .qingting import QingTingIE
 from .qqmusic import (
     QQMusicIE,
     QQMusicSingerIE,
@@ -1640,7 +1645,6 @@
     SkyItVideoIE,
     SkyItVideoLiveIE,
     SkyItIE,
-    SkyItAcademyIE,
     SkyItArteIE,
     CieloTVItIE,
     TV8ItIE,
@@ -1760,6 +1764,7 @@
     SVTPlayIE,
     SVTSeriesIE,
 )
+from .swearnet import SwearnetEpisodeIE
 from .swrmediathek import SWRMediathekIE
 from .syvdk import SYVDKIE
 from .syfy import SyfyIE
@@ -1960,7 +1965,8 @@
     TVPEmbedIE,
     TVPIE,
     TVPStreamIE,
-    TVPWebsiteIE,
+    TVPVODSeriesIE,
+    TVPVODVideoIE,
 )
 from .tvplay import (
     TVPlayIE,

yt_dlp/extractor/acfun.py

@@ -161,7 +161,7 @@ class AcFunBangumiIE(AcFunVideoBaseIE):
     def _real_extract(self, url):
         video_id = self._match_id(url)
         ac_idx = parse_qs(url).get('ac', [None])[-1]
-        video_id = f'{video_id}{format_field(ac_idx, template="__%s")}'
+        video_id = f'{video_id}{format_field(ac_idx, None, "__%s")}'
 
         webpage = self._download_webpage(url, video_id)
         json_bangumi_data = self._search_json(r'window.bangumiData\s*=', webpage, 'bangumiData', video_id)

yt_dlp/extractor/adn.py

@@ -28,30 +28,34 @@
 
 
 class ADNIE(InfoExtractor):
-    IE_DESC = 'Anime Digital Network'
-    _VALID_URL = r'https?://(?:www\.)?animedigitalnetwork\.fr/video/[^/]+/(?P<id>\d+)'
-    _TEST = {
-        'url': 'http://animedigitalnetwork.fr/video/blue-exorcist-kyoto-saga/7778-episode-1-debut-des-hostilites',
-        'md5': '0319c99885ff5547565cacb4f3f9348d',
+    IE_DESC = 'Animation Digital Network'
+    _VALID_URL = r'https?://(?:www\.)?(?:animation|anime)digitalnetwork\.fr/video/[^/]+/(?P<id>\d+)'
+    _TESTS = [{
+        'url': 'https://animationdigitalnetwork.fr/video/fruits-basket/9841-episode-1-a-ce-soir',
+        'md5': '1c9ef066ceb302c86f80c2b371615261',
         'info_dict': {
-            'id': '7778',
+            'id': '9841',
             'ext': 'mp4',
-            'title': 'Blue Exorcist - Kyôto Saga - Episode 1',
-            'description': 'md5:2f7b5aa76edbc1a7a92cedcda8a528d5',
-            'series': 'Blue Exorcist - Kyôto Saga',
-            'duration': 1467,
-            'release_date': '20170106',
+            'title': 'Fruits Basket - Episode 1',
+            'description': 'md5:14be2f72c3c96809b0ca424b0097d336',
+            'series': 'Fruits Basket',
+            'duration': 1437,
+            'release_date': '20190405',
             'comment_count': int,
             'average_rating': float,
-            'season_number': 2,
-            'episode': 'Début des hostilités',
+            'season_number': 1,
+            'episode': 'À ce soir !',
             'episode_number': 1,
-        }
-    }
+        },
+        'skip': 'Only available in region (FR, ...)',
+    }, {
+        'url': 'http://animedigitalnetwork.fr/video/blue-exorcist-kyoto-saga/7778-episode-1-debut-des-hostilites',
+        'only_matching': True,
+    }]
 
-    _NETRC_MACHINE = 'animedigitalnetwork'
-    _BASE_URL = 'http://animedigitalnetwork.fr'
-    _API_BASE_URL = 'https://gw.api.animedigitalnetwork.fr/'
+    _NETRC_MACHINE = 'animationdigitalnetwork'
+    _BASE = 'animationdigitalnetwork.fr'
+    _API_BASE_URL = 'https://gw.api.' + _BASE + '/'
     _PLAYER_BASE_URL = _API_BASE_URL + 'player/'
     _HEADERS = {}
     _LOGIN_ERR_MESSAGE = 'Unable to log in'
@@ -75,11 +79,11 @@ def _get_subtitles(self, sub_url, video_id):
         if subtitle_location:
             enc_subtitles = self._download_webpage(
                 subtitle_location, video_id, 'Downloading subtitles data',
-                fatal=False, headers={'Origin': 'https://animedigitalnetwork.fr'})
+                fatal=False, headers={'Origin': 'https://' + self._BASE})
         if not enc_subtitles:
             return None
 
-        # http://animedigitalnetwork.fr/components/com_vodvideo/videojs/adn-vjs.min.js
+        # http://animationdigitalnetwork.fr/components/com_vodvideo/videojs/adn-vjs.min.js
         dec_subtitles = unpad_pkcs7(aes_cbc_decrypt_bytes(
             compat_b64decode(enc_subtitles[24:]),
             binascii.unhexlify(self._K + '7fac1178830cfe0c'),

yt_dlp/extractor/bilibili.py

@@ -368,7 +368,7 @@ def _real_extract(self, url):
                 or '正在观看预览，大会员免费看全片' in webpage):
             self.raise_login_required('This video is for premium members only')
 
-        play_info = self._search_json(r'window\.__playinfo__\s*=\s*', webpage, 'play info', video_id)['data']
+        play_info = self._search_json(r'window\.__playinfo__\s*=', webpage, 'play info', video_id)['data']
         formats = self.extract_formats(play_info)
         if (not formats and '成为大会员抢先看' in webpage
                 and play_info.get('durl') and not play_info.get('dash')):

yt_dlp/extractor/ceskatelevize.py

@@ -9,6 +9,7 @@
     ExtractorError,
     float_or_none,
     sanitized_Request,
+    str_or_none,
     traverse_obj,
     urlencode_postdata,
     USER_AGENTS,
@@ -16,13 +17,13 @@
 
 
 class CeskaTelevizeIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?ceskatelevize\.cz/(?:ivysilani|porady)/(?:[^/?#&]+/)*(?P<id>[^/#?]+)'
+    _VALID_URL = r'https?://(?:www\.)?ceskatelevize\.cz/(?:ivysilani|porady|zive)/(?:[^/?#&]+/)*(?P<id>[^/#?]+)'
     _TESTS = [{
         'url': 'http://www.ceskatelevize.cz/ivysilani/10441294653-hyde-park-civilizace/215411058090502/bonus/20641-bonus-01-en',
         'info_dict': {
             'id': '61924494877028507',
             'ext': 'mp4',
-            'title': 'Hyde Park Civilizace: Bonus 01 - En',
+            'title': 'Bonus 01 - En - Hyde Park Civilizace',
             'description': 'English Subtittles',
             'thumbnail': r're:^https?://.*\.jpg',
             'duration': 81.3,
@@ -33,18 +34,29 @@ class CeskaTelevizeIE(InfoExtractor):
         },
     }, {
         # live stream
-        'url': 'http://www.ceskatelevize.cz/ivysilani/zive/ct4/',
+        'url': 'http://www.ceskatelevize.cz/zive/ct1/',
         'info_dict': {
-            'id': 402,
+            'id': '102',
             'ext': 'mp4',
-            'title': r're:^ČT Sport \d{4}-\d{2}-\d{2} \d{2}:\d{2}$',
+            'title': r'ČT1 - živé vysílání online',
+            'description': 'Sledujte živé vysílání kanálu ČT1 online. Vybírat si můžete i z dalších kanálů České televize na kterémkoli z vašich zařízení.',
             'is_live': True,
         },
         'params': {
             # m3u8 download
             'skip_download': True,
         },
-        'skip': 'Georestricted to Czech Republic',
+    }, {
+        # another
+        'url': 'http://www.ceskatelevize.cz/ivysilani/zive/ct4/',
+        'only_matching': True,
+        'info_dict': {
+            'id': 402,
+            'ext': 'mp4',
+            'title': r're:^ČT Sport \d{4}-\d{2}-\d{2} \d{2}:\d{2}$',
+            'is_live': True,
+        },
+        # 'skip': 'Georestricted to Czech Republic',
     }, {
         'url': 'http://www.ceskatelevize.cz/ivysilani/embed/iFramePlayer.php?hash=d6a3e1370d2e4fa76296b90bad4dfc19673b641e&IDEC=217 562 22150/0004&channelID=1&width=100%25',
         'only_matching': True,
@@ -53,21 +65,21 @@ class CeskaTelevizeIE(InfoExtractor):
         'url': 'http://www.ceskatelevize.cz/porady/10520528904-queer/215562210900007-bogotart/',
         'info_dict': {
             'id': '215562210900007-bogotart',
-            'title': 'Queer: Bogotart',
-            'description': 'Hlavní město Kolumbie v doprovodu queer umělců. Vroucí svět plný vášně, sebevědomí, ale i násilí a bolesti. Připravil Peter Serge Butko',
+            'title': 'Bogotart - Queer',
+            'description': 'Hlavní město Kolumbie v doprovodu queer umělců. Vroucí svět plný vášně, sebevědomí, ale i násilí a bolesti',
         },
         'playlist': [{
             'info_dict': {
                 'id': '61924494877311053',
                 'ext': 'mp4',
-                'title': 'Queer: Bogotart (Varování 18+)',
+                'title': 'Bogotart - Queer (Varování 18+)',
                 'duration': 11.9,
             },
         }, {
             'info_dict': {
                 'id': '61924494877068022',
                 'ext': 'mp4',
-                'title': 'Queer: Bogotart (Queer)',
+                'title': 'Bogotart - Queer (Queer)',
                 'thumbnail': r're:^https?://.*\.jpg',
                 'duration': 1558.3,
             },
@@ -84,28 +96,42 @@ class CeskaTelevizeIE(InfoExtractor):
 
     def _real_extract(self, url):
         playlist_id = self._match_id(url)
-        parsed_url = compat_urllib_parse_urlparse(url)
-        webpage = self._download_webpage(url, playlist_id)
-        site_name = self._og_search_property('site_name', webpage, fatal=False, default=None)
+        webpage, urlh = self._download_webpage_handle(url, playlist_id)
+        parsed_url = compat_urllib_parse_urlparse(urlh.geturl())
+        site_name = self._og_search_property('site_name', webpage, fatal=False, default='Česká televize')
         playlist_title = self._og_search_title(webpage, default=None)
         if site_name and playlist_title:
-            playlist_title = playlist_title.replace(f' — {site_name}', '', 1)
+            playlist_title = re.split(r'\s*[—|]\s*%s' % (site_name, ), playlist_title, 1)[0]
         playlist_description = self._og_search_description(webpage, default=None)
         if playlist_description:
             playlist_description = playlist_description.replace('\xa0', ' ')
 
-        if parsed_url.path.startswith('/porady/'):
+        type_ = 'IDEC'
+        if re.search(r'(^/porady|/zive)/', parsed_url.path):
             next_data = self._search_nextjs_data(webpage, playlist_id)
-            idec = traverse_obj(next_data, ('props', 'pageProps', 'data', ('show', 'mediaMeta'), 'idec'), get_all=False)
+            if '/zive/' in parsed_url.path:
+                idec = traverse_obj(next_data, ('props', 'pageProps', 'data', 'liveBroadcast', 'current', 'idec'), get_all=False)
+            else:
+                idec = traverse_obj(next_data, ('props', 'pageProps', 'data', ('show', 'mediaMeta'), 'idec'), get_all=False)
+                if not idec:
+                    idec = traverse_obj(next_data, ('props', 'pageProps', 'data', 'videobonusDetail', 'bonusId'), get_all=False)
+                    if idec:
+                        type_ = 'bonus'
             if not idec:
                 raise ExtractorError('Failed to find IDEC id')
-            iframe_hash = self._download_webpage('https://www.ceskatelevize.cz/v-api/iframe-hash/', playlist_id)
-            webpage = self._download_webpage('https://www.ceskatelevize.cz/ivysilani/embed/iFramePlayer.php', playlist_id,
-                                             query={'hash': iframe_hash, 'origin': 'iVysilani', 'autoStart': 'true', 'IDEC': idec})
+            iframe_hash = self._download_webpage(
+                'https://www.ceskatelevize.cz/v-api/iframe-hash/',
+                playlist_id, note='Getting IFRAME hash')
+            query = {'hash': iframe_hash, 'origin': 'iVysilani', 'autoStart': 'true', type_: idec, }
+            webpage = self._download_webpage(
+                'https://www.ceskatelevize.cz/ivysilani/embed/iFramePlayer.php',
+                playlist_id, note='Downloading player', query=query)
 
         NOT_AVAILABLE_STRING = 'This content is not available at your territory due to limited copyright.'
         if '%s</p>' % NOT_AVAILABLE_STRING in webpage:
-            raise ExtractorError(NOT_AVAILABLE_STRING, expected=True)
+            self.raise_geo_restricted(NOT_AVAILABLE_STRING)
+        if any(not_found in webpage for not_found in ('Neplatný parametr pro videopřehrávač', 'IDEC nebyl nalezen', )):
+            raise ExtractorError('no video with IDEC available', video_id=idec, expected=True)
 
         type_ = None
         episode_id = None
@@ -174,7 +200,6 @@ def _real_extract(self, url):
                 is_live = item.get('type') == 'LIVE'
                 formats = []
                 for format_id, stream_url in item.get('streamUrls', {}).items():
-                    stream_url = stream_url.replace('https://', 'http://')
                     if 'playerType=flash' in stream_url:
                         stream_formats = self._extract_m3u8_formats(
                             stream_url, playlist_id, 'mp4', 'm3u8_native',
@@ -196,7 +221,7 @@ def _real_extract(self, url):
                     entries[num]['formats'].extend(formats)
                     continue
 
-                item_id = item.get('id') or item['assetId']
+                item_id = str_or_none(item.get('id') or item['assetId'])
                 title = item['title']
 
                 duration = float_or_none(item.get('duration'))
@@ -227,6 +252,8 @@ def _real_extract(self, url):
         for e in entries:
             self._sort_formats(e['formats'])
 
+        if len(entries) == 1:
+            return entries[0]
         return self.playlist_result(entries, playlist_id, playlist_title, playlist_description)
 
     def _get_subtitles(self, episode_id, subs):

yt_dlp/extractor/common.py

@@ -3725,7 +3725,8 @@ def description(cls, *, markdown=True, search_examples=None):
         if not cls.working():
             desc += ' (**Currently broken**)' if markdown else ' (Currently broken)'
 
-        name = f' - **{cls.IE_NAME}**' if markdown else cls.IE_NAME
+        # Escape emojis. Ref: https://github.com/github/markup/issues/1153
+        name = (' - **%s**' % re.sub(r':(\w+:)', ':\u200B\\g<1>', cls.IE_NAME)) if markdown else cls.IE_NAME
         return f'{name}:{desc}' if desc else name
 
     def extract_subtitles(self, *args, **kwargs):

yt_dlp/extractor/crunchyroll.py

@@ -1,40 +1,16 @@
 import base64
-import json
-import re
-import urllib.request
-import xml.etree.ElementTree
-import zlib
-from hashlib import sha1
-from math import floor, pow, sqrt
+import urllib.parse
 
 from .common import InfoExtractor
-from .vrv import VRVBaseIE
-from ..aes import aes_cbc_decrypt
-from ..compat import (
-    compat_b64decode,
-    compat_etree_fromstring,
-    compat_str,
-    compat_urllib_parse_urlencode,
-    compat_urlparse,
-)
 from ..utils import (
     ExtractorError,
-    bytes_to_intlist,
-    extract_attributes,
     float_or_none,
     format_field,
-    int_or_none,
-    intlist_to_bytes,
     join_nonempty,
-    lowercase_escape,
-    merge_dicts,
     parse_iso8601,
     qualities,
-    remove_end,
-    sanitized_Request,
     traverse_obj,
     try_get,
-    xpath_text,
 )
 
 
@@ -42,16 +18,7 @@ class CrunchyrollBaseIE(InfoExtractor):
     _LOGIN_URL = 'https://www.crunchyroll.com/welcome/login'
     _API_BASE = 'https://api.crunchyroll.com'
     _NETRC_MACHINE = 'crunchyroll'
-
-    def _call_rpc_api(self, method, video_id, note=None, data=None):
-        data = data or {}
-        data['req'] = 'RpcApi' + method
-        data = compat_urllib_parse_urlencode(data).encode('utf-8')
-        return self._download_xml(
-            'https://www.crunchyroll.com/xml/',
-            video_id, note, fatal=False, data=data, headers={
-                'Content-Type': 'application/x-www-form-urlencoded',
-            })
+    params = None
 
     def _perform_login(self, username, password):
         if self._get_cookies(self._LOGIN_URL).get('etp_rt'):
@@ -72,7 +39,7 @@ def _perform_login(self, username, password):
 
         login_response = self._download_json(
             f'{self._API_BASE}/login.1.json', None, 'Logging in',
-            data=compat_urllib_parse_urlencode({
+            data=urllib.parse.urlencode({
                 'account': username,
                 'password': password,
                 'session_id': session_id
@@ -82,652 +49,23 @@ def _perform_login(self, username, password):
         if not self._get_cookies(self._LOGIN_URL).get('etp_rt'):
             raise ExtractorError('Login succeeded but did not set etp_rt cookie')
 
-    # Beta-specific, but needed for redirects
-    def _get_beta_embedded_json(self, webpage, display_id):
+    def _get_embedded_json(self, webpage, display_id):
         initial_state = self._parse_json(self._search_regex(
             r'__INITIAL_STATE__\s*=\s*({.+?})\s*;', webpage, 'initial state'), display_id)
         app_config = self._parse_json(self._search_regex(
             r'__APP_CONFIG__\s*=\s*({.+?})\s*;', webpage, 'app config'), display_id)
         return initial_state, app_config
 
-    def _redirect_to_beta(self, webpage, iekey, video_id):
-        if not self._get_cookies(self._LOGIN_URL).get('etp_rt'):
-            raise ExtractorError('Received a beta page from non-beta url when not logged in.')
-        initial_state, app_config = self._get_beta_embedded_json(webpage, video_id)
-        url = app_config['baseSiteUrl'] + initial_state['router']['locations']['current']['pathname']
-        self.to_screen(f'{video_id}: Redirected to beta site - {url}')
-        return self.url_result(f'{url}', iekey, video_id)
-
-    @staticmethod
-    def _add_skip_wall(url):
-        parsed_url = compat_urlparse.urlparse(url)
-        qs = compat_urlparse.parse_qs(parsed_url.query)
-        # Always force skip_wall to bypass maturity wall, namely 18+ confirmation message:
-        # > This content may be inappropriate for some people.
-        # > Are you sure you want to continue?
-        # since it's not disabled by default in crunchyroll account's settings.
-        # See https://github.com/ytdl-org/youtube-dl/issues/7202.
-        qs['skip_wall'] = ['1']
-        return compat_urlparse.urlunparse(
-            parsed_url._replace(query=compat_urllib_parse_urlencode(qs, True)))
-
-
-class CrunchyrollIE(CrunchyrollBaseIE, VRVBaseIE):
-    IE_NAME = 'crunchyroll'
-    _VALID_URL = r'''(?x)
-        https?://(?:(?P<prefix>www|m)\.)?(?P<url>
-            crunchyroll\.(?:com|fr)/(?:
-                media(?:-|/\?id=)|
-                (?!series/|watch/)(?:[^/]+/){1,2}[^/?&#]*?
-            )(?P<id>[0-9]+)
-        )(?:[/?&#]|$)'''
-
-    _TESTS = [{
-        'url': 'http://www.crunchyroll.com/wanna-be-the-strongest-in-the-world/episode-1-an-idol-wrestler-is-born-645513',
-        'info_dict': {
-            'id': '645513',
-            'ext': 'mp4',
-            'title': 'Wanna be the Strongest in the World Episode 1 – An Idol-Wrestler is Born!',
-            'description': 'md5:2d17137920c64f2f49981a7797d275ef',
-            'thumbnail': r're:^https?://.*\.jpg$',
-            'uploader': 'Yomiuri Telecasting Corporation (YTV)',
-            'upload_date': '20131013',
-            'url': 're:(?!.*&amp)',
-        },
-        'params': {
-            # rtmp
-            'skip_download': True,
-        },
-        'skip': 'Video gone',
-    }, {
-        'url': 'http://www.crunchyroll.com/media-589804/culture-japan-1',
-        'info_dict': {
-            'id': '589804',
-            'ext': 'flv',
-            'title': 'Culture Japan Episode 1 – Rebuilding Japan after the 3.11',
-            'description': 'md5:2fbc01f90b87e8e9137296f37b461c12',
-            'thumbnail': r're:^https?://.*\.jpg$',
-            'uploader': 'Danny Choo Network',
-            'upload_date': '20120213',
-        },
-        'params': {
-            # rtmp
-            'skip_download': True,
-        },
-        'skip': 'Video gone',
-    }, {
-        'url': 'http://www.crunchyroll.com/rezero-starting-life-in-another-world-/episode-5-the-morning-of-our-promise-is-still-distant-702409',
-        'info_dict': {
-            'id': '702409',
-            'ext': 'mp4',
-            'title': compat_str,
-            'description': compat_str,
-            'thumbnail': r're:^https?://.*\.jpg$',
-            'uploader': 'Re:Zero Partners',
-            'timestamp': 1462098900,
-            'upload_date': '20160501',
-        },
-        'params': {
-            # m3u8 download
-            'skip_download': True,
-        },
-    }, {
-        'url': 'http://www.crunchyroll.com/konosuba-gods-blessing-on-this-wonderful-world/episode-1-give-me-deliverance-from-this-judicial-injustice-727589',
-        'info_dict': {
-            'id': '727589',
-            'ext': 'mp4',
-            'title': compat_str,
-            'description': compat_str,
-            'thumbnail': r're:^https?://.*\.jpg$',
-            'uploader': 'Kadokawa Pictures Inc.',
-            'timestamp': 1484130900,
-            'upload_date': '20170111',
-            'series': compat_str,
-            'season': "KONOSUBA -God's blessing on this wonderful world! 2",
-            'season_number': 2,
-            'episode': 'Give Me Deliverance From This Judicial Injustice!',
-            'episode_number': 1,
-        },
-        'params': {
-            # m3u8 download
-            'skip_download': True,
-        },
-    }, {
-        'url': 'http://www.crunchyroll.fr/girl-friend-beta/episode-11-goodbye-la-mode-661697',
-        'only_matching': True,
-    }, {
-        # geo-restricted (US), 18+ maturity wall, non-premium available
-        'url': 'http://www.crunchyroll.com/cosplay-complex-ova/episode-1-the-birth-of-the-cosplay-club-565617',
-        'only_matching': True,
-    }, {
-        # A description with double quotes
-        'url': 'http://www.crunchyroll.com/11eyes/episode-1-piros-jszaka-red-night-535080',
-        'info_dict': {
-            'id': '535080',
-            'ext': 'mp4',
-            'title': compat_str,
-            'description': compat_str,
-            'uploader': 'Marvelous AQL Inc.',
-            'timestamp': 1255512600,
-            'upload_date': '20091014',
-        },
-        'params': {
-            # Just test metadata extraction
-            'skip_download': True,
-        },
-    }, {
-        # make sure we can extract an uploader name that's not a link
-        'url': 'http://www.crunchyroll.com/hakuoki-reimeiroku/episode-1-dawn-of-the-divine-warriors-606899',
-        'info_dict': {
-            'id': '606899',
-            'ext': 'mp4',
-            'title': 'Hakuoki Reimeiroku Episode 1 – Dawn of the Divine Warriors',
-            'description': 'Ryunosuke was left to die, but Serizawa-san asked him a simple question "Do you want to live?"',
-            'uploader': 'Geneon Entertainment',
-            'upload_date': '20120717',
-        },
-        'params': {
-            # just test metadata extraction
-            'skip_download': True,
-        },
-        'skip': 'Video gone',
-    }, {
-        # A video with a vastly different season name compared to the series name
-        'url': 'http://www.crunchyroll.com/nyarko-san-another-crawling-chaos/episode-1-test-590532',
-        'info_dict': {
-            'id': '590532',
-            'ext': 'mp4',
-            'title': compat_str,
-            'description': compat_str,
-            'uploader': 'TV TOKYO',
-            'timestamp': 1330956000,
-            'upload_date': '20120305',
-            'series': 'Nyarko-san: Another Crawling Chaos',
-            'season': 'Haiyoru! Nyaruani (ONA)',
-        },
-        'params': {
-            # Just test metadata extraction
-            'skip_download': True,
-        },
-    }, {
-        'url': 'http://www.crunchyroll.com/media-723735',
-        'only_matching': True,
-    }, {
-        'url': 'https://www.crunchyroll.com/en-gb/mob-psycho-100/episode-2-urban-legends-encountering-rumors-780921',
-        'only_matching': True,
-    }]
-
-    _FORMAT_IDS = {
-        '360': ('60', '106'),
-        '480': ('61', '106'),
-        '720': ('62', '106'),
-        '1080': ('80', '108'),
-    }
-
-    def _download_webpage(self, url_or_request, *args, **kwargs):
-        request = (url_or_request if isinstance(url_or_request, urllib.request.Request)
-                   else sanitized_Request(url_or_request))
-        # Accept-Language must be set explicitly to accept any language to avoid issues
-        # similar to https://github.com/ytdl-org/youtube-dl/issues/6797.
-        # Along with IP address Crunchyroll uses Accept-Language to guess whether georestriction
-        # should be imposed or not (from what I can see it just takes the first language
-        # ignoring the priority and requires it to correspond the IP). By the way this causes
-        # Crunchyroll to not work in georestriction cases in some browsers that don't place
-        # the locale lang first in header. However allowing any language seems to workaround the issue.
-        request.add_header('Accept-Language', '*')
-        return super(CrunchyrollBaseIE, self)._download_webpage(request, *args, **kwargs)
-
-    def _decrypt_subtitles(self, data, iv, id):
-        data = bytes_to_intlist(compat_b64decode(data))
-        iv = bytes_to_intlist(compat_b64decode(iv))
-        id = int(id)
-
-        def obfuscate_key_aux(count, modulo, start):
-            output = list(start)
-            for _ in range(count):
-                output.append(output[-1] + output[-2])
-            # cut off start values
-            output = output[2:]
-            output = list(map(lambda x: x % modulo + 33, output))
-            return output
-
-        def obfuscate_key(key):
-            num1 = int(floor(pow(2, 25) * sqrt(6.9)))
-            num2 = (num1 ^ key) << 5
-            num3 = key ^ num1
-            num4 = num3 ^ (num3 >> 3) ^ num2
-            prefix = intlist_to_bytes(obfuscate_key_aux(20, 97, (1, 2)))
-            shaHash = bytes_to_intlist(sha1(prefix + str(num4).encode('ascii')).digest())
-            # Extend 160 Bit hash to 256 Bit
-            return shaHash + [0] * 12
-
-        key = obfuscate_key(id)
-
-        decrypted_data = intlist_to_bytes(aes_cbc_decrypt(data, key, iv))
-        return zlib.decompress(decrypted_data)
-
-    def _convert_subtitles_to_srt(self, sub_root):
-        output = ''
-
-        for i, event in enumerate(sub_root.findall('./events/event'), 1):
-            start = event.attrib['start'].replace('.', ',')
-            end = event.attrib['end'].replace('.', ',')
-            text = event.attrib['text'].replace('\\N', '\n')
-            output += '%d\n%s --> %s\n%s\n\n' % (i, start, end, text)
-        return output
-
-    def _convert_subtitles_to_ass(self, sub_root):
-        output = ''
-
-        def ass_bool(strvalue):
-            assvalue = '0'
-            if strvalue == '1':
-                assvalue = '-1'
-            return assvalue
-
-        output = '[Script Info]\n'
-        output += 'Title: %s\n' % sub_root.attrib['title']
-        output += 'ScriptType: v4.00+\n'
-        output += 'WrapStyle: %s\n' % sub_root.attrib['wrap_style']
-        output += 'PlayResX: %s\n' % sub_root.attrib['play_res_x']
-        output += 'PlayResY: %s\n' % sub_root.attrib['play_res_y']
-        output += """
-[V4+ Styles]
-Format: Name, Fontname, Fontsize, PrimaryColour, SecondaryColour, OutlineColour, BackColour, Bold, Italic, Underline, StrikeOut, ScaleX, ScaleY, Spacing, Angle, BorderStyle, Outline, Shadow, Alignment, MarginL, MarginR, MarginV, Encoding
-"""
-        for style in sub_root.findall('./styles/style'):
-            output += 'Style: ' + style.attrib['name']
-            output += ',' + style.attrib['font_name']
-            output += ',' + style.attrib['font_size']
-            output += ',' + style.attrib['primary_colour']
-            output += ',' + style.attrib['secondary_colour']
-            output += ',' + style.attrib['outline_colour']
-            output += ',' + style.attrib['back_colour']
-            output += ',' + ass_bool(style.attrib['bold'])
-            output += ',' + ass_bool(style.attrib['italic'])
-            output += ',' + ass_bool(style.attrib['underline'])
-            output += ',' + ass_bool(style.attrib['strikeout'])
-            output += ',' + style.attrib['scale_x']
-            output += ',' + style.attrib['scale_y']
-            output += ',' + style.attrib['spacing']
-            output += ',' + style.attrib['angle']
-            output += ',' + style.attrib['border_style']
-            output += ',' + style.attrib['outline']
-            output += ',' + style.attrib['shadow']
-            output += ',' + style.attrib['alignment']
-            output += ',' + style.attrib['margin_l']
-            output += ',' + style.attrib['margin_r']
-            output += ',' + style.attrib['margin_v']
-            output += ',' + style.attrib['encoding']
-            output += '\n'
-
-        output += """
-[Events]
-Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
-"""
-        for event in sub_root.findall('./events/event'):
-            output += 'Dialogue: 0'
-            output += ',' + event.attrib['start']
-            output += ',' + event.attrib['end']
-            output += ',' + event.attrib['style']
-            output += ',' + event.attrib['name']
-            output += ',' + event.attrib['margin_l']
-            output += ',' + event.attrib['margin_r']
-            output += ',' + event.attrib['margin_v']
-            output += ',' + event.attrib['effect']
-            output += ',' + event.attrib['text']
-            output += '\n'
-
-        return output
-
-    def _extract_subtitles(self, subtitle):
-        sub_root = compat_etree_fromstring(subtitle)
-        return [{
-            'ext': 'srt',
-            'data': self._convert_subtitles_to_srt(sub_root),
-        }, {
-            'ext': 'ass',
-            'data': self._convert_subtitles_to_ass(sub_root),
-        }]
-
-    def _get_subtitles(self, video_id, webpage):
-        subtitles = {}
-        for sub_id, sub_name in re.findall(r'\bssid=([0-9]+)"[^>]+?\btitle="([^"]+)', webpage):
-            sub_doc = self._call_rpc_api(
-                'Subtitle_GetXml', video_id,
-                'Downloading subtitles for ' + sub_name, data={
-                    'subtitle_script_id': sub_id,
-                })
-            if not isinstance(sub_doc, xml.etree.ElementTree.Element):
-                continue
-            sid = sub_doc.get('id')
-            iv = xpath_text(sub_doc, 'iv', 'subtitle iv')
-            data = xpath_text(sub_doc, 'data', 'subtitle data')
-            if not sid or not iv or not data:
-                continue
-            subtitle = self._decrypt_subtitles(data, iv, sid).decode('utf-8')
-            lang_code = self._search_regex(r'lang_code=["\']([^"\']+)', subtitle, 'subtitle_lang_code', fatal=False)
-            if not lang_code:
-                continue
-            subtitles[lang_code] = self._extract_subtitles(subtitle)
-        return subtitles
-
-    def _real_extract(self, url):
-        mobj = self._match_valid_url(url)
-        video_id = mobj.group('id')
-
-        if mobj.group('prefix') == 'm':
-            mobile_webpage = self._download_webpage(url, video_id, 'Downloading mobile webpage')
-            webpage_url = self._search_regex(r'<link rel="canonical" href="([^"]+)" />', mobile_webpage, 'webpage_url')
-        else:
-            webpage_url = 'http://www.' + mobj.group('url')
-
-        webpage = self._download_webpage(
-            self._add_skip_wall(webpage_url), video_id,
-            headers=self.geo_verification_headers())
-        if re.search(r'<div id="preload-data">', webpage):
-            return self._redirect_to_beta(webpage, CrunchyrollBetaIE.ie_key(), video_id)
-        note_m = self._html_search_regex(
-            r'<div class="showmedia-trailer-notice">(.+?)</div>',
-            webpage, 'trailer-notice', default='')
-        if note_m:
-            raise ExtractorError(note_m, expected=True)
-
-        mobj = re.search(r'Page\.messaging_box_controller\.addItems\(\[(?P<msg>{.+?})\]\)', webpage)
-        if mobj:
-            msg = json.loads(mobj.group('msg'))
-            if msg.get('type') == 'error':
-                raise ExtractorError('crunchyroll returned error: %s' % msg['message_body'], expected=True)
-
-        if 'To view this, please log in to verify you are 18 or older.' in webpage:
-            self.raise_login_required()
-
-        media = self._parse_json(self._search_regex(
-            r'vilos\.config\.media\s*=\s*({.+?});',
-            webpage, 'vilos media', default='{}'), video_id)
-        media_metadata = media.get('metadata') or {}
-
-        language = self._search_regex(
-            r'(?:vilos\.config\.player\.language|LOCALE)\s*=\s*(["\'])(?P<lang>(?:(?!\1).)+)\1',
-            webpage, 'language', default=None, group='lang')
-
-        video_title = self._html_search_regex(
-            (r'(?s)<h1[^>]*>((?:(?!<h1).)*?<(?:span[^>]+itemprop=["\']title["\']|meta[^>]+itemprop=["\']position["\'])[^>]*>(?:(?!<h1).)+?)</h1>',
-             r'<title>(.+?),\s+-\s+.+? Crunchyroll'),
-            webpage, 'video_title', default=None)
-        if not video_title:
-            video_title = re.sub(r'^Watch\s+', '', self._og_search_description(webpage))
-        video_title = re.sub(r' {2,}', ' ', video_title)
-        video_description = (self._parse_json(self._html_search_regex(
-            r'<script[^>]*>\s*.+?\[media_id=%s\].+?({.+?"description"\s*:.+?})\);' % video_id,
-            webpage, 'description', default='{}'), video_id) or media_metadata).get('description')
-
-        thumbnails = []
-        thumbnail_url = (self._parse_json(self._html_search_regex(
-            r'<script type="application\/ld\+json">\n\s*(.+?)<\/script>',
-            webpage, 'thumbnail_url', default='{}'), video_id)).get('image')
-        if thumbnail_url:
-            thumbnails.append({
-                'url': thumbnail_url,
-                'width': 1920,
-                'height': 1080
-            })
-
-        if video_description:
-            video_description = lowercase_escape(video_description.replace(r'\r\n', '\n'))
-        video_uploader = self._html_search_regex(
-            # try looking for both an uploader that's a link and one that's not
-            [r'<a[^>]+href="/publisher/[^"]+"[^>]*>([^<]+)</a>', r'<div>\s*Publisher:\s*<span>\s*(.+?)\s*</span>\s*</div>'],
-            webpage, 'video_uploader', default=False)
-
-        requested_languages = self._configuration_arg('language')
-        requested_hardsubs = [('' if val == 'none' else val) for val in self._configuration_arg('hardsub')]
-        language_preference = qualities((requested_languages or [language or ''])[::-1])
-        hardsub_preference = qualities((requested_hardsubs or ['', language or ''])[::-1])
-
-        formats = []
-        for stream in media.get('streams', []):
-            audio_lang = stream.get('audio_lang') or ''
-            hardsub_lang = stream.get('hardsub_lang') or ''
-            if (requested_languages and audio_lang.lower() not in requested_languages
-                    or requested_hardsubs and hardsub_lang.lower() not in requested_hardsubs):
-                continue
-            vrv_formats = self._extract_vrv_formats(
-                stream.get('url'), video_id, stream.get('format'),
-                audio_lang, hardsub_lang)
-            for f in vrv_formats:
-                f['language_preference'] = language_preference(audio_lang)
-                f['quality'] = hardsub_preference(hardsub_lang)
-            formats.extend(vrv_formats)
-        if not formats:
-            available_fmts = []
-            for a, fmt in re.findall(r'(<a[^>]+token=["\']showmedia\.([0-9]{3,4})p["\'][^>]+>)', webpage):
-                attrs = extract_attributes(a)
-                href = attrs.get('href')
-                if href and '/freetrial' in href:
-                    continue
-                available_fmts.append(fmt)
-            if not available_fmts:
-                for p in (r'token=["\']showmedia\.([0-9]{3,4})p"', r'showmedia\.([0-9]{3,4})p'):
-                    available_fmts = re.findall(p, webpage)
-                    if available_fmts:
-                        break
-            if not available_fmts:
-                available_fmts = self._FORMAT_IDS.keys()
-            video_encode_ids = []
-
-            for fmt in available_fmts:
-                stream_quality, stream_format = self._FORMAT_IDS[fmt]
-                video_format = fmt + 'p'
-                stream_infos = []
-                streamdata = self._call_rpc_api(
-                    'VideoPlayer_GetStandardConfig', video_id,
-                    'Downloading media info for %s' % video_format, data={
-                        'media_id': video_id,
-                        'video_format': stream_format,
-                        'video_quality': stream_quality,
-                        'current_page': url,
-                    })
-                if isinstance(streamdata, xml.etree.ElementTree.Element):
-                    stream_info = streamdata.find('./{default}preload/stream_info')
-                    if stream_info is not None:
-                        stream_infos.append(stream_info)
-                stream_info = self._call_rpc_api(
-                    'VideoEncode_GetStreamInfo', video_id,
-                    'Downloading stream info for %s' % video_format, data={
-                        'media_id': video_id,
-                        'video_format': stream_format,
-                        'video_encode_quality': stream_quality,
-                    })
-                if isinstance(stream_info, xml.etree.ElementTree.Element):
-                    stream_infos.append(stream_info)
-                for stream_info in stream_infos:
-                    video_encode_id = xpath_text(stream_info, './video_encode_id')
-                    if video_encode_id in video_encode_ids:
-                        continue
-                    video_encode_ids.append(video_encode_id)
-
-                    video_file = xpath_text(stream_info, './file')
-                    if not video_file:
-                        continue
-                    if video_file.startswith('http'):
-                        formats.extend(self._extract_m3u8_formats(
-                            video_file, video_id, 'mp4', entry_protocol='m3u8_native',
-                            m3u8_id='hls', fatal=False))
-                        continue
-
-                    video_url = xpath_text(stream_info, './host')
-                    if not video_url:
-                        continue
-                    metadata = stream_info.find('./metadata')
-                    format_info = {
-                        'format': video_format,
-                        'height': int_or_none(xpath_text(metadata, './height')),
-                        'width': int_or_none(xpath_text(metadata, './width')),
-                    }
-
-                    if '.fplive.net/' in video_url:
-                        video_url = re.sub(r'^rtmpe?://', 'http://', video_url.strip())
-                        parsed_video_url = compat_urlparse.urlparse(video_url)
-                        direct_video_url = compat_urlparse.urlunparse(parsed_video_url._replace(
-                            netloc='v.lvlt.crcdn.net',
-                            path='%s/%s' % (remove_end(parsed_video_url.path, '/'), video_file.split(':')[-1])))
-                        if self._is_valid_url(direct_video_url, video_id, video_format):
-                            format_info.update({
-                                'format_id': 'http-' + video_format,
-                                'url': direct_video_url,
-                            })
-                            formats.append(format_info)
-                            continue
-
-                    format_info.update({
-                        'format_id': 'rtmp-' + video_format,
-                        'url': video_url,
-                        'play_path': video_file,
-                        'ext': 'flv',
-                    })
-                    formats.append(format_info)
-        self._sort_formats(formats)
-
-        metadata = self._call_rpc_api(
-            'VideoPlayer_GetMediaMetadata', video_id,
-            note='Downloading media info', data={
-                'media_id': video_id,
-            })
-
-        subtitles = {}
-        for subtitle in media.get('subtitles', []):
-            subtitle_url = subtitle.get('url')
-            if not subtitle_url:
-                continue
-            subtitles.setdefault(subtitle.get('language', 'enUS'), []).append({
-                'url': subtitle_url,
-                'ext': subtitle.get('format', 'ass'),
-            })
-        if not subtitles:
-            subtitles = self.extract_subtitles(video_id, webpage)
-
-        # webpage provide more accurate data than series_title from XML
-        series = self._html_search_regex(
-            r'(?s)<h\d[^>]+\bid=["\']showmedia_about_episode_num[^>]+>(.+?)</h\d',
-            webpage, 'series', fatal=False)
-
-        season = episode = episode_number = duration = None
-
-        if isinstance(metadata, xml.etree.ElementTree.Element):
-            season = xpath_text(metadata, 'series_title')
-            episode = xpath_text(metadata, 'episode_title')
-            episode_number = int_or_none(xpath_text(metadata, 'episode_number'))
-            duration = float_or_none(media_metadata.get('duration'), 1000)
-
-        if not episode:
-            episode = media_metadata.get('title')
-        if not episode_number:
-            episode_number = int_or_none(media_metadata.get('episode_number'))
-        thumbnail_url = try_get(media, lambda x: x['thumbnail']['url'])
-        if thumbnail_url:
-            thumbnails.append({
-                'url': thumbnail_url,
-                'width': 640,
-                'height': 360
-            })
-
-        season_number = int_or_none(self._search_regex(
-            r'(?s)<h\d[^>]+id=["\']showmedia_about_episode_num[^>]+>.+?</h\d>\s*<h4>\s*Season (\d+)',
-            webpage, 'season number', default=None))
-
-        info = self._search_json_ld(webpage, video_id, default={})
-
-        return merge_dicts({
-            'id': video_id,
-            'title': video_title,
-            'description': video_description,
-            'duration': duration,
-            'thumbnails': thumbnails,
-            'uploader': video_uploader,
-            'series': series,
-            'season': season,
-            'season_number': season_number,
-            'episode': episode,
-            'episode_number': episode_number,
-            'subtitles': subtitles,
-            'formats': formats,
-        }, info)
-
-
-class CrunchyrollShowPlaylistIE(CrunchyrollBaseIE):
-    IE_NAME = 'crunchyroll:playlist'
-    _VALID_URL = r'https?://(?:(?P<prefix>www|m)\.)?(?P<url>crunchyroll\.com/(?:\w{2}(?:-\w{2})?/)?(?!(?:news|anime-news|library|forum|launchcalendar|lineup|store|comics|freetrial|login|media-\d+))(?P<id>[\w\-]+))/?(?:\?|$)'
-
-    _TESTS = [{
-        'url': 'https://www.crunchyroll.com/a-bridge-to-the-starry-skies-hoshizora-e-kakaru-hashi',
-        'info_dict': {
-            'id': 'a-bridge-to-the-starry-skies-hoshizora-e-kakaru-hashi',
-            'title': 'A Bridge to the Starry Skies - Hoshizora e Kakaru Hashi'
-        },
-        'playlist_count': 13,
-    }, {
-        # geo-restricted (US), 18+ maturity wall, non-premium available
-        'url': 'http://www.crunchyroll.com/cosplay-complex-ova',
-        'info_dict': {
-            'id': 'cosplay-complex-ova',
-            'title': 'Cosplay Complex OVA'
-        },
-        'playlist_count': 3,
-        'skip': 'Georestricted',
-    }, {
-        # geo-restricted (US), 18+ maturity wall, non-premium will be available since 2015.11.14
-        'url': 'http://www.crunchyroll.com/ladies-versus-butlers?skip_wall=1',
-        'only_matching': True,
-    }, {
-        'url': 'http://www.crunchyroll.com/fr/ladies-versus-butlers',
-        'only_matching': True,
-    }]
-
-    def _real_extract(self, url):
-        show_id = self._match_id(url)
-
-        webpage = self._download_webpage(
-            # https:// gives a 403, but http:// does not
-            self._add_skip_wall(url).replace('https://', 'http://'), show_id,
-            headers=self.geo_verification_headers())
-        if re.search(r'<div id="preload-data">', webpage):
-            return self._redirect_to_beta(webpage, CrunchyrollBetaShowIE.ie_key(), show_id)
-        title = self._html_search_meta('name', webpage, default=None)
-
-        episode_re = r'<li id="showview_videos_media_(\d+)"[^>]+>.*?<a href="([^"]+)"'
-        season_re = r'<a [^>]+season-dropdown[^>]+>([^<]+)'
-        paths = re.findall(f'(?s){episode_re}|{season_re}', webpage)
-
-        entries, current_season = [], None
-        for ep_id, ep, season in paths:
-            if season:
-                current_season = season
-                continue
-            entries.append(self.url_result(
-                f'http://www.crunchyroll.com{ep}', CrunchyrollIE.ie_key(), ep_id, season=current_season))
-
-        return {
-            '_type': 'playlist',
-            'id': show_id,
-            'title': title,
-            'entries': reversed(entries),
-        }
-
-
-class CrunchyrollBetaBaseIE(CrunchyrollBaseIE):
-    params = None
-
     def _get_params(self, lang):
-        if not CrunchyrollBetaBaseIE.params:
-            if self._get_cookies(f'https://beta.crunchyroll.com/{lang}').get('etp_rt'):
+        if not CrunchyrollBaseIE.params:
+            if self._get_cookies(f'https://www.crunchyroll.com/{lang}').get('etp_rt'):
                 grant_type, key = 'etp_rt_cookie', 'accountAuthClientId'
             else:
                 grant_type, key = 'client_id', 'anonClientId'
 
-            initial_state, app_config = self._get_beta_embedded_json(self._download_webpage(
-                f'https://beta.crunchyroll.com/{lang}', None, note='Retrieving main page'), None)
-            api_domain = app_config['cxApiParams']['apiDomain']
+            initial_state, app_config = self._get_embedded_json(self._download_webpage(
+                f'https://www.crunchyroll.com/{lang}', None, note='Retrieving main page'), None)
+            api_domain = app_config['cxApiParams']['apiDomain'].replace('beta.crunchyroll.com', 'www.crunchyroll.com')
 
             auth_response = self._download_json(
                 f'{api_domain}/auth/v1/token', None, note=f'Authenticating with grant_type={grant_type}',
@@ -739,7 +77,7 @@ def _get_params(self, lang):
                 headers={
                     'Authorization': auth_response['token_type'] + ' ' + auth_response['access_token']
                 })
-            cms = traverse_obj(policy_response, 'cms_beta', 'cms')
+            cms = policy_response.get('cms_web')
             bucket = cms['bucket']
             params = {
                 'Policy': cms['policy'],
@@ -749,19 +87,19 @@ def _get_params(self, lang):
             locale = traverse_obj(initial_state, ('localization', 'locale'))
             if locale:
                 params['locale'] = locale
-            CrunchyrollBetaBaseIE.params = (api_domain, bucket, params)
-        return CrunchyrollBetaBaseIE.params
+            CrunchyrollBaseIE.params = (api_domain, bucket, params)
+        return CrunchyrollBaseIE.params
 
 
-class CrunchyrollBetaIE(CrunchyrollBetaBaseIE):
-    IE_NAME = 'crunchyroll:beta'
+class CrunchyrollBetaIE(CrunchyrollBaseIE):
+    IE_NAME = 'crunchyroll'
     _VALID_URL = r'''(?x)
-        https?://beta\.crunchyroll\.com/
+        https?://(?:beta|www)\.crunchyroll\.com/
         (?P<lang>(?:\w{2}(?:-\w{2})?/)?)
         watch/(?P<id>\w+)
         (?:/(?P<display_id>[\w-]+))?/?(?:[?#]|$)'''
     _TESTS = [{
-        'url': 'https://beta.crunchyroll.com/watch/GY2P1Q98Y/to-the-future',
+        'url': 'https://www.crunchyroll.com/watch/GY2P1Q98Y/to-the-future',
         'info_dict': {
             'id': 'GY2P1Q98Y',
             'ext': 'mp4',
@@ -777,11 +115,11 @@ class CrunchyrollBetaIE(CrunchyrollBetaBaseIE):
             'season_number': 1,
             'episode': 'To the Future',
             'episode_number': 73,
-            'thumbnail': r're:^https://beta.crunchyroll.com/imgsrv/.*\.jpeg$',
+            'thumbnail': r're:^https://www.crunchyroll.com/imgsrv/.*\.jpeg$',
         },
         'params': {'skip_download': 'm3u8', 'format': 'all[format_id~=hardsub]'},
     }, {
-        'url': 'https://beta.crunchyroll.com/watch/GYE5WKQGR',
+        'url': 'https://www.crunchyroll.com/watch/GYE5WKQGR',
         'info_dict': {
             'id': 'GYE5WKQGR',
             'ext': 'mp4',
@@ -797,12 +135,12 @@ class CrunchyrollBetaIE(CrunchyrollBetaBaseIE):
             'season_number': 1,
             'episode': 'Porter Robinson presents Shelter the Animation',
             'episode_number': 0,
-            'thumbnail': r're:^https://beta.crunchyroll.com/imgsrv/.*\.jpeg$',
+            'thumbnail': r're:^https://www.crunchyroll.com/imgsrv/.*\.jpeg$',
         },
         'params': {'skip_download': True},
         'skip': 'Video is Premium only',
     }, {
-        'url': 'https://beta.crunchyroll.com/watch/GY2P1Q98Y',
+        'url': 'https://www.crunchyroll.com/watch/GY2P1Q98Y',
         'only_matching': True,
     }, {
         'url': 'https://beta.crunchyroll.com/pt-br/watch/G8WUN8VKP/the-ruler-of-conspiracy',
@@ -901,15 +239,15 @@ def _real_extract(self, url):
         }
 
 
-class CrunchyrollBetaShowIE(CrunchyrollBetaBaseIE):
-    IE_NAME = 'crunchyroll:playlist:beta'
+class CrunchyrollBetaShowIE(CrunchyrollBaseIE):
+    IE_NAME = 'crunchyroll:playlist'
     _VALID_URL = r'''(?x)
-        https?://beta\.crunchyroll\.com/
+        https?://(?:beta|www)\.crunchyroll\.com/
         (?P<lang>(?:\w{2}(?:-\w{2})?/)?)
         series/(?P<id>\w+)
         (?:/(?P<display_id>[\w-]+))?/?(?:[?#]|$)'''
     _TESTS = [{
-        'url': 'https://beta.crunchyroll.com/series/GY19NQ2QR/Girl-Friend-BETA',
+        'url': 'https://www.crunchyroll.com/series/GY19NQ2QR/Girl-Friend-BETA',
         'info_dict': {
             'id': 'GY19NQ2QR',
             'title': 'Girl Friend BETA',
@@ -942,7 +280,7 @@ def entries():
                     episode_display_id = episode['slug_title']
                     yield {
                         '_type': 'url',
-                        'url': f'https://beta.crunchyroll.com/{lang}watch/{episode_id}/{episode_display_id}',
+                        'url': f'https://www.crunchyroll.com/{lang}watch/{episode_id}/{episode_display_id}',
                         'ie_key': CrunchyrollBetaIE.ie_key(),
                         'id': episode_id,
                         'title': '%s Episode %s – %s' % (episode.get('season_title'), episode.get('episode'), episode.get('title')),

yt_dlp/extractor/deuxm.py

@@ -0,0 +1,76 @@
+from .common import InfoExtractor
+from ..utils import url_or_none
+
+
+class DeuxMIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?2m\.ma/[^/]+/replay/single/(?P<id>([\w.]{1,24})+)'
+
+    _TESTS = [{
+        'url': 'https://2m.ma/fr/replay/single/6351d439b15e1a613b3debe8',
+        'md5': '5f761f04c9d686e553b685134dca5d32',
+        'info_dict': {
+            'id': '6351d439b15e1a613b3debe8',
+            'ext': 'mp4',
+            'title': 'Grand Angle : Jeudi 20 Octobre 2022',
+            'thumbnail': r're:^https?://2msoread-ww.amagi.tv/mediasfiles/videos/images/.*\.png$'
+        }
+    }, {
+        'url': 'https://2m.ma/fr/replay/single/635c0aeab4eec832622356da',
+        'md5': 'ad6af2f5e4d5b2ad2194a84b6e890b4c',
+        'info_dict': {
+            'id': '635c0aeab4eec832622356da',
+            'ext': 'mp4',
+            'title': 'Journal  Amazigh : Vendredi 28 Octobre 2022',
+            'thumbnail': r're:^https?://2msoread-ww.amagi.tv/mediasfiles/videos/images/.*\.png$'
+        }
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        video = self._download_json(
+            f'https://2m.ma/api/watchDetail/{video_id}', video_id)['response']['News']
+        return {
+            'id': video_id,
+            'title': video.get('titre'),
+            'url': video['url'],
+            'description': video.get('description'),
+            'thumbnail': url_or_none(video.get('image')),
+        }
+
+
+class DeuxMNewsIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?2m\.ma/(?P<lang>\w+)/news/(?P<id>[^/#?]+)'
+
+    _TESTS = [{
+        'url': 'https://2m.ma/fr/news/Kan-Ya-Mkan-d%C3%A9poussi%C3%A8re-l-histoire-du-phare-du-Cap-Beddouza-20221028',
+        'md5': '43d5e693a53fa0b71e8a5204c7d4542a',
+        'info_dict': {
+            'id': '635c5d1233b83834e35b282e',
+            'ext': 'mp4',
+            'title': 'Kan Ya Mkan d\u00e9poussi\u00e8re l\u2019histoire du phare du Cap Beddouza',
+            'description': 'md5:99dcf29b82f1d7f2a4acafed1d487527',
+            'thumbnail': r're:^https?://2msoread-ww.amagi.tv/mediasfiles/videos/images/.*\.png$'
+        }
+    }, {
+        'url': 'https://2m.ma/fr/news/Interview-Casablanca-hors-des-sentiers-battus-avec-Abderrahim-KASSOU-Replay--20221017',
+        'md5': '7aca29f02230945ef635eb8290283c0c',
+        'info_dict': {
+            'id': '634d9e108b70d40bc51a844b',
+            'ext': 'mp4',
+            'title': 'Interview: Casablanca hors des sentiers battus avec Abderrahim KASSOU (Replay) ',
+            'description': 'md5:3b8e78111de9fcc6ef7f7dd6cff2430c',
+            'thumbnail': r're:^https?://2msoread-ww.amagi.tv/mediasfiles/videos/images/.*\.png$'
+        }
+    }]
+
+    def _real_extract(self, url):
+        article_name, lang = self._match_valid_url(url).group('id', 'lang')
+        video = self._download_json(
+            f'https://2m.ma/api/articlesByUrl?lang={lang}&url=/news/{article_name}', article_name)['response']['article'][0]
+        return {
+            'id': video['id'],
+            'title': video.get('title'),
+            'url': video['image'][0],
+            'description': video.get('content'),
+            'thumbnail': url_or_none(video.get('cover')),
+        }

yt_dlp/extractor/epoch.py

@@ -1,4 +1,5 @@
 from .common import InfoExtractor
+from ..utils import extract_attributes, get_element_html_by_id
 
 
 class EpochIE(InfoExtractor):
@@ -28,13 +29,21 @@ class EpochIE(InfoExtractor):
                 'title': 'Kash Patel: A ‘6-Year-Saga’ of Government Corruption, From Russiagate to Mar-a-Lago',
             }
         },
+        {
+            'url': 'https://www.theepochtimes.com/dick-morris-discusses-his-book-the-return-trumps-big-2024-comeback_4819205.html',
+            'info_dict': {
+                'id': '9489f994-2a20-4812-b233-ac0e5c345632',
+                'ext': 'mp4',
+                'title': 'Dick Morris Discusses His Book ‘The Return: Trump’s Big 2024 Comeback’',
+            }
+        },
     ]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
 
-        youmaker_video_id = self._search_regex(r'data-trailer="[\w-]+" data-id="([\w-]+)"', webpage, 'url')
+        youmaker_video_id = extract_attributes(get_element_html_by_id('videobox', webpage))['data-id']
         formats, subtitles = self._extract_m3u8_formats_and_subtitles(
             f'http://vs1.youmaker.com/assets/{youmaker_video_id}/playlist.m3u8', video_id, 'mp4', m3u8_id='hls')
 

yt_dlp/extractor/foxnews.py

@@ -75,6 +75,29 @@ def _real_extract(self, url):
         return info
 
 
+class FoxNewsVideoIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?foxnews\.com/video/(?P<id>\d+)'
+    _TESTS = [{
+        'url': 'https://www.foxnews.com/video/6313058664112',
+        'info_dict': {
+            'id': '6313058664112',
+            'ext': 'mp4',
+            'thumbnail': r're:https://.+/1280x720/match/image\.jpg',
+            'upload_date': '20220930',
+            'description': 'New York City, Kids Therapy, Biden',
+            'duration': 2415,
+            'title': 'Gutfeld! - Thursday, September 29',
+            'timestamp': 1664527538,
+        },
+        'expected_warnings': ['Ignoring subtitle tracks'],
+        'params': {'skip_download': 'm3u8'},
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        return self.url_result(f'https://video.foxnews.com/v/{video_id}', FoxNewsIE, video_id)
+
+
 class FoxNewsArticleIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?(?:insider\.)?foxnews\.com/(?!v)([^/]+/)+(?P<id>[a-z-]+)'
     IE_NAME = 'foxnews:article'

yt_dlp/extractor/listennotes.py

@@ -0,0 +1,86 @@
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    clean_html,
+    extract_attributes,
+    get_element_by_class,
+    get_element_html_by_id,
+    get_element_text_and_html_by_tag,
+    parse_duration,
+    strip_or_none,
+    traverse_obj,
+    try_call,
+)
+
+
+class ListenNotesIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?listennotes\.com/podcasts/[^/]+/[^/]+-(?P<id>.+)/'
+    _TESTS = [{
+        'url': 'https://www.listennotes.com/podcasts/thriving-on-overload/tim-oreilly-on-noticing-KrDgvNb_u1n/',
+        'md5': '5b91a32f841e5788fb82b72a1a8af7f7',
+        'info_dict': {
+            'id': 'KrDgvNb_u1n',
+            'ext': 'mp3',
+            'title': 'md5:32236591a921adf17bbdbf0441b6c0e9',
+            'description': 'md5:c581ed197eeddcee55a67cdb547c8cbd',
+            'duration': 2148.0,
+            'channel': 'Thriving on Overload',
+            'channel_id': 'ed84wITivxF',
+            'episode_id': 'e1312583fa7b4e24acfbb5131050be00',
+            'thumbnail': 'https://production.listennotes.com/podcasts/thriving-on-overload-ross-dawson-1wb_KospA3P-ed84wITivxF.300x300.jpg',
+            'channel_url': 'https://www.listennotes.com/podcasts/thriving-on-overload-ross-dawson-ed84wITivxF/',
+            'cast': ['Tim O’Reilly', 'Cookie Monster', 'Lao Tzu', 'Wallace Steven', 'Eric Raymond', 'Christine Peterson', 'John Maynard Keyne', 'Ross Dawson'],
+        }
+    }, {
+        'url': 'https://www.listennotes.com/podcasts/ask-noah-show/episode-177-wireguard-with-lwEA3154JzG/',
+        'md5': '62fb4ffe7fc525632a1138bf72a5ce53',
+        'info_dict': {
+            'id': 'lwEA3154JzG',
+            'ext': 'mp3',
+            'title': 'Episode 177: WireGuard with Jason Donenfeld',
+            'description': 'md5:24744f36456a3e95f83c1193a3458594',
+            'duration': 3861.0,
+            'channel': 'Ask Noah Show',
+            'channel_id': '4DQTzdS5-j7',
+            'episode_id': '8c8954b95e0b4859ad1eecec8bf6d3a4',
+            'channel_url': 'https://www.listennotes.com/podcasts/ask-noah-show-noah-j-chelliah-4DQTzdS5-j7/',
+            'thumbnail': 'https://production.listennotes.com/podcasts/ask-noah-show-noah-j-chelliah-cfbRUw9Gs3F-4DQTzdS5-j7.300x300.jpg',
+            'cast': ['noah showlink', 'noah show', 'noah dashboard', 'jason donenfeld'],
+        }
+    }]
+
+    def _clean_description(self, description):
+        return clean_html(re.sub(r'(</?(div|p)>\s*)+', '<br/><br/>', description or ''))
+
+    def _real_extract(self, url):
+        audio_id = self._match_id(url)
+        webpage = self._download_webpage(url, audio_id)
+        data = self._search_json(
+            r'<script id="original-content"[^>]+\btype="application/json">', webpage, 'content', audio_id)
+        data.update(extract_attributes(get_element_html_by_id(
+            r'episode-play-button-toolbar|episode-no-play-button-toolbar', webpage, escape_value=False)))
+
+        duration, description = self._search_regex(
+            r'(?P<duration>[\d:]+)\s*-\s*(?P<description>.+)',
+            self._html_search_meta(['og:description', 'description', 'twitter:description'], webpage),
+            'description', fatal=False, group=('duration', 'description')) or (None, None)
+
+        return {
+            'id': audio_id,
+            'url': data['audio'],
+            'title': (data.get('data-title')
+                      or try_call(lambda: get_element_text_and_html_by_tag('h1', webpage)[0])
+                      or self._html_search_meta(('og:title', 'title', 'twitter:title'), webpage, 'title')),
+            'description': (self._clean_description(get_element_by_class('ln-text-p', webpage))
+                            or strip_or_none(description)),
+            'duration': parse_duration(traverse_obj(data, 'audio_length', 'data-duration') or duration),
+            'episode_id': traverse_obj(data, 'uuid', 'data-episode-uuid'),
+            **traverse_obj(data, {
+                'thumbnail': 'data-image',
+                'channel': 'data-channel-title',
+                'cast': ('nlp_entities', ..., 'name'),
+                'channel_url': 'channel_url',
+                'channel_id': 'channel_short_uuid',
+            })
+        }

yt_dlp/extractor/manyvids.py

@@ -1,8 +1,12 @@
+import re
+
 from .common import InfoExtractor
 from ..utils import (
     determine_ext,
+    extract_attributes,
     int_or_none,
     str_to_int,
+    url_or_none,
     urlencode_postdata,
 )
 
@@ -17,17 +21,20 @@ class ManyVidsIE(InfoExtractor):
             'id': '133957',
             'ext': 'mp4',
             'title': 'everthing about me (Preview)',
+            'uploader': 'ellyxxix',
             'view_count': int,
             'like_count': int,
         },
     }, {
         # full video
         'url': 'https://www.manyvids.com/Video/935718/MY-FACE-REVEAL/',
-        'md5': 'f3e8f7086409e9b470e2643edb96bdcc',
+        'md5': 'bb47bab0e0802c2a60c24ef079dfe60f',
         'info_dict': {
             'id': '935718',
             'ext': 'mp4',
             'title': 'MY FACE REVEAL',
+            'description': 'md5:ec5901d41808b3746fed90face161612',
+            'uploader': 'Sarah Calanthe',
             'view_count': int,
             'like_count': int,
         },
@@ -36,17 +43,50 @@ class ManyVidsIE(InfoExtractor):
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
-        webpage = self._download_webpage(url, video_id)
+        real_url = 'https://www.manyvids.com/video/%s/gtm.js' % (video_id, )
+        try:
+            webpage = self._download_webpage(real_url, video_id)
+        except Exception:
+            # probably useless fallback
+            webpage = self._download_webpage(url, video_id)
 
-        video_url = self._search_regex(
-            r'data-(?:video-filepath|meta-video)\s*=s*(["\'])(?P<url>(?:(?!\1).)+)\1',
-            webpage, 'video URL', group='url')
+        info = self._search_regex(
+            r'''(<div\b[^>]*\bid\s*=\s*(['"])pageMetaDetails\2[^>]*>)''',
+            webpage, 'meta details', default='')
+        info = extract_attributes(info)
 
-        title = self._html_search_regex(
-            (r'<span[^>]+class=["\']item-title[^>]+>([^<]+)',
-             r'<h2[^>]+class=["\']h2 m-0["\'][^>]*>([^<]+)'),
-            webpage, 'title', default=None) or self._html_search_meta(
-            'twitter:title', webpage, 'title', fatal=True)
+        player = self._search_regex(
+            r'''(<div\b[^>]*\bid\s*=\s*(['"])rmpPlayerStream\2[^>]*>)''',
+            webpage, 'player details', default='')
+        player = extract_attributes(player)
+
+        video_urls_and_ids = (
+            (info.get('data-meta-video'), 'video'),
+            (player.get('data-video-transcoded'), 'transcoded'),
+            (player.get('data-video-filepath'), 'filepath'),
+            (self._og_search_video_url(webpage, secure=False, default=None), 'og_video'),
+        )
+
+        def txt_or_none(s, default=None):
+            return (s.strip() or default) if isinstance(s, str) else default
+
+        uploader = txt_or_none(info.get('data-meta-author'))
+
+        def mung_title(s):
+            if uploader:
+                s = re.sub(r'^\s*%s\s+[|-]' % (re.escape(uploader), ), '', s)
+            return txt_or_none(s)
+
+        title = (
+            mung_title(info.get('data-meta-title'))
+            or self._html_search_regex(
+                (r'<span[^>]+class=["\']item-title[^>]+>([^<]+)',
+                 r'<h2[^>]+class=["\']h2 m-0["\'][^>]*>([^<]+)'),
+                webpage, 'title', default=None)
+            or self._html_search_meta(
+                'twitter:title', webpage, 'title', fatal=True))
+
+        title = re.sub(r'\s*[|-]\s+ManyVids\s*$', '', title) or title
 
         if any(p in webpage for p in ('preview_videos', '_preview.mp4')):
             title += ' (Preview)'
@@ -59,7 +99,8 @@ def _real_extract(self, url):
             # Sets some cookies
             self._download_webpage(
                 'https://www.manyvids.com/includes/ajax_repository/you_had_me_at_hello.php',
-                video_id, fatal=False, data=urlencode_postdata({
+                video_id, note='Setting format cookies', fatal=False,
+                data=urlencode_postdata({
                     'mvtoken': mv_token,
                     'vid': video_id,
                 }), headers={
@@ -67,24 +108,56 @@ def _real_extract(self, url):
                     'X-Requested-With': 'XMLHttpRequest'
                 })
 
-        if determine_ext(video_url) == 'm3u8':
-            formats = self._extract_m3u8_formats(
-                video_url, video_id, 'mp4', entry_protocol='m3u8_native',
-                m3u8_id='hls')
-        else:
-            formats = [{'url': video_url}]
+        formats = []
+        for v_url, fmt in video_urls_and_ids:
+            v_url = url_or_none(v_url)
+            if not v_url:
+                continue
+            if determine_ext(v_url) == 'm3u8':
+                formats.extend(self._extract_m3u8_formats(
+                    v_url, video_id, 'mp4', entry_protocol='m3u8_native',
+                    m3u8_id='hls'))
+            else:
+                formats.append({
+                    'url': v_url,
+                    'format_id': fmt,
+                })
 
-        like_count = int_or_none(self._search_regex(
-            r'data-likes=["\'](\d+)', webpage, 'like count', default=None))
-        view_count = str_to_int(self._html_search_regex(
-            r'(?s)<span[^>]+class="views-wrapper"[^>]*>(.+?)</span', webpage,
-            'view count', default=None))
+        self._remove_duplicate_formats(formats)
+
+        for f in formats:
+            if f.get('height') is None:
+                f['height'] = int_or_none(
+                    self._search_regex(r'_(\d{2,3}[02468])_', f['url'], 'video height', default=None))
+            if '/preview/' in f['url']:
+                f['format_id'] = '_'.join(filter(None, (f.get('format_id'), 'preview')))
+                f['preference'] = -10
+            if 'transcoded' in f['format_id']:
+                f['preference'] = f.get('preference', -1) - 1
+
+        self._sort_formats(formats)
+
+        def get_likes():
+            likes = self._search_regex(
+                r'''(<a\b[^>]*\bdata-id\s*=\s*(['"])%s\2[^>]*>)''' % (video_id, ),
+                webpage, 'likes', default='')
+            likes = extract_attributes(likes)
+            return int_or_none(likes.get('data-likes'))
+
+        def get_views():
+            return str_to_int(self._html_search_regex(
+                r'''(?s)<span\b[^>]*\bclass\s*=["']views-wrapper\b[^>]+>.+?<span\b[^>]+>\s*(\d[\d,.]*)\s*</span>''',
+                webpage, 'view count', default=None))
 
         return {
             'id': video_id,
             'title': title,
-            'view_count': view_count,
-            'like_count': like_count,
             'formats': formats,
-            'uploader': self._html_search_regex(r'<meta[^>]+name="author"[^>]*>([^<]+)', webpage, 'uploader'),
+            'description': txt_or_none(info.get('data-meta-description')),
+            'uploader': txt_or_none(info.get('data-meta-author')),
+            'thumbnail': (
+                url_or_none(info.get('data-meta-image'))
+                or url_or_none(player.get('data-video-screenshot'))),
+            'view_count': get_views(),
+            'like_count': get_likes(),
         }

yt_dlp/extractor/motherless.py

@@ -69,7 +69,7 @@ class MotherlessIE(InfoExtractor):
             'title': 'a/ Hot Teens',
             'categories': list,
             'upload_date': '20210104',
-            'uploader_id': 'yonbiw',
+            'uploader_id': 'anonymous',
             'thumbnail': r're:https?://.*\.jpg',
             'age_limit': 18,
         },
@@ -123,11 +123,12 @@ def _real_extract(self, url):
                 kwargs = {_AGO_UNITS.get(uploaded_ago[-1]): delta}
                 upload_date = (datetime.datetime.utcnow() - datetime.timedelta(**kwargs)).strftime('%Y%m%d')
 
-        comment_count = webpage.count('class="media-comment-contents"')
+        comment_count = len(re.findall(r'''class\s*=\s*['"]media-comment-contents\b''', webpage))
         uploader_id = self._html_search_regex(
-            (r'"media-meta-member">\s+<a href="/m/([^"]+)"',
-             r'<span\b[^>]+\bclass="username">([^<]+)</span>'),
+            (r'''<span\b[^>]+\bclass\s*=\s*["']username\b[^>]*>([^<]+)</span>''',
+             r'''(?s)['"](?:media-meta-member|thumb-member-username)\b[^>]+>\s*<a\b[^>]+\bhref\s*=\s*['"]/m/([^"']+)'''),
             webpage, 'uploader_id', fatal=False)
+
         categories = self._html_search_meta('keywords', webpage, default=None)
         if categories:
             categories = [cat.strip() for cat in categories.split(',')]
@@ -217,23 +218,23 @@ def _real_extract(self, url):
             r'<title>([\w\s]+\w)\s+-', webpage, 'title', fatal=False)
         description = self._html_search_meta(
             'description', webpage, fatal=False)
-        page_count = self._int(self._search_regex(
-            r'(\d+)</(?:a|span)><(?:a|span)[^>]+rel="next">',
-            webpage, 'page_count', default=0), 'page_count')
+        page_count = str_to_int(self._search_regex(
+            r'(\d+)\s*</(?:a|span)>\s*<(?:a|span)[^>]+(?:>\s*NEXT|\brel\s*=\s*["\']?next)\b',
+            webpage, 'page_count', default=0))
         if not page_count:
             message = self._search_regex(
-                r'class="error-page"[^>]*>\s*<p[^>]*>\s*(?P<error_msg>[^<]+)(?<=\S)\s*',
+                r'''class\s*=\s*['"]error-page\b[^>]*>\s*<p[^>]*>\s*(?P<error_msg>[^<]+)(?<=\S)\s*''',
                 webpage, 'error_msg', default=None) or 'This group has no videos.'
             self.report_warning(message, group_id)
+            page_count = 1
         PAGE_SIZE = 80
 
         def _get_page(idx):
-            if not page_count:
-                return
-            webpage = self._download_webpage(
-                page_url, group_id, query={'page': idx + 1},
-                note='Downloading page %d/%d' % (idx + 1, page_count)
-            )
+            if idx > 0:
+                webpage = self._download_webpage(
+                    page_url, group_id, query={'page': idx + 1},
+                    note='Downloading page %d/%d' % (idx + 1, page_count)
+                )
             for entry in self._extract_entries(webpage, url):
                 yield entry
 

yt_dlp/extractor/neteasemusic.py

@@ -1,12 +1,26 @@
 import itertools
+import json
 import re
+import time
 from base64 import b64encode
+from binascii import hexlify
 from datetime import datetime
 from hashlib import md5
+from random import randint
 
 from .common import InfoExtractor
-from ..compat import compat_str, compat_urllib_parse_urlencode
-from ..utils import float_or_none, sanitized_Request
+from ..aes import aes_ecb_encrypt, pkcs7_padding
+from ..compat import compat_urllib_parse_urlencode
+from ..utils import (
+    ExtractorError,
+    bytes_to_intlist,
+    error_to_compat_str,
+    float_or_none,
+    int_or_none,
+    intlist_to_bytes,
+    sanitized_Request,
+    try_get,
+)
 
 
 class NetEaseMusicBaseIE(InfoExtractor):
@@ -17,7 +31,7 @@ class NetEaseMusicBaseIE(InfoExtractor):
     @classmethod
     def _encrypt(cls, dfsid):
         salt_bytes = bytearray(cls._NETEASE_SALT.encode('utf-8'))
-        string_bytes = bytearray(compat_str(dfsid).encode('ascii'))
+        string_bytes = bytearray(str(dfsid).encode('ascii'))
         salt_len = len(salt_bytes)
         for i in range(len(string_bytes)):
             string_bytes[i] = string_bytes[i] ^ salt_bytes[i % salt_len]
@@ -26,32 +40,105 @@ def _encrypt(cls, dfsid):
         result = b64encode(m.digest()).decode('ascii')
         return result.replace('/', '_').replace('+', '-')
 
+    def make_player_api_request_data_and_headers(self, song_id, bitrate):
+        KEY = b'e82ckenh8dichen8'
+        URL = '/api/song/enhance/player/url'
+        now = int(time.time() * 1000)
+        rand = randint(0, 1000)
+        cookie = {
+            'osver': None,
+            'deviceId': None,
+            'appver': '8.0.0',
+            'versioncode': '140',
+            'mobilename': None,
+            'buildver': '1623435496',
+            'resolution': '1920x1080',
+            '__csrf': '',
+            'os': 'pc',
+            'channel': None,
+            'requestId': '{0}_{1:04}'.format(now, rand),
+        }
+        request_text = json.dumps(
+            {'ids': '[{0}]'.format(song_id), 'br': bitrate, 'header': cookie},
+            separators=(',', ':'))
+        message = 'nobody{0}use{1}md5forencrypt'.format(
+            URL, request_text).encode('latin1')
+        msg_digest = md5(message).hexdigest()
+
+        data = '{0}-36cd479b6b5-{1}-36cd479b6b5-{2}'.format(
+            URL, request_text, msg_digest)
+        data = pkcs7_padding(bytes_to_intlist(data))
+        encrypted = intlist_to_bytes(aes_ecb_encrypt(data, bytes_to_intlist(KEY)))
+        encrypted_params = hexlify(encrypted).decode('ascii').upper()
+
+        cookie = '; '.join(
+            ['{0}={1}'.format(k, v if v is not None else 'undefined')
+             for [k, v] in cookie.items()])
+
+        headers = {
+            'User-Agent': self.extractor.get_param('http_headers')['User-Agent'],
+            'Content-Type': 'application/x-www-form-urlencoded',
+            'Referer': 'https://music.163.com',
+            'Cookie': cookie,
+        }
+        return ('params={0}'.format(encrypted_params), headers)
+
+    def _call_player_api(self, song_id, bitrate):
+        url = 'https://interface3.music.163.com/eapi/song/enhance/player/url'
+        data, headers = self.make_player_api_request_data_and_headers(song_id, bitrate)
+        try:
+            msg = 'empty result'
+            result = self._download_json(
+                url, song_id, data=data.encode('ascii'), headers=headers)
+            if result:
+                return result
+        except ExtractorError as e:
+            if type(e.cause) in (ValueError, TypeError):
+                # JSON load failure
+                raise
+        except Exception as e:
+            msg = error_to_compat_str(e)
+            self.report_warning('%s API call (%s) failed: %s' % (
+                song_id, bitrate, msg))
+        return {}
+
     def extract_formats(self, info):
+        err = 0
         formats = []
+        song_id = info['id']
         for song_format in self._FORMATS:
             details = info.get(song_format)
             if not details:
                 continue
-            song_file_path = '/%s/%s.%s' % (
-                self._encrypt(details['dfsId']), details['dfsId'], details['extension'])
 
-            # 203.130.59.9, 124.40.233.182, 115.231.74.139, etc is a reverse proxy-like feature
-            # from NetEase's CDN provider that can be used if m5.music.126.net does not
-            # work, especially for users outside of Mainland China
-            # via: https://github.com/JixunMoe/unblock-163/issues/3#issuecomment-163115880
-            for host in ('http://m5.music.126.net', 'http://115.231.74.139/m1.music.126.net',
-                         'http://124.40.233.182/m1.music.126.net', 'http://203.130.59.9/m1.music.126.net'):
-                song_url = host + song_file_path
+            bitrate = int_or_none(details.get('bitrate')) or 999000
+            data = self._call_player_api(song_id, bitrate)
+            for song in try_get(data, lambda x: x['data'], list) or []:
+                song_url = try_get(song, lambda x: x['url'])
+                if not song_url:
+                    continue
                 if self._is_valid_url(song_url, info['id'], 'song'):
                     formats.append({
                         'url': song_url,
                         'ext': details.get('extension'),
-                        'abr': float_or_none(details.get('bitrate'), scale=1000),
+                        'abr': float_or_none(song.get('br'), scale=1000),
                         'format_id': song_format,
-                        'filesize': details.get('size'),
-                        'asr': details.get('sr')
+                        'filesize': int_or_none(song.get('size')),
+                        'asr': int_or_none(details.get('sr')),
                     })
-                    break
+                elif err == 0:
+                    err = try_get(song, lambda x: x['code'], int)
+
+        if not formats:
+            msg = 'No media links found'
+            if err != 0 and (err < 200 or err >= 400):
+                raise ExtractorError(
+                    '%s (site code %d)' % (msg, err, ), expected=True)
+            else:
+                self.raise_geo_restricted(
+                    msg + ': probably this video is not available from your location due to geo restriction.',
+                    countries=['CN'])
+
         return formats
 
     @classmethod
@@ -67,33 +154,19 @@ def query_api(self, endpoint, video_id, note):
 class NetEaseMusicIE(NetEaseMusicBaseIE):
     IE_NAME = 'netease:song'
     IE_DESC = '网易云音乐'
-    _VALID_URL = r'https?://music\.163\.com/(#/)?song\?id=(?P<id>[0-9]+)'
+    _VALID_URL = r'https?://(y\.)?music\.163\.com/(?:[#m]/)?song\?.*?\bid=(?P<id>[0-9]+)'
     _TESTS = [{
         'url': 'http://music.163.com/#/song?id=32102397',
-        'md5': 'f2e97280e6345c74ba9d5677dd5dcb45',
+        'md5': '3e909614ce09b1ccef4a3eb205441190',
         'info_dict': {
             'id': '32102397',
             'ext': 'mp3',
-            'title': 'Bad Blood (feat. Kendrick Lamar)',
+            'title': 'Bad Blood',
             'creator': 'Taylor Swift / Kendrick Lamar',
-            'upload_date': '20150517',
-            'timestamp': 1431878400,
-            'description': 'md5:a10a54589c2860300d02e1de821eb2ef',
+            'upload_date': '20150516',
+            'timestamp': 1431792000,
+            'description': 'md5:25fc5f27e47aad975aa6d36382c7833c',
         },
-        'skip': 'Blocked outside Mainland China',
-    }, {
-        'note': 'No lyrics translation.',
-        'url': 'http://music.163.com/#/song?id=29822014',
-        'info_dict': {
-            'id': '29822014',
-            'ext': 'mp3',
-            'title': '听见下雨的声音',
-            'creator': '周杰伦',
-            'upload_date': '20141225',
-            'timestamp': 1419523200,
-            'description': 'md5:a4d8d89f44656af206b7b2555c0bce6c',
-        },
-        'skip': 'Blocked outside Mainland China',
     }, {
         'note': 'No lyrics.',
         'url': 'http://music.163.com/song?id=17241424',
@@ -103,9 +176,9 @@ class NetEaseMusicIE(NetEaseMusicBaseIE):
             'title': 'Opus 28',
             'creator': 'Dustin O\'Halloran',
             'upload_date': '20080211',
+            'description': 'md5:f12945b0f6e0365e3b73c5032e1b0ff4',
             'timestamp': 1202745600,
         },
-        'skip': 'Blocked outside Mainland China',
     }, {
         'note': 'Has translated name.',
         'url': 'http://music.163.com/#/song?id=22735043',
@@ -119,7 +192,18 @@ class NetEaseMusicIE(NetEaseMusicBaseIE):
             'timestamp': 1264608000,
             'alt_title': '说出愿望吧(Genie)',
         },
-        'skip': 'Blocked outside Mainland China',
+    }, {
+        'url': 'https://y.music.163.com/m/song?app_version=8.8.45&id=95670&uct2=sKnvS4+0YStsWkqsPhFijw%3D%3D&dlt=0846',
+        'md5': '95826c73ea50b1c288b22180ec9e754d',
+        'info_dict': {
+            'id': '95670',
+            'ext': 'mp3',
+            'title': '国际歌',
+            'creator': '马备',
+            'upload_date': '19911130',
+            'timestamp': 691516800,
+            'description': 'md5:1ba2f911a2b0aa398479f595224f2141',
+        },
     }]
 
     def _process_lyrics(self, lyrics_info):

yt_dlp/extractor/nrk.py

@@ -58,8 +58,7 @@ def _call_api(self, path, video_id, item=None, note=None, fatal=True, query=None
         return self._download_json(
             urljoin('https://psapi.nrk.no/', path),
             video_id, note or 'Downloading %s JSON' % item,
-            fatal=fatal, query=query,
-            headers={'Accept-Encoding': 'gzip, deflate, br'})
+            fatal=fatal, query=query)
 
 
 class NRKIE(NRKBaseIE):

yt_dlp/extractor/qingting.py

@@ -0,0 +1,47 @@
+from .common import InfoExtractor
+
+from ..utils import traverse_obj
+
+
+class QingTingIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.|m\.)?(?:qingting\.fm|qtfm\.cn)/v?channels/(?P<channel>\d+)/programs/(?P<id>\d+)'
+    _TESTS = [{
+        'url': 'https://www.qingting.fm/channels/378005/programs/22257411/',
+        'md5': '47e6a94f4e621ed832c316fd1888fb3c',
+        'info_dict': {
+            'id': '22257411',
+            'title': '用了十年才修改，谁在乎教科书？',
+            'channel_id': '378005',
+            'channel': '睡前消息',
+            'uploader': '马督工',
+            'ext': 'm4a',
+        }
+    }, {
+        'url': 'https://m.qtfm.cn/vchannels/378005/programs/23023573/',
+        'md5': '2703120b6abe63b5fa90b975a58f4c0e',
+        'info_dict': {
+            'id': '23023573',
+            'title': '【睡前消息488】重庆山火之后，有图≠真相',
+            'channel_id': '378005',
+            'channel': '睡前消息',
+            'uploader': '马督工',
+            'ext': 'm4a',
+        }
+    }]
+
+    def _real_extract(self, url):
+        channel_id, pid = self._match_valid_url(url).group('channel', 'id')
+        webpage = self._download_webpage(
+            f'https://m.qtfm.cn/vchannels/{channel_id}/programs/{pid}/', pid)
+        info = self._search_json(r'window\.__initStores\s*=', webpage, 'program info', pid)
+        return {
+            'id': pid,
+            'title': traverse_obj(info, ('ProgramStore', 'programInfo', 'title')),
+            'channel_id': channel_id,
+            'channel': traverse_obj(info, ('ProgramStore', 'channelInfo', 'title')),
+            'uploader': traverse_obj(info, ('ProgramStore', 'podcasterInfo', 'podcaster', 'nickname')),
+            'url': traverse_obj(info, ('ProgramStore', 'programInfo', 'audioUrl')),
+            'vcodec': 'none',
+            'acodec': 'm4a',
+            'ext': 'm4a',
+        }

yt_dlp/extractor/redgifs.py

@@ -1,4 +1,5 @@
 import functools
+import urllib
 
 from .common import InfoExtractor
 from ..compat import compat_parse_qs
@@ -72,14 +73,20 @@ def _fetch_oauth_token(self, video_id):
         self._API_HEADERS['authorization'] = f'Bearer {auth["token"]}'
 
     def _call_api(self, ep, video_id, *args, **kwargs):
-        if 'authorization' not in self._API_HEADERS:
-            self._fetch_oauth_token(video_id)
-        assert 'authorization' in self._API_HEADERS
+        for attempt in range(2):
+            if 'authorization' not in self._API_HEADERS:
+                self._fetch_oauth_token(video_id)
+            try:
+                headers = dict(self._API_HEADERS)
+                headers['x-customheader'] = f'https://www.redgifs.com/watch/{video_id}'
+                data = self._download_json(
+                    f'https://api.redgifs.com/v2/{ep}', video_id, headers=headers, *args, **kwargs)
+                break
+            except ExtractorError as e:
+                if not attempt and isinstance(e.cause, urllib.error.HTTPError) and e.cause.code == 401:
+                    del self._API_HEADERS['authorization']  # refresh the token
+                raise
 
-        headers = dict(self._API_HEADERS)
-        headers['x-customheader'] = f'https://www.redgifs.com/watch/{video_id}'
-        data = self._download_json(
-            f'https://api.redgifs.com/v2/{ep}', video_id, headers=headers, *args, **kwargs)
         if 'error' in data:
             raise ExtractorError(f'RedGifs said: {data["error"]}', expected=True, video_id=video_id)
         return data

yt_dlp/extractor/skyit.py

@@ -25,7 +25,6 @@ class SkyItPlayerIE(InfoExtractor):
         'salesforce': 'C6D585FD1615272C98DE38235F38BD86',
         'sitocommerciale': 'VJwfFuSGnLKnd9Phe9y96WkXgYDCguPMJ2dLhGMb2RE',
         'sky': 'F96WlOd8yoFmLQgiqv6fNQRvHZcsWk5jDaYnDvhbiJk',
-        'skyacademy': 'A6LAn7EkO2Q26FRy0IAMBekX6jzDXYL3',
         'skyarte': 'LWk29hfiU39NNdq87ePeRach3nzTSV20o0lTv2001Cd',
         'theupfront': 'PRSGmDMsg6QMGc04Obpoy7Vsbn7i2Whp',
     }
@@ -42,11 +41,7 @@ def _parse_video(self, video, video_id):
         if not hls_url and video.get('geoblock' if is_live else 'geob'):
             self.raise_geo_restricted(countries=['IT'])
 
-        if is_live:
-            formats = self._extract_m3u8_formats(hls_url, video_id, 'mp4')
-        else:
-            formats = self._extract_akamai_formats(
-                hls_url, video_id, {'http': 'videoplatform.sky.it'})
+        formats = self._extract_m3u8_formats(hls_url, video_id, 'mp4')
         self._sort_formats(formats)
 
         return {
@@ -80,14 +75,17 @@ class SkyItVideoIE(SkyItPlayerIE):
     _VALID_URL = r'https?://(?:masterchef|video|xfactor)\.sky\.it(?:/[^/]+)*/video/[0-9a-z-]+-(?P<id>\d+)'
     _TESTS = [{
         'url': 'https://video.sky.it/news/mondo/video/uomo-ucciso-da-uno-squalo-in-australia-631227',
-        'md5': 'fe5c91e59a84a3437eaa0bca6e134ccd',
+        'md5': '5b858a62d9ffe2ab77b397553024184a',
         'info_dict': {
             'id': '631227',
             'ext': 'mp4',
             'title': 'Uomo ucciso da uno squalo in Australia',
             'timestamp': 1606036192,
             'upload_date': '20201122',
-        }
+            'duration': 26,
+            'thumbnail': 'https://video.sky.it/captures/thumbs/631227/631227_thumb_880x494.jpg',
+        },
+        'params': {'skip_download': 'm3u8'},
     }, {
         'url': 'https://xfactor.sky.it/video/x-factor-2020-replay-audizioni-1-615820',
         'only_matching': True,
@@ -110,7 +108,8 @@ class SkyItVideoLiveIE(SkyItPlayerIE):
             'id': '1',
             'ext': 'mp4',
             'title': r're:Diretta TG24 \d{4}-\d{2}-\d{2} \d{2}:\d{2}',
-            'description': 'Guarda la diretta streaming di SkyTg24, segui con Sky tutti gli appuntamenti e gli speciali di Tg24.',
+            'description': r're:(?:Clicca play e )?[Gg]uarda la diretta streaming di SkyTg24, segui con Sky tutti gli appuntamenti e gli speciali di Tg24\.',
+            'live_status': 'is_live',
         },
         'params': {
             # m3u8 download
@@ -132,15 +131,17 @@ class SkyItIE(SkyItPlayerIE):
     IE_NAME = 'sky.it'
     _VALID_URL = r'https?://(?:sport|tg24)\.sky\.it(?:/[^/]+)*/\d{4}/\d{2}/\d{2}/(?P<id>[^/?&#]+)'
     _TESTS = [{
-        'url': 'https://sport.sky.it/calcio/serie-a/2020/11/21/juventus-cagliari-risultato-gol',
+        'url': 'https://sport.sky.it/calcio/serie-a/2022/11/03/brozovic-inter-news',
         'info_dict': {
-            'id': '631201',
+            'id': '789222',
             'ext': 'mp4',
-            'title': 'Un rosso alla violenza: in campo per i diritti delle donne',
-            'upload_date': '20201121',
-            'timestamp': 1605995753,
+            'title': 'Brozovic con il gruppo: verso convocazione per Juve-Inter',
+            'upload_date': '20221103',
+            'timestamp': 1667484130,
+            'duration': 22,
+            'thumbnail': 'https://videoplatform.sky.it/still/2022/11/03/1667480526353_brozovic_videostill_1.jpg',
         },
-        'expected_warnings': ['Unable to download f4m manifest'],
+        'params': {'skip_download': 'm3u8'},
     }, {
         'url': 'https://tg24.sky.it/mondo/2020/11/22/australia-squalo-uccide-uomo',
         'md5': 'fe5c91e59a84a3437eaa0bca6e134ccd',
@@ -150,7 +151,10 @@ class SkyItIE(SkyItPlayerIE):
             'title': 'Uomo ucciso da uno squalo in Australia',
             'timestamp': 1606036192,
             'upload_date': '20201122',
+            'duration': 26,
+            'thumbnail': 'https://video.sky.it/captures/thumbs/631227/631227_thumb_880x494.jpg',
         },
+        'params': {'skip_download': 'm3u8'},
     }]
     _VIDEO_ID_REGEX = r'data-videoid="(\d+)"'
 
@@ -162,40 +166,25 @@ def _real_extract(self, url):
         return self._player_url_result(video_id)
 
 
-class SkyItAcademyIE(SkyItIE):
-    IE_NAME = 'skyacademy.it'
-    _VALID_URL = r'https?://(?:www\.)?skyacademy\.it(?:/[^/]+)*/\d{4}/\d{2}/\d{2}/(?P<id>[^/?&#]+)'
-    _TESTS = [{
-        'url': 'https://www.skyacademy.it/eventi-speciali/2019/07/05/a-lezione-di-cinema-con-sky-academy-/',
-        'md5': 'ced5c26638b7863190cbc44dd6f6ba08',
-        'info_dict': {
-            'id': '523458',
-            'ext': 'mp4',
-            'title': 'Sky Academy "The Best CineCamp 2019"',
-            'timestamp': 1562843784,
-            'upload_date': '20190711',
-        }
-    }]
-    _DOMAIN = 'skyacademy'
-    _VIDEO_ID_REGEX = r'id="news-videoId_(\d+)"'
-
-
 class SkyItArteIE(SkyItIE):
     IE_NAME = 'arte.sky.it'
     _VALID_URL = r'https?://arte\.sky\.it/video/(?P<id>[^/?&#]+)'
     _TESTS = [{
-        'url': 'https://arte.sky.it/video/serie-musei-venezia-collezionismo-12-novembre/',
+        'url': 'https://arte.sky.it/video/oliviero-toscani-torino-galleria-mazzoleni-788962',
         'md5': '515aee97b87d7a018b6c80727d3e7e17',
         'info_dict': {
-            'id': '627926',
+            'id': '788962',
             'ext': 'mp4',
-            'title': "Musei Galleria Franchetti alla Ca' d'Oro Palazzo Grimani",
-            'upload_date': '20201106',
-            'timestamp': 1604664493,
-        }
+            'title': 'La fotografia di Oliviero Toscani conquista Torino',
+            'upload_date': '20221102',
+            'timestamp': 1667399996,
+            'duration': 12,
+            'thumbnail': 'https://videoplatform.sky.it/still/2022/11/02/1667396388552_oliviero-toscani-torino-galleria-mazzoleni_videostill_1.jpg',
+        },
+        'params': {'skip_download': 'm3u8'},
     }]
     _DOMAIN = 'skyarte'
-    _VIDEO_ID_REGEX = r'(?s)<iframe[^>]+src="(?:https:)?//player\.sky\.it/player/external\.html\?[^"]*\bid=(\d+)'
+    _VIDEO_ID_REGEX = r'"embedUrl"\s*:\s*"(?:https:)?//player\.sky\.it/player/external\.html\?[^"]*\bid=(\d+)'
 
 
 class CieloTVItIE(SkyItIE):
@@ -210,7 +199,10 @@ class CieloTVItIE(SkyItIE):
             'title': 'Il lunedì è sempre un dramma',
             'upload_date': '20190329',
             'timestamp': 1553862178,
-        }
+            'duration': 30,
+            'thumbnail': 'https://videoplatform.sky.it/still/2019/03/29/1553858575610_lunedi_dramma_mant_videostill_1.jpg',
+        },
+        'params': {'skip_download': 'm3u8'},
     }]
     _DOMAIN = 'cielo'
     _VIDEO_ID_REGEX = r'videoId\s*=\s*"(\d+)"'
@@ -218,9 +210,9 @@ class CieloTVItIE(SkyItIE):
 
 class TV8ItIE(SkyItVideoIE):
     IE_NAME = 'tv8.it'
-    _VALID_URL = r'https?://tv8\.it/showvideo/(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:www\.)?tv8\.it/(?:show)?video/[0-9a-z-]+-(?P<id>\d+)'
     _TESTS = [{
-        'url': 'https://tv8.it/showvideo/630529/ogni-mattina-ucciso-asino-di-andrea-lo-cicero/18-11-2020/',
+        'url': 'https://www.tv8.it/video/ogni-mattina-ucciso-asino-di-andrea-lo-cicero-630529',
         'md5': '9ab906a3f75ea342ed928442f9dabd21',
         'info_dict': {
             'id': '630529',
@@ -228,6 +220,9 @@ class TV8ItIE(SkyItVideoIE):
             'title': 'Ogni mattina - Ucciso asino di Andrea Lo Cicero',
             'timestamp': 1605721374,
             'upload_date': '20201118',
-        }
+            'duration': 114,
+            'thumbnail': 'https://videoplatform.sky.it/still/2020/11/18/1605717753954_ogni-mattina-ucciso-asino-di-andrea-lo-cicero_videostill_1.jpg',
+        },
+        'params': {'skip_download': 'm3u8'},
     }]
     _DOMAIN = 'mtv8'

yt_dlp/extractor/stripchat.py

@@ -1,22 +1,15 @@
 from .common import InfoExtractor
-from ..compat import (
-    compat_str,
-)
-from ..utils import (
-    ExtractorError,
-    lowercase_escape,
-    try_get,
-)
+from ..utils import ExtractorError, lowercase_escape, traverse_obj
 
 
 class StripchatIE(InfoExtractor):
     _VALID_URL = r'https?://stripchat\.com/(?P<id>[^/?#]+)'
     _TESTS = [{
-        'url': 'https://stripchat.com/feel_me',
+        'url': 'https://stripchat.com/Joselin_Flower',
         'info_dict': {
-            'id': 'feel_me',
+            'id': 'Joselin_Flower',
             'ext': 'mp4',
-            'title': 're:^feel_me [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
+            'title': 're:^Joselin_Flower [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
             'description': str,
             'is_live': True,
             'age_limit': 18,
@@ -39,18 +32,22 @@ def _real_extract(self, url):
         if not data:
             raise ExtractorError('Unable to find configuration for stream.')
 
-        if try_get(data, lambda x: x['viewCam']['show'], dict):
+        if traverse_obj(data, ('viewCam', 'show'), expected_type=dict):
             raise ExtractorError('Model is in private show', expected=True)
-        elif not try_get(data, lambda x: x['viewCam']['model']['isLive'], bool):
+        elif not traverse_obj(data, ('viewCam', 'model', 'isLive'), expected_type=bool):
             raise ExtractorError('Model is offline', expected=True)
 
-        server = try_get(data, lambda x: x['viewCam']['viewServers']['flashphoner-hls'], compat_str)
-        host = try_get(data, lambda x: x['config']['data']['hlsStreamHost'], compat_str)
-        model_id = try_get(data, lambda x: x['viewCam']['model']['id'], int)
+        server = traverse_obj(data, ('viewCam', 'viewServers', 'flashphoner-hls'), expected_type=str)
+        model_id = traverse_obj(data, ('viewCam', 'model', 'id'), expected_type=int)
+
+        for host in traverse_obj(data, (
+                'config', 'data', (('featuresV2', 'hlsFallback', 'fallbackDomains', ...), 'hlsStreamHost'))):
+            formats = self._extract_m3u8_formats(
+                f'https://b-{server}.{host}/hls/{model_id}/{model_id}.m3u8',
+                video_id, ext='mp4', m3u8_id='hls', fatal=False, live=True)
+            if formats:
+                break
 
-        formats = self._extract_m3u8_formats(
-            'https://b-%s.%s/hls/%d/%d.m3u8' % (server, host, model_id, model_id),
-            video_id, ext='mp4', m3u8_id='hls', fatal=False, live=True)
         self._sort_formats(formats)
 
         return {

yt_dlp/extractor/swearnet.py

@@ -0,0 +1,73 @@
+from .common import InfoExtractor
+from ..utils import int_or_none, traverse_obj
+
+
+class SwearnetEpisodeIE(InfoExtractor):
+    _VALID_URL = r'https?://www\.swearnet\.com/shows/(?P<id>[\w-]+)/seasons/(?P<season_num>\d+)/episodes/(?P<episode_num>\d+)'
+    _TESTS = [{
+        'url': 'https://www.swearnet.com/shows/gettin-learnt-with-ricky/seasons/1/episodes/1',
+        'info_dict': {
+            'id': '232819',
+            'ext': 'mp4',
+            'episode_number': 1,
+            'episode': 'Episode 1',
+            'duration': 719,
+            'description': 'md5:c48ef71440ce466284c07085cd7bd761',
+            'season': 'Season 1',
+            'title': 'Episode 1 - Grilled Cheese Sammich',
+            'season_number': 1,
+            'thumbnail': 'https://cdn.vidyard.com/thumbnails/232819/_RX04IKIq60a2V6rIRqq_Q_small.jpg',
+        }
+    }]
+
+    def _get_formats_and_subtitle(self, video_source, video_id):
+        video_source = video_source or {}
+        formats, subtitles = [], {}
+        for key, value in video_source.items():
+            if key == 'hls':
+                for video_hls in value:
+                    fmts, subs = self._extract_m3u8_formats_and_subtitles(video_hls.get('url'), video_id)
+                    formats.extend(fmts)
+                    self._merge_subtitles(subs, target=subtitles)
+            else:
+                formats.extend({
+                    'url': video_mp4.get('url'),
+                    'ext': 'mp4'
+                } for video_mp4 in value)
+
+        return formats, subtitles
+
+    def _get_direct_subtitle(self, caption_json):
+        subs = {}
+        for caption in caption_json:
+            subs.setdefault(caption.get('language') or 'und', []).append({
+                'url': caption.get('vttUrl'),
+                'name': caption.get('name')
+            })
+
+        return subs
+
+    def _real_extract(self, url):
+        display_id, season_number, episode_number = self._match_valid_url(url).group('id', 'season_num', 'episode_num')
+        webpage = self._download_webpage(url, display_id)
+
+        external_id = self._search_regex(r'externalid\s*=\s*"([^"]+)', webpage, 'externalid')
+        json_data = self._download_json(
+            f'https://play.vidyard.com/player/{external_id}.json', display_id)['payload']['chapters'][0]
+
+        formats, subtitles = self._get_formats_and_subtitle(json_data['sources'], display_id)
+        self._merge_subtitles(self._get_direct_subtitle(json_data.get('captions')), target=subtitles)
+
+        return {
+            'id': str(json_data['videoId']),
+            'title': json_data.get('name') or self._html_search_meta(['og:title', 'twitter:title'], webpage),
+            'description': (json_data.get('description')
+                            or self._html_search_meta(['og:description', 'twitter:description'])),
+            'duration': int_or_none(json_data.get('seconds')),
+            'formats': formats,
+            'subtitles': subtitles,
+            'season_number': int_or_none(season_number),
+            'episode_number': int_or_none(episode_number),
+            'thumbnails': [{'url': thumbnail_url}
+                           for thumbnail_url in traverse_obj(json_data, ('thumbnailUrls', ...))]
+        }

yt_dlp/extractor/telegram.py

@@ -1,41 +1,137 @@
+import re
+
 from .common import InfoExtractor
-from ..utils import clean_html, get_element_by_class
+from ..utils import (
+    clean_html,
+    format_field,
+    get_element_by_class,
+    parse_duration,
+    parse_qs,
+    traverse_obj,
+    unified_timestamp,
+    update_url_query,
+    url_basename,
+)
 
 
 class TelegramEmbedIE(InfoExtractor):
     IE_NAME = 'telegram:embed'
-    _VALID_URL = r'https?://t\.me/(?P<channel_name>[^/]+)/(?P<id>\d+)'
+    _VALID_URL = r'https?://t\.me/(?P<channel_id>[^/]+)/(?P<id>\d+)'
     _TESTS = [{
         'url': 'https://t.me/europa_press/613',
+        'md5': 'dd707708aea958c11a590e8068825f22',
         'info_dict': {
             'id': '613',
             'ext': 'mp4',
-            'title': 'Europa Press',
-            'description': '6ce2d7e8d56eda16d80607b23db7b252',
-            'thumbnail': r're:^https?:\/\/cdn.*?telesco\.pe\/file\/\w+',
+            'title': 'md5:6ce2d7e8d56eda16d80607b23db7b252',
+            'description': 'md5:6ce2d7e8d56eda16d80607b23db7b252',
+            'channel_id': 'europa_press',
+            'channel': 'Europa Press ✔',
+            'thumbnail': r're:^https?://.+',
+            'timestamp': 1635631203,
+            'upload_date': '20211030',
+            'duration': 61,
+        },
+    }, {
+        # 2-video post
+        'url': 'https://t.me/vorposte/29342',
+        'info_dict': {
+            'id': 'vorposte-29342',
+            'title': 'Форпост 29342',
+            'description': 'md5:9d92e22169a3e136d5d69df25f82c3dc',
+        },
+        'playlist_count': 2,
+        'params': {
+            'skip_download': True,
+        },
+    }, {
+        # 2-video post with --no-playlist
+        'url': 'https://t.me/vorposte/29343',
+        'md5': '1724e96053c18e788c8464038876e245',
+        'info_dict': {
+            'id': '29343',
+            'ext': 'mp4',
+            'title': 'md5:9d92e22169a3e136d5d69df25f82c3dc',
+            'description': 'md5:9d92e22169a3e136d5d69df25f82c3dc',
+            'channel_id': 'vorposte',
+            'channel': 'Форпост',
+            'thumbnail': r're:^https?://.+',
+            'timestamp': 1666384480,
+            'upload_date': '20221021',
+            'duration': 35,
+        },
+        'params': {
+            'noplaylist': True,
+        }
+    }, {
+        # 2-video post with 'single' query param
+        'url': 'https://t.me/vorposte/29342?single',
+        'md5': 'd20b202f1e41400a9f43201428add18f',
+        'info_dict': {
+            'id': '29342',
+            'ext': 'mp4',
+            'title': 'md5:9d92e22169a3e136d5d69df25f82c3dc',
+            'description': 'md5:9d92e22169a3e136d5d69df25f82c3dc',
+            'channel_id': 'vorposte',
+            'channel': 'Форпост',
+            'thumbnail': r're:^https?://.+',
+            'timestamp': 1666384480,
+            'upload_date': '20221021',
+            'duration': 33,
         },
     }]
 
     def _real_extract(self, url):
-        video_id = self._match_id(url)
-        webpage = self._download_webpage(url, video_id, query={'embed': 0})
-        webpage_embed = self._download_webpage(url, video_id, query={'embed': 1}, note='Downloading ermbed page')
+        channel_id, msg_id = self._match_valid_url(url).group('channel_id', 'id')
+        embed = self._download_webpage(
+            url, msg_id, query={'embed': '1', 'single': []}, note='Downloading embed frame')
 
-        formats = [{
-            'url': self._proto_relative_url(self._search_regex(
-                '<video[^>]+src="([^"]+)"', webpage_embed, 'source')),
-            'ext': 'mp4',
-        }]
-        self._sort_formats(formats)
+        def clean_text(html_class, html):
+            text = clean_html(get_element_by_class(html_class, html))
+            return text.replace('\n', ' ') if text else None
 
-        return {
-            'id': video_id,
-            'title': self._html_search_meta(['og:title', 'twitter:title'], webpage, default=None),
-            'description': self._html_search_meta(
-                ['og:description', 'twitter:description'], webpage,
-                default=clean_html(get_element_by_class('tgme_widget_message_text', webpage_embed))),
-            'thumbnail': self._search_regex(
-                r'tgme_widget_message_video_thumb"[^>]+background-image:url\(\'([^\']+)\'\)',
-                webpage_embed, 'thumbnail'),
-            'formats': formats,
+        description = clean_text('tgme_widget_message_text', embed)
+        message = {
+            'title': description or '',
+            'description': description,
+            'channel': clean_text('tgme_widget_message_author', embed),
+            'channel_id': channel_id,
+            'timestamp': unified_timestamp(self._search_regex(
+                r'<time[^>]*datetime="([^"]*)"', embed, 'timestamp', fatal=False)),
         }
+
+        videos = []
+        for video in re.findall(r'<a class="tgme_widget_message_video_player(?s:.+?)</time>', embed):
+            video_url = self._search_regex(
+                r'<video[^>]+src="([^"]+)"', video, 'video URL', fatal=False)
+            webpage_url = self._search_regex(
+                r'<a class="tgme_widget_message_video_player[^>]+href="([^"]+)"',
+                video, 'webpage URL', fatal=False)
+            if not video_url or not webpage_url:
+                continue
+            formats = [{
+                'url': video_url,
+                'ext': 'mp4',
+            }]
+            self._sort_formats(formats)
+            videos.append({
+                'id': url_basename(webpage_url),
+                'webpage_url': update_url_query(webpage_url, {'single': True}),
+                'duration': parse_duration(self._search_regex(
+                    r'<time[^>]+duration[^>]*>([\d:]+)</time>', video, 'duration', fatal=False)),
+                'thumbnail': self._search_regex(
+                    r'tgme_widget_message_video_thumb"[^>]+background-image:url\(\'([^\']+)\'\)',
+                    video, 'thumbnail', fatal=False),
+                'formats': formats,
+                **message,
+            })
+
+        playlist_id = None
+        if len(videos) > 1 and 'single' not in parse_qs(url, keep_blank_values=True):
+            playlist_id = f'{channel_id}-{msg_id}'
+
+        if self._yes_playlist(playlist_id, msg_id):
+            return self.playlist_result(
+                videos, playlist_id, format_field(message, 'channel', f'%s {msg_id}'), description)
+        else:
+            return traverse_obj(videos, lambda _, x: x['id'] == msg_id, get_all=False)

yt_dlp/extractor/tvp.py

@@ -4,40 +4,51 @@
 
 from .common import InfoExtractor
 from ..utils import (
+    clean_html,
     determine_ext,
     dict_get,
     ExtractorError,
     int_or_none,
     js_to_json,
-    orderedSet,
     str_or_none,
+    strip_or_none,
+    traverse_obj,
     try_get,
+    url_or_none,
 )
 
 
 class TVPIE(InfoExtractor):
     IE_NAME = 'tvp'
     IE_DESC = 'Telewizja Polska'
-    _VALID_URL = r'https?://(?:[^/]+\.)?(?:tvp(?:parlament)?\.(?:pl|info)|polandin\.com)/(?:video/(?:[^,\s]*,)*|(?:(?!\d+/)[^/]+/)*)(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:[^/]+\.)?(?:tvp(?:parlament)?\.(?:pl|info)|tvpworld\.com|swipeto\.pl)/(?:(?!\d+/)[^/]+/)*(?P<id>\d+)'
 
     _TESTS = [{
         # TVPlayer 2 in js wrapper
-        'url': 'https://vod.tvp.pl/video/czas-honoru,i-seria-odc-13,194536',
+        'url': 'https://swipeto.pl/64095316/uliczny-foxtrot-wypozyczalnia-kaset-kto-pamieta-dvdvideo',
         'info_dict': {
-            'id': '194536',
+            'id': '64095316',
             'ext': 'mp4',
-            'title': 'Czas honoru, odc. 13 – Władek',
-            'description': 'md5:437f48b93558370b031740546b696e24',
-            'age_limit': 12,
+            'title': 'Uliczny Foxtrot — Wypożyczalnia kaset. Kto pamięta DVD-Video?',
+            'age_limit': 0,
+            'duration': 374,
+            'thumbnail': r're:https://.+',
         },
+        'expected_warnings': [
+            'Failed to download ISM manifest: HTTP Error 404: Not Found',
+            'Failed to download m3u8 information: HTTP Error 404: Not Found',
+        ],
     }, {
         # TVPlayer legacy
-        'url': 'http://www.tvp.pl/there-can-be-anything-so-i-shortened-it/17916176',
+        'url': 'https://www.tvp.pl/polska-press-video-uploader/wideo/62042351',
         'info_dict': {
-            'id': '17916176',
+            'id': '62042351',
             'ext': 'mp4',
-            'title': 'TVP Gorzów pokaże filmy studentów z podroży dookoła świata',
-            'description': 'TVP Gorzów pokaże filmy studentów z podroży dookoła świata',
+            'title': 'Wideo',
+            'description': 'Wideo Kamera',
+            'duration': 24,
+            'age_limit': 0,
+            'thumbnail': r're:https://.+',
         },
     }, {
         # TVPlayer 2 in iframe
@@ -48,6 +59,8 @@ class TVPIE(InfoExtractor):
             'title': 'Dzieci na sprzedaż dla homoseksualistów',
             'description': 'md5:7d318eef04e55ddd9f87a8488ac7d590',
             'age_limit': 12,
+            'duration': 259,
+            'thumbnail': r're:https://.+',
         },
     }, {
         # TVPlayer 2 in client-side rendered website (regional; window.__newsData)
@@ -58,7 +71,11 @@ class TVPIE(InfoExtractor):
             'title': 'Studio Yayo',
             'upload_date': '20160616',
             'timestamp': 1466075700,
-        }
+            'age_limit': 0,
+            'duration': 20,
+            'thumbnail': r're:https://.+',
+        },
+        'skip': 'Geo-blocked outside PL',
     }, {
         # TVPlayer 2 in client-side rendered website (tvp.info; window.__videoData)
         'url': 'https://www.tvp.info/52880236/09042021-0800',
@@ -66,7 +83,10 @@ class TVPIE(InfoExtractor):
             'id': '52880236',
             'ext': 'mp4',
             'title': '09.04.2021, 08:00',
+            'age_limit': 0,
+            'thumbnail': r're:https://.+',
         },
+        'skip': 'Geo-blocked outside PL',
     }, {
         # client-side rendered (regional) program (playlist) page
         'url': 'https://opole.tvp.pl/9660819/rozmowa-dnia',
@@ -122,7 +142,7 @@ class TVPIE(InfoExtractor):
         'url': 'https://www.tvpparlament.pl/retransmisje-vod/inne/wizyta-premiera-mateusza-morawieckiego-w-firmie-berotu-sp-z-oo/48857277',
         'only_matching': True,
     }, {
-        'url': 'https://polandin.com/47942651/pln-10-billion-in-subsidies-transferred-to-companies-pm',
+        'url': 'https://tvpworld.com/48583640/tescos-polish-business-bought-by-danish-chain-netto',
         'only_matching': True,
     }]
 
@@ -151,16 +171,13 @@ def _extract_vue_video(self, video_data, page_id=None):
         is_website = video_data.get('type') == 'website'
         if is_website:
             url = video_data['url']
-            fucked_up_url_parts = re.match(r'https?://vod\.tvp\.pl/(\d+)/([^/?#]+)', url)
-            if fucked_up_url_parts:
-                url = f'https://vod.tvp.pl/website/{fucked_up_url_parts.group(2)},{fucked_up_url_parts.group(1)}'
         else:
             url = 'tvp:' + str_or_none(video_data.get('_id') or page_id)
         return {
             '_type': 'url_transparent',
             'id': str_or_none(video_data.get('_id') or page_id),
             'url': url,
-            'ie_key': 'TVPEmbed' if not is_website else 'TVPWebsite',
+            'ie_key': (TVPIE if is_website else TVPEmbedIE).ie_key(),
             'title': str_or_none(video_data.get('title')),
             'description': str_or_none(video_data.get('lead')),
             'timestamp': int_or_none(video_data.get('release_date_long')),
@@ -217,8 +234,9 @@ def _real_extract(self, url):
 
         # The URL may redirect to a VOD
         # example: https://vod.tvp.pl/48463890/wadowickie-spotkania-z-janem-pawlem-ii
-        if TVPWebsiteIE.suitable(urlh.url):
-            return self.url_result(urlh.url, ie=TVPWebsiteIE.ie_key(), video_id=page_id)
+        for ie_cls in (TVPVODSeriesIE, TVPVODVideoIE):
+            if ie_cls.suitable(urlh.url):
+                return self.url_result(urlh.url, ie=ie_cls.ie_key(), video_id=page_id)
 
         if re.search(
                 r'window\.__(?:video|news|website|directory)Data\s*=',
@@ -297,12 +315,13 @@ def _real_extract(self, url):
 class TVPEmbedIE(InfoExtractor):
     IE_NAME = 'tvp:embed'
     IE_DESC = 'Telewizja Polska'
+    _GEO_BYPASS = False
     _VALID_URL = r'''(?x)
         (?:
             tvp:
             |https?://
                 (?:[^/]+\.)?
-                (?:tvp(?:parlament)?\.pl|tvp\.info|polandin\.com)/
+                (?:tvp(?:parlament)?\.pl|tvp\.info|tvpworld\.com|swipeto\.pl)/
                 (?:sess/
                         (?:tvplayer\.php\?.*?object_id
                         |TVPlayer2/(?:embed|api)\.php\?.*[Ii][Dd])
@@ -320,6 +339,12 @@ class TVPEmbedIE(InfoExtractor):
             'title': 'Czas honoru, odc. 13 – Władek',
             'description': 'md5:76649d2014f65c99477be17f23a4dead',
             'age_limit': 12,
+            'duration': 2652,
+            'series': 'Czas honoru',
+            'episode': 'Episode 13',
+            'episode_number': 13,
+            'season': 'sezon 1',
+            'thumbnail': r're:https://.+',
         },
     }, {
         'url': 'https://www.tvp.pl/sess/tvplayer.php?object_id=51247504&amp;autoplay=false',
@@ -327,6 +352,9 @@ class TVPEmbedIE(InfoExtractor):
             'id': '51247504',
             'ext': 'mp4',
             'title': 'Razmova 091220',
+            'duration': 876,
+            'age_limit': 0,
+            'thumbnail': r're:https://.+',
         },
     }, {
         # TVPlayer2 embed URL
@@ -361,40 +389,48 @@ def _real_extract(self, url):
         # stripping JSONP padding
         datastr = webpage[15 + len(callback):-3]
         if datastr.startswith('null,'):
-            error = self._parse_json(datastr[5:], video_id)
-            raise ExtractorError(error[0]['desc'])
+            error = self._parse_json(datastr[5:], video_id, fatal=False)
+            error_desc = traverse_obj(error, (0, 'desc'))
+
+            if error_desc == 'Obiekt wymaga płatności':
+                raise ExtractorError('Video requires payment and log-in, but log-in is not implemented')
+
+            raise ExtractorError(error_desc or 'unexpected JSON error')
 
         content = self._parse_json(datastr, video_id)['content']
         info = content['info']
         is_live = try_get(info, lambda x: x['isLive'], bool)
 
+        if info.get('isGeoBlocked'):
+            # actual country list is not provided, we just assume it's always available in PL
+            self.raise_geo_restricted(countries=['PL'])
+
         formats = []
         for file in content['files']:
-            video_url = file.get('url')
+            video_url = url_or_none(file.get('url'))
             if not video_url:
                 continue
-            if video_url.endswith('.m3u8'):
+            ext = determine_ext(video_url, None)
+            if ext == 'm3u8':
                 formats.extend(self._extract_m3u8_formats(video_url, video_id, m3u8_id='hls', fatal=False, live=is_live))
-            elif video_url.endswith('.mpd'):
+            elif ext == 'mpd':
                 if is_live:
                     # doesn't work with either ffmpeg or native downloader
                     continue
                 formats.extend(self._extract_mpd_formats(video_url, video_id, mpd_id='dash', fatal=False))
-            elif video_url.endswith('.f4m'):
+            elif ext == 'f4m':
                 formats.extend(self._extract_f4m_formats(video_url, video_id, f4m_id='hds', fatal=False))
             elif video_url.endswith('.ism/manifest'):
                 formats.extend(self._extract_ism_formats(video_url, video_id, ism_id='mss', fatal=False))
             else:
-                # mp4, wmv or something
-                quality = file.get('quality', {})
                 formats.append({
                     'format_id': 'direct',
                     'url': video_url,
-                    'ext': determine_ext(video_url, file['type']),
-                    'fps': int_or_none(quality.get('fps')),
-                    'tbr': int_or_none(quality.get('bitrate')),
-                    'width': int_or_none(quality.get('width')),
-                    'height': int_or_none(quality.get('height')),
+                    'ext': ext or file.get('type'),
+                    'fps': int_or_none(traverse_obj(file, ('quality', 'fps'))),
+                    'tbr': int_or_none(traverse_obj(file, ('quality', 'bitrate')), scale=1000),
+                    'width': int_or_none(traverse_obj(file, ('quality', 'width'))),
+                    'height': int_or_none(traverse_obj(file, ('quality', 'height'))),
                 })
 
         self._sort_formats(formats)
@@ -449,57 +485,105 @@ def _real_extract(self, url):
         return info_dict
 
 
-class TVPWebsiteIE(InfoExtractor):
-    IE_NAME = 'tvp:series'
-    _VALID_URL = r'https?://vod\.tvp\.pl/website/(?P<display_id>[^,]+),(?P<id>\d+)'
+class TVPVODBaseIE(InfoExtractor):
+    _API_BASE_URL = 'https://vod.tvp.pl/api/products'
+
+    def _call_api(self, resource, video_id, **kwargs):
+        return self._download_json(
+            f'{self._API_BASE_URL}/{resource}', video_id,
+            query={'lang': 'pl', 'platform': 'BROWSER'}, **kwargs)
+
+    def _parse_video(self, video):
+        return {
+            '_type': 'url',
+            'url': 'tvp:' + video['externalUid'],
+            'ie_key': TVPEmbedIE.ie_key(),
+            'title': video.get('title'),
+            'description': traverse_obj(video, ('lead', 'description')),
+            'age_limit': int_or_none(video.get('rating')),
+            'duration': int_or_none(video.get('duration')),
+        }
+
+
+class TVPVODVideoIE(TVPVODBaseIE):
+    IE_NAME = 'tvp:vod'
+    _VALID_URL = r'https?://vod\.tvp\.pl/[a-z\d-]+,\d+/[a-z\d-]+(?<!-odcinki)(?:-odcinki,\d+/odcinek-\d+,S\d+E\d+)?,(?P<id>\d+)(?:\?[^#]+)?(?:#.+)?$'
 
     _TESTS = [{
-        # series
-        'url': 'https://vod.tvp.pl/website/wspaniale-stulecie,17069012/video',
+        'url': 'https://vod.tvp.pl/dla-dzieci,24/laboratorium-alchemika-odcinki,309338/odcinek-24,S01E24,311357',
         'info_dict': {
-            'id': '17069012',
-        },
-        'playlist_count': 312,
-    }, {
-        # film
-        'url': 'https://vod.tvp.pl/website/krzysztof-krawczyk-cale-moje-zycie,51374466',
-        'info_dict': {
-            'id': '51374509',
+            'id': '60468609',
             'ext': 'mp4',
-            'title': 'Krzysztof Krawczyk – całe moje życie, Krzysztof Krawczyk – całe moje życie',
-            'description': 'md5:2e80823f00f5fc263555482f76f8fa42',
-            'age_limit': 12,
+            'title': 'Laboratorium alchemika, Tusze termiczne. Jak zobaczyć niewidoczne. Odcinek 24',
+            'description': 'md5:1d4098d3e537092ccbac1abf49b7cd4c',
+            'duration': 300,
+            'episode_number': 24,
+            'episode': 'Episode 24',
+            'age_limit': 0,
+            'series': 'Laboratorium alchemika',
+            'thumbnail': 're:https://.+',
         },
-        'params': {
-            'skip_download': True,
-        },
-        'add_ie': ['TVPEmbed'],
     }, {
-        'url': 'https://vod.tvp.pl/website/lzy-cennet,38678312',
+        'url': 'https://vod.tvp.pl/filmy-dokumentalne,163/ukrainski-sluga-narodu,339667',
+        'info_dict': {
+            'id': '51640077',
+            'ext': 'mp4',
+            'title': 'Ukraiński sługa narodu, Ukraiński sługa narodu',
+            'series': 'Ukraiński sługa narodu',
+            'description': 'md5:b7940c0a8e439b0c81653a986f544ef3',
+            'age_limit': 12,
+            'episode': 'Episode 0',
+            'episode_number': 0,
+            'duration': 3051,
+            'thumbnail': 're:https://.+',
+        },
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        return self._parse_video(self._call_api(f'vods/{video_id}', video_id))
+
+
+class TVPVODSeriesIE(TVPVODBaseIE):
+    IE_NAME = 'tvp:vod:series'
+    _VALID_URL = r'https?://vod\.tvp\.pl/[a-z\d-]+,\d+/[a-z\d-]+-odcinki,(?P<id>\d+)(?:\?[^#]+)?(?:#.+)?$'
+
+    _TESTS = [{
+        'url': 'https://vod.tvp.pl/seriale,18/ranczo-odcinki,316445',
+        'info_dict': {
+            'id': '316445',
+            'title': 'Ranczo',
+            'age_limit': 12,
+            'categories': ['seriale'],
+        },
+        'playlist_count': 129,
+    }, {
+        'url': 'https://vod.tvp.pl/programy,88/rolnik-szuka-zony-odcinki,284514',
+        'only_matching': True,
+    }, {
+        'url': 'https://vod.tvp.pl/dla-dzieci,24/laboratorium-alchemika-odcinki,309338',
         'only_matching': True,
     }]
 
-    def _entries(self, display_id, playlist_id):
-        url = 'https://vod.tvp.pl/website/%s,%s/video' % (display_id, playlist_id)
-        for page_num in itertools.count(1):
-            page = self._download_webpage(
-                url, display_id, 'Downloading page %d' % page_num,
-                query={'page': page_num})
-
-            video_ids = orderedSet(re.findall(
-                r'<a[^>]+\bhref=["\']/video/%s,[^,]+,(\d+)' % display_id,
-                page))
-
-            if not video_ids:
-                break
-
-            for video_id in video_ids:
-                yield self.url_result(
-                    'tvp:%s' % video_id, ie=TVPEmbedIE.ie_key(),
-                    video_id=video_id)
+    def _entries(self, seasons, playlist_id):
+        for season in seasons:
+            episodes = self._call_api(
+                f'vods/serials/{playlist_id}/seasons/{season["id"]}/episodes', playlist_id,
+                note=f'Downloading episode list for {season["title"]}')
+            yield from map(self._parse_video, episodes)
 
     def _real_extract(self, url):
-        mobj = self._match_valid_url(url)
-        display_id, playlist_id = mobj.group('display_id', 'id')
+        playlist_id = self._match_id(url)
+        metadata = self._call_api(
+            f'vods/serials/{playlist_id}', playlist_id,
+            note='Downloading serial metadata')
+        seasons = self._call_api(
+            f'vods/serials/{playlist_id}/seasons', playlist_id,
+            note='Downloading season list')
         return self.playlist_result(
-            self._entries(display_id, playlist_id), playlist_id)
+            self._entries(seasons, playlist_id), playlist_id, strip_or_none(metadata.get('title')),
+            clean_html(traverse_obj(metadata, ('description', 'lead'), expected_type=strip_or_none)),
+            categories=[traverse_obj(metadata, ('mainCategory', 'name'))],
+            age_limit=int_or_none(metadata.get('rating')),
+        )

yt_dlp/extractor/vimeo.py

@@ -870,7 +870,7 @@ def _real_extract(self, url):
 
         if '://player.vimeo.com/video/' in url:
             config = self._parse_json(self._search_regex(
-                r'\bconfig\s*=\s*({.+?})\s*;', webpage, 'info section'), video_id)
+                r'\b(?:playerC|c)onfig\s*=\s*({.+?})\s*;', webpage, 'info section'), video_id)
             if config.get('view') == 4:
                 config = self._verify_player_video_password(
                     redirect_url, video_id, headers)

yt_dlp/extractor/vlive.py

@@ -13,6 +13,7 @@
     merge_dicts,
     str_or_none,
     strip_or_none,
+    traverse_obj,
     try_get,
     urlencode_postdata,
     url_or_none,
@@ -81,6 +82,13 @@ class VLiveIE(VLiveBaseIE):
             'upload_date': '20150817',
             'thumbnail': r're:^https?://.*\.(?:jpg|png)$',
             'timestamp': 1439816449,
+            'like_count': int,
+            'channel': 'Girl\'s Day',
+            'channel_id': 'FDF27',
+            'comment_count': int,
+            'release_timestamp': 1439818140,
+            'release_date': '20150817',
+            'duration': 1014,
         },
         'params': {
             'skip_download': True,
@@ -98,6 +106,13 @@ class VLiveIE(VLiveBaseIE):
             'upload_date': '20161112',
             'thumbnail': r're:^https?://.*\.(?:jpg|png)$',
             'timestamp': 1478923074,
+            'like_count': int,
+            'channel': 'EXO',
+            'channel_id': 'F94BD',
+            'comment_count': int,
+            'release_timestamp': 1478924280,
+            'release_date': '20161112',
+            'duration': 906,
         },
         'params': {
             'skip_download': True,
@@ -169,6 +184,7 @@ def get_common_fields():
                 'like_count': int_or_none(video.get('likeCount')),
                 'comment_count': int_or_none(video.get('commentCount')),
                 'timestamp': int_or_none(video.get('createdAt'), scale=1000),
+                'release_timestamp': int_or_none(traverse_obj(video, 'onAirStartAt', 'willStartAt'), scale=1000),
                 'thumbnail': video.get('thumb'),
             }
 

yt_dlp/extractor/yandexvideo.py

@@ -255,7 +255,7 @@ class ZenYandexIE(InfoExtractor):
     def _real_extract(self, url):
         video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
-        redirect = self._search_json(r'var it\s*=\s*', webpage, 'redirect', id, default={}).get('retpath')
+        redirect = self._search_json(r'var it\s*=', webpage, 'redirect', id, default={}).get('retpath')
         if redirect:
             video_id = self._match_id(redirect)
             webpage = self._download_webpage(redirect, video_id, note='Redirecting')
@@ -373,7 +373,7 @@ def _real_extract(self, url):
         item_id = self._match_id(url)
         webpage = self._download_webpage(url, item_id)
         redirect = self._search_json(
-            r'var it\s*=\s*', webpage, 'redirect', item_id, default={}).get('retpath')
+            r'var it\s*=', webpage, 'redirect', item_id, default={}).get('retpath')
         if redirect:
             item_id = self._match_id(redirect)
             webpage = self._download_webpage(redirect, item_id, note='Redirecting')

yt_dlp/extractor/youtube.py

@@ -369,14 +369,24 @@ class YoutubeBaseInfoExtractor(InfoExtractor):
         r'(?:www\.)?hpniueoejy4opn7bc4ftgazyqjoeqwlvh2uiku2xqku6zpoa4bf5ruid\.onion',
         # piped instances from https://github.com/TeamPiped/Piped/wiki/Instances
         r'(?:www\.)?piped\.kavin\.rocks',
-        r'(?:www\.)?piped\.silkky\.cloud',
         r'(?:www\.)?piped\.tokhmi\.xyz',
-        r'(?:www\.)?piped\.moomoo\.me',
-        r'(?:www\.)?il\.ax',
-        r'(?:www\.)?piped\.syncpundit\.com',
+        r'(?:www\.)?piped\.syncpundit\.io',
         r'(?:www\.)?piped\.mha\.fi',
+        r'(?:www\.)?watch\.whatever\.social',
+        r'(?:www\.)?piped\.garudalinux\.org',
+        r'(?:www\.)?piped\.rivo\.lol',
+        r'(?:www\.)?piped-libre\.kavin\.rocks',
+        r'(?:www\.)?yt\.jae\.fi',
         r'(?:www\.)?piped\.mint\.lgbt',
-        r'(?:www\.)?piped\.privacy\.com\.de',
+        r'(?:www\.)?il\.ax',
+        r'(?:www\.)?piped\.esmailelbob\.xyz',
+        r'(?:www\.)?piped\.projectsegfau\.lt',
+        r'(?:www\.)?piped\.privacydev\.net',
+        r'(?:www\.)?piped\.palveluntarjoaja\.eu',
+        r'(?:www\.)?piped\.smnz\.de',
+        r'(?:www\.)?piped\.adminforge\.de',
+        r'(?:www\.)?watch\.whatevertinfoil\.de',
+        r'(?:www\.)?piped\.qdi\.fi',
     )
 
     # extracted from account/account_menu ep

yt_dlp/extractor/zdf.py

@@ -3,13 +3,14 @@
 from .common import InfoExtractor
 from ..compat import compat_str
 from ..utils import (
+    NO_DEFAULT,
+    ExtractorError,
     determine_ext,
+    extract_attributes,
     float_or_none,
     int_or_none,
     join_nonempty,
     merge_dicts,
-    NO_DEFAULT,
-    orderedSet,
     parse_codecs,
     qualities,
     traverse_obj,
@@ -188,7 +189,7 @@ class ZDFIE(ZDFBaseIE):
         },
     }, {
         'url': 'https://www.zdf.de/funk/druck-11790/funk-alles-ist-verzaubert-102.html',
-        'md5': '57af4423db0455a3975d2dc4578536bc',
+        'md5': '1b93bdec7d02fc0b703c5e7687461628',
         'info_dict': {
             'ext': 'mp4',
             'id': 'video_funk_1770473',
@@ -250,17 +251,15 @@ def _extract_entry(self, url, player, content, video_id):
         title = content.get('title') or content['teaserHeadline']
 
         t = content['mainVideoContent']['http://zdf.de/rels/target']
-
-        ptmd_path = t.get('http://zdf.de/rels/streams/ptmd')
-
+        ptmd_path = traverse_obj(t, (
+            (('streams', 'default'), None),
+            ('http://zdf.de/rels/streams/ptmd', 'http://zdf.de/rels/streams/ptmd-template')
+        ), get_all=False)
         if not ptmd_path:
-            ptmd_path = traverse_obj(
-                t, ('streams', 'default', 'http://zdf.de/rels/streams/ptmd-template'),
-                'http://zdf.de/rels/streams/ptmd-template').replace(
-                '{playerId}', 'ngplayer_2_4')
+            raise ExtractorError('Could not extract ptmd_path')
 
         info = self._extract_ptmd(
-            urljoin(url, ptmd_path), video_id, player['apiToken'], url)
+            urljoin(url, ptmd_path.replace('{playerId}', 'ngplayer_2_4')), video_id, player['apiToken'], url)
 
         thumbnails = []
         layouts = try_get(
@@ -309,15 +308,16 @@ def _extract_mobile(self, video_id):
             'https://zdf-cdn.live.cellular.de/mediathekV2/document/%s' % video_id,
             video_id)
 
-        document = video['document']
-
-        title = document['titel']
-        content_id = document['basename']
-
         formats = []
-        format_urls = set()
-        for f in document['formitaeten']:
-            self._extract_format(content_id, formats, format_urls, f)
+        formitaeten = try_get(video, lambda x: x['document']['formitaeten'], list)
+        document = formitaeten and video['document']
+        if formitaeten:
+            title = document['titel']
+            content_id = document['basename']
+
+            format_urls = set()
+            for f in formitaeten or []:
+                self._extract_format(content_id, formats, format_urls, f)
         self._sort_formats(formats)
 
         thumbnails = []
@@ -364,9 +364,9 @@ class ZDFChannelIE(ZDFBaseIE):
         'url': 'https://www.zdf.de/sport/das-aktuelle-sportstudio',
         'info_dict': {
             'id': 'das-aktuelle-sportstudio',
-            'title': 'das aktuelle sportstudio | ZDF',
+            'title': 'das aktuelle sportstudio',
         },
-        'playlist_mincount': 23,
+        'playlist_mincount': 18,
     }, {
         'url': 'https://www.zdf.de/dokumentation/planet-e',
         'info_dict': {
@@ -374,6 +374,14 @@ class ZDFChannelIE(ZDFBaseIE):
             'title': 'planet e.',
         },
         'playlist_mincount': 50,
+    }, {
+        'url': 'https://www.zdf.de/gesellschaft/aktenzeichen-xy-ungeloest',
+        'info_dict': {
+            'id': 'aktenzeichen-xy-ungeloest',
+            'title': 'Aktenzeichen XY... ungelöst',
+            'entries': "lambda x: not any('xy580-fall1-kindermoerder-gesucht-100' in e['url'] for e in x)",
+        },
+        'playlist_mincount': 2,
     }, {
         'url': 'https://www.zdf.de/filme/taunuskrimi/',
         'only_matching': True,
@@ -383,60 +391,36 @@ class ZDFChannelIE(ZDFBaseIE):
     def suitable(cls, url):
         return False if ZDFIE.suitable(url) else super(ZDFChannelIE, cls).suitable(url)
 
+    def _og_search_title(self, webpage, fatal=False):
+        title = super(ZDFChannelIE, self)._og_search_title(webpage, fatal=fatal)
+        return re.split(r'\s+[-|]\s+ZDF(?:mediathek)?$', title or '')[0] or None
+
     def _real_extract(self, url):
         channel_id = self._match_id(url)
 
         webpage = self._download_webpage(url, channel_id)
 
-        entries = [
-            self.url_result(item_url, ie=ZDFIE.ie_key())
-            for item_url in orderedSet(re.findall(
-                r'data-plusbar-url=["\'](http.+?\.html)', webpage))]
+        matches = re.finditer(
+            r'''<div\b[^>]*?\sdata-plusbar-id\s*=\s*(["'])(?P<p_id>[\w-]+)\1[^>]*?\sdata-plusbar-url=\1(?P<url>%s)\1''' % ZDFIE._VALID_URL,
+            webpage)
 
-        return self.playlist_result(
-            entries, channel_id, self._og_search_title(webpage, fatal=False))
+        if self._downloader.params.get('noplaylist', False):
+            entry = next(
+                (self.url_result(m.group('url'), ie=ZDFIE.ie_key()) for m in matches),
+                None)
+            self.to_screen('Downloading just the main video because of --no-playlist')
+            if entry:
+                return entry
+        else:
+            self.to_screen('Downloading playlist %s - add --no-playlist to download just the main video' % (channel_id, ))
 
-        r"""
-        player = self._extract_player(webpage, channel_id)
+        def check_video(m):
+            v_ref = self._search_regex(
+                r'''(<a\b[^>]*?\shref\s*=[^>]+?\sdata-target-id\s*=\s*(["'])%s\2[^>]*>)''' % (m.group('p_id'), ),
+                webpage, 'check id', default='')
+            v_ref = extract_attributes(v_ref)
+            return v_ref.get('data-target-video-type') != 'novideo'
 
-        channel_id = self._search_regex(
-            r'docId\s*:\s*(["\'])(?P<id>(?!\1).+?)\1', webpage,
-            'channel id', group='id')
-
-        channel = self._call_api(
-            'https://api.zdf.de/content/documents/%s.json' % channel_id,
-            player, url, channel_id)
-
-        items = []
-        for module in channel['module']:
-            for teaser in try_get(module, lambda x: x['teaser'], list) or []:
-                t = try_get(
-                    teaser, lambda x: x['http://zdf.de/rels/target'], dict)
-                if not t:
-                    continue
-                items.extend(try_get(
-                    t,
-                    lambda x: x['resultsWithVideo']['http://zdf.de/rels/search/results'],
-                    list) or [])
-            items.extend(try_get(
-                module,
-                lambda x: x['filterRef']['resultsWithVideo']['http://zdf.de/rels/search/results'],
-                list) or [])
-
-        entries = []
-        entry_urls = set()
-        for item in items:
-            t = try_get(item, lambda x: x['http://zdf.de/rels/target'], dict)
-            if not t:
-                continue
-            sharing_url = t.get('http://zdf.de/rels/sharing-url')
-            if not sharing_url or not isinstance(sharing_url, compat_str):
-                continue
-            if sharing_url in entry_urls:
-                continue
-            entry_urls.add(sharing_url)
-            entries.append(self.url_result(
-                sharing_url, ie=ZDFIE.ie_key(), video_id=t.get('id')))
-
-        return self.playlist_result(entries, channel_id, channel.get('title'))
-        """
+        return self.playlist_from_matches(
+            (m.group('url') for m in matches if check_video(m)),
+            channel_id, self._og_search_title(webpage, fatal=False))

yt_dlp/options.py

@@ -294,9 +294,10 @@ def _create_alias(option, opt_str, value, parser):
 
         aliases = (x if x.startswith('-') else f'--{x}' for x in map(str.strip, aliases.split(',')))
         try:
+            args = [f'ARG{i}' for i in range(nargs)]
             alias_group.add_option(
-                *aliases, help=opts, nargs=nargs, dest=parser.ALIAS_DEST, type='str' if nargs else None,
-                metavar=' '.join(f'ARG{i}' for i in range(nargs)), action='callback',
+                *aliases, nargs=nargs, dest=parser.ALIAS_DEST, type='str' if nargs else None,
+                metavar=' '.join(args), help=opts.format(*args), action='callback',
                 callback=_alias_callback, callback_kwargs={'opts': opts, 'nargs': nargs})
         except Exception as err:
             raise optparse.OptionValueError(f'wrong {opt_str} formatting; {err}')
@@ -549,11 +550,11 @@ def _alias_callback(option, opt_str, value, parser, opts, nargs):
     selection.add_option(
         '--min-filesize',
         metavar='SIZE', dest='min_filesize', default=None,
-        help='Do not download any videos smaller than SIZE, e.g. 50k or 44.6M')
+        help='Abort download if filesize is smaller than SIZE, e.g. 50k or 44.6M')
     selection.add_option(
         '--max-filesize',
         metavar='SIZE', dest='max_filesize', default=None,
-        help='Do not download any videos larger than SIZE, e.g. 50k or 44.6M')
+        help='Abort download if filesize if larger than SIZE, e.g. 50k or 44.6M')
     selection.add_option(
         '--date',
         metavar='DATE', dest='date', default=None,

yt_dlp/update.py

@@ -174,6 +174,7 @@ def release_hash(self):
 
     def _report_error(self, msg, expected=False):
         self.ydl.report_error(msg, tb=False if expected else None)
+        self.ydl._download_retcode = 100
 
     def _report_permission_error(self, file):
         self._report_error(f'Unable to write to {file}; Try running as administrator', True)

yt_dlp/utils.py

@@ -480,6 +480,7 @@ def handle_endtag(self, tag):
             raise self.HTMLBreakOnClosingTagException()
 
 
+# XXX: This should be far less strict
 def get_element_text_and_html_by_tag(tag, html):
     """
     For the first element with the specified tag in the passed HTML document
@@ -524,6 +525,7 @@ def __init__(self):
 
     def handle_starttag(self, tag, attrs):
         self.attrs = dict(attrs)
+        raise compat_HTMLParseError('done')
 
 
 class HTMLListAttrsParser(html.parser.HTMLParser):
@@ -684,7 +686,8 @@ def replace_insane(char):
             return '\0_'
         return char
 
-    if restricted and is_id is NO_DEFAULT:
+    # Replace look-alike Unicode glyphs
+    if restricted and (is_id is NO_DEFAULT or not is_id):
         s = unicodedata.normalize('NFKC', s)
     s = re.sub(r'[0-9]+(?::[0-9]+)+', lambda m: m.group(0).replace(':', '_'), s)  # Handle timestamps
     result = ''.join(map(replace_insane, s))
@@ -985,6 +988,25 @@ def make_HTTPS_handler(params, **kwargs):
         context.options |= 4  # SSL_OP_LEGACY_SERVER_CONNECT
         # Allow use of weaker ciphers in Python 3.10+. See https://bugs.python.org/issue43998
         context.set_ciphers('DEFAULT')
+    elif (
+        sys.version_info < (3, 10)
+        and ssl.OPENSSL_VERSION_INFO >= (1, 1, 1)
+        and not ssl.OPENSSL_VERSION.startswith('LibreSSL')
+    ):
+        # Backport the default SSL ciphers and minimum TLS version settings from Python 3.10 [1].
+        # This is to ensure consistent behavior across Python versions, and help avoid fingerprinting
+        # in some situations [2][3].
+        # Python 3.10 only supports OpenSSL 1.1.1+ [4]. Because this change is likely
+        # untested on older versions, we only apply this to OpenSSL 1.1.1+ to be safe.
+        # LibreSSL is excluded until further investigation due to cipher support issues [5][6].
+        # 1. https://github.com/python/cpython/commit/e983252b516edb15d4338b0a47631b59ef1e2536
+        # 2. https://github.com/yt-dlp/yt-dlp/issues/4627
+        # 3. https://github.com/yt-dlp/yt-dlp/pull/5294
+        # 4. https://peps.python.org/pep-0644/
+        # 5. https://peps.python.org/pep-0644/#libressl-support
+        # 6. https://github.com/yt-dlp/yt-dlp/commit/5b9f253fa0aee996cf1ed30185d4b502e00609c4#commitcomment-89054368
+        context.set_ciphers('@SECLEVEL=2:ECDH+AESGCM:ECDH+CHACHA20:ECDH+AES:DHE+AES:!aNULL:!eNULL:!aDSS:!SHA1:!AESCCM')
+        context.minimum_version = ssl.TLSVersion.TLSv1_2
 
     context.verify_mode = ssl.CERT_REQUIRED if opts_check_certificate else ssl.CERT_NONE
     if opts_check_certificate:
@@ -1982,12 +2004,13 @@ def system_identifier():
     with contextlib.suppress(OSError):  # We may not have access to the executable
         libc_ver = platform.libc_ver()
 
-    return 'Python %s (%s %s) - %s %s' % (
+    return 'Python %s (%s %s) - %s (%s%s)' % (
         platform.python_version(),
         python_implementation,
         platform.architecture()[0],
         platform.platform(),
-        format_field(join_nonempty(*libc_ver, delim=' '), None, '(%s)'),
+        ssl.OPENSSL_VERSION,
+        format_field(join_nonempty(*libc_ver, delim=' '), None, ', %s'),
     )
 
 
@@ -3078,8 +3101,8 @@ def escape_url(url):
     ).geturl()
 
 
-def parse_qs(url):
-    return urllib.parse.parse_qs(urllib.parse.urlparse(url).query)
+def parse_qs(url, **kwargs):
+    return urllib.parse.parse_qs(urllib.parse.urlparse(url).query, **kwargs)
 
 
 def read_batch_urls(batch_fd):