[ie/n-tv.de] Fix extractor (#8414)

Closes #3179
Authored by: 1100101

yt_dlp/extractor/_extractors.py

@@ -953,6 +953,7 @@ from .lastfm import (
     LastFMPlaylistIE,
     LastFMUserIE,
 )
+from .laxarxames import LaXarxaMesIE
 from .lbry import (
     LBRYIE,
     LBRYChannelIE,
@@ -1387,7 +1388,10 @@ from .oftv import (
 from .oktoberfesttv import OktoberfestTVIE
 from .olympics import OlympicsReplayIE
 from .on24 import On24IE
-from .ondemandkorea import OnDemandKoreaIE
+from .ondemandkorea import (
+    OnDemandKoreaIE,
+    OnDemandKoreaProgramIE,
+)
 from .onefootball import OneFootballIE
 from .onenewsnz import OneNewsNZIE
 from .oneplace import OnePlacePodcastIE
@@ -1416,6 +1420,7 @@ from .orf import (
     ORFTVthekIE,
     ORFFM4StoryIE,
     ORFRadioIE,
+    ORFPodcastIE,
     ORFIPTVIE,
 )
 from .outsidetv import OutsideTVIE
@@ -1578,6 +1583,10 @@ from .radiocanada import (
     RadioCanadaIE,
     RadioCanadaAudioVideoIE,
 )
+from .radiocomercial import (
+    RadioComercialIE,
+    RadioComercialPlaylistIE,
+)
 from .radiode import RadioDeIE
 from .radiojavan import RadioJavanIE
 from .radiobremen import RadioBremenIE
@@ -1758,6 +1767,11 @@ from .samplefocus import SampleFocusIE
 from .sapo import SapoIE
 from .savefrom import SaveFromIE
 from .sbs import SBSIE
+from .sbscokr import (
+    SBSCoKrIE,
+    SBSCoKrAllvodProgramIE,
+    SBSCoKrProgramsVodIE,
+)
 from .screen9 import Screen9IE
 from .screencast import ScreencastIE
 from .screencastify import ScreencastifyIE
@@ -1902,6 +1916,8 @@ from .srmediathek import SRMediathekIE
 from .stacommu import (
     StacommuLiveIE,
     StacommuVODIE,
+    TheaterComplexTownVODIE,
+    TheaterComplexTownPPVIE,
 )
 from .stanfordoc import StanfordOpenClassroomIE
 from .startv import StarTVIE
@@ -2014,7 +2030,6 @@ from .thestar import TheStarIE
 from .thesun import TheSunIE
 from .theweatherchannel import TheWeatherChannelIE
 from .thisamericanlife import ThisAmericanLifeIE
-from .thisav import ThisAVIE
 from .thisoldhouse import ThisOldHouseIE
 from .thisvid import (
     ThisVidIE,

yt_dlp/extractor/brilliantpala.py

@@ -21,10 +21,10 @@ class BrilliantpalaBaseIE(InfoExtractor):
 
     def _get_logged_in_username(self, url, video_id):
         webpage, urlh = self._download_webpage_handle(url, video_id)
-        if self._LOGIN_API == urlh.url:
+        if urlh.url.startswith(self._LOGIN_API):
             self.raise_login_required()
         return self._html_search_regex(
-            r'"username"\s*:\s*"(?P<username>[^"]+)"', webpage, 'stream page info', 'username')
+            r'"username"\s*:\s*"(?P<username>[^"]+)"', webpage, 'logged-in username')
 
     def _perform_login(self, username, password):
         login_form = self._hidden_inputs(self._download_webpage(

yt_dlp/extractor/laxarxames.py

@@ -0,0 +1,73 @@
+import json
+
+from .brightcove import BrightcoveNewIE
+from .common import InfoExtractor
+from ..utils import ExtractorError
+from ..utils.traversal import traverse_obj
+
+
+class LaXarxaMesIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?laxarxames\.cat/(?:[^/?#]+/)*?(player|movie-details)/(?P<id>\d+)'
+    _NETRC_MACHINE = 'laxarxames'
+    _TOKEN = None
+    _TESTS = [{
+        'url': 'https://www.laxarxames.cat/player/3459421',
+        'md5': '0966f46c34275934c19af78f3df6e2bc',
+        'info_dict': {
+            'id': '6339612436112',
+            'ext': 'mp4',
+            'title': 'Resum | UA Horta — UD Viladecans',
+            'timestamp': 1697905186,
+            'thumbnail': r're:https?://.*\.jpg',
+            'description': '',
+            'upload_date': '20231021',
+            'duration': 129.44,
+            'tags': ['ott', 'esports', '23-24', ' futbol', ' futbol-partits', 'elit', 'resum'],
+            'uploader_id': '5779379807001',
+        },
+        'skip': 'Requires login',
+    }]
+
+    def _perform_login(self, username, password):
+        if self._TOKEN:
+            return
+
+        login = self._download_json(
+            'https://api.laxarxames.cat/Authorization/SignIn', None, note='Logging in', headers={
+                'X-Tenantorigin': 'https://laxarxames.cat',
+                'Content-Type': 'application/json',
+            }, data=json.dumps({
+                'Username': username,
+                'Password': password,
+                'Device': {
+                    'PlatformCode': 'WEB',
+                    'Name': 'Mac OS ()',
+                },
+            }).encode(), expected_status=401)
+
+        self._TOKEN = traverse_obj(login, ('AuthorizationToken', 'Token', {str}))
+        if not self._TOKEN:
+            raise ExtractorError('Login failed', expected=True)
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        if not self._TOKEN:
+            self.raise_login_required()
+
+        media_play_info = self._download_json(
+            'https://api.laxarxames.cat/Media/GetMediaPlayInfo', video_id,
+            data=json.dumps({
+                'MediaId': int(video_id),
+                'StreamType': 'MAIN'
+            }).encode(), headers={
+                'Authorization': f'Bearer {self._TOKEN}',
+                'X-Tenantorigin': 'https://laxarxames.cat',
+                'Content-Type': 'application/json',
+            })
+
+        if not traverse_obj(media_play_info, ('ContentUrl', {str})):
+            self.raise_no_formats('No video found', expected=True)
+
+        return self.url_result(
+            f'https://players.brightcove.net/5779379807001/default_default/index.html?videoId={media_play_info["ContentUrl"]}',
+            BrightcoveNewIE, video_id, media_play_info.get('Title'))

yt_dlp/extractor/neteasemusic.py

@@ -142,6 +142,9 @@ class NetEaseMusicIE(NetEaseMusicBaseIE):
             'subtitles': {'lyrics': [{'ext': 'lrc'}]},
             "duration": 256,
             'thumbnail': r're:^http.*\.jpg',
+            'album': '偶像练习生 表演曲目合集',
+            'average_rating': int,
+            'album_artist': '偶像练习生',
         },
     }, {
         'note': 'No lyrics.',
@@ -155,6 +158,9 @@ class NetEaseMusicIE(NetEaseMusicBaseIE):
             'timestamp': 1202745600,
             'duration': 263,
             'thumbnail': r're:^http.*\.jpg',
+            'album': 'Piano Solos Vol. 2',
+            'album_artist': 'Dustin O\'Halloran',
+            'average_rating': int,
         },
     }, {
         'url': 'https://y.music.163.com/m/song?app_version=8.8.45&id=95670&uct2=sKnvS4+0YStsWkqsPhFijw%3D%3D&dlt=0846',
@@ -171,6 +177,9 @@ class NetEaseMusicIE(NetEaseMusicBaseIE):
             'duration': 268,
             'alt_title': '伴唱:现代人乐队 合唱:总政歌舞团',
             'thumbnail': r're:^http.*\.jpg',
+            'average_rating': int,
+            'album': '红色摇滚',
+            'album_artist': '侯牧人',
         },
     }, {
         'url': 'http://music.163.com/#/song?id=32102397',
@@ -186,6 +195,9 @@ class NetEaseMusicIE(NetEaseMusicBaseIE):
             'subtitles': {'lyrics': [{'ext': 'lrc'}]},
             'duration': 199,
             'thumbnail': r're:^http.*\.jpg',
+            'album': 'Bad Blood',
+            'average_rating': int,
+            'album_artist': 'Taylor Swift',
         },
         'skip': 'Blocked outside Mainland China',
     }, {
@@ -203,6 +215,9 @@ class NetEaseMusicIE(NetEaseMusicBaseIE):
             'duration': 229,
             'alt_title': '说出愿望吧(Genie)',
             'thumbnail': r're:^http.*\.jpg',
+            'average_rating': int,
+            'album': 'Oh!',
+            'album_artist': '少女时代',
         },
         'skip': 'Blocked outside Mainland China',
     }]
@@ -253,12 +268,15 @@ class NetEaseMusicIE(NetEaseMusicBaseIE):
             'formats': formats,
             'alt_title': '/'.join(traverse_obj(info, (('transNames', 'alias'), ...))) or None,
             'creator': ' / '.join(traverse_obj(info, ('artists', ..., 'name'))) or None,
+            'album_artist': ' / '.join(traverse_obj(info, ('album', 'artists', ..., 'name'))) or None,
             **lyric_data,
             **traverse_obj(info, {
                 'title': ('name', {str}),
                 'timestamp': ('album', 'publishTime', {self.kilo_or_none}),
                 'thumbnail': ('album', 'picUrl', {url_or_none}),
                 'duration': ('duration', {self.kilo_or_none}),
+                'album': ('album', 'name', {str}),
+                'average_rating': ('score', {int_or_none}),
             }),
         }
 

yt_dlp/extractor/nhk.py

@@ -3,6 +3,8 @@ import re
 from .common import InfoExtractor
 from ..utils import (
     ExtractorError,
+    clean_html,
+    get_element_by_class,
     int_or_none,
     join_nonempty,
     parse_duration,
@@ -45,25 +47,36 @@ class NhkBaseIE(InfoExtractor):
         self.cache.store('nhk', 'api_info', api_info)
         return api_info
 
-    def _extract_formats_and_subtitles(self, vod_id):
+    def _extract_stream_info(self, vod_id):
         for refresh in (False, True):
             api_info = self._get_api_info(refresh)
             if not api_info:
                 continue
 
             api_url = api_info.pop('url')
-            stream_url = traverse_obj(
+            meta = traverse_obj(
                 self._download_json(
                     api_url, vod_id, 'Downloading stream url info', fatal=False, query={
                         **api_info,
                         'type': 'json',
                         'optional_id': vod_id,
                         'active_flg': 1,
-                    }),
+                    }), ('meta', 0))
-                ('meta', 0, 'movie_url', ('mb_auto', 'auto_sp', 'auto_pc'), {url_or_none}), get_all=False)
+            stream_url = traverse_obj(
-            if stream_url:
+                meta, ('movie_url', ('mb_auto', 'auto_sp', 'auto_pc'), {url_or_none}), get_all=False)
-                return self._extract_m3u8_formats_and_subtitles(stream_url, vod_id)
 
+            if stream_url:
+                formats, subtitles = self._extract_m3u8_formats_and_subtitles(stream_url, vod_id)
+                return {
+                    **traverse_obj(meta, {
+                        'duration': ('duration', {int_or_none}),
+                        'timestamp': ('publication_date', {unified_timestamp}),
+                        'release_timestamp': ('insert_date', {unified_timestamp}),
+                        'modified_timestamp': ('update_date', {unified_timestamp}),
+                    }),
+                    'formats': formats,
+                    'subtitles': subtitles,
+                }
         raise ExtractorError('Unable to extract stream url')
 
     def _extract_episode_info(self, url, episode=None):
@@ -77,11 +90,11 @@ class NhkBaseIE(InfoExtractor):
         if fetch_episode:
             episode = self._call_api(
                 episode_id, lang, is_video, True, episode_id[:4] == '9999')[0]
-        title = episode.get('sub_title_clean') or episode['sub_title']
 
         def get_clean_field(key):
-            return episode.get(key + '_clean') or episode.get(key)
+            return clean_html(episode.get(key + '_clean') or episode.get(key))
 
+        title = get_clean_field('sub_title')
         series = get_clean_field('title')
 
         thumbnails = []
@@ -96,22 +109,30 @@ class NhkBaseIE(InfoExtractor):
                 'url': 'https://www3.nhk.or.jp' + img_path,
             })
 
+        episode_name = title
+        if series and title:
+            title = f'{series} - {title}'
+        elif series and not title:
+            title = series
+            series = None
+            episode_name = None
+        else:  # title, no series
+            episode_name = None
+
         info = {
             'id': episode_id + '-' + lang,
-            'title': '%s - %s' % (series, title) if series and title else title,
+            'title': title,
             'description': get_clean_field('description'),
             'thumbnails': thumbnails,
             'series': series,
-            'episode': title,
+            'episode': episode_name,
         }
+
         if is_video:
             vod_id = episode['vod_id']
-            formats, subs = self._extract_formats_and_subtitles(vod_id)
-
             info.update({
+                **self._extract_stream_info(vod_id),
                 'id': vod_id,
-                'formats': formats,
-                'subtitles': subs,
             })
 
         else:
@@ -148,6 +169,14 @@ class NhkVodIE(NhkBaseIE):
             'thumbnail': 'md5:51bcef4a21936e7fea1ff4e06353f463',
             'episode': 'The Tohoku Shinkansen: Full Speed Ahead',
             'series': 'Japan Railway Journal',
+            'modified_timestamp': 1694243656,
+            'timestamp': 1681428600,
+            'release_timestamp': 1693883728,
+            'duration': 1679,
+            'upload_date': '20230413',
+            'modified_date': '20230909',
+            'release_date': '20230905',
+
         },
     }, {
         # video clip
@@ -161,6 +190,13 @@ class NhkVodIE(NhkBaseIE):
             'thumbnail': 'md5:d6a4d9b6e9be90aaadda0bcce89631ed',
             'series': 'Dining with the Chef',
             'episode': 'Chef Saito\'s Family recipe: MENCHI-KATSU',
+            'duration': 148,
+            'upload_date': '20190816',
+            'release_date': '20230902',
+            'release_timestamp': 1693619292,
+            'modified_timestamp': 1694168033,
+            'modified_date': '20230908',
+            'timestamp': 1565997540,
         },
     }, {
         # radio
@@ -170,7 +206,7 @@ class NhkVodIE(NhkBaseIE):
             'ext': 'm4a',
             'title': 'Living in Japan - Tips for Travelers to Japan / Ramen Vending Machines',
             'series': 'Living in Japan',
-            'description': 'md5:850611969932874b4a3309e0cae06c2f',
+            'description': 'md5:0a0e2077d8f07a03071e990a6f51bfab',
             'thumbnail': 'md5:960622fb6e06054a4a1a0c97ea752545',
             'episode': 'Tips for Travelers to Japan / Ramen Vending Machines'
         },
@@ -212,6 +248,23 @@ class NhkVodIE(NhkBaseIE):
             'description': 'md5:9c1d6cbeadb827b955b20e99ab920ff0',
         },
         'skip': 'expires 2023-10-15',
+    }, {
+        # a one-off (single-episode series). title from the api is just '<p></p>'
+        'url': 'https://www3.nhk.or.jp/nhkworld/en/ondemand/video/3004952/',
+        'info_dict': {
+            'id': 'nw_vod_v_en_3004_952_20230723091000_01_1690074552',
+            'ext': 'mp4',
+            'title': 'Barakan Discovers AMAMI OSHIMA: Isson\'s Treasure Island',
+            'description': 'md5:5db620c46a0698451cc59add8816b797',
+            'thumbnail': 'md5:67d9ff28009ba379bfa85ad1aaa0e2bd',
+            'release_date': '20230905',
+            'timestamp': 1690103400,
+            'duration': 2939,
+            'release_timestamp': 1693898699,
+            'modified_timestamp': 1698057495,
+            'modified_date': '20231023',
+            'upload_date': '20230723',
+        },
     }]
 
     def _real_extract(self, url):
@@ -226,13 +279,15 @@ class NhkVodProgramIE(NhkBaseIE):
         'info_dict': {
             'id': 'sumo',
             'title': 'GRAND SUMO Highlights',
+            'description': 'md5:fc20d02dc6ce85e4b72e0273aa52fdbf',
         },
-        'playlist_mincount': 12,
+        'playlist_mincount': 0,
     }, {
         'url': 'https://www3.nhk.or.jp/nhkworld/en/ondemand/program/video/japanrailway',
         'info_dict': {
             'id': 'japanrailway',
             'title': 'Japan Railway Journal',
+            'description': 'md5:ea39d93af7d05835baadf10d1aae0e3f',
         },
         'playlist_mincount': 12,
     }, {
@@ -241,6 +296,7 @@ class NhkVodProgramIE(NhkBaseIE):
         'info_dict': {
             'id': 'japanrailway',
             'title': 'Japan Railway Journal',
+            'description': 'md5:ea39d93af7d05835baadf10d1aae0e3f',
         },
         'playlist_mincount': 5,
     }, {
@@ -265,11 +321,11 @@ class NhkVodProgramIE(NhkBaseIE):
             entries.append(self._extract_episode_info(
                 urljoin(url, episode_path), episode))
 
-        program_title = None
+        html = self._download_webpage(url, program_id)
-        if entries:
+        program_title = clean_html(get_element_by_class('p-programDetail__title', html))
-            program_title = entries[0].get('series')
+        program_description = clean_html(get_element_by_class('p-programDetail__text', html))
 
-        return self.playlist_result(entries, program_id, program_title)
+        return self.playlist_result(entries, program_id, program_title, program_description)
 
 
 class NhkForSchoolBangumiIE(InfoExtractor):
@@ -421,6 +477,7 @@ class NhkRadiruIE(InfoExtractor):
         'skip': 'Episode expired on 2023-04-16',
         'info_dict': {
             'channel': 'NHK-FM',
+            'uploader': 'NHK-FM',
             'description': 'md5:94b08bdeadde81a97df4ec882acce3e9',
             'ext': 'm4a',
             'id': '0449_01_3853544',
@@ -441,6 +498,7 @@ class NhkRadiruIE(InfoExtractor):
             'title': 'ベストオブクラシック',
             'description': '世界中の上質な演奏会をじっくり堪能する本格派クラシック番組。',
             'channel': 'NHK-FM',
+            'uploader': 'NHK-FM',
             'thumbnail': 'https://www.nhk.or.jp/prog/img/458/g458.jpg',
         },
         'playlist_mincount': 3,
@@ -454,6 +512,7 @@ class NhkRadiruIE(InfoExtractor):
             'title': '有島武郎「一房のぶどう」',
             'description': '朗読：川野一宇（ラジオ深夜便アンカー）\r\n\r\n（2016年12月8日放送「ラジオ深夜便『アンカー朗読シリーズ』」より）',
             'channel': 'NHKラジオ第1、NHK-FM',
+            'uploader': 'NHKラジオ第1、NHK-FM',
             'timestamp': 1635757200,
             'thumbnail': 'https://www.nhk.or.jp/radioondemand/json/F300/img/corner/box_109_thumbnail.jpg',
             'release_date': '20161207',
@@ -469,6 +528,7 @@ class NhkRadiruIE(InfoExtractor):
             'id': 'F261_01_3855109',
             'ext': 'm4a',
             'channel': 'NHKラジオ第1',
+            'uploader': 'NHKラジオ第1',
             'timestamp': 1681635900,
             'release_date': '20230416',
             'series': 'NHKラジオニュース',
@@ -513,6 +573,7 @@ class NhkRadiruIE(InfoExtractor):
         series_meta = traverse_obj(meta, {
             'title': 'program_name',
             'channel': 'media_name',
+            'uploader': 'media_name',
             'thumbnail': (('thumbnail_c', 'thumbnail_p'), {url_or_none}),
         }, get_all=False)
 
@@ -541,6 +602,7 @@ class NhkRadioNewsPageIE(InfoExtractor):
             'thumbnail': 'https://www.nhk.or.jp/radioondemand/json/F261/img/RADIONEWS_640.jpg',
             'description': 'md5:bf2c5b397e44bc7eb26de98d8f15d79d',
             'channel': 'NHKラジオ第1',
+            'uploader': 'NHKラジオ第1',
             'title': 'NHKラジオニュース',
         }
     }]

yt_dlp/extractor/nova.py

@@ -13,7 +13,7 @@ from ..utils import (
 
 
 class NovaEmbedIE(InfoExtractor):
-    _VALID_URL = r'https?://media\.cms\.nova\.cz/embed/(?P<id>[^/?#&]+)'
+    _VALID_URL = r'https?://media(?:tn)?\.cms\.nova\.cz/embed/(?P<id>[^/?#&]+)'
     _TESTS = [{
         'url': 'https://media.cms.nova.cz/embed/8o0n0r?autoplay=1',
         'info_dict': {
@@ -37,6 +37,16 @@ class NovaEmbedIE(InfoExtractor):
             'duration': 114,
         },
         'params': {'skip_download': 'm3u8'},
+    }, {
+        'url': 'https://mediatn.cms.nova.cz/embed/EU5ELEsmOHt?autoplay=1',
+        'info_dict': {
+            'id': 'EU5ELEsmOHt',
+            'ext': 'mp4',
+            'title': 'Haptické křeslo, bionická ruka nebo roboti. Reportérka se podívala na Týden inovací',
+            'thumbnail': r're:^https?://.*\.jpg',
+            'duration': 1780,
+        },
+        'params': {'skip_download': 'm3u8'},
     }]
 
     def _real_extract(self, url):

yt_dlp/extractor/ntvde.py

@@ -1,21 +1,21 @@
 import re
 
 from .common import InfoExtractor
-from ..compat import compat_urlparse
 from ..utils import (
     int_or_none,
     js_to_json,
-    parse_duration,
+    url_or_none,
 )
+from ..utils.traversal import traverse_obj
 
 
 class NTVDeIE(InfoExtractor):
     IE_NAME = 'n-tv.de'
-    _VALID_URL = r'https?://(?:www\.)?n-tv\.de/mediathek/videos/[^/?#]+/[^/?#]+-article(?P<id>.+)\.html'
+    _VALID_URL = r'https?://(?:www\.)?n-tv\.de/mediathek/(?:videos|magazine)/[^/?#]+/[^/?#]+-article(?P<id>[^/?#]+)\.html'
 
     _TESTS = [{
         'url': 'http://www.n-tv.de/mediathek/videos/panorama/Schnee-und-Glaette-fuehren-zu-zahlreichen-Unfaellen-und-Staus-article14438086.html',
-        'md5': '6ef2514d4b1e8e03ca24b49e2f167153',
+        'md5': '6bcf2a6638cb83f45d5561659a1cb498',
         'info_dict': {
             'id': '14438086',
             'ext': 'mp4',
@@ -23,51 +23,61 @@ class NTVDeIE(InfoExtractor):
             'title': 'Schnee und Glätte führen zu zahlreichen Unfällen und Staus',
             'alt_title': 'Winterchaos auf deutschen Straßen',
             'description': 'Schnee und Glätte sorgen deutschlandweit für einen chaotischen Start in die Woche: Auf den Straßen kommt es zu kilometerlangen Staus und Dutzenden Glätteunfällen. In Düsseldorf und München wirbelt der Schnee zudem den Flugplan durcheinander. Dutzende Flüge landen zu spät, einige fallen ganz aus.',
-            'duration': 4020,
+            'duration': 67,
             'timestamp': 1422892797,
             'upload_date': '20150202',
         },
+    }, {
+        'url': 'https://www.n-tv.de/mediathek/magazine/auslandsreport/Juedische-Siedler-wollten-Rache-die-wollten-nur-toeten-article24523089.html',
+        'md5': 'c5c6014c014ccc3359470e1d34472bfd',
+        'info_dict': {
+            'id': '24523089',
+            'ext': 'mp4',
+            'thumbnail': r're:^https?://.*\.jpg$',
+            'title': 'Jüdische Siedler "wollten Rache, die wollten nur töten"',
+            'alt_title': 'Israelische Gewalt fern von Gaza',
+            'description': 'Vier Tage nach dem Massaker der Hamas greifen jüdische Siedler das Haus einer palästinensischen Familie im Westjordanland an. Die Überlebenden berichten, sie waren unbewaffnet, die Angreifer seien nur auf "Rache und Töten" aus gewesen. Als die Toten beerdigt werden sollen, eröffnen die Siedler erneut das Feuer.',
+            'duration': 326,
+            'timestamp': 1699688294,
+            'upload_date': '20231111',
+        },
     }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
 
-        info = self._parse_json(self._search_regex(
+        info = self._search_json(
-            r'(?s)ntv\.pageInfo\.article\s*=\s*(\{.*?\});', webpage, 'info'),
+            r'article:', webpage, 'info', video_id, transform_source=js_to_json)
-            video_id, transform_source=js_to_json)
+
-        timestamp = int_or_none(info.get('publishedDateAsUnixTimeStamp'))
+        vdata = self._search_json(
-        vdata = self._parse_json(self._search_regex(
+            r'\$\(\s*"#playerwrapper"\s*\)\s*\.data\(\s*"player",',
-            r'(?s)\$\(\s*"\#player"\s*\)\s*\.data\(\s*"player",\s*(\{.*?\})\);',
+            webpage, 'player data', video_id,
-            webpage, 'player data'), video_id,
+            transform_source=lambda s: js_to_json(re.sub(r'ivw:[^},]+', '', s)))['setup']['source']
-            transform_source=lambda s: js_to_json(re.sub(r'advertising:\s*{[^}]+},', '', s)))
-        duration = parse_duration(vdata.get('duration'))
 
         formats = []
-        if vdata.get('video'):
+        if vdata.get('progressive'):
             formats.append({
-                'format_id': 'flash',
+                'format_id': 'http',
-                'url': 'rtmp://fms.n-tv.de/%s' % vdata['video'],
+                'url': vdata['progressive'],
             })
-        if vdata.get('videoMp4'):
+        if vdata.get('hls'):
-            formats.append({
-                'format_id': 'mobile',
-                'url': compat_urlparse.urljoin('http://video.n-tv.de', vdata['videoMp4']),
-                'tbr': 400,  # estimation
-            })
-        if vdata.get('videoM3u8'):
-            m3u8_url = compat_urlparse.urljoin('http://video.n-tv.de', vdata['videoM3u8'])
             formats.extend(self._extract_m3u8_formats(
-                m3u8_url, video_id, ext='mp4', entry_protocol='m3u8_native',
+                vdata['hls'], video_id, 'mp4', m3u8_id='hls', fatal=False))
-                quality=1, m3u8_id='hls', fatal=False))
+        if vdata.get('dash'):
+            formats.extend(self._extract_mpd_formats(vdata['dash'], video_id, fatal=False, mpd_id='dash'))
 
         return {
             'id': video_id,
-            'title': info['headline'],
+            **traverse_obj(info, {
-            'description': info.get('intro'),
+                'title': 'headline',
-            'alt_title': info.get('kicker'),
+                'description': 'intro',
-            'timestamp': timestamp,
+                'alt_title': 'kicker',
-            'thumbnail': vdata.get('html5VideoPoster'),
+                'timestamp': ('publishedDateAsUnixTimeStamp', {int_or_none}),
-            'duration': duration,
+            }),
+            **traverse_obj(vdata, {
+                'thumbnail': ('poster', {url_or_none}),
+                'duration': ('length', {int_or_none}),
+            }),
             'formats': formats,
         }

yt_dlp/extractor/ondemandkorea.py

@@ -1,87 +1,167 @@
+import functools
 import re
+import uuid
 
 from .common import InfoExtractor
+from ..networking import HEADRequest
 from ..utils import (
     ExtractorError,
-    js_to_json,
+    OnDemandPagedList,
+    float_or_none,
+    int_or_none,
+    join_nonempty,
+    parse_age_limit,
+    parse_qs,
+    unified_strdate,
+    url_or_none,
 )
+from ..utils.traversal import traverse_obj
 
 
 class OnDemandKoreaIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?ondemandkorea\.com/(?P<id>[^/]+)\.html'
+    _VALID_URL = r'https?://(?:www\.)?ondemandkorea\.com/(?:en/)?player/vod/[a-z0-9-]+\?(?:[^#]+&)?contentId=(?P<id>\d+)'
     _GEO_COUNTRIES = ['US', 'CA']
+
     _TESTS = [{
-        'url': 'https://www.ondemandkorea.com/ask-us-anything-e351.html',
+        'url': 'https://www.ondemandkorea.com/player/vod/ask-us-anything?contentId=686471',
+        'md5': 'e2ff77255d989e3135bde0c5889fbce8',
         'info_dict': {
-            'id': 'ask-us-anything-e351',
+            'id': '686471',
             'ext': 'mp4',
-            'title': 'Ask Us Anything : Jung Sung-ho, Park Seul-gi, Kim Bo-min, Yang Seung-won - 09/24/2022',
+            'title': 'Ask Us Anything: Jung Sung-ho, Park Seul-gi, Kim Bo-min, Yang Seung-won',
-            'description': 'A talk show/game show with a school theme where celebrity guests appear as “transfer students.”',
+            'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)',
-            'thumbnail': r're:^https?://.*\.jpg$',
+            'duration': 5486.955,
+            'release_date': '20220924',
+            'series': 'Ask Us Anything',
+            'series_id': 11790,
+            'episode_number': 351,
+            'episode': 'Jung Sung-ho, Park Seul-gi, Kim Bo-min, Yang Seung-won',
         },
-        'params': {
-            'skip_download': 'm3u8 download'
-        }
     }, {
-        'url': 'https://www.ondemandkorea.com/work-later-drink-now-e1.html',
+        'url': 'https://www.ondemandkorea.com/player/vod/breakup-probation-a-week?contentId=1595796',
+        'md5': '57266c720006962be7ff415b24775caa',
         'info_dict': {
-            'id': 'work-later-drink-now-e1',
+            'id': '1595796',
             'ext': 'mp4',
-            'title': 'Work Later, Drink Now : E01',
+            'title': 'Breakup Probation, A Week: E08',
-            'description': 'Work Later, Drink First follows three women who find solace in a glass of liquor at the end of the day. So-hee, who gets comfort from a cup of soju af',
+            'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)',
-            'thumbnail': r're:^https?://.*\.png$',
+            'duration': 1586.0,
-            'subtitles': {
+            'release_date': '20231001',
-                'English': 'mincount:1',
+            'series': 'Breakup Probation, A Week',
-            },
+            'series_id': 22912,
+            'episode_number': 8,
+            'episode': 'E08',
         },
-        'params': {
+    }, {
-            'skip_download': 'm3u8 download'
+        'url': 'https://www.ondemandkorea.com/player/vod/the-outlaws?contentId=369531',
-        }
+        'md5': 'fa5523b87aa1f6d74fc622a97f2b47cd',
+        'info_dict': {
+            'id': '369531',
+            'ext': 'mp4',
+            'release_date': '20220519',
+            'duration': 7267.0,
+            'title': 'The Outlaws: Main Movie',
+            'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)',
+            'age_limit': 18,
+        },
+    }, {
+        'url': 'https://www.ondemandkorea.com/en/player/vod/capture-the-moment-how-is-that-possible?contentId=1605006',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
-        webpage = self._download_webpage(url, video_id, fatal=False)
 
-        if not webpage:
+        data = self._download_json(
-            # Page sometimes returns captcha page with HTTP 403
+            f'https://odkmedia.io/odx/api/v3/playback/{video_id}/', video_id, fatal=False,
-            raise ExtractorError(
+            headers={'service-name': 'odk'}, query={'did': str(uuid.uuid4())}, expected_status=(403, 404))
-                'Unable to access page. You may have been blocked.',
+        if not traverse_obj(data, ('result', {dict})):
-                expected=True)
+            msg = traverse_obj(data, ('messages', '__default'), 'title', expected_type=str)
+            raise ExtractorError(msg or 'Got empty response from playback API', expected=True)
 
-        if 'msg_block_01.png' in webpage:
+        data = data['result']
-            self.raise_geo_restricted(
-                msg='This content is not available in your region',
-                countries=self._GEO_COUNTRIES)
 
-        if 'This video is only available to ODK PLUS members.' in webpage:
+        def try_geo_bypass(url):
-            raise ExtractorError(
+            return traverse_obj(url, ({parse_qs}, 'stream_url', 0, {url_or_none})) or url
-                'This video is only available to ODK PLUS members.',
-                expected=True)
 
-        if 'ODK PREMIUM Members Only' in webpage:
+        def try_upgrade_quality(url):
-            raise ExtractorError(
+            mod_url = re.sub(r'_720(p?)\.m3u8', r'_1080\1.m3u8', url)
-                'This video is only available to ODK PREMIUM members.',
+            return mod_url if mod_url != url and self._request_webpage(
-                expected=True)
+                HEADRequest(mod_url), video_id, note='Checking for higher quality format',
+                errnote='No higher quality format found', fatal=False) else url
 
-        title = self._search_regex(
+        formats = []
-            r'class=["\']episode_title["\'][^>]*>([^<]+)',
+        for m3u8_url in traverse_obj(data, (('sources', 'manifest'), ..., 'url', {url_or_none}, {try_geo_bypass})):
-            webpage, 'episode_title', fatal=False) or self._og_search_title(webpage)
+            formats.extend(self._extract_m3u8_formats(try_upgrade_quality(m3u8_url), video_id, fatal=False))
 
-        jw_config = self._parse_json(
+        subtitles = {}
-            self._search_regex((
+        for track in traverse_obj(data, ('text_tracks', lambda _, v: url_or_none(v['url']))):
-                r'(?P<options>{\s*[\'"]tracks[\'"].*?})[)\];]+$',
+            subtitles.setdefault(track.get('language', 'und'), []).append({
-                r'playlist\s*=\s*\[(?P<options>.+)];?$',
+                'url': track['url'],
-                r'odkPlayer\.init.*?(?P<options>{[^;]+}).*?;',
+                'ext': track.get('codec'),
-            ), webpage, 'jw config', flags=re.MULTILINE | re.DOTALL, group='options'),
+                'name': track.get('label'),
-            video_id, transform_source=js_to_json)
+            })
-        info = self._parse_jwplayer_data(
-            jw_config, video_id, require_title=False, m3u8_id='hls',
-            base_url=url)
 
-        info.update({
+        def if_series(key=None):
-            'title': title,
+            return lambda obj: obj[key] if key and obj['kind'] == 'series' else None
-            'description': self._og_search_description(webpage),
+
-            'thumbnail': self._og_search_thumbnail(webpage)
+        return {
-        })
+            'id': video_id,
-        return info
+            'title': join_nonempty(
+                ('episode', 'program', 'title'),
+                ('episode', 'title'), from_dict=data, delim=': '),
+            **traverse_obj(data, {
+                'thumbnail': ('episode', 'images', 'thumbnail', {url_or_none}),
+                'release_date': ('episode', 'release_date', {lambda x: x.replace('-', '')}, {unified_strdate}),
+                'duration': ('duration', {functools.partial(float_or_none, scale=1000)}),
+                'age_limit': ('age_rating', 'name', {lambda x: x.replace('R', '')}, {parse_age_limit}),
+                'series': ('episode', {if_series(key='program')}, 'title'),
+                'series_id': ('episode', {if_series(key='program')}, 'id'),
+                'episode': ('episode', {if_series(key='title')}),
+                'episode_number': ('episode', {if_series(key='number')}, {int_or_none}),
+            }, get_all=False),
+            'formats': formats,
+            'subtitles': subtitles,
+        }
+
+
+class OnDemandKoreaProgramIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?ondemandkorea\.com/(?:en/)?player/vod/(?P<id>[a-z0-9-]+)(?:$|#)'
+    _GEO_COUNTRIES = ['US', 'CA']
+
+    _TESTS = [{
+        'url': 'https://www.ondemandkorea.com/player/vod/uskn-news',
+        'info_dict': {
+            'id': 'uskn-news',
+        },
+        'playlist_mincount': 755,
+    }, {
+        'url': 'https://www.ondemandkorea.com/en/player/vod/the-land',
+        'info_dict': {
+            'id': 'the-land',
+        },
+        'playlist_count': 52,
+    }]
+
+    _PAGE_SIZE = 100
+
+    def _fetch_page(self, display_id, page):
+        page += 1
+        page_data = self._download_json(
+            f'https://odkmedia.io/odx/api/v3/program/{display_id}/episodes/', display_id,
+            headers={'service-name': 'odk'}, query={
+                'page': page,
+                'page_size': self._PAGE_SIZE,
+            }, note=f'Downloading page {page}', expected_status=404)
+        for episode in traverse_obj(page_data, ('result', 'results', ...)):
+            yield self.url_result(
+                f'https://www.ondemandkorea.com/player/vod/{display_id}?contentId={episode["id"]}',
+                ie=OnDemandKoreaIE, video_title=episode.get('title'))
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+
+        entries = OnDemandPagedList(functools.partial(
+            self._fetch_page, display_id), self._PAGE_SIZE)
+
+        return self.playlist_result(entries, display_id)

yt_dlp/extractor/orf.py

@@ -4,15 +4,16 @@ import re
 from .common import InfoExtractor
 from ..networking import HEADRequest
 from ..utils import (
+    InAdvancePagedList,
     clean_html,
     determine_ext,
     float_or_none,
-    InAdvancePagedList,
     int_or_none,
     join_nonempty,
+    make_archive_id,
+    mimetype2ext,
     orderedSet,
     remove_end,
-    make_archive_id,
     smuggle_url,
     strip_jsonp,
     try_call,
@@ -21,6 +22,7 @@ from ..utils import (
     unsmuggle_url,
     url_or_none,
 )
+from ..utils.traversal import traverse_obj
 
 
 class ORFTVthekIE(InfoExtractor):
@@ -334,6 +336,45 @@ class ORFRadioIE(InfoExtractor):
             self._entries(data, station or station2), show_id, data.get('title'), clean_html(data.get('subtitle')))
 
 
+class ORFPodcastIE(InfoExtractor):
+    IE_NAME = 'orf:podcast'
+    _STATION_RE = '|'.join(map(re.escape, (
+        'bgl', 'fm4', 'ktn', 'noe', 'oe1', 'oe3',
+        'ooe', 'sbg', 'stm', 'tir', 'tv', 'vbg', 'wie')))
+    _VALID_URL = rf'https?://sound\.orf\.at/podcast/(?P<station>{_STATION_RE})/(?P<show>[\w-]+)/(?P<id>[\w-]+)'
+    _TESTS = [{
+        'url': 'https://sound.orf.at/podcast/oe3/fruehstueck-bei-mir/nicolas-stockhammer-15102023',
+        'md5': '526a5700e03d271a1505386a8721ab9b',
+        'info_dict': {
+            'id': 'nicolas-stockhammer-15102023',
+            'ext': 'mp3',
+            'title': 'Nicolas Stockhammer (15.10.2023)',
+            'duration': 3396.0,
+            'series': 'Frühstück bei mir',
+        },
+        'skip': 'ORF podcasts are only available for a limited time'
+    }]
+
+    def _real_extract(self, url):
+        station, show, show_id = self._match_valid_url(url).group('station', 'show', 'id')
+        data = self._download_json(
+            f'https://audioapi.orf.at/radiothek/api/2.0/podcast/{station}/{show}/{show_id}', show_id)
+
+        return {
+            'id': show_id,
+            'ext': 'mp3',
+            'vcodec': 'none',
+            **traverse_obj(data, ('payload', {
+                'url': ('enclosures', 0, 'url'),
+                'ext': ('enclosures', 0, 'type', {mimetype2ext}),
+                'title': 'title',
+                'description': ('description', {clean_html}),
+                'duration': ('duration', {functools.partial(float_or_none, scale=1000)}),
+                'series': ('podcast', 'title'),
+            })),
+        }
+
+
 class ORFIPTVIE(InfoExtractor):
     IE_NAME = 'orf:iptv'
     IE_DESC = 'iptv.ORF.at'

yt_dlp/extractor/periscope.py

@@ -4,6 +4,7 @@ from ..utils import (
     parse_iso8601,
     unescapeHTML,
 )
+from ..utils.traversal import traverse_obj
 
 
 class PeriscopeBaseIE(InfoExtractor):
@@ -20,8 +21,6 @@ class PeriscopeBaseIE(InfoExtractor):
         title = broadcast.get('status') or 'Periscope Broadcast'
         uploader = broadcast.get('user_display_name') or broadcast.get('username')
         title = '%s - %s' % (uploader, title) if uploader else title
-        is_live = broadcast.get('state').lower() == 'running'
-
         thumbnails = [{
             'url': broadcast[image],
         } for image in ('image_url', 'image_url_medium', 'image_url_small') if broadcast.get(image)]
@@ -31,12 +30,16 @@ class PeriscopeBaseIE(InfoExtractor):
             'title': title,
             'timestamp': parse_iso8601(broadcast.get('created_at')) or int_or_none(
                 broadcast.get('created_at_ms'), scale=1000),
+            'release_timestamp': int_or_none(broadcast.get('scheduled_start_ms'), scale=1000),
             'uploader': uploader,
             'uploader_id': broadcast.get('user_id') or broadcast.get('username'),
             'thumbnails': thumbnails,
             'view_count': int_or_none(broadcast.get('total_watched')),
             'tags': broadcast.get('tags'),
-            'is_live': is_live,
+            'live_status': {
+                'running': 'is_live',
+                'not_started': 'is_upcoming',
+            }.get(traverse_obj(broadcast, ('state', {str.lower}))) or 'was_live'
         }
 
     @staticmethod

yt_dlp/extractor/radiocomercial.py

@@ -0,0 +1,150 @@
+import itertools
+
+from .common import InfoExtractor
+from ..networking.exceptions import HTTPError
+from ..utils import (
+    ExtractorError,
+    extract_attributes,
+    get_element_by_class,
+    get_element_html_by_class,
+    get_element_text_and_html_by_tag,
+    get_elements_html_by_class,
+    int_or_none,
+    join_nonempty,
+    try_call,
+    unified_strdate,
+    update_url,
+    urljoin
+)
+from ..utils.traversal import traverse_obj
+
+
+class RadioComercialIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?radiocomercial\.pt/podcasts/[^/?#]+/t?(?P<season>\d+)/(?P<id>[\w-]+)'
+    _TESTS = [{
+        'url': 'https://radiocomercial.pt/podcasts/o-homem-que-mordeu-o-cao/t6/taylor-swift-entranhando-se-que-nem-uma-espada-no-ventre-dos-fas#page-content-wrapper',
+        'md5': '5f4fe8e485b29d2e8fd495605bc2c7e4',
+        'info_dict': {
+            'id': 'taylor-swift-entranhando-se-que-nem-uma-espada-no-ventre-dos-fas',
+            'ext': 'mp3',
+            'title': 'Taylor Swift entranhando-se que nem uma espada no ventre dos fãs.',
+            'release_date': '20231025',
+            'thumbnail': r're:https://radiocomercial.pt/upload/[^.]+.jpg',
+            'season': 6
+        }
+    }, {
+        'url': 'https://radiocomercial.pt/podcasts/convenca-me-num-minuto/t3/convenca-me-num-minuto-que-os-lobisomens-existem',
+        'md5': '47e96c273aef96a8eb160cd6cf46d782',
+        'info_dict': {
+            'id': 'convenca-me-num-minuto-que-os-lobisomens-existem',
+            'ext': 'mp3',
+            'title': 'Convença-me num minuto que os lobisomens existem',
+            'release_date': '20231026',
+            'thumbnail': r're:https://radiocomercial.pt/upload/[^.]+.jpg',
+            'season': 3
+        }
+    }, {
+        'url': 'https://radiocomercial.pt/podcasts/inacreditavel-by-ines-castel-branco/t2/o-desastre-de-aviao',
+        'md5': '69be64255420fec23b7259955d771e54',
+        'info_dict': {
+            'id': 'o-desastre-de-aviao',
+            'ext': 'mp3',
+            'title': 'O desastre de avião',
+            'description': 'md5:8a82beeb372641614772baab7246245f',
+            'release_date': '20231101',
+            'thumbnail': r're:https://radiocomercial.pt/upload/[^.]+.jpg',
+            'season': 2
+        },
+        'params': {
+            # inconsistant md5
+            'skip_download': True,
+        },
+    }, {
+        'url': 'https://radiocomercial.pt/podcasts/tnt-todos-no-top/2023/t-n-t-29-de-outubro',
+        'md5': '91d32d4d4b1407272068b102730fc9fa',
+        'info_dict': {
+            'id': 't-n-t-29-de-outubro',
+            'ext': 'mp3',
+            'title': 'T.N.T 29 de outubro',
+            'release_date': '20231029',
+            'thumbnail': r're:https://radiocomercial.pt/upload/[^.]+.jpg',
+            'season': 2023
+        }
+    }]
+
+    def _real_extract(self, url):
+        video_id, season = self._match_valid_url(url).group('id', 'season')
+        webpage = self._download_webpage(url, video_id)
+        return {
+            'id': video_id,
+            'title': self._html_extract_title(webpage),
+            'description': self._og_search_description(webpage, default=None),
+            'release_date': unified_strdate(get_element_by_class(
+                'date', get_element_html_by_class('descriptions', webpage) or '')),
+            'thumbnail': self._og_search_thumbnail(webpage),
+            'season': int_or_none(season),
+            'url': extract_attributes(get_element_html_by_class('audiofile', webpage) or '').get('href'),
+        }
+
+
+class RadioComercialPlaylistIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?radiocomercial\.pt/podcasts/(?P<id>[\w-]+)(?:/t?(?P<season>\d+))?/?(?:$|[?#])'
+    _TESTS = [{
+        'url': 'https://radiocomercial.pt/podcasts/convenca-me-num-minuto/t3',
+        'info_dict': {
+            'id': 'convenca-me-num-minuto_t3',
+            'title': 'Convença-me num Minuto - Temporada 3',
+        },
+        'playlist_mincount': 32
+    }, {
+        'url': 'https://radiocomercial.pt/podcasts/o-homem-que-mordeu-o-cao',
+        'info_dict': {
+            'id': 'o-homem-que-mordeu-o-cao',
+            'title': 'O Homem Que Mordeu o Cão',
+        },
+        'playlist_mincount': 19
+    }, {
+        'url': 'https://radiocomercial.pt/podcasts/as-minhas-coisas-favoritas',
+        'info_dict': {
+            'id': 'as-minhas-coisas-favoritas',
+            'title': 'As Minhas Coisas Favoritas',
+        },
+        'playlist_mincount': 131
+    }, {
+        'url': 'https://radiocomercial.pt/podcasts/tnt-todos-no-top/t2023',
+        'info_dict': {
+            'id': 'tnt-todos-no-top_t2023',
+            'title': 'TNT - Todos No Top - Temporada 2023',
+        },
+        'playlist_mincount': 39
+    }]
+
+    def _entries(self, url, playlist_id):
+        for page in itertools.count(1):
+            try:
+                webpage = self._download_webpage(
+                    f'{url}/{page}', playlist_id, f'Downloading page {page}')
+            except ExtractorError as e:
+                if isinstance(e.cause, HTTPError) and e.cause.status == 404:
+                    break
+                raise
+
+            episodes = get_elements_html_by_class('tm-ouvir-podcast', webpage)
+            if not episodes:
+                break
+            for url_path in traverse_obj(episodes, (..., {extract_attributes}, 'href')):
+                episode_url = urljoin(url, url_path)
+                if RadioComercialIE.suitable(episode_url):
+                    yield episode_url
+
+    def _real_extract(self, url):
+        podcast, season = self._match_valid_url(url).group('id', 'season')
+        playlist_id = join_nonempty(podcast, season, delim='_t')
+        url = update_url(url, query=None, fragment=None)
+        webpage = self._download_webpage(url, playlist_id)
+
+        name = try_call(lambda: get_element_text_and_html_by_tag('h1', webpage)[0])
+        title = name if name == season else join_nonempty(name, season, delim=' - Temporada ')
+
+        return self.playlist_from_matches(
+            self._entries(url, playlist_id), playlist_id, title, ie=RadioComercialIE)

yt_dlp/extractor/sbscokr.py

@@ -0,0 +1,200 @@
+from .common import InfoExtractor
+from ..utils import (
+    clean_html,
+    int_or_none,
+    parse_iso8601,
+    parse_resolution,
+    url_or_none,
+)
+from ..utils.traversal import traverse_obj
+
+
+class SBSCoKrIE(InfoExtractor):
+    IE_NAME = 'sbs.co.kr'
+    _VALID_URL = [r'https?://allvod\.sbs\.co\.kr/allvod/vod(?:Package)?EndPage\.do\?(?:[^#]+&)?mdaId=(?P<id>\d+)',
+                  r'https?://programs\.sbs\.co\.kr/(?:enter|drama|culture|sports|plus|mtv|kth)/[a-z0-9]+/(?:vod|clip|movie)/\d+/(?P<id>(?:OC)?\d+)']
+
+    _TESTS = [{
+        'url': 'https://programs.sbs.co.kr/enter/dongsang2/clip/52007/OC467706746?div=main_pop_clip',
+        'md5': 'c3f6d45e1fb5682039d94cda23c36f19',
+        'info_dict': {
+            'id': 'OC467706746',
+            'ext': 'mp4',
+            'title': '‘아슬아슬’ 박군♥한영의 새 집 인테리어 대첩♨',
+            'description': 'md5:6a71eb1979ee4a94ea380310068ccab4',
+            'thumbnail': 'https://img2.sbs.co.kr/ops_clip_img/2023/10/10/34c4c0f9-a9a5-4ff6-a92e-9bb4b5f6fa65915w1280.jpg',
+            'release_timestamp': 1696889400,
+            'release_date': '20231009',
+            'view_count': int,
+            'like_count': int,
+            'duration': 238,
+            'age_limit': 15,
+            'series': '동상이몽2_너는 내 운명',
+            'episode': '레이디제인, ‘혼전임신설’ ‘3개월’ 앞당긴 결혼식 비하인드 스토리 최초 공개!',
+            'episode_number': 311,
+        },
+    }, {
+        'url': 'https://allvod.sbs.co.kr/allvod/vodPackageEndPage.do?mdaId=22000489324&combiId=PA000000284&packageType=A&isFreeYN=',
+        'md5': 'bf46b2e89fda7ae7de01f5743cef7236',
+        'info_dict': {
+            'id': '22000489324',
+            'ext': 'mp4',
+            'title': '[다시보기] 트롤리 15회',
+            'description': 'md5:0e55d74bef1ac55c61ae90c73ac485f4',
+            'thumbnail': 'https://img2.sbs.co.kr/img/sbs_cms/WE/2023/02/14/arC1676333794938-1280-720.jpg',
+            'release_timestamp': 1676325600,
+            'release_date': '20230213',
+            'view_count': int,
+            'like_count': int,
+            'duration': 5931,
+            'age_limit': 15,
+            'series': '트롤리',
+            'episode': '이거 다 거짓말이야',
+            'episode_number': 15,
+        },
+    }, {
+        'url': 'https://programs.sbs.co.kr/enter/fourman/vod/69625/22000508948',
+        'md5': '41e8ae4cc6c8424f4e4d76661a4becbf',
+        'info_dict': {
+            'id': '22000508948',
+            'ext': 'mp4',
+            'title': '[다시보기] 신발 벗고 돌싱포맨 104회',
+            'description': 'md5:c6a247383c4dd661e4b956bf4d3b586e',
+            'thumbnail': 'https://img2.sbs.co.kr/img/sbs_cms/WE/2023/08/30/2vb1693355446261-1280-720.jpg',
+            'release_timestamp': 1693342800,
+            'release_date': '20230829',
+            'view_count': int,
+            'like_count': int,
+            'duration': 7036,
+            'age_limit': 15,
+            'series': '신발 벗고 돌싱포맨',
+            'episode': '돌싱포맨 저격수들 등장!',
+            'episode_number': 104,
+        },
+    }]
+
+    def _call_api(self, video_id, rscuse=''):
+        return self._download_json(
+            f'https://api.play.sbs.co.kr/1.0/sbs_vodall/{video_id}', video_id,
+            note=f'Downloading m3u8 information {rscuse}',
+            query={
+                'platform': 'pcweb',
+                'protocol': 'download',
+                'absolute_show': 'Y',
+                'service': 'program',
+                'ssl': 'Y',
+                'rscuse': rscuse,
+            })
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        details = self._call_api(video_id)
+        source = traverse_obj(details, ('vod', 'source', 'mediasource', {dict})) or {}
+
+        formats = []
+        for stream in traverse_obj(details, (
+            'vod', 'source', 'mediasourcelist', lambda _, v: v['mediaurl'] or v['mediarscuse']
+        ), default=[source]):
+            if not stream.get('mediaurl'):
+                new_source = traverse_obj(
+                    self._call_api(video_id, rscuse=stream['mediarscuse']),
+                    ('vod', 'source', 'mediasource', {dict})) or {}
+                if new_source.get('mediarscuse') == source.get('mediarscuse') or not new_source.get('mediaurl'):
+                    continue
+                stream = new_source
+            formats.append({
+                'url': stream['mediaurl'],
+                'format_id': stream.get('mediarscuse'),
+                'format_note': stream.get('medianame'),
+                **parse_resolution(stream.get('quality')),
+                'preference': int_or_none(stream.get('mediarscuse'))
+            })
+
+        caption_url = traverse_obj(details, ('vod', 'source', 'subtitle', {url_or_none}))
+
+        return {
+            'id': video_id,
+            **traverse_obj(details, ('vod', {
+                'title': ('info', 'title'),
+                'duration': ('info', 'duration', {int_or_none}),
+                'view_count': ('info', 'viewcount', {int_or_none}),
+                'like_count': ('info', 'likecount', {int_or_none}),
+                'description': ('info', 'synopsis', {clean_html}),
+                'episode': ('info', 'content', ('contenttitle', 'title')),
+                'episode_number': ('info', 'content', 'number', {int_or_none}),
+                'series': ('info', 'program', 'programtitle'),
+                'age_limit': ('info', 'targetage', {int_or_none}),
+                'release_timestamp': ('info', 'broaddate', {parse_iso8601}),
+                'thumbnail': ('source', 'thumbnail', 'origin', {url_or_none}),
+            }), get_all=False),
+            'formats': formats,
+            'subtitles': {'ko': [{'url': caption_url}]} if caption_url else None,
+        }
+
+
+class SBSCoKrAllvodProgramIE(InfoExtractor):
+    IE_NAME = 'sbs.co.kr:allvod_program'
+    _VALID_URL = r'https?://allvod\.sbs\.co\.kr/allvod/vod(?:Free)?ProgramDetail\.do\?(?:[^#]+&)?pgmId=(?P<id>P?\d+)'
+
+    _TESTS = [{
+        'url': 'https://allvod.sbs.co.kr/allvod/vodFreeProgramDetail.do?type=legend&pgmId=22000010159&listOrder=vodCntAsc',
+        'info_dict': {
+            '_type': 'playlist',
+            'id': '22000010159',
+        },
+        'playlist_count': 18,
+    }, {
+        'url': 'https://allvod.sbs.co.kr/allvod/vodProgramDetail.do?pgmId=P460810577',
+        'info_dict': {
+            '_type': 'playlist',
+            'id': 'P460810577',
+        },
+        'playlist_count': 13,
+    }]
+
+    def _real_extract(self, url):
+        program_id = self._match_id(url)
+
+        details = self._download_json(
+            'https://allvod.sbs.co.kr/allvod/vodProgramDetail/vodProgramDetailAjax.do',
+            program_id, note='Downloading program details',
+            query={
+                'pgmId': program_id,
+                'currentCount': '10000',
+            })
+
+        return self.playlist_result(
+            [self.url_result(f'https://allvod.sbs.co.kr/allvod/vodEndPage.do?mdaId={video_id}', SBSCoKrIE)
+             for video_id in traverse_obj(details, ('list', ..., 'mdaId'))], program_id)
+
+
+class SBSCoKrProgramsVodIE(InfoExtractor):
+    IE_NAME = 'sbs.co.kr:programs_vod'
+    _VALID_URL = r'https?://programs\.sbs\.co\.kr/(?:enter|drama|culture|sports|plus|mtv)/(?P<id>[a-z0-9]+)/vods'
+
+    _TESTS = [{
+        'url': 'https://programs.sbs.co.kr/culture/morningwide/vods/65007',
+        'info_dict': {
+            '_type': 'playlist',
+            'id': '00000210215',
+        },
+        'playlist_mincount': 9782,
+    }, {
+        'url': 'https://programs.sbs.co.kr/enter/dongsang2/vods/52006',
+        'info_dict': {
+            '_type': 'playlist',
+            'id': '22000010476',
+        },
+        'playlist_mincount': 312,
+    }]
+
+    def _real_extract(self, url):
+        program_slug = self._match_id(url)
+
+        program_id = self._download_json(
+            f'https://static.apis.sbs.co.kr/program-api/1.0/menu/{program_slug}', program_slug,
+            note='Downloading program menu data')['program']['programid']
+
+        return self.url_result(
+            f'https://allvod.sbs.co.kr/allvod/vodProgramDetail.do?pgmId={program_id}', SBSCoKrAllvodProgramIE)

yt_dlp/extractor/stacommu.py

@@ -38,9 +38,48 @@ class StacommuBaseIE(WrestleUniverseBaseIE):
             return None
         return traverse_obj(encryption_data, {'key': ('key', {decrypt}), 'iv': ('iv', {decrypt})})
 
+    def _extract_vod(self, url):
+        video_id = self._match_id(url)
+        video_info = self._download_metadata(
+            url, video_id, 'ja', ('dehydratedState', 'queries', 0, 'state', 'data'))
+        hls_info, decrypt = self._call_encrypted_api(
+            video_id, ':watch', 'stream information', data={'method': 1})
+
+        return {
+            'id': video_id,
+            'formats': self._get_formats(hls_info, ('protocolHls', 'url', {url_or_none}), video_id),
+            'hls_aes': self._extract_hls_key(hls_info, 'protocolHls', decrypt),
+            **traverse_obj(video_info, {
+                'title': ('displayName', {str}),
+                'description': ('description', {str}),
+                'timestamp': ('watchStartTime', {int_or_none}),
+                'thumbnail': ('keyVisualUrl', {url_or_none}),
+                'cast': ('casts', ..., 'displayName', {str}),
+                'duration': ('duration', {int}),
+            }),
+        }
+
+    def _extract_ppv(self, url):
+        video_id = self._match_id(url)
+        video_info = self._call_api(video_id, msg='video information', query={'al': 'ja'}, auth=False)
+        hls_info, decrypt = self._call_encrypted_api(
+            video_id, ':watchArchive', 'stream information', data={'method': 1})
+
+        return {
+            'id': video_id,
+            'formats': self._get_formats(hls_info, ('hls', 'urls', ..., {url_or_none}), video_id),
+            'hls_aes': self._extract_hls_key(hls_info, 'hls', decrypt),
+            **traverse_obj(video_info, {
+                'title': ('displayName', {str}),
+                'timestamp': ('startTime', {int_or_none}),
+                'thumbnail': ('keyVisualUrl', {url_or_none}),
+                'duration': ('duration', {int_or_none}),
+            }),
+        }
+
 
 class StacommuVODIE(StacommuBaseIE):
-    _VALID_URL = r'https?://www\.stacommu\.jp/videos/episodes/(?P<id>[\da-zA-Z]+)'
+    _VALID_URL = r'https?://www\.stacommu\.jp/(?:en/)?videos/episodes/(?P<id>[\da-zA-Z]+)'
     _TESTS = [{
         # not encrypted
         'url': 'https://www.stacommu.jp/videos/episodes/aXcVKjHyAENEjard61soZZ',
@@ -79,34 +118,19 @@ class StacommuVODIE(StacommuBaseIE):
         'params': {
             'skip_download': 'm3u8',
         },
+    }, {
+        'url': 'https://www.stacommu.jp/en/videos/episodes/aXcVKjHyAENEjard61soZZ',
+        'only_matching': True,
     }]
 
     _API_PATH = 'videoEpisodes'
 
     def _real_extract(self, url):
-        video_id = self._match_id(url)
+        return self._extract_vod(url)
-        video_info = self._download_metadata(
-            url, video_id, 'ja', ('dehydratedState', 'queries', 0, 'state', 'data'))
-        hls_info, decrypt = self._call_encrypted_api(
-            video_id, ':watch', 'stream information', data={'method': 1})
-
-        return {
-            'id': video_id,
-            'formats': self._get_formats(hls_info, ('protocolHls', 'url', {url_or_none}), video_id),
-            'hls_aes': self._extract_hls_key(hls_info, 'protocolHls', decrypt),
-            **traverse_obj(video_info, {
-                'title': ('displayName', {str}),
-                'description': ('description', {str}),
-                'timestamp': ('watchStartTime', {int_or_none}),
-                'thumbnail': ('keyVisualUrl', {url_or_none}),
-                'cast': ('casts', ..., 'displayName', {str}),
-                'duration': ('duration', {int}),
-            }),
-        }
 
 
 class StacommuLiveIE(StacommuBaseIE):
-    _VALID_URL = r'https?://www\.stacommu\.jp/live/(?P<id>[\da-zA-Z]+)'
+    _VALID_URL = r'https?://www\.stacommu\.jp/(?:en/)?live/(?P<id>[\da-zA-Z]+)'
     _TESTS = [{
         'url': 'https://www.stacommu.jp/live/d2FJ3zLnndegZJCAEzGM3m',
         'info_dict': {
@@ -125,24 +149,83 @@ class StacommuLiveIE(StacommuBaseIE):
         'params': {
             'skip_download': 'm3u8',
         },
+    }, {
+        'url': 'https://www.stacommu.jp/en/live/d2FJ3zLnndegZJCAEzGM3m',
+        'only_matching': True,
     }]
 
     _API_PATH = 'events'
 
     def _real_extract(self, url):
-        video_id = self._match_id(url)
+        return self._extract_ppv(url)
-        video_info = self._call_api(video_id, msg='video information', query={'al': 'ja'}, auth=False)
-        hls_info, decrypt = self._call_encrypted_api(
-            video_id, ':watchArchive', 'stream information', data={'method': 1})
 
-        return {
+
-            'id': video_id,
+class TheaterComplexTownBaseIE(StacommuBaseIE):
-            'formats': self._get_formats(hls_info, ('hls', 'urls', ..., {url_or_none}), video_id),
+    _NETRC_MACHINE = 'theatercomplextown'
-            'hls_aes': self._extract_hls_key(hls_info, 'hls', decrypt),
+    _API_HOST = 'api.theater-complex.town'
-            **traverse_obj(video_info, {
+    _LOGIN_QUERY = {'key': 'AIzaSyAgNCqToaIz4a062EeIrkhI_xetVfAOrfc'}
-                'title': ('displayName', {str}),
+    _LOGIN_HEADERS = {
-                'timestamp': ('startTime', {int_or_none}),
+        'Accept': '*/*',
-                'thumbnail': ('keyVisualUrl', {url_or_none}),
+        'Content-Type': 'application/json',
-                'duration': ('duration', {int_or_none}),
+        'X-Client-Version': 'Chrome/JsCore/9.23.0/FirebaseCore-web',
-            }),
+        'Referer': 'https://www.theater-complex.town/',
-        }
+        'Origin': 'https://www.theater-complex.town',
+    }
+
+
+class TheaterComplexTownVODIE(TheaterComplexTownBaseIE):
+    _VALID_URL = r'https?://(?:www\.)?theater-complex\.town/(?:en/)?videos/episodes/(?P<id>\w+)'
+    IE_NAME = 'theatercomplextown:vod'
+    _TESTS = [{
+        'url': 'https://www.theater-complex.town/videos/episodes/hoxqidYNoAn7bP92DN6p78',
+        'info_dict': {
+            'id': 'hoxqidYNoAn7bP92DN6p78',
+            'ext': 'mp4',
+            'title': '演劇ドラフトグランプリ2023　劇団『恋のぼり』〜劇団名決定秘話ラジオ',
+            'description': 'md5:a7e2e9cf570379ea67fb630f345ff65d',
+            'cast': ['玉城 裕規', '石川 凌雅'],
+            'thumbnail': 'https://image.theater-complex.town/5URnXX6KCeDysuFrPkP38o/5URnXX6KCeDysuFrPkP38o',
+            'upload_date': '20231103',
+            'timestamp': 1699016400,
+            'duration': 868,
+        },
+        'params': {
+            'skip_download': 'm3u8',
+        },
+    }, {
+        'url': 'https://www.theater-complex.town/en/videos/episodes/6QT7XYwM9dJz5Gf9VB6K5y',
+        'only_matching': True,
+    }]
+
+    _API_PATH = 'videoEpisodes'
+
+    def _real_extract(self, url):
+        return self._extract_vod(url)
+
+
+class TheaterComplexTownPPVIE(TheaterComplexTownBaseIE):
+    _VALID_URL = r'https?://(?:www\.)?theater-complex\.town/(?:en/)?ppv/(?P<id>\w+)'
+    IE_NAME = 'theatercomplextown:ppv'
+    _TESTS = [{
+        'url': 'https://www.theater-complex.town/ppv/wytW3X7khrjJBUpKuV3jen',
+        'info_dict': {
+            'id': 'wytW3X7khrjJBUpKuV3jen',
+            'ext': 'mp4',
+            'title': 'BREAK FREE STARS　11月5日（日）12:30千秋楽公演',
+            'thumbnail': 'https://image.theater-complex.town/5GWEB31JcTUfjtgdeV5t6o/5GWEB31JcTUfjtgdeV5t6o',
+            'upload_date': '20231105',
+            'timestamp': 1699155000,
+            'duration': 8378,
+        },
+        'params': {
+            'skip_download': 'm3u8',
+        },
+    }, {
+        'url': 'https://www.theater-complex.town/en/ppv/wytW3X7khrjJBUpKuV3jen',
+        'only_matching': True,
+    }]
+
+    _API_PATH = 'events'
+
+    def _real_extract(self, url):
+        return self._extract_ppv(url)

yt_dlp/extractor/thisav.py

@@ -1,66 +0,0 @@
-from .common import InfoExtractor
-from ..utils import remove_end
-
-
-class ThisAVIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?thisav\.com/video/(?P<id>[0-9]+)/.*'
-    _TESTS = [{
-        # jwplayer
-        'url': 'http://www.thisav.com/video/47734/%98%26sup1%3B%83%9E%83%82---just-fit.html',
-        'md5': '0480f1ef3932d901f0e0e719f188f19b',
-        'info_dict': {
-            'id': '47734',
-            'ext': 'flv',
-            'title': '高樹マリア - Just fit',
-            'uploader': 'dj7970',
-            'uploader_id': 'dj7970'
-        }
-    }, {
-        # html5 media
-        'url': 'http://www.thisav.com/video/242352/nerdy-18yo-big-ass-tattoos-and-glasses.html',
-        'md5': 'ba90c076bd0f80203679e5b60bf523ee',
-        'info_dict': {
-            'id': '242352',
-            'ext': 'mp4',
-            'title': 'Nerdy 18yo Big Ass Tattoos and Glasses',
-            'uploader': 'cybersluts',
-            'uploader_id': 'cybersluts',
-        },
-    }]
-
-    def _real_extract(self, url):
-        mobj = self._match_valid_url(url)
-
-        video_id = mobj.group('id')
-        webpage = self._download_webpage(url, video_id)
-        title = remove_end(self._html_extract_title(webpage), ' - 視頻 - ThisAV.com-世界第一中文成人娛樂網站')
-        video_url = self._html_search_regex(
-            r"addVariable\('file','([^']+)'\);", webpage, 'video url', default=None)
-        if video_url:
-            info_dict = {
-                'formats': [{
-                    'url': video_url,
-                }],
-            }
-        else:
-            entries = self._parse_html5_media_entries(url, webpage, video_id)
-            if entries:
-                info_dict = entries[0]
-            else:
-                info_dict = self._extract_jwplayer_data(
-                    webpage, video_id, require_title=False)
-        uploader = self._html_search_regex(
-            r': <a href="http://www\.thisav\.com/user/[0-9]+/(?:[^"]+)">([^<]+)</a>',
-            webpage, 'uploader name', fatal=False)
-        uploader_id = self._html_search_regex(
-            r': <a href="http://www\.thisav\.com/user/[0-9]+/([^"]+)">(?:[^<]+)</a>',
-            webpage, 'uploader id', fatal=False)
-
-        info_dict.update({
-            'id': video_id,
-            'uploader': uploader,
-            'uploader_id': uploader_id,
-            'title': title,
-        })
-
-        return info_dict

yt_dlp/extractor/thisoldhouse.py

@@ -1,11 +1,23 @@
+import json
+
 from .common import InfoExtractor
+from .zype import ZypeIE
 from ..networking import HEADRequest
+from ..networking.exceptions import HTTPError
+from ..utils import (
+    ExtractorError,
+    filter_dict,
+    parse_qs,
+    try_call,
+    urlencode_postdata,
+)
 
 
 class ThisOldHouseIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?thisoldhouse\.com/(?:watch|how-to|tv-episode|(?:[^/]+/)?\d+)/(?P<id>[^/?#]+)'
+    _NETRC_MACHINE = 'thisoldhouse'
+    _VALID_URL = r'https?://(?:www\.)?thisoldhouse\.com/(?:watch|how-to|tv-episode|(?:[^/?#]+/)?\d+)/(?P<id>[^/?#]+)'
     _TESTS = [{
-        'url': 'https://www.thisoldhouse.com/how-to/how-to-build-storage-bench',
+        'url': 'https://www.thisoldhouse.com/furniture/21017078/how-to-build-a-storage-bench',
         'info_dict': {
             'id': '5dcdddf673c3f956ef5db202',
             'ext': 'mp4',
@@ -23,13 +35,16 @@ class ThisOldHouseIE(InfoExtractor):
             'skip_download': True,
         },
     }, {
+        # Page no longer has video
         'url': 'https://www.thisoldhouse.com/watch/arlington-arts-crafts-arts-and-crafts-class-begins',
         'only_matching': True,
     }, {
+        # 404 Not Found
         'url': 'https://www.thisoldhouse.com/tv-episode/ask-toh-shelf-rough-electric',
         'only_matching': True,
     }, {
-        'url': 'https://www.thisoldhouse.com/furniture/21017078/how-to-build-a-storage-bench',
+        # 404 Not Found
+        'url': 'https://www.thisoldhouse.com/how-to/how-to-build-storage-bench',
         'only_matching': True,
     }, {
         'url': 'https://www.thisoldhouse.com/21113884/s41-e13-paradise-lost',
@@ -39,17 +54,51 @@ class ThisOldHouseIE(InfoExtractor):
         'url': 'https://www.thisoldhouse.com/21083431/seaside-transformation-the-westerly-project',
         'only_matching': True,
     }]
-    _ZYPE_TMPL = 'https://player.zype.com/embed/%s.html?api_key=hsOk_yMSPYNrT22e9pu8hihLXjaZf0JW5jsOWv4ZqyHJFvkJn6rtToHl09tbbsbe'
+
+    _LOGIN_URL = 'https://login.thisoldhouse.com/usernamepassword/login'
+
+    def _perform_login(self, username, password):
+        self._request_webpage(
+            HEADRequest('https://www.thisoldhouse.com/insider'), None, 'Requesting session cookies')
+        urlh = self._request_webpage(
+            'https://www.thisoldhouse.com/wp-login.php', None, 'Requesting login info',
+            errnote='Unable to login', query={'redirect_to': 'https://www.thisoldhouse.com/insider'})
+
+        try:
+            auth_form = self._download_webpage(
+                self._LOGIN_URL, None, 'Submitting credentials', headers={
+                    'Content-Type': 'application/json',
+                    'Referer': urlh.url,
+                }, data=json.dumps(filter_dict({
+                    **{('client_id' if k == 'client' else k): v[0] for k, v in parse_qs(urlh.url).items()},
+                    'tenant': 'thisoldhouse',
+                    'username': username,
+                    'password': password,
+                    'popup_options': {},
+                    'sso': True,
+                    '_csrf': try_call(lambda: self._get_cookies(self._LOGIN_URL)['_csrf'].value),
+                    '_intstate': 'deprecated',
+                }), separators=(',', ':')).encode())
+        except ExtractorError as e:
+            if isinstance(e.cause, HTTPError) and e.cause.status == 401:
+                raise ExtractorError('Invalid username or password', expected=True)
+            raise
+
+        self._request_webpage(
+            'https://login.thisoldhouse.com/login/callback', None, 'Completing login',
+            data=urlencode_postdata(self._hidden_inputs(auth_form)))
 
     def _real_extract(self, url):
         display_id = self._match_id(url)
         webpage = self._download_webpage(url, display_id)
         if 'To Unlock This content' in webpage:
-            self.raise_login_required(method='cookies')
+            self.raise_login_required(
-        video_url = self._search_regex(
+                'This video is only available for subscribers. '
+                'Note that --cookies-from-browser may not work due to this site using session cookies')
+
+        video_url, video_id = self._search_regex(
             r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?thisoldhouse\.(?:chorus\.build|com)/videos/zype/([0-9a-f]{24})[^\'"]*)[\'"]',
-            webpage, 'video url')
+            webpage, 'video url', group=(1, 2))
-        if 'subscription_required=true' in video_url or 'c-entry-group-labels__image' in webpage:
+        video_url = self._request_webpage(HEADRequest(video_url), video_id, 'Resolving Zype URL').url
-            return self.url_result(self._request_webpage(HEADRequest(video_url), display_id).url, 'Zype', display_id)
+
-        video_id = self._search_regex(r'(?:https?:)?//(?:www\.)?thisoldhouse\.(?:chorus\.build|com)/videos/zype/([0-9a-f]{24})', video_url, 'video id')
+        return self.url_result(video_url, ZypeIE, video_id)
-        return self.url_result(self._ZYPE_TMPL % video_id, 'Zype', video_id)

yt_dlp/extractor/twitter.py

@@ -1619,6 +1619,9 @@ class TwitterBroadcastIE(TwitterBaseIE, PeriscopeBaseIE):
         info['title'] = broadcast.get('status') or info.get('title')
         info['uploader_id'] = broadcast.get('twitter_username') or info.get('uploader_id')
         info['uploader_url'] = format_field(broadcast, 'twitter_username', 'https://twitter.com/%s', default=None)
+        if info['live_status'] == 'is_upcoming':
+            return info
+
         media_key = broadcast['media_key']
         source = self._call_api(
             f'live_video_stream/status/{media_key}', media_key)['source']

yt_dlp/extractor/unsupported.py

@@ -164,11 +164,15 @@ class KnownPiracyIE(UnsupportedInfoExtractor):
         r'viewsb\.com',
         r'filemoon\.sx',
         r'hentai\.animestigma\.com',
+        r'thisav\.com',
     )
 
     _TESTS = [{
         'url': 'http://dood.to/e/5s1wmbdacezb',
         'only_matching': True,
+    }, {
+        'url': 'https://thisav.com/en/terms',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):

yt_dlp/extractor/weibo.py

@@ -1,3 +1,4 @@
+import json
 import random
 import itertools
 import urllib.parse
@@ -18,24 +19,33 @@ from ..utils import (
 
 
 class WeiboBaseIE(InfoExtractor):
-    def _update_visitor_cookies(self, video_id):
+    def _update_visitor_cookies(self, visitor_url, video_id):
+        headers = {'Referer': visitor_url}
+        chrome_ver = self._search_regex(
+            r'Chrome/(\d+)', self.get_param('http_headers')['User-Agent'], 'user agent version', default='90')
         visitor_data = self._download_json(
             'https://passport.weibo.com/visitor/genvisitor', video_id,
             note='Generating first-visit guest request',
-            transform_source=strip_jsonp,
+            headers=headers, transform_source=strip_jsonp,
             data=urlencode_postdata({
                 'cb': 'gen_callback',
-                'fp': '{"os":"2","browser":"Gecko57,0,0,0","fonts":"undefined","screenInfo":"1440*900*24","plugins":""}',
+                'fp': json.dumps({
-            }))
+                    'os': '1',
+                    'browser': f'Chrome{chrome_ver},0,0,0',
+                    'fonts': 'undefined',
+                    'screenInfo': '1920*1080*24',
+                    'plugins': ''
+                }, separators=(',', ':'))}))['data']
 
         self._download_webpage(
             'https://passport.weibo.com/visitor/visitor', video_id,
             note='Running first-visit callback to get guest cookies',
-            query={
+            headers=headers, query={
                 'a': 'incarnate',
-                't': visitor_data['data']['tid'],
+                't': visitor_data['tid'],
-                'w': 2,
+                'w': 3 if visitor_data.get('new_tid') else 2,
-                'c': '%03d' % visitor_data['data']['confidence'],
+                'c': f'{visitor_data.get("confidence", 100):03d}',
+                'gc': '',
                 'cb': 'cross_domain',
                 'from': 'weibo',
                 '_rand': random.random(),
@@ -44,7 +54,7 @@ class WeiboBaseIE(InfoExtractor):
     def _weibo_download_json(self, url, video_id, *args, fatal=True, note='Downloading JSON metadata', **kwargs):
         webpage, urlh = self._download_webpage_handle(url, video_id, *args, fatal=fatal, note=note, **kwargs)
         if urllib.parse.urlparse(urlh.url).netloc == 'passport.weibo.com':
-            self._update_visitor_cookies(video_id)
+            self._update_visitor_cookies(urlh.url, video_id)
             webpage = self._download_webpage(url, video_id, *args, fatal=fatal, note=note, **kwargs)
         return self._parse_json(webpage, video_id, fatal=fatal)
 

yt_dlp/extractor/zoom.py

@@ -2,10 +2,12 @@ from .common import InfoExtractor
 from ..utils import (
     ExtractorError,
     int_or_none,
-    str_or_none,
     js_to_json,
     parse_filesize,
+    parse_resolution,
+    str_or_none,
     traverse_obj,
+    url_basename,
     urlencode_postdata,
     urljoin,
 )
@@ -41,6 +43,18 @@ class ZoomIE(InfoExtractor):
             'ext': 'mp4',
             'title': 'Timea Andrea Lelik\'s Personal Meeting Room',
         },
+        'skip': 'This recording has expired',
+    }, {
+        # view_with_share URL
+        'url': 'https://cityofdetroit.zoom.us/rec/share/VjE-5kW3xmgbEYqR5KzRgZ1OFZvtMtiXk5HyRJo5kK4m5PYE6RF4rF_oiiO_9qaM.UTAg1MI7JSnF3ZjX',
+        'md5': 'bdc7867a5934c151957fb81321b3c024',
+        'info_dict': {
+            'id': 'VjE-5kW3xmgbEYqR5KzRgZ1OFZvtMtiXk5HyRJo5kK4m5PYE6RF4rF_oiiO_9qaM.UTAg1MI7JSnF3ZjX',
+            'ext': 'mp4',
+            'title': 'February 2022 Detroit Revenue Estimating Conference',
+            'duration': 7299,
+            'formats': 'mincount:3',
+        },
     }]
 
     def _get_page_data(self, webpage, video_id):
@@ -72,6 +86,7 @@ class ZoomIE(InfoExtractor):
 
     def _real_extract(self, url):
         base_url, url_type, video_id = self._match_valid_url(url).group('base_url', 'type', 'id')
+        query = {}
 
         if url_type == 'share':
             webpage = self._get_real_webpage(url, base_url, video_id, 'share')
@@ -80,6 +95,7 @@ class ZoomIE(InfoExtractor):
                 f'{base_url}nws/recording/1.0/play/share-info/{meeting_id}',
                 video_id, note='Downloading share info JSON')['result']['redirectUrl']
             url = urljoin(base_url, redirect_path)
+            query['continueMode'] = 'true'
 
         webpage = self._get_real_webpage(url, base_url, video_id, 'play')
         file_id = self._get_page_data(webpage, video_id)['fileId']
@@ -88,7 +104,7 @@ class ZoomIE(InfoExtractor):
             raise ExtractorError('Unable to extract file ID')
 
         data = self._download_json(
-            f'{base_url}nws/recording/1.0/play/info/{file_id}', video_id,
+            f'{base_url}nws/recording/1.0/play/info/{file_id}', video_id, query=query,
             note='Downloading play info JSON')['result']
 
         subtitles = {}
@@ -104,10 +120,10 @@ class ZoomIE(InfoExtractor):
         if data.get('viewMp4Url'):
             formats.append({
                 'format_note': 'Camera stream',
-                'url': str_or_none(data.get('viewMp4Url')),
+                'url': data['viewMp4Url'],
                 'width': int_or_none(traverse_obj(data, ('viewResolvtions', 0))),
                 'height': int_or_none(traverse_obj(data, ('viewResolvtions', 1))),
-                'format_id': str_or_none(traverse_obj(data, ('recording', 'id'))),
+                'format_id': 'view',
                 'ext': 'mp4',
                 'filesize_approx': parse_filesize(str_or_none(traverse_obj(data, ('recording', 'fileSizeInMB')))),
                 'preference': 0
@@ -116,14 +132,26 @@ class ZoomIE(InfoExtractor):
         if data.get('shareMp4Url'):
             formats.append({
                 'format_note': 'Screen share stream',
-                'url': str_or_none(data.get('shareMp4Url')),
+                'url': data['shareMp4Url'],
                 'width': int_or_none(traverse_obj(data, ('shareResolvtions', 0))),
                 'height': int_or_none(traverse_obj(data, ('shareResolvtions', 1))),
-                'format_id': str_or_none(traverse_obj(data, ('shareVideo', 'id'))),
+                'format_id': 'share',
                 'ext': 'mp4',
                 'preference': -1
             })
 
+        view_with_share_url = data.get('viewMp4WithshareUrl')
+        if view_with_share_url:
+            formats.append({
+                **parse_resolution(self._search_regex(
+                    r'_(\d+x\d+)\.mp4', url_basename(view_with_share_url), 'resolution', default=None)),
+                'format_note': 'Screen share with camera',
+                'url': view_with_share_url,
+                'format_id': 'view_with_share',
+                'ext': 'mp4',
+                'preference': 1
+            })
+
         return {
             'id': video_id,
             'title': str_or_none(traverse_obj(data, ('meet', 'topic'))),