Merge 7ab6662997 into 37cd7660ea

Authored by: seproDev

test/test_subtitles.py

@@ -11,7 +11,7 @@ sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
 from test.helper import FakeYDL, is_download_test, md5
 from yt_dlp.extractor import (
     NPOIE,
-    NRKTVIE,
+    NRKIE,
     PBSIE,
     CeskaTelevizeIE,
     ComedyCentralIE,
@@ -299,15 +299,16 @@ class TestMTVSubtitles(BaseTestSubtitles):
 
 @is_download_test
 class TestNRKSubtitles(BaseTestSubtitles):
-    url = 'http://tv.nrk.no/serie/ikke-gjoer-dette-hjemme/DMPV73000411/sesong-2/episode-1'
+    url = 'nrk:DMPV73000411'  # http://tv.nrk.no/serie/ikke-gjoer-dette-hjemme/DMPV73000411/sesong-2/episode-1
-    IE = NRKTVIE
+    IE = NRKIE
 
     def test_allsubtitles(self):
         self.DL.params['writesubtitles'] = True
         self.DL.params['allsubtitles'] = True
         subtitles = self.getSubtitles()
-        self.assertEqual(set(subtitles.keys()), {'nb-ttv'})
+        self.assertEqual(set(subtitles.keys()), {'nb-ttv', 'no'})
         self.assertEqual(md5(subtitles['nb-ttv']), '67e06ff02d0deaf975e68f6cb8f6a149')
+        self.assertEqual(md5(subtitles['no']), 'fc01036074116d245ddc6ba6f679263b')
 
 
 @is_download_test

yt_dlp/extractor/_extractors.py

@@ -946,6 +946,10 @@ from .kaltura import KalturaIE
 from .kankanews import KankaNewsIE
 from .karaoketv import KaraoketvIE
 from .kelbyone import KelbyOneIE
+from .kenh14 import (
+    Kenh14PlaylistIE,
+    Kenh14VideoIE,
+)
 from .khanacademy import (
     KhanAcademyIE,
     KhanAcademyUnitIE,
@@ -1135,12 +1139,6 @@ from .microsoftembed import (
     MicrosoftMediusIE,
 )
 from .microsoftstream import MicrosoftStreamIE
-from .mildom import (
-    MildomClipIE,
-    MildomIE,
-    MildomUserVodIE,
-    MildomVodIE,
-)
 from .minds import (
     MindsChannelIE,
     MindsGroupIE,
@@ -1404,7 +1402,6 @@ from .nrk import (
     NRKSkoleIE,
     NRKTVDirekteIE,
     NRKTVEpisodeIE,
-    NRKTVEpisodesIE,
     NRKTVSeasonIE,
     NRKTVSeriesIE,
 )
@@ -1522,8 +1519,8 @@ from .pgatour import PGATourIE
 from .philharmoniedeparis import PhilharmonieDeParisIE
 from .phoenix import PhoenixIE
 from .photobucket import PhotobucketIE
+from .pialive import PiaLiveIE
 from .piapro import PiaproIE
-from .piaulizaportal import PIAULIZAPortalIE
 from .picarto import (
     PicartoIE,
     PicartoVodIE,
@@ -1559,10 +1556,6 @@ from .podbayfm import (
 )
 from .podchaser import PodchaserIE
 from .podomatic import PodomaticIE
-from .pokemon import (
-    PokemonIE,
-    PokemonWatchIE,
-)
 from .pokergo import (
     PokerGoCollectionIE,
     PokerGoIE,
@@ -2256,6 +2249,10 @@ from .ufctv import (
 )
 from .ukcolumn import UkColumnIE
 from .uktvplay import UKTVPlayIE
+from .uliza import (
+    UlizaPlayerIE,
+    UlizaPortalIE,
+)
 from .umg import UMGDeIE
 from .unistra import UnistraIE
 from .unity import UnityIE
@@ -2284,10 +2281,6 @@ from .utreon import UtreonIE
 from .varzesh3 import Varzesh3IE
 from .vbox7 import Vbox7IE
 from .veo import VeoIE
-from .veoh import (
-    VeohIE,
-    VeohUserIE,
-)
 from .vesti import VestiIE
 from .vevo import (
     VevoIE,

yt_dlp/extractor/chaturbate.py

@@ -79,7 +79,7 @@ class ChaturbateIE(InfoExtractor):
             'formats': self._extract_m3u8_formats(m3u8_url, video_id, ext='mp4', live=True),
         }
 
-    def _extract_from_webpage(self, video_id, tld):
+    def _extract_from_html(self, video_id, tld):
         webpage = self._download_webpage(
             f'https://chaturbate.{tld}/{video_id}/', video_id,
             headers=self.geo_verification_headers(), impersonate=True)
@@ -151,4 +151,4 @@ class ChaturbateIE(InfoExtractor):
 
     def _real_extract(self, url):
         video_id, tld = self._match_valid_url(url).group('id', 'tld')
-        return self._extract_from_api(video_id, tld) or self._extract_from_webpage(video_id, tld)
+        return self._extract_from_api(video_id, tld) or self._extract_from_html(video_id, tld)

yt_dlp/extractor/kenh14.py

@@ -0,0 +1,160 @@
+from .common import InfoExtractor
+from ..utils import (
+    clean_html,
+    extract_attributes,
+    get_element_by_class,
+    get_element_html_by_attribute,
+    get_elements_html_by_class,
+    int_or_none,
+    parse_duration,
+    parse_iso8601,
+    remove_start,
+    strip_or_none,
+    unescapeHTML,
+    update_url,
+    url_or_none,
+)
+from ..utils.traversal import traverse_obj
+
+
+class Kenh14VideoIE(InfoExtractor):
+    _VALID_URL = r'https?://video\.kenh14\.vn/(?:video/)?[\w-]+-(?P<id>[0-9]+)\.chn'
+    _TESTS = [{
+        'url': 'https://video.kenh14.vn/video/mo-hop-iphone-14-pro-max-nguon-unbox-therapy-316173.chn',
+        'md5': '1ed67f9c3a1e74acf15db69590cf6210',
+        'info_dict': {
+            'id': '316173',
+            'ext': 'mp4',
+            'title': 'Video mở hộp iPhone 14 Pro Max (Nguồn: Unbox Therapy)',
+            'description': 'Video mở hộp iPhone 14 Pro MaxVideo mở hộp iPhone 14 Pro Max (Nguồn: Unbox Therapy)',
+            'thumbnail': r're:^https?://videothumbs\.mediacdn\.vn/.*\.jpg$',
+            'tags': [],
+            'uploader': 'Unbox Therapy',
+            'upload_date': '20220517',
+            'view_count': int,
+            'duration': 722.86,
+            'timestamp': 1652764468,
+        },
+    }, {
+        'url': 'https://video.kenh14.vn/video-316174.chn',
+        'md5': '2b41877d2afaf4a3f487ceda8e5c7cbd',
+        'info_dict': {
+            'id': '316174',
+            'ext': 'mp4',
+            'title': 'Khoảnh khắc VĐV nằm gục khóc sau chiến thắng: 7 năm trời Việt Nam mới có HCV kiếm chém nữ, chỉ có 8 tháng để khổ luyện trước khi lên sàn đấu',
+            'description': 'md5:de86aa22e143e2b277bce8ec9c6f17dc',
+            'thumbnail': r're:^https?://videothumbs\.mediacdn\.vn/.*\.jpg$',
+            'tags': [],
+            'upload_date': '20220517',
+            'view_count': int,
+            'duration': 70.04,
+            'timestamp': 1652766021,
+        },
+    }, {
+        'url': 'https://video.kenh14.vn/0-344740.chn',
+        'md5': 'b843495d5e728142c8870c09b46df2a9',
+        'info_dict': {
+            'id': '344740',
+            'ext': 'mov',
+            'title': 'Kỳ Duyên đầy căng thẳng trong buổi ra quân đi Miss Universe, nghi thức tuyên thuệ lần đầu xuất hiện gây nhiều tranh cãi',
+            'description': 'md5:2a2dbb4a7397169fb21ee68f09160497',
+            'thumbnail': r're:^https?://kenh14cdn\.com/.*\.jpg$',
+            'tags': ['kỳ duyên', 'Kỳ Duyên tuyên thuệ', 'miss universe'],
+            'uploader': 'Quang Vũ',
+            'upload_date': '20241024',
+            'view_count': int,
+            'duration': 198.88,
+            'timestamp': 1729741590,
+        },
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+
+        attrs = extract_attributes(get_element_html_by_attribute('type', 'VideoStream', webpage) or '')
+        direct_url = attrs['data-vid']
+
+        metadata = self._download_json(
+            'https://api.kinghub.vn/video/api/v1/detailVideoByGet?FileName={}'.format(
+                remove_start(direct_url, 'kenh14cdn.com/')), video_id, fatal=False)
+
+        formats = [{'url': f'https://{direct_url}', 'format_id': 'http', 'quality': 1}]
+        subtitles = {}
+        video_data = self._download_json(
+            f'https://{direct_url}.json', video_id, note='Downloading video data', fatal=False)
+        if hls_url := traverse_obj(video_data, ('hls', {url_or_none})):
+            fmts, subs = self._extract_m3u8_formats_and_subtitles(
+                hls_url, video_id, m3u8_id='hls', fatal=False)
+            formats.extend(fmts)
+            self._merge_subtitles(subs, target=subtitles)
+        if dash_url := traverse_obj(video_data, ('mpd', {url_or_none})):
+            fmts, subs = self._extract_mpd_formats_and_subtitles(
+                dash_url, video_id, mpd_id='dash', fatal=False)
+            formats.extend(fmts)
+            self._merge_subtitles(subs, target=subtitles)
+
+        return {
+            **traverse_obj(metadata, {
+                'duration': ('duration', {parse_duration}),
+                'uploader': ('author', {strip_or_none}),
+                'timestamp': ('uploadtime', {parse_iso8601(delimiter=' ')}),
+                'view_count': ('views', {int_or_none}),
+            }),
+            'id': video_id,
+            'title': (
+                traverse_obj(metadata, ('title', {strip_or_none}))
+                or clean_html(self._og_search_title(webpage))
+                or clean_html(get_element_by_class('vdbw-title', webpage))),
+            'formats': formats,
+            'subtitles': subtitles,
+            'description': (
+                clean_html(self._og_search_description(webpage))
+                or clean_html(get_element_by_class('vdbw-sapo', webpage))),
+            'thumbnail': (self._og_search_thumbnail(webpage) or attrs.get('data-thumb')),
+            'tags': traverse_obj(self._html_search_meta('keywords', webpage), (
+                {lambda x: x.split(';')}, ..., filter)),
+        }
+
+
+class Kenh14PlaylistIE(InfoExtractor):
+    _VALID_URL = r'https?://video\.kenh14\.vn/playlist/[\w-]+-(?P<id>[0-9]+)\.chn'
+    _TESTS = [{
+        'url': 'https://video.kenh14.vn/playlist/tran-tinh-naked-love-mua-2-71.chn',
+        'info_dict': {
+            'id': '71',
+            'title': 'Trần Tình (Naked love) mùa 2',
+            'description': 'md5:e9522339304956dea931722dd72eddb2',
+            'thumbnail': r're:^https?://kenh14cdn\.com/.*\.png$',
+        },
+        'playlist_count': 9,
+    }, {
+        'url': 'https://video.kenh14.vn/playlist/0-72.chn',
+        'info_dict': {
+            'id': '72',
+            'title': 'Lau Lại Đầu Từ',
+            'description': 'Cùng xem xưa và nay có gì khác biệt nhé!',
+            'thumbnail': r're:^https?://kenh14cdn\.com/.*\.png$',
+        },
+        'playlist_count': 6,
+    }]
+
+    def _real_extract(self, url):
+        playlist_id = self._match_id(url)
+        webpage = self._download_webpage(url, playlist_id)
+
+        category_detail = get_element_by_class('category-detail', webpage) or ''
+        embed_info = traverse_obj(
+            self._yield_json_ld(webpage, playlist_id),
+            (lambda _, v: v['name'] and v['alternateName'], any)) or {}
+
+        return self.playlist_from_matches(
+            get_elements_html_by_class('video-item', webpage), playlist_id,
+            (clean_html(get_element_by_class('name', category_detail)) or unescapeHTML(embed_info.get('name'))),
+            getter=lambda x: 'https://video.kenh14.vn/video/video-{}.chn'.format(extract_attributes(x)['data-id']),
+            ie=Kenh14VideoIE, playlist_description=(
+                clean_html(get_element_by_class('description', category_detail))
+                or unescapeHTML(embed_info.get('alternateName'))),
+            thumbnail=traverse_obj(
+                self._og_search_thumbnail(webpage),
+                ({url_or_none}, {update_url(query=None)})))

yt_dlp/extractor/mildom.py

@@ -1,291 +0,0 @@
-import functools
-import json
-import uuid
-
-from .common import InfoExtractor
-from ..utils import (
-    ExtractorError,
-    OnDemandPagedList,
-    determine_ext,
-    dict_get,
-    float_or_none,
-    traverse_obj,
-)
-
-
-class MildomBaseIE(InfoExtractor):
-    _GUEST_ID = None
-
-    def _call_api(self, url, video_id, query=None, note='Downloading JSON metadata', body=None):
-        if not self._GUEST_ID:
-            self._GUEST_ID = f'pc-gp-{uuid.uuid4()}'
-
-        content = self._download_json(
-            url, video_id, note=note, data=json.dumps(body).encode() if body else None,
-            headers={'Content-Type': 'application/json'} if body else {},
-            query={
-                '__guest_id': self._GUEST_ID,
-                '__platform': 'web',
-                **(query or {}),
-            })
-
-        if content['code'] != 0:
-            raise ExtractorError(
-                f'Mildom says: {content["message"]} (code {content["code"]})',
-                expected=True)
-        return content['body']
-
-
-class MildomIE(MildomBaseIE):
-    IE_NAME = 'mildom'
-    IE_DESC = 'Record ongoing live by specific user in Mildom'
-    _VALID_URL = r'https?://(?:(?:www|m)\.)mildom\.com/(?P<id>\d+)'
-
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-        webpage = self._download_webpage(f'https://www.mildom.com/{video_id}', video_id)
-
-        enterstudio = self._call_api(
-            'https://cloudac.mildom.com/nonolive/gappserv/live/enterstudio', video_id,
-            note='Downloading live metadata', query={'user_id': video_id})
-        result_video_id = enterstudio.get('log_id', video_id)
-
-        servers = self._call_api(
-            'https://cloudac.mildom.com/nonolive/gappserv/live/liveserver', result_video_id,
-            note='Downloading live server list', query={
-                'user_id': video_id,
-                'live_server_type': 'hls',
-            })
-
-        playback_token = self._call_api(
-            'https://cloudac.mildom.com/nonolive/gappserv/live/token', result_video_id,
-            note='Obtaining live playback token', body={'host_id': video_id, 'type': 'hls'})
-        playback_token = traverse_obj(playback_token, ('data', ..., 'token'), get_all=False)
-        if not playback_token:
-            raise ExtractorError('Failed to obtain live playback token')
-
-        formats = self._extract_m3u8_formats(
-            f'{servers["stream_server"]}/{video_id}_master.m3u8?{playback_token}',
-            result_video_id, 'mp4', headers={
-                'Referer': 'https://www.mildom.com/',
-                'Origin': 'https://www.mildom.com',
-            })
-
-        for fmt in formats:
-            fmt.setdefault('http_headers', {})['Referer'] = 'https://www.mildom.com/'
-
-        return {
-            'id': result_video_id,
-            'title': self._html_search_meta('twitter:description', webpage, default=None) or traverse_obj(enterstudio, 'anchor_intro'),
-            'description': traverse_obj(enterstudio, 'intro', 'live_intro', expected_type=str),
-            'timestamp': float_or_none(enterstudio.get('live_start_ms'), scale=1000),
-            'uploader': self._html_search_meta('twitter:title', webpage, default=None) or traverse_obj(enterstudio, 'loginname'),
-            'uploader_id': video_id,
-            'formats': formats,
-            'is_live': True,
-        }
-
-
-class MildomVodIE(MildomBaseIE):
-    IE_NAME = 'mildom:vod'
-    IE_DESC = 'VOD in Mildom'
-    _VALID_URL = r'https?://(?:(?:www|m)\.)mildom\.com/playback/(?P<user_id>\d+)/(?P<id>(?P=user_id)-[a-zA-Z0-9]+-?[0-9]*)'
-    _TESTS = [{
-        'url': 'https://www.mildom.com/playback/10882672/10882672-1597662269',
-        'info_dict': {
-            'id': '10882672-1597662269',
-            'ext': 'mp4',
-            'title': '始めてのミルダム配信じゃぃ！',
-            'thumbnail': r're:^https?://.*\.(png|jpg)$',
-            'upload_date': '20200817',
-            'duration': 4138.37,
-            'description': 'ゲームをしたくて！',
-            'timestamp': 1597662269.0,
-            'uploader_id': '10882672',
-            'uploader': 'kson組長(けいそん)',
-        },
-    }, {
-        'url': 'https://www.mildom.com/playback/10882672/10882672-1597758589870-477',
-        'info_dict': {
-            'id': '10882672-1597758589870-477',
-            'ext': 'mp4',
-            'title': '【kson】感染メイズ！麻酔銃で無双する',
-            'thumbnail': r're:^https?://.*\.(png|jpg)$',
-            'timestamp': 1597759093.0,
-            'uploader': 'kson組長(けいそん)',
-            'duration': 4302.58,
-            'uploader_id': '10882672',
-            'description': 'このステージ絶対乗り越えたい',
-            'upload_date': '20200818',
-        },
-    }, {
-        'url': 'https://www.mildom.com/playback/10882672/10882672-buha9td2lrn97fk2jme0',
-        'info_dict': {
-            'id': '10882672-buha9td2lrn97fk2jme0',
-            'ext': 'mp4',
-            'title': '【kson組長】CART RACER!!!',
-            'thumbnail': r're:^https?://.*\.(png|jpg)$',
-            'uploader_id': '10882672',
-            'uploader': 'kson組長(けいそん)',
-            'upload_date': '20201104',
-            'timestamp': 1604494797.0,
-            'duration': 4657.25,
-            'description': 'WTF',
-        },
-    }]
-
-    def _real_extract(self, url):
-        user_id, video_id = self._match_valid_url(url).group('user_id', 'id')
-        webpage = self._download_webpage(f'https://www.mildom.com/playback/{user_id}/{video_id}', video_id)
-
-        autoplay = self._call_api(
-            'https://cloudac.mildom.com/nonolive/videocontent/playback/getPlaybackDetail', video_id,
-            note='Downloading playback metadata', query={
-                'v_id': video_id,
-            })['playback']
-
-        formats = [{
-            'url': autoplay['audio_url'],
-            'format_id': 'audio',
-            'protocol': 'm3u8_native',
-            'vcodec': 'none',
-            'acodec': 'aac',
-            'ext': 'm4a',
-        }]
-        for fmt in autoplay['video_link']:
-            formats.append({
-                'format_id': 'video-{}'.format(fmt['name']),
-                'url': fmt['url'],
-                'protocol': 'm3u8_native',
-                'width': fmt['level'] * autoplay['video_width'] // autoplay['video_height'],
-                'height': fmt['level'],
-                'vcodec': 'h264',
-                'acodec': 'aac',
-                'ext': 'mp4',
-            })
-
-        return {
-            'id': video_id,
-            'title': self._html_search_meta(('og:description', 'description'), webpage, default=None) or autoplay.get('title'),
-            'description': traverse_obj(autoplay, 'video_intro'),
-            'timestamp': float_or_none(autoplay.get('publish_time'), scale=1000),
-            'duration': float_or_none(autoplay.get('video_length'), scale=1000),
-            'thumbnail': dict_get(autoplay, ('upload_pic', 'video_pic')),
-            'uploader': traverse_obj(autoplay, ('author_info', 'login_name')),
-            'uploader_id': user_id,
-            'formats': formats,
-        }
-
-
-class MildomClipIE(MildomBaseIE):
-    IE_NAME = 'mildom:clip'
-    IE_DESC = 'Clip in Mildom'
-    _VALID_URL = r'https?://(?:(?:www|m)\.)mildom\.com/clip/(?P<id>(?P<user_id>\d+)-[a-zA-Z0-9]+)'
-    _TESTS = [{
-        'url': 'https://www.mildom.com/clip/10042245-63921673e7b147ebb0806d42b5ba5ce9',
-        'info_dict': {
-            'id': '10042245-63921673e7b147ebb0806d42b5ba5ce9',
-            'title': '全然違ったよ',
-            'timestamp': 1619181890,
-            'duration': 59,
-            'thumbnail': r're:https?://.+',
-            'uploader': 'ざきんぽ',
-            'uploader_id': '10042245',
-        },
-    }, {
-        'url': 'https://www.mildom.com/clip/10111524-ebf4036e5aa8411c99fb3a1ae0902864',
-        'info_dict': {
-            'id': '10111524-ebf4036e5aa8411c99fb3a1ae0902864',
-            'title': 'かっこいい',
-            'timestamp': 1621094003,
-            'duration': 59,
-            'thumbnail': r're:https?://.+',
-            'uploader': '(ルーキー',
-            'uploader_id': '10111524',
-        },
-    }, {
-        'url': 'https://www.mildom.com/clip/10660174-2c539e6e277c4aaeb4b1fbe8d22cb902',
-        'info_dict': {
-            'id': '10660174-2c539e6e277c4aaeb4b1fbe8d22cb902',
-            'title': 'あ',
-            'timestamp': 1614769431,
-            'duration': 31,
-            'thumbnail': r're:https?://.+',
-            'uploader': 'ドルゴルスレンギーン＝ダグワドルジ',
-            'uploader_id': '10660174',
-        },
-    }]
-
-    def _real_extract(self, url):
-        user_id, video_id = self._match_valid_url(url).group('user_id', 'id')
-        webpage = self._download_webpage(f'https://www.mildom.com/clip/{video_id}', video_id)
-
-        clip_detail = self._call_api(
-            'https://cloudac-cf-jp.mildom.com/nonolive/videocontent/clip/detail', video_id,
-            note='Downloading playback metadata', query={
-                'clip_id': video_id,
-            })
-
-        return {
-            'id': video_id,
-            'title': self._html_search_meta(
-                ('og:description', 'description'), webpage, default=None) or clip_detail.get('title'),
-            'timestamp': float_or_none(clip_detail.get('create_time')),
-            'duration': float_or_none(clip_detail.get('length')),
-            'thumbnail': clip_detail.get('cover'),
-            'uploader': traverse_obj(clip_detail, ('user_info', 'loginname')),
-            'uploader_id': user_id,
-
-            'url': clip_detail['url'],
-            'ext': determine_ext(clip_detail.get('url'), 'mp4'),
-        }
-
-
-class MildomUserVodIE(MildomBaseIE):
-    IE_NAME = 'mildom:user:vod'
-    IE_DESC = 'Download all VODs from specific user in Mildom'
-    _VALID_URL = r'https?://(?:(?:www|m)\.)mildom\.com/profile/(?P<id>\d+)'
-    _TESTS = [{
-        'url': 'https://www.mildom.com/profile/10093333',
-        'info_dict': {
-            'id': '10093333',
-            'title': 'Uploads from ねこばたけ',
-        },
-        'playlist_mincount': 732,
-    }, {
-        'url': 'https://www.mildom.com/profile/10882672',
-        'info_dict': {
-            'id': '10882672',
-            'title': 'Uploads from kson組長(けいそん)',
-        },
-        'playlist_mincount': 201,
-    }]
-
-    def _fetch_page(self, user_id, page):
-        page += 1
-        reply = self._call_api(
-            'https://cloudac.mildom.com/nonolive/videocontent/profile/playbackList',
-            user_id, note=f'Downloading page {page}', query={
-                'user_id': user_id,
-                'page': page,
-                'limit': '30',
-            })
-        if not reply:
-            return
-        for x in reply:
-            v_id = x.get('v_id')
-            if not v_id:
-                continue
-            yield self.url_result(f'https://www.mildom.com/playback/{user_id}/{v_id}')
-
-    def _real_extract(self, url):
-        user_id = self._match_id(url)
-        self.to_screen(f'This will download all VODs belonging to user. To download ongoing live video, use "https://www.mildom.com/{user_id}" instead')
-
-        profile = self._call_api(
-            'https://cloudac.mildom.com/nonolive/gappserv/user/profileV2', user_id,
-            query={'user_id': user_id}, note='Downloading user profile')['user_info']
-
-        return self.playlist_result(
-            OnDemandPagedList(functools.partial(self._fetch_page, user_id), 30),
-            user_id, f'Uploads from {profile["loginname"]}')

yt_dlp/extractor/nrk.py

@@ -1,4 +1,5 @@
 import itertools
+import json
 import random
 import re
 
@@ -7,11 +8,12 @@ from ..networking.exceptions import HTTPError
 from ..utils import (
     ExtractorError,
     determine_ext,
+    float_or_none,
     int_or_none,
     parse_duration,
     parse_iso8601,
     str_or_none,
-    try_get,
+    traverse_obj,
     url_or_none,
     urljoin,
 )
@@ -25,18 +27,23 @@ class NRKBaseIE(InfoExtractor):
             nrk-od-no\.telenorcdn\.net|
             minicdn-od\.nrk\.no/od/nrkhd-osl-rr\.netwerk\.no/no
         )/'''
+    _NETRC_MACHINE = 'nrk'
+    _LOGIN_URL = 'https://innlogging.nrk.no/logginn'
+    _AUTH_TOKEN = ''
+    _API_CALL_HEADERS = {'Accept': 'application/json;device=player-core'}
+
+    def _extract_nrk_formats_and_subtitles(self, asset_url, video_id):
 
-    def _extract_nrk_formats(self, asset_url, video_id):
         if re.match(r'https?://[^/]+\.akamaihd\.net/i/', asset_url):
             return self._extract_akamai_formats(asset_url, video_id)
-        asset_url = re.sub(r'(?:bw_(?:low|high)=\d+|no_audio_only)&?', '', asset_url)
+        asset_url = re.sub(r'(?:bw_(?:low|high)=\d+|no_audio_only|adap=.+?\b)&?', '', asset_url)
-        formats = self._extract_m3u8_formats(
+        formats, subtitles = self._extract_m3u8_formats_and_subtitles(
             asset_url, video_id, 'mp4', 'm3u8_native', fatal=False)
         if not formats and re.search(self._CDN_REPL_REGEX, asset_url):
-            formats = self._extract_m3u8_formats(
+            formats, subtitles = self._extract_m3u8_formats_and_subtitles(
                 re.sub(self._CDN_REPL_REGEX, '://nrk-od-%02d.akamaized.net/no/' % random.randint(0, 99), asset_url),
                 video_id, 'mp4', 'm3u8_native', fatal=False)
-        return formats
+        return formats, subtitles
 
     def _raise_error(self, data):
         MESSAGES = {
@@ -47,7 +54,7 @@ class NRKBaseIE(InfoExtractor):
         }
         message_type = data.get('messageType', '')
         # Can be ProgramIsGeoBlocked or ChannelIsGeoBlocked*
-        if 'IsGeoBlocked' in message_type or try_get(data, lambda x: x['usageRights']['isGeoBlocked']) is True:
+        if 'IsGeoBlocked' in message_type or traverse_obj(data, ('usageRights', 'isGeoBlocked')) is True:
             self.raise_geo_restricted(
                 msg=MESSAGES.get('ProgramIsGeoBlocked'),
                 countries=self._GEO_COUNTRIES)
@@ -58,7 +65,7 @@ class NRKBaseIE(InfoExtractor):
         return self._download_json(
             urljoin('https://psapi.nrk.no/', path),
             video_id, note or f'Downloading {item} JSON',
-            fatal=fatal, query=query)
+            fatal=fatal, query=query, headers=self._API_CALL_HEADERS)
 
 
 class NRKIE(NRKBaseIE):
@@ -73,17 +80,20 @@ class NRKIE(NRKBaseIE):
                             )
                             (?P<id>[^?\#&]+)
                         '''
-
     _TESTS = [{
         # video
         'url': 'http://www.nrk.no/video/PS*150533',
-        'md5': 'f46be075326e23ad0e524edfcb06aeb6',
+        'md5': '2b88a652ad2e275591e61cf550887eec',
         'info_dict': {
             'id': '150533',
             'ext': 'mp4',
             'title': 'Dompap og andre fugler i Piip-Show',
             'description': 'md5:d9261ba34c43b61c812cb6b0269a5c8f',
             'duration': 262,
+            'timestamp': 1395751833,
+            'upload_date': '20140325',
+            'thumbnail': 'https://gfx.nrk.no/0mZgeckEzRU6qTWrbQHD2QcyralHrYB08wBvh-K-AtAQ',
+            'alt_title': 'md5:d9261ba34c43b61c812cb6b0269a5c8f',
         },
     }, {
         # audio
@@ -95,6 +105,10 @@ class NRKIE(NRKBaseIE):
             'title': 'Slik høres internett ut når du er blind',
             'description': 'md5:a621f5cc1bd75c8d5104cb048c6b8568',
             'duration': 20,
+            'alt_title': 'Cathrine Lie Wathne er blind, og bruker hurtigtaster for å navigere seg rundt på ulike nettsider.',
+            'upload_date': '20140425',
+            'timestamp': 1398429565,
+            'thumbnail': 'https://gfx.nrk.no/urxQMSXF-WnbfjBH5ke2igLGyN27EdJVWZ6FOsEAclhA',
         },
     }, {
         'url': 'nrk:ecc1b952-96dc-4a98-81b9-5296dc7a98d9',
@@ -144,18 +158,10 @@ class NRKIE(NRKBaseIE):
     def _real_extract(self, url):
         video_id = self._match_id(url).split('/')[-1]
 
-        def call_playback_api(item, query=None):
-            try:
-                return self._call_api(f'playback/{item}/program/{video_id}', video_id, item, query=query)
-            except ExtractorError as e:
-                if isinstance(e.cause, HTTPError) and e.cause.status == 400:
-                    return self._call_api(f'playback/{item}/{video_id}', video_id, item, query=query)
-                raise
-
         # known values for preferredCdn: akamai, iponly, minicdn and telenor
-        manifest = call_playback_api('manifest', {'preferredCdn': 'akamai'})
+        manifest = self._call_api(f'playback/manifest/{video_id}', video_id, 'manifest', query={'preferredCdn': 'akamai'})
 
-        video_id = try_get(manifest, lambda x: x['id'], str) or video_id
+        video_id = manifest.get('id') or video_id
 
         if manifest.get('playability') == 'nonPlayable':
             self._raise_error(manifest['nonPlayable'])
@@ -163,17 +169,22 @@ class NRKIE(NRKBaseIE):
         playable = manifest['playable']
 
         formats = []
-        for asset in playable['assets']:
+        subtitles = {}
-            if not isinstance(asset, dict):
+        has_drm = False
-                continue
+        for asset in traverse_obj(playable, ('assets', ..., {dict})):
-            if asset.get('encrypted'):
+            encryption_scheme = asset.get('encryptionScheme')
+            if encryption_scheme not in (None, 'none', 'statickey'):
+                self.report_warning(f'Skipping asset with unsupported encryption scheme "{encryption_scheme}"')
+                has_drm = True
                 continue
             format_url = url_or_none(asset.get('url'))
             if not format_url:
                 continue
             asset_format = (asset.get('format') or '').lower()
             if asset_format == 'hls' or determine_ext(format_url) == 'm3u8':
-                formats.extend(self._extract_nrk_formats(format_url, video_id))
+                fmts, subs = self._extract_nrk_formats_and_subtitles(format_url, video_id)
+                formats.extend(fmts)
+                self._merge_subtitles(subs, target=subtitles)
             elif asset_format == 'mp3':
                 formats.append({
                     'url': format_url,
@@ -181,19 +192,22 @@ class NRKIE(NRKBaseIE):
                     'vcodec': 'none',
                 })
 
-        data = call_playback_api('metadata')
+        if not formats and has_drm:
+            self.report_drm(video_id)
 
-        preplay = data['preplay']
+        data = self._call_api(traverse_obj(manifest, ('_links', 'metadata', 'href', {str})), video_id, 'metadata')
-        titles = preplay['titles']
+
-        title = titles['title']
+        preplay = data.get('preplay')
+        titles = preplay.get('titles')
+        title = titles.get('title')
         alt_title = titles.get('subtitle')
 
-        description = try_get(preplay, lambda x: x['description'].replace('\r', '\n'))
+        description = preplay.get('description')
-        duration = parse_duration(playable.get('duration')) or parse_duration(data.get('duration'))
+        # Use m3u8 vod dueration for NRKSkoleIE because of incorrect duration in metadata
+        duration = parse_duration(playable.get('duration')) or parse_duration(data.get('duration')) or self._extract_m3u8_vod_duration(formats[0]['url'], video_id)
 
         thumbnails = []
-        for image in try_get(
+        for image in traverse_obj(preplay, ('poster', 'images', {list})) or []:
-                preplay, lambda x: x['poster']['images'], list) or []:
             if not isinstance(image, dict):
                 continue
             image_url = url_or_none(image.get('url'))
@@ -205,13 +219,13 @@ class NRKIE(NRKBaseIE):
                 'height': int_or_none(image.get('pixelHeight')),
             })
 
-        subtitles = {}
+        for sub in traverse_obj(playable, ('subtitles', {list})) or []:
-        for sub in try_get(playable, lambda x: x['subtitles'], list) or []:
             if not isinstance(sub, dict):
                 continue
             sub_url = url_or_none(sub.get('webVtt'))
             if not sub_url:
                 continue
+
             sub_key = str_or_none(sub.get('language')) or 'nb'
             sub_type = str_or_none(sub.get('type'))
             if sub_type:
@@ -220,8 +234,26 @@ class NRKIE(NRKBaseIE):
                 'url': sub_url,
             })
 
-        legal_age = try_get(
+        chapters = []
-            data, lambda x: x['legalAge']['body']['rating']['code'], str)
+        if data.get('skipDialogInfo'):
+            chapters = [item for item in [{
+                'start_time': float_or_none(traverse_obj(data, ('skipDialogInfo', 'startIntroInSeconds'))),
+                'end_time': float_or_none(traverse_obj(data, ('skipDialogInfo', 'endIntroInSeconds'))),
+                'title': 'Intro',
+            }, {
+                'start_time': float_or_none(traverse_obj(data, ('skipDialogInfo', 'startCreditsInSeconds'))),
+                'end_time': duration,
+                'title': 'Outro',
+            }] if item['start_time'] != item['end_time']]
+        if preplay.get('indexPoints'):
+            seconds_or_none = lambda x: float_or_none(parse_duration(x))
+            chapters += traverse_obj(preplay, ('indexPoints', ..., {
+                'start_time': ('startPoint', {seconds_or_none}),
+                'end_time': ('endPoint', {seconds_or_none}),
+                'title': ('title', {lambda x: x}),
+            }))
+        chapters = sorted(chapters, key=lambda x: x['start_time']) if chapters else None
+        legal_age = traverse_obj(data, ('legalAge', 'body', 'rating', 'code'))
         # https://en.wikipedia.org/wiki/Norwegian_Media_Authority
         age_limit = None
         if legal_age:
@@ -230,7 +262,7 @@ class NRKIE(NRKBaseIE):
             elif legal_age.isdigit():
                 age_limit = int_or_none(legal_age)
 
-        is_series = try_get(data, lambda x: x['_links']['series']['name']) == 'series'
+        is_series = traverse_obj(data, ('_links', 'series', 'name')) == 'series'
 
         info = {
             'id': video_id,
@@ -242,13 +274,23 @@ class NRKIE(NRKBaseIE):
             'age_limit': age_limit,
             'formats': formats,
             'subtitles': subtitles,
-            'timestamp': parse_iso8601(try_get(manifest, lambda x: x['availability']['onDemand']['from'], str)),
+            'chapters': chapters,
+            'timestamp': parse_iso8601(traverse_obj(data, ('availability', 'onDemand', 'from'))),
         }
-
         if is_series:
             series = season_id = season_number = episode = episode_number = None
+
             programs = self._call_api(
                 f'programs/{video_id}', video_id, 'programs', fatal=False)
+            matched_dates = [
+                int(match.group()) // 1000
+                for date in [
+                    traverse_obj(programs, ('firstTimeTransmitted', 'publicationDate')),
+                    traverse_obj(programs, ('usageRights', 'availableFrom')),
+                ] if date for match in [re.search(r'\d+', date)] if match
+            ]
+            if matched_dates:
+                info.update({'timestamp': min(info['timestamp'], *matched_dates)})
             if programs and isinstance(programs, dict):
                 series = str_or_none(programs.get('seriesTitle'))
                 season_id = str_or_none(programs.get('seasonId'))
@@ -284,8 +326,38 @@ class NRKIE(NRKBaseIE):
 
         return info
 
+    def _perform_login(self, username, password):
+        try:
+            self._download_json(
+                self._LOGIN_URL, None, headers={'Content-Type': 'application/json; charset=UTF-8', 'accept': 'application/json; charset=utf-8'},
+                data=json.dumps({
+                    'clientId': '',
+                    'hashedPassword': {'current': {
+                        'hash': password,
+                        'recipe': {
+                            'algorithm': 'cleartext',
+                            'salt': '',
+                        },
+                    },
+                    },
+                    'password': password,
+                    'username': username,
+                }).encode())
 
-class NRKTVIE(InfoExtractor):
+            self._download_webpage('https://tv.nrk.no/auth/web/login/opsession', None)
+            response = self._download_json('https://tv.nrk.no/auth/session/tokenforsub/_', None)
+            self._AUTH_TOKEN = traverse_obj(response, ('session', 'accessToken'))
+            self._API_CALL_HEADERS['authorization'] = f'Bearer {self._AUTH_TOKEN}'
+        except ExtractorError as e:
+            message = None
+            if isinstance(e.cause, HTTPError) and e.cause.status in (401, 400):
+                resp = self._parse_json(
+                    e.cause.response.read().decode(), None, fatal=False) or {}
+                message = next((error['message'] for error in resp['errors'] if error['field'] == 'Password'), None)
+            self.report_warning(message or 'Unable to log in')
+
+
+class NRKTVIE(NRKBaseIE):
     IE_DESC = 'NRK TV and NRK Radio'
     _EPISODE_RE = r'(?P<id>[a-zA-Z]{4}\d{8})'
     _VALID_URL = rf'https?://(?:tv|radio)\.nrk(?:super)?\.no/(?:[^/]+/)*{_EPISODE_RE}'
@@ -307,6 +379,14 @@ class NRKTVIE(InfoExtractor):
                     'ext': 'vtt',
                 }],
             },
+            'upload_date': '20170627',
+            'chapters': [{'start_time': 0, 'end_time': 2213.0, 'title': '<Untitled Chapter 1>'}, {'start_time': 2213.0, 'end_time': 2223.44, 'title': 'Outro'}],
+            'timestamp': 1498591822,
+            'thumbnail': 'https://gfx.nrk.no/myRSc4vuFlahB60P3n6swwRTQUZI1LqJZl9B7icZFgzA',
+            'alt_title': 'md5:46923a6e6510eefcce23d5ef2a58f2ce',
+        },
+        'params': {
+            'skip_download': True,
         },
     }, {
         'url': 'https://tv.nrk.no/serie/20-spoersmaal-tv/MUHH48000314/23-05-2014',
@@ -318,9 +398,31 @@ class NRKTVIE(InfoExtractor):
             'alt_title': '23. mai 2014',
             'description': 'md5:bdea103bc35494c143c6a9acdd84887a',
             'duration': 1741,
+            'age_limit': 0,
             'series': '20 spørsmål',
             'episode': '23. mai 2014',
-            'age_limit': 0,
+            'upload_date': '20140523',
+            'thumbnail': 'https://gfx.nrk.no/u7uCe79SEfPVGRAGVp2_uAZnNc4mfz_kjXg6Bgek8lMQ',
+            'season_id': '126936',
+            'season_number': 2014,
+            'season': 'Season 2014',
+            'chapters': [
+                {'start_time': 0.0, 'end_time': 39.0, 'title': 'Intro'},
+                {'start_time': 0.0, 'title': 'Velkommen', 'end_time': 152.32},
+                {'start_time': 152.32, 'title': 'Tannpirker', 'end_time': 304.76},
+                {'start_time': 304.76, 'title': 'Orgelbrus', 'end_time': 513.48},
+                {'start_time': 513.48, 'title': 'G-streng', 'end_time': 712.96},
+                {'start_time': 712.96, 'title': 'Medalje', 'end_time': 837.76},
+                {'start_time': 837.76, 'title': 'Globus', 'end_time': 1124.48},
+                {'start_time': 1124.48, 'title': 'Primstav', 'end_time': 1417.4},
+                {'start_time': 1417.4, 'title': 'Fyr', 'end_time': 1721.0},
+                {'start_time': 1721.0, 'end_time': 1741.0, 'title': 'Outro'},
+            ],
+            'episode_number': 3,
+            'timestamp': 1400871900,
+        },
+        'params': {
+            'skip_download': True,
         },
     }, {
         'url': 'https://tv.nrk.no/program/mdfp15000514',
@@ -333,6 +435,18 @@ class NRKTVIE(InfoExtractor):
             'series': 'Kunnskapskanalen',
             'episode': 'Grunnlovsjubiléet - Stor ståhei for ingenting',
             'age_limit': 0,
+            'upload_date': '20140524',
+            'episode_number': 17,
+            'chapters': [
+                {'start_time': 0, 'end_time': 4595.0, 'title': '<Untitled Chapter 1>'},
+                {'start_time': 4595.0, 'end_time': 4605.08, 'title': 'Outro'},
+            ],
+            'season': 'Season 2014',
+            'timestamp': 1400937600,
+            'thumbnail': 'https://gfx.nrk.no/D2u6-EyVUZpVCq0PdSNHRgdBZCV40ekpk6s9fZWiMtyg',
+            'season_number': 2014,
+            'season_id': '39240',
+            'alt_title': 'Grunnlovsjubiléet - Stor ståhei for ingenting',
         },
         'params': {
             'skip_download': True,
@@ -343,23 +457,51 @@ class NRKTVIE(InfoExtractor):
         'info_dict': {
             'id': 'MSPO40010515',
             'ext': 'mp4',
-            'title': 'Sprint fri teknikk, kvinner og menn 06.01.2015',
+            'title': 'Tour de Ski - Sprint fri teknikk, kvinner og menn',
-            'description': 'md5:c03aba1e917561eface5214020551b7a',
+            'description': 'md5:1f97a41f05a9486ee00c56f35f82993d',
             'age_limit': 0,
+            'episode': 'Sprint fri teknikk, kvinner og menn',
+            'series': 'Tour de Ski',
+            'thumbnail': 'https://gfx.nrk.no/s9vNwGPGN-Un-UCvitD09we9HRLDxisnipA9K__d5c3Q',
+            'season_id': '53512',
+            'chapters': [
+                {'start_time': 0, 'end_time': 6938.0, 'title': '<Untitled Chapter 1>'},
+                {'start_time': 6938.0, 'end_time': 6947.52, 'title': 'Outro'},
+            ],
+            'season_number': 2015,
+            'episode_number': 5,
+            'upload_date': '20150106',
+            'duration': 6947.52,
+            'timestamp': 1420545563,
+            'alt_title': 'Sprint fri teknikk, kvinner og menn',
+            'season': 'Season 2015',
         },
         'params': {
             'skip_download': True,
         },
-        'expected_warnings': ['Failed to download m3u8 information'],
-        'skip': 'particular part is not supported currently',
     }, {
         'url': 'https://tv.nrk.no/serie/tour-de-ski/MSPO40010515/06-01-2015',
         'info_dict': {
             'id': 'MSPO40010515',
             'ext': 'mp4',
-            'title': 'Sprint fri teknikk, kvinner og menn 06.01.2015',
+            'title': 'Tour de Ski - Sprint fri teknikk, kvinner og menn',
-            'description': 'md5:c03aba1e917561eface5214020551b7a',
+            'description': 'md5:1f97a41f05a9486ee00c56f35f82993d',
             'age_limit': 0,
+            'episode': 'Sprint fri teknikk, kvinner og menn',
+            'series': 'Tour de Ski',
+            'thumbnail': 'https://gfx.nrk.no/s9vNwGPGN-Un-UCvitD09we9HRLDxisnipA9K__d5c3Q',
+            'season_id': '53512',
+            'chapters': [
+                {'start_time': 0, 'end_time': 6938.0, 'title': '<Untitled Chapter 1>'},
+                {'start_time': 6938.0, 'end_time': 6947.52, 'title': 'Outro'},
+            ],
+            'season_number': 2015,
+            'episode_number': 5,
+            'upload_date': '20150106',
+            'duration': 6947.52,
+            'timestamp': 1420545563,
+            'alt_title': 'Sprint fri teknikk, kvinner og menn',
+            'season': 'Season 2015',
         },
         'expected_warnings': ['Failed to download m3u8 information'],
         'skip': 'Ikke tilgjengelig utenfor Norge',
@@ -380,6 +522,7 @@ class NRKTVIE(InfoExtractor):
         'params': {
             'skip_download': True,
         },
+        'skip': 'ProgramRightsHasExpired',
     }, {
         'url': 'https://tv.nrk.no/serie/nytt-paa-nytt/MUHH46000317/27-01-2017',
         'info_dict': {
@@ -413,7 +556,7 @@ class NRKTVIE(InfoExtractor):
             f'nrk:{video_id}', ie=NRKIE.ie_key(), video_id=video_id)
 
 
-class NRKTVEpisodeIE(InfoExtractor):
+class NRKTVEpisodeIE(NRKBaseIE):
     _VALID_URL = r'https?://tv\.nrk\.no/serie/(?P<id>[^/]+/sesong/(?P<season_number>\d+)/episode/(?P<episode_number>\d+))'
     _TESTS = [{
         'url': 'https://tv.nrk.no/serie/hellums-kro/sesong/1/episode/2',
@@ -421,13 +564,24 @@ class NRKTVEpisodeIE(InfoExtractor):
             'id': 'MUHH36005220',
             'ext': 'mp4',
             'title': 'Hellums kro - 2. Kro, krig og kjærlighet',
-            'description': 'md5:ad92ddffc04cea8ce14b415deef81787',
+            'description': 'md5:b32a7dc0b1ed27c8064f58b97bda4350',
             'duration': 1563.92,
             'series': 'Hellums kro',
             'season_number': 1,
             'episode_number': 2,
             'episode': '2. Kro, krig og kjærlighet',
             'age_limit': 6,
+            'timestamp': 1572584520,
+            'upload_date': '20191101',
+            'thumbnail': 'https://gfx.nrk.no/2_4mhU2JhR-8IYRC_OMmAQDbbOHgwcHqgi2sBrNrsjkg',
+            'alt_title': '2. Kro, krig og kjærlighet',
+            'season': 'Season 1',
+            'season_id': '124163',
+            'chapters': [
+                {'start_time': 0, 'end_time': 29.0, 'title': '<Untitled Chapter 1>'},
+                {'start_time': 29.0, 'end_time': 50.0, 'title': 'Intro'},
+                {'start_time': 1530.0, 'end_time': 1563.92, 'title': 'Outro'},
+            ],
         },
         'params': {
             'skip_download': True,
@@ -453,26 +607,14 @@ class NRKTVEpisodeIE(InfoExtractor):
     }]
 
     def _real_extract(self, url):
-        display_id, season_number, episode_number = self._match_valid_url(url).groups()
+        # HEADRequest(url) only works if a regular GET request was recently made by anyone for the specific URL being requested.
+        response = self._request_webpage(url, None, expected_status=True)
 
-        webpage = self._download_webpage(url, display_id)
+        nrk_id = self._match_id(url)
 
-        info = self._search_json_ld(webpage, display_id, default={})
+        return self.url_result(
-        nrk_id = info.get('@id') or self._html_search_meta(
+            response.url, NRKTVIE.ie_key(), nrk_id, url_transparent=True,
-            'nrk:program-id', webpage, default=None) or self._search_regex(
+        )
-            rf'data-program-id=["\']({NRKTVIE._EPISODE_RE})', webpage,
-            'nrk id')
-        assert re.match(NRKTVIE._EPISODE_RE, nrk_id)
-
-        info.update({
-            '_type': 'url',
-            'id': nrk_id,
-            'url': f'nrk:{nrk_id}',
-            'ie_key': NRKIE.ie_key(),
-            'season_number': int(season_number),
-            'episode_number': int(episode_number),
-        })
-        return info
 
 
 class NRKTVSerieBaseIE(NRKBaseIE):
@@ -482,6 +624,9 @@ class NRKTVSerieBaseIE(NRKBaseIE):
         entries = []
         for episode in entry_list:
             nrk_id = episode.get('prfId') or episode.get('episodeId')
+            if traverse_obj(episode, ('availability', 'status')) == 'expired':
+                self.report_warning(episode['availability'].get('label'), nrk_id)
+                continue
             if not nrk_id or not isinstance(nrk_id, str):
                 continue
             entries.append(self.url_result(
@@ -508,18 +653,18 @@ class NRKTVSerieBaseIE(NRKBaseIE):
             if not assets_key:
                 break
             # Extract entries
-            entries = try_get(
+            entries = traverse_obj(
                 embedded,
-                (lambda x: x[assets_key]['_embedded'][assets_key],
+                (assets_key, '_embedded', assets_key, {list}),
-                 lambda x: x[assets_key]),
+                (assets_key, {list}),
-                list)
+            )
             yield from self._extract_entries(entries)
             # Find next URL
-            next_url_path = try_get(
+            next_url_path = traverse_obj(
                 data,
-                (lambda x: x['_links']['next']['href'],
+                ('_links', 'next', 'href'),
-                 lambda x: x['_embedded'][assets_key]['_links']['next']['href']),
+                ('_embedded', assets_key, '_links', 'next', 'href'),
-                str)
+            )
             if not next_url_path:
                 break
             data = self._call_api(
@@ -548,6 +693,27 @@ class NRKTVSeasonIE(NRKTVSerieBaseIE):
             'title': 'Sesong 1',
         },
         'playlist_mincount': 30,
+    }, {
+        'url': 'https://tv.nrk.no/serie/presten/sesong/ekstramateriale',
+        'info_dict': {
+            'id': 'MUHH47005117',
+            'ext': 'mp4',
+            'description': '',
+            'thumbnail': 'https://gfx.nrk.no/sJZroQqD2P8wGMMl5ADznwqiIlAXaCpNofA2pIhe3udA',
+            'alt_title': 'Bloopers: Episode 1',
+            'chapters': [
+                {'start_time': 0, 'end_time': 356.0, 'title': '<Untitled Chapter 1>'},
+                {'start_time': 356.0, 'end_time': 365.8, 'title': 'Outro'},
+            ],
+            'upload_date': '20180302',
+            'timestamp': 1519966800,
+            'title': 'Presten',
+            'age_limit': 0,
+            'duration': 365.8,
+        },
+        'params': {
+            'skip_download': True,
+        },
     }, {
         # no /sesong/ in path
         'url': 'https://tv.nrk.no/serie/lindmo/2016',
@@ -572,6 +738,7 @@ class NRKTVSeasonIE(NRKTVSerieBaseIE):
             'title': 'September 2015',
         },
         'playlist_mincount': 841,
+        'skip': 'ProgramRightsHasExpired',
     }, {
         # 180 entries, single page
         'url': 'https://tv.nrk.no/serie/spangas/sesong/1',
@@ -594,21 +761,20 @@ class NRKTVSeasonIE(NRKTVSerieBaseIE):
                 else super().suitable(url))
 
     def _real_extract(self, url):
-        mobj = self._match_valid_url(url)
+        domain, serie_kind, serie, season_id, season_id_2 = self._match_valid_url(url).group(
-        domain = mobj.group('domain')
+            'domain', 'serie_kind', 'serie', 'id', 'id_2')
-        serie_kind = mobj.group('serie_kind')
+        season_id = season_id or season_id_2
-        serie = mobj.group('serie')
-        season_id = mobj.group('id') or mobj.group('id_2')
         display_id = f'{serie}/{season_id}'
 
+        api_suffix = f'/seasons/{season_id}' if season_id != 'ekstramateriale' else '/extramaterial'
+
         data = self._call_api(
-            f'{domain}/catalog/{self._catalog_name(serie_kind)}/{serie}/seasons/{season_id}',
+            f'{domain}/catalog/{self._catalog_name(serie_kind)}/{serie}{api_suffix}',
             display_id, 'season', query={'pageSize': 50})
 
-        title = try_get(data, lambda x: x['titles']['title'], str) or display_id
         return self.playlist_result(
-            self._entries(data, display_id),
+            self._entries(data, display_id), display_id,
-            display_id, title)
+            title=traverse_obj(data, ('titles', 'title', {str})))
 
 
 class NRKTVSeriesIE(NRKTVSerieBaseIE):
@@ -666,7 +832,7 @@ class NRKTVSeriesIE(NRKTVSerieBaseIE):
         'info_dict': {
             'id': 'dickie-dick-dickens',
             'title': 'Dickie Dick Dickens',
-            'description': 'md5:19e67411ffe57f7dce08a943d7a0b91f',
+            'description': 'md5:605464fab26d06b1ce6a11c3ea37d36d',
         },
         'playlist_mincount': 8,
     }, {
@@ -676,6 +842,8 @@ class NRKTVSeriesIE(NRKTVSerieBaseIE):
         'url': 'https://radio.nrk.no/podkast/ulrikkes_univers',
         'info_dict': {
             'id': 'ulrikkes_univers',
+            'title': 'Ulrikkes univers',
+            'description': 'md5:8af9fc2ee4aecd7f91777383fde50dcc',
         },
         'playlist_mincount': 10,
     }, {
@@ -699,16 +867,18 @@ class NRKTVSeriesIE(NRKTVSerieBaseIE):
         series = self._call_api(
             f'{domain}/catalog/{self._catalog_name(serie_kind)}/{series_id}',
             series_id, 'serie', query={size_prefix + 'ageSize': 50})
-        titles = try_get(series, [
+        titles = traverse_obj(
-            lambda x: x['titles'],
+            series,
-            lambda x: x[x['type']]['titles'],
+            (..., 'titles'),
-            lambda x: x[x['seriesType']]['titles'],
+            (..., 'type', 'titles'),
-        ]) or {}
+            (..., 'seriesType', 'titles'),
+            get_all=False,
 
+        )
         entries = []
         entries.extend(self._entries(series, series_id))
         embedded = series.get('_embedded') or {}
-        linked_seasons = try_get(series, lambda x: x['_links']['seasons']) or []
+        linked_seasons = traverse_obj(series, ('_links', 'seasons')) or []
         embedded_seasons = embedded.get('seasons') or []
         if len(linked_seasons) > len(embedded_seasons):
             for season in linked_seasons:
@@ -731,7 +901,7 @@ class NRKTVSeriesIE(NRKTVSerieBaseIE):
             entries, series_id, titles.get('title'), titles.get('subtitle'))
 
 
-class NRKTVDirekteIE(NRKTVIE):  # XXX: Do not subclass from concrete IE
+class NRKTVDirekteIE(NRKBaseIE):
     IE_DESC = 'NRK TV Direkte and NRK Radio Direkte'
     _VALID_URL = r'https?://(?:tv|radio)\.nrk\.no/direkte/(?P<id>[^/?#&]+)'
 
@@ -743,21 +913,29 @@ class NRKTVDirekteIE(NRKTVIE):  # XXX: Do not subclass from concrete IE
         'only_matching': True,
     }]
 
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        return self.url_result(
+            f'nrk:{video_id}', ie=NRKIE.ie_key(), video_id=video_id)
 
-class NRKRadioPodkastIE(InfoExtractor):
+
+class NRKRadioPodkastIE(NRKBaseIE):
     _VALID_URL = r'https?://radio\.nrk\.no/pod[ck]ast/(?:[^/]+/)+(?P<id>l_[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})'
 
     _TESTS = [{
         'url': 'https://radio.nrk.no/podkast/ulrikkes_univers/l_96f4f1b0-de54-4e6a-b4f1-b0de54fe6af8',
-        'md5': '8d40dab61cea8ab0114e090b029a0565',
+        'md5': 'a68c3564be2f4426254f026c95a06348',
         'info_dict': {
-            'id': 'MUHH48000314AA',
+            'id': 'l_96f4f1b0-de54-4e6a-b4f1-b0de54fe6af8',
-            'ext': 'mp4',
+            'ext': 'mp3',
-            'title': '20 spørsmål 23.05.2014',
+            'timestamp': 1522897200,
-            'description': 'md5:bdea103bc35494c143c6a9acdd84887a',
+            'alt_title': 'md5:06eae9f8c8ccf0718b54c83654e65550',
-            'duration': 1741,
+            'upload_date': '20180405',
-            'series': '20 spørsmål',
+            'thumbnail': 'https://gfx.nrk.no/CEDlVkEKxLYiBZ-CXjxSxgduDdaL-a4XTZlar9AoJFOA',
-            'episode': '23.05.2014',
+            'description': '',
+            'title': 'Jeg er sinna og det må du tåle!',
+            'age_limit': 0,
+            'duration': 1682.0,
         },
     }, {
         'url': 'https://radio.nrk.no/podcast/ulrikkes_univers/l_96f4f1b0-de54-4e6a-b4f1-b0de54fe6af8',
@@ -776,15 +954,16 @@ class NRKRadioPodkastIE(InfoExtractor):
             f'nrk:{video_id}', ie=NRKIE.ie_key(), video_id=video_id)
 
 
-class NRKPlaylistBaseIE(InfoExtractor):
+class NRKPlaylistBaseIE(NRKBaseIE):
     def _extract_description(self, webpage):
         pass
 
     def _real_extract(self, url):
         playlist_id = self._match_id(url)
 
-        webpage = self._download_webpage(url, playlist_id)
+        # Uses the render HTML endpoint instead of the regular article URL to prevent unrelated videos from being downloaded
-
+        # if .rich[data-video-id] elements appear in the "related articles" section too instead of just the main article.
+        webpage = self._download_webpage(f'https://www.nrk.no/serum/api/render/{playlist_id.split("-")[-1]}', playlist_id)
         entries = [
             self.url_result(f'nrk:{video_id}', NRKIE.ie_key())
             for video_id in re.findall(self._ITEM_RE, webpage)
@@ -800,6 +979,8 @@ class NRKPlaylistBaseIE(InfoExtractor):
 class NRKPlaylistIE(NRKPlaylistBaseIE):
     _VALID_URL = r'https?://(?:www\.)?nrk\.no/(?!video|skole)(?:[^/]+/)+(?P<id>[^/]+)'
     _ITEM_RE = r'class="[^"]*\brich\b[^"]*"[^>]+data-video-id="([^"]+)"'
+    _TITLE_RE = r'class="[^"]*\barticle-title\b[^"]*"[^>]*>([^<]+)<'
+    _DESCRIPTION_RE = r'class="[^"]*[\s"]article-lead[\s"][^>]*>[^<]*<p>([^<]*)<'
     _TESTS = [{
         'url': 'http://www.nrk.no/troms/gjenopplev-den-historiske-solformorkelsen-1.12270763',
         'info_dict': {
@@ -819,42 +1000,29 @@ class NRKPlaylistIE(NRKPlaylistBaseIE):
     }]
 
     def _extract_title(self, webpage):
-        return self._og_search_title(webpage, fatal=False)
+        return re.search(self._TITLE_RE, webpage).group(1)
 
     def _extract_description(self, webpage):
-        return self._og_search_description(webpage)
+        return re.search(self._DESCRIPTION_RE, webpage).group(1)
 
 
-class NRKTVEpisodesIE(NRKPlaylistBaseIE):
+class NRKSkoleIE(NRKBaseIE):
-    _VALID_URL = r'https?://tv\.nrk\.no/program/[Ee]pisodes/[^/]+/(?P<id>\d+)'
-    _ITEM_RE = rf'data-episode=["\']{NRKTVIE._EPISODE_RE}'
-    _TESTS = [{
-        'url': 'https://tv.nrk.no/program/episodes/nytt-paa-nytt/69031',
-        'info_dict': {
-            'id': '69031',
-            'title': 'Nytt på nytt, sesong: 201210',
-        },
-        'playlist_count': 4,
-    }]
-
-    def _extract_title(self, webpage):
-        return self._html_search_regex(
-            r'<h1>([^<]+)</h1>', webpage, 'title', fatal=False)
-
-
-class NRKSkoleIE(InfoExtractor):
     IE_DESC = 'NRK Skole'
     _VALID_URL = r'https?://(?:www\.)?nrk\.no/skole/?\?.*\bmediaId=(?P<id>\d+)'
 
     _TESTS = [{
         'url': 'https://www.nrk.no/skole/?page=search&q=&mediaId=14099',
-        'md5': '18c12c3d071953c3bf8d54ef6b2587b7',
+        'md5': '1d54ec4cff70d8f2c7909d1922514af2',
         'info_dict': {
             'id': '6021',
             'ext': 'mp4',
             'title': 'Genetikk og eneggede tvillinger',
-            'description': 'md5:3aca25dcf38ec30f0363428d2b265f8d',
+            'description': 'md5:7c0cc42d35d99bbc58f45639cdbcc163',
             'duration': 399,
+            'thumbnail': 'https://gfx.nrk.no/5SN-Uq11iR3ADwrCwTv0bAKbbBXXNpVJsaCLGiU8lFoQ',
+            'timestamp': 1205622000,
+            'upload_date': '20080315',
+            'alt_title': '',
         },
     }, {
         'url': 'https://www.nrk.no/skole/?page=objectives&subject=naturfag&objective=K15114&mediaId=19355',
@@ -863,9 +1031,14 @@ class NRKSkoleIE(InfoExtractor):
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
-
+        response = self._download_json(
-        nrk_id = self._download_json(
             f'https://nrkno-skole-prod.kube.nrk.no/skole/api/media/{video_id}',
-            video_id)['psId']
+            video_id)
-
+        nrk_id = response['psId']
-        return self.url_result(f'nrk:{nrk_id}')
+        return self.url_result(
+            f'nrk:{nrk_id}', NRKIE, nrk_id, url_transparent=True,
+            **traverse_obj(response, {
+                'title': ('title', {str}),
+                'timestamp': ('airedDate', {parse_iso8601}),
+                'description': ('summary', {str}),
+            }))

yt_dlp/extractor/pialive.py

@@ -0,0 +1,122 @@
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+    clean_html,
+    extract_attributes,
+    get_element_by_class,
+    get_element_html_by_class,
+    multipart_encode,
+    str_or_none,
+    unified_timestamp,
+    url_or_none,
+)
+from ..utils.traversal import traverse_obj
+
+
+class PiaLiveIE(InfoExtractor):
+    _VALID_URL = r'https?://player\.pia-live\.jp/stream/(?P<id>[\w-]+)'
+    _PLAYER_ROOT_URL = 'https://player.pia-live.jp/'
+    _PIA_LIVE_API_URL = 'https://api.pia-live.jp'
+    _API_KEY = 'kfds)FKFps-dms9e'
+    _TESTS = [{
+        'url': 'https://player.pia-live.jp/stream/4JagFBEIM14s_hK9aXHKf3k3F3bY5eoHFQxu68TC6krUDqGOwN4d61dCWQYOd6CTxl4hjya9dsfEZGsM4uGOUdax60lEI4twsXGXf7crmz8Gk__GhupTrWxA7RFRVt76',
+        'info_dict': {
+            'id': '88f3109a-f503-4d0f-a9f7-9f39ac745d84',
+            'display_id': '2431867_001',
+            'title': 'こながめでたい日２０２４の視聴ページ | PIA LIVE STREAM(ぴあライブストリーム)',
+            'live_status': 'was_live',
+            'comment_count': int,
+        },
+        'params': {
+            'getcomments': True,
+            'skip_download': True,
+            'ignore_no_formats_error': True,
+        },
+        'skip': 'The video is no longer available',
+    }, {
+        'url': 'https://player.pia-live.jp/stream/4JagFBEIM14s_hK9aXHKf3k3F3bY5eoHFQxu68TC6krJdu0GVBVbVy01IwpJ6J3qBEm3d9TCTt1d0eWpsZGj7DrOjVOmS7GAWGwyscMgiThopJvzgWC4H5b-7XQjAfRZ',
+        'info_dict': {
+            'id': '9ce8b8ba-f6d1-4d1f-83a0-18c3148ded93',
+            'display_id': '2431867_002',
+            'title': 'こながめでたい日２０２４の視聴ページ | PIA LIVE STREAM(ぴあライブストリーム)',
+            'live_status': 'was_live',
+            'comment_count': int,
+        },
+        'params': {
+            'getcomments': True,
+            'skip_download': True,
+            'ignore_no_formats_error': True,
+        },
+        'skip': 'The video is no longer available',
+    }]
+
+    def _extract_var(self, variable, html):
+        return self._search_regex(
+            rf'(?:var|const|let)\s+{variable}\s*=\s*(["\'])(?P<value>(?:(?!\1).)+)\1',
+            html, f'variable {variable}', group='value')
+
+    def _real_extract(self, url):
+        video_key = self._match_id(url)
+        webpage = self._download_webpage(url, video_key)
+
+        program_code = self._extract_var('programCode', webpage)
+        article_code = self._extract_var('articleCode', webpage)
+        title = self._html_extract_title(webpage)
+
+        if get_element_html_by_class('play-end', webpage):
+            raise ExtractorError('The video is no longer available', expected=True, video_id=program_code)
+
+        if start_info := clean_html(get_element_by_class('play-waiting__date', webpage)):
+            date, time = self._search_regex(
+                r'(?P<date>\d{4}/\d{1,2}/\d{1,2})\([月火水木金土日]\)(?P<time>\d{2}:\d{2})',
+                start_info, 'start_info', fatal=False, group=('date', 'time'))
+            if date and time:
+                release_timestamp_str = f'{date} {time} +09:00'
+                release_timestamp = unified_timestamp(release_timestamp_str)
+                self.raise_no_formats(f'The video will be available after {release_timestamp_str}', expected=True)
+                return {
+                    'id': program_code,
+                    'title': title,
+                    'live_status': 'is_upcoming',
+                    'release_timestamp': release_timestamp,
+                }
+
+        payload, content_type = multipart_encode({
+            'play_url': video_key,
+            'api_key': self._API_KEY,
+        })
+        api_data_and_headers = {
+            'data': payload,
+            'headers': {'Content-Type': content_type, 'Referer': self._PLAYER_ROOT_URL},
+        }
+
+        player_tag_list = self._download_json(
+            f'{self._PIA_LIVE_API_URL}/perf/player-tag-list/{program_code}', program_code,
+            'Fetching player tag list', 'Unable to fetch player tag list', **api_data_and_headers)
+
+        return self.url_result(
+            extract_attributes(player_tag_list['data']['movie_one_tag'])['src'],
+            url_transparent=True, title=title, display_id=program_code,
+            __post_extractor=self.extract_comments(program_code, article_code, api_data_and_headers))
+
+    def _get_comments(self, program_code, article_code, api_data_and_headers):
+        chat_room_url = traverse_obj(self._download_json(
+            f'{self._PIA_LIVE_API_URL}/perf/chat-tag-list/{program_code}/{article_code}', program_code,
+            'Fetching chat info', 'Unable to fetch chat info', fatal=False, **api_data_and_headers),
+            ('data', 'chat_one_tag', {extract_attributes}, 'src', {url_or_none}))
+        if not chat_room_url:
+            return
+        comment_page = self._download_webpage(
+            chat_room_url, program_code, 'Fetching comment page', 'Unable to fetch comment page',
+            fatal=False, headers={'Referer': self._PLAYER_ROOT_URL})
+        if not comment_page:
+            return
+        yield from traverse_obj(self._search_json(
+            r'var\s+_history\s*=', comment_page, 'comment list',
+            program_code, contains_pattern=r'\[(?s:.+)\]', fatal=False), (..., {
+                'timestamp': (0, {int}),
+                'author_is_uploader': (1, {lambda x: x == 2}),
+                'author': (2, {str}),
+                'text': (3, {str}),
+                'id': (4, {str_or_none}),
+            }))

yt_dlp/extractor/piaulizaportal.py

@@ -1,70 +0,0 @@
-from .common import InfoExtractor
-from ..utils import (
-    ExtractorError,
-    int_or_none,
-    parse_qs,
-    time_seconds,
-    traverse_obj,
-)
-
-
-class PIAULIZAPortalIE(InfoExtractor):
-    IE_DESC = 'ulizaportal.jp - PIA LIVE STREAM'
-    _VALID_URL = r'https?://(?:www\.)?ulizaportal\.jp/pages/(?P<id>[\da-f]{8}-(?:[\da-f]{4}-){3}[\da-f]{12})'
-    _TESTS = [{
-        'url': 'https://ulizaportal.jp/pages/005f18b7-e810-5618-cb82-0987c5755d44',
-        'info_dict': {
-            'id': '005f18b7-e810-5618-cb82-0987c5755d44',
-            'title': 'プレゼンテーションプレイヤーのサンプル',
-            'live_status': 'not_live',
-        },
-        'params': {
-            'skip_download': True,
-            'ignore_no_formats_error': True,
-        },
-    }, {
-        'url': 'https://ulizaportal.jp/pages/005e1b23-fe93-5780-19a0-98e917cc4b7d?expires=4102412400&signature=f422a993b683e1068f946caf406d211c17d1ef17da8bef3df4a519502155aa91&version=1',
-        'info_dict': {
-            'id': '005e1b23-fe93-5780-19a0-98e917cc4b7d',
-            'title': '【確認用】視聴サンプルページ（ULIZA）',
-            'live_status': 'not_live',
-        },
-        'params': {
-            'skip_download': True,
-            'ignore_no_formats_error': True,
-        },
-    }]
-
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-
-        expires = int_or_none(traverse_obj(parse_qs(url), ('expires', 0)))
-        if expires and expires <= time_seconds():
-            raise ExtractorError('The link is expired.', video_id=video_id, expected=True)
-
-        webpage = self._download_webpage(url, video_id)
-
-        player_data = self._download_webpage(
-            self._search_regex(
-                r'<script [^>]*\bsrc="(https://player-api\.p\.uliza\.jp/v1/players/[^"]+)"',
-                webpage, 'player data url'),
-            video_id, headers={'Referer': 'https://ulizaportal.jp/'},
-            note='Fetching player data', errnote='Unable to fetch player data')
-
-        formats = self._extract_m3u8_formats(
-            self._search_regex(
-                r'["\'](https://vms-api\.p\.uliza\.jp/v1/prog-index\.m3u8[^"\']+)', player_data,
-                'm3u8 url', default=None),
-            video_id, fatal=False)
-        m3u8_type = self._search_regex(
-            r'/hls/(dvr|video)/', traverse_obj(formats, (0, 'url')), 'm3u8 type', default=None)
-
-        return {
-            'id': video_id,
-            'title': self._html_extract_title(webpage),
-            'formats': formats,
-            'live_status': {
-                'video': 'is_live',
-                'dvr': 'was_live',  # short-term archives
-            }.get(m3u8_type, 'not_live'),  # VOD or long-term archives
-        }

yt_dlp/extractor/pokemon.py

@@ -1,136 +0,0 @@
-from .common import InfoExtractor
-from ..utils import (
-    ExtractorError,
-    extract_attributes,
-    int_or_none,
-    js_to_json,
-    merge_dicts,
-)
-
-
-class PokemonIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?pokemon\.com/[a-z]{2}(?:.*?play=(?P<id>[a-z0-9]{32})|/(?:[^/]+/)+(?P<display_id>[^/?#&]+))'
-    _TESTS = [{
-        'url': 'https://www.pokemon.com/us/pokemon-episodes/20_30-the-ol-raise-and-switch/',
-        'md5': '2fe8eaec69768b25ef898cda9c43062e',
-        'info_dict': {
-            'id': 'afe22e30f01c41f49d4f1d9eab5cd9a4',
-            'ext': 'mp4',
-            'title': 'The Ol’ Raise and Switch!',
-            'description': 'md5:7db77f7107f98ba88401d3adc80ff7af',
-        },
-        'add_id': ['LimelightMedia'],
-    }, {
-        # no data-video-title
-        'url': 'https://www.pokemon.com/fr/episodes-pokemon/films-pokemon/pokemon-lascension-de-darkrai-2008',
-        'info_dict': {
-            'id': 'dfbaf830d7e54e179837c50c0c6cc0e1',
-            'ext': 'mp4',
-            'title': "Pokémon : L'ascension de Darkrai",
-            'description': 'md5:d1dbc9e206070c3e14a06ff557659fb5',
-        },
-        'add_id': ['LimelightMedia'],
-        'params': {
-            'skip_download': True,
-        },
-    }, {
-        'url': 'http://www.pokemon.com/uk/pokemon-episodes/?play=2e8b5c761f1d4a9286165d7748c1ece2',
-        'only_matching': True,
-    }, {
-        'url': 'http://www.pokemon.com/fr/episodes-pokemon/18_09-un-hiver-inattendu/',
-        'only_matching': True,
-    }, {
-        'url': 'http://www.pokemon.com/de/pokemon-folgen/01_20-bye-bye-smettbo/',
-        'only_matching': True,
-    }]
-
-    def _real_extract(self, url):
-        video_id, display_id = self._match_valid_url(url).groups()
-        webpage = self._download_webpage(url, video_id or display_id)
-        video_data = extract_attributes(self._search_regex(
-            r'(<[^>]+data-video-id="{}"[^>]*>)'.format(video_id if video_id else '[a-z0-9]{32}'),
-            webpage, 'video data element'))
-        video_id = video_data['data-video-id']
-        title = video_data.get('data-video-title') or self._html_search_meta(
-            'pkm-title', webpage, ' title', default=None) or self._search_regex(
-            r'<h1[^>]+\bclass=["\']us-title[^>]+>([^<]+)', webpage, 'title')
-        return {
-            '_type': 'url_transparent',
-            'id': video_id,
-            'url': f'limelight:media:{video_id}',
-            'title': title,
-            'description': video_data.get('data-video-summary'),
-            'thumbnail': video_data.get('data-video-poster'),
-            'series': 'Pokémon',
-            'season_number': int_or_none(video_data.get('data-video-season')),
-            'episode': title,
-            'episode_number': int_or_none(video_data.get('data-video-episode')),
-            'ie_key': 'LimelightMedia',
-        }
-
-
-class PokemonWatchIE(InfoExtractor):
-    _VALID_URL = r'https?://watch\.pokemon\.com/[a-z]{2}-[a-z]{2}/(?:#/)?player(?:\.html)?\?id=(?P<id>[a-z0-9]{32})'
-    _API_URL = 'https://www.pokemon.com/api/pokemontv/v2/channels/{0:}'
-    _TESTS = [{
-        'url': 'https://watch.pokemon.com/en-us/player.html?id=8309a40969894a8e8d5bc1311e9c5667',
-        'md5': '62833938a31e61ab49ada92f524c42ff',
-        'info_dict': {
-            'id': '8309a40969894a8e8d5bc1311e9c5667',
-            'ext': 'mp4',
-            'title': 'Lillier and the Staff!',
-            'description': 'md5:338841b8c21b283d24bdc9b568849f04',
-        },
-    }, {
-        'url': 'https://watch.pokemon.com/en-us/#/player?id=3fe7752ba09141f0b0f7756d1981c6b2',
-        'only_matching': True,
-    }, {
-        'url': 'https://watch.pokemon.com/de-de/player.html?id=b3c402e111a4459eb47e12160ab0ba07',
-        'only_matching': True,
-    }]
-
-    def _extract_media(self, channel_array, video_id):
-        for channel in channel_array:
-            for media in channel.get('media'):
-                if media.get('id') == video_id:
-                    return media
-        return None
-
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-
-        info = {
-            '_type': 'url',
-            'id': video_id,
-            'url': f'limelight:media:{video_id}',
-            'ie_key': 'LimelightMedia',
-        }
-
-        # API call can be avoided entirely if we are listing formats
-        if self.get_param('listformats', False):
-            return info
-
-        webpage = self._download_webpage(url, video_id)
-        build_vars = self._parse_json(self._search_regex(
-            r'(?s)buildVars\s*=\s*({.*?})', webpage, 'build vars'),
-            video_id, transform_source=js_to_json)
-        region = build_vars.get('region')
-        channel_array = self._download_json(self._API_URL.format(region), video_id)
-        video_data = self._extract_media(channel_array, video_id)
-
-        if video_data is None:
-            raise ExtractorError(
-                f'Video {video_id} does not exist', expected=True)
-
-        info['_type'] = 'url_transparent'
-        images = video_data.get('images')
-
-        return merge_dicts(info, {
-            'title': video_data.get('title'),
-            'description': video_data.get('description'),
-            'thumbnail': images.get('medium') or images.get('small'),
-            'series': 'Pokémon',
-            'season_number': int_or_none(video_data.get('season')),
-            'episode': video_data.get('title'),
-            'episode_number': int_or_none(video_data.get('episode')),
-        })

yt_dlp/extractor/uliza.py

@@ -0,0 +1,113 @@
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+    int_or_none,
+    make_archive_id,
+    parse_qs,
+    time_seconds,
+)
+from ..utils.traversal import traverse_obj
+
+
+class UlizaPlayerIE(InfoExtractor):
+    _VALID_URL = r'https://player-api\.p\.uliza\.jp/v1/players/[^?#]+\?(?:[^#]*&)?name=(?P<id>[^#&]+)'
+    _TESTS = [{
+        'url': 'https://player-api.p.uliza.jp/v1/players/timeshift-disabled/pia/admin?type=normal&playerobjectname=ulizaPlayer&name=livestream01_dvr&repeatable=true',
+        'info_dict': {
+            'id': '88f3109a-f503-4d0f-a9f7-9f39ac745d84',
+            'ext': 'mp4',
+            'title': '88f3109a-f503-4d0f-a9f7-9f39ac745d84',
+            'live_status': 'was_live',
+            '_old_archive_ids': ['piaulizaportal 88f3109a-f503-4d0f-a9f7-9f39ac745d84'],
+        },
+    }, {
+        'url': 'https://player-api.p.uliza.jp/v1/players/uliza_jp_gallery_normal/promotion/admin?type=presentation&name=cookings&targetid=player1',
+        'info_dict': {
+            'id': 'ae350126-5e22-4a7f-a8ac-8d0fd448b800',
+            'ext': 'mp4',
+            'title': 'ae350126-5e22-4a7f-a8ac-8d0fd448b800',
+            'live_status': 'not_live',
+            '_old_archive_ids': ['piaulizaportal ae350126-5e22-4a7f-a8ac-8d0fd448b800'],
+        },
+    }, {
+        'url': 'https://player-api.p.uliza.jp/v1/players/default-player/pia/admin?type=normal&name=pia_movie_uliza_fix&targetid=ulizahtml5&repeatable=true',
+        'info_dict': {
+            'id': '0644ecc8-e354-41b4-b957-3b08a2d63df1',
+            'ext': 'mp4',
+            'title': '0644ecc8-e354-41b4-b957-3b08a2d63df1',
+            'live_status': 'not_live',
+            '_old_archive_ids': ['piaulizaportal 0644ecc8-e354-41b4-b957-3b08a2d63df1'],
+        },
+    }]
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        player_data = self._download_webpage(
+            url, display_id, headers={'Referer': 'https://player-api.p.uliza.jp/'},
+            note='Fetching player data', errnote='Unable to fetch player data')
+
+        m3u8_url = self._search_regex(
+            r'["\'](https://vms-api\.p\.uliza\.jp/v1/prog-index\.m3u8[^"\']+)', player_data, 'm3u8 url')
+        video_id = parse_qs(m3u8_url).get('ss', [display_id])[0]
+
+        formats = self._extract_m3u8_formats(m3u8_url, video_id)
+        m3u8_type = self._search_regex(
+            r'/hls/(dvr|video)/', traverse_obj(formats, (0, 'url')), 'm3u8 type', default=None)
+        return {
+            'id': video_id,
+            'title': video_id,
+            'formats': formats,
+            'live_status': {
+                'video': 'is_live',
+                'dvr': 'was_live',  # short-term archives
+            }.get(m3u8_type, 'not_live'),  # VOD or long-term archives
+            '_old_archive_ids': [make_archive_id('PIAULIZAPortal', video_id)],
+        }
+
+
+class UlizaPortalIE(InfoExtractor):
+    IE_DESC = 'ulizaportal.jp'
+    _VALID_URL = r'https?://(?:www\.)?ulizaportal\.jp/pages/(?P<id>[\da-f]{8}-(?:[\da-f]{4}-){3}[\da-f]{12})'
+    _TESTS = [{
+        'url': 'https://ulizaportal.jp/pages/005f18b7-e810-5618-cb82-0987c5755d44',
+        'info_dict': {
+            'id': 'ae350126-5e22-4a7f-a8ac-8d0fd448b800',
+            'display_id': '005f18b7-e810-5618-cb82-0987c5755d44',
+            'title': 'プレゼンテーションプレイヤーのサンプル',
+            'live_status': 'not_live',
+            '_old_archive_ids': ['piaulizaportal ae350126-5e22-4a7f-a8ac-8d0fd448b800'],
+        },
+        'params': {
+            'skip_download': True,
+            'ignore_no_formats_error': True,
+        },
+    }, {
+        'url': 'https://ulizaportal.jp/pages/005e1b23-fe93-5780-19a0-98e917cc4b7d?expires=4102412400&signature=f422a993b683e1068f946caf406d211c17d1ef17da8bef3df4a519502155aa91&version=1',
+        'info_dict': {
+            'id': '0644ecc8-e354-41b4-b957-3b08a2d63df1',
+            'display_id': '005e1b23-fe93-5780-19a0-98e917cc4b7d',
+            'title': '【確認用】視聴サンプルページ（ULIZA）',
+            'live_status': 'not_live',
+            '_old_archive_ids': ['piaulizaportal 0644ecc8-e354-41b4-b957-3b08a2d63df1'],
+        },
+        'params': {
+            'skip_download': True,
+            'ignore_no_formats_error': True,
+        },
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        expires = int_or_none(traverse_obj(parse_qs(url), ('expires', 0)))
+        if expires and expires <= time_seconds():
+            raise ExtractorError('The link is expired', video_id=video_id, expected=True)
+
+        webpage = self._download_webpage(url, video_id)
+
+        player_data_url = self._search_regex(
+            r'<script [^>]*\bsrc="(https://player-api\.p\.uliza\.jp/v1/players/[^"]+)"',
+            webpage, 'player data url')
+        return self.url_result(
+            player_data_url, UlizaPlayerIE, url_transparent=True,
+            display_id=video_id, video_title=self._html_extract_title(webpage))

yt_dlp/extractor/veoh.py

@@ -1,189 +0,0 @@
-import functools
-import json
-
-from .common import InfoExtractor
-from ..utils import (
-    ExtractorError,
-    OnDemandPagedList,
-    int_or_none,
-    parse_duration,
-    qualities,
-    remove_start,
-    strip_or_none,
-)
-
-
-class VeohIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?veoh\.com/(?:watch|videos|embed|iphone/#_Watch)/(?P<id>(?:v|e|yapi-)[\da-zA-Z]+)'
-
-    _TESTS = [{
-        'url': 'http://www.veoh.com/watch/v56314296nk7Zdmz3',
-        'md5': '620e68e6a3cff80086df3348426c9ca3',
-        'info_dict': {
-            'id': 'v56314296nk7Zdmz3',
-            'ext': 'mp4',
-            'title': 'Straight Backs Are Stronger',
-            'description': 'md5:203f976279939a6dc664d4001e13f5f4',
-            'thumbnail': 're:https://fcache\\.veoh\\.com/file/f/th56314296\\.jpg(\\?.*)?',
-            'uploader': 'LUMOback',
-            'duration': 46,
-            'view_count': int,
-            'average_rating': int,
-            'comment_count': int,
-            'age_limit': 0,
-            'categories': ['technology_and_gaming'],
-            'tags': ['posture', 'posture', 'sensor', 'back', 'pain', 'wearable', 'tech', 'lumo'],
-        },
-    }, {
-        'url': 'http://www.veoh.com/embed/v56314296nk7Zdmz3',
-        'only_matching': True,
-    }, {
-        'url': 'http://www.veoh.com/watch/v27701988pbTc4wzN?h1=Chile+workers+cover+up+to+avoid+skin+damage',
-        'md5': '4a6ff84b87d536a6a71e6aa6c0ad07fa',
-        'info_dict': {
-            'id': '27701988',
-            'ext': 'mp4',
-            'title': 'Chile workers cover up to avoid skin damage',
-            'description': 'md5:2bd151625a60a32822873efc246ba20d',
-            'uploader': 'afp-news',
-            'duration': 123,
-        },
-        'skip': 'This video has been deleted.',
-    }, {
-        'url': 'http://www.veoh.com/watch/v69525809F6Nc4frX',
-        'md5': '4fde7b9e33577bab2f2f8f260e30e979',
-        'note': 'Embedded ooyala video',
-        'info_dict': {
-            'id': '69525809',
-            'ext': 'mp4',
-            'title': 'Doctors Alter Plan For Preteen\'s Weight Loss Surgery',
-            'description': 'md5:f5a11c51f8fb51d2315bca0937526891',
-            'uploader': 'newsy-videos',
-        },
-        'skip': 'This video has been deleted.',
-    }, {
-        'url': 'http://www.veoh.com/watch/e152215AJxZktGS',
-        'only_matching': True,
-    }, {
-        'url': 'https://www.veoh.com/videos/v16374379WA437rMH',
-        'md5': 'cceb73f3909063d64f4b93d4defca1b3',
-        'info_dict': {
-            'id': 'v16374379WA437rMH',
-            'ext': 'mp4',
-            'title': 'Phantasmagoria 2, pt. 1-3',
-            'description': 'Phantasmagoria: a Puzzle of Flesh',
-            'thumbnail': 're:https://fcache\\.veoh\\.com/file/f/th16374379\\.jpg(\\?.*)?',
-            'uploader': 'davidspackage',
-            'duration': 968,
-            'view_count': int,
-            'average_rating': int,
-            'comment_count': int,
-            'age_limit': 18,
-            'categories': ['technology_and_gaming', 'gaming'],
-            'tags': ['puzzle', 'of', 'flesh'],
-        },
-    }]
-
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-        metadata = self._download_json(
-            'https://www.veoh.com/watch/getVideo/' + video_id,
-            video_id)
-        video = metadata['video']
-        title = video['title']
-
-        thumbnail_url = None
-        q = qualities(['Regular', 'HQ'])
-        formats = []
-        for f_id, f_url in video.get('src', {}).items():
-            if not f_url:
-                continue
-            if f_id == 'poster':
-                thumbnail_url = f_url
-            else:
-                formats.append({
-                    'format_id': f_id,
-                    'quality': q(f_id),
-                    'url': f_url,
-                })
-
-        categories = metadata.get('categoryPath')
-        if not categories:
-            category = remove_start(strip_or_none(video.get('category')), 'category_')
-            categories = [category] if category else None
-        tags = video.get('tags')
-
-        return {
-            'id': video_id,
-            'title': title,
-            'description': video.get('description'),
-            'thumbnail': thumbnail_url,
-            'uploader': video.get('author', {}).get('nickname'),
-            'duration': int_or_none(video.get('lengthBySec')) or parse_duration(video.get('length')),
-            'view_count': int_or_none(video.get('views')),
-            'formats': formats,
-            'average_rating': int_or_none(video.get('rating')),
-            'comment_count': int_or_none(video.get('numOfComments')),
-            'age_limit': 18 if video.get('contentRatingId') == 2 else 0,
-            'categories': categories,
-            'tags': tags.split(', ') if tags else None,
-        }
-
-
-class VeohUserIE(VeohIE):  # XXX: Do not subclass from concrete IE
-    _VALID_URL = r'https?://(?:www\.)?veoh\.com/users/(?P<id>[\w-]+)'
-    IE_NAME = 'veoh:user'
-
-    _TESTS = [
-        {
-            'url': 'https://www.veoh.com/users/valentinazoe',
-            'info_dict': {
-                'id': 'valentinazoe',
-                'title': 'valentinazoe (Uploads)',
-            },
-            'playlist_mincount': 75,
-        },
-        {
-            'url': 'https://www.veoh.com/users/PiensaLibre',
-            'info_dict': {
-                'id': 'PiensaLibre',
-                'title': 'PiensaLibre (Uploads)',
-            },
-            'playlist_mincount': 2,
-        }]
-
-    _PAGE_SIZE = 16
-
-    def _fetch_page(self, uploader, page):
-        response = self._download_json(
-            'https://www.veoh.com/users/published/videos', uploader,
-            note=f'Downloading videos page {page + 1}',
-            headers={
-                'x-csrf-token': self._TOKEN,
-                'content-type': 'application/json;charset=UTF-8',
-            },
-            data=json.dumps({
-                'username': uploader,
-                'maxResults': self._PAGE_SIZE,
-                'page': page + 1,
-                'requestName': 'userPage',
-            }).encode())
-        if not response.get('success'):
-            raise ExtractorError(response['message'])
-
-        for video in response['videos']:
-            yield self.url_result(f'https://www.veoh.com/watch/{video["permalinkId"]}', VeohIE,
-                                  video['permalinkId'], video.get('title'))
-
-    def _real_initialize(self):
-        webpage = self._download_webpage(
-            'https://www.veoh.com', None, note='Downloading authorization token')
-        self._TOKEN = self._search_regex(
-            r'csrfToken:\s*(["\'])(?P<token>[0-9a-zA-Z]{40})\1', webpage,
-            'request token', group='token')
-
-    def _real_extract(self, url):
-        uploader = self._match_id(url)
-        return self.playlist_result(OnDemandPagedList(
-            functools.partial(self._fetch_page, uploader),
-            self._PAGE_SIZE), uploader, f'{uploader} (Uploads)')

yt_dlp/extractor/youtube.py

@@ -5087,7 +5087,7 @@ class YoutubeTabBaseInfoExtractor(YoutubeBaseInfoExtractor):
     def _rich_entries(self, rich_grid_renderer):
         renderer = traverse_obj(
             rich_grid_renderer,
-            ('content', ('videoRenderer', 'reelItemRenderer', 'playlistRenderer', 'shortsLockupViewModel'), any)) or {}
+            ('content', ('videoRenderer', 'reelItemRenderer', 'playlistRenderer', 'shortsLockupViewModel', 'lockupViewModel'), any)) or {}
         video_id = renderer.get('videoId')
         if video_id:
             yield self._extract_video(renderer)
@@ -5114,6 +5114,18 @@ class YoutubeTabBaseInfoExtractor(YoutubeBaseInfoExtractor):
                 })),
                 thumbnails=self._extract_thumbnails(renderer, 'thumbnail', final_key='sources'))
             return
+        # lockupViewModel extraction
+        content_id = renderer.get('contentId')
+        if content_id and renderer.get('contentType') == 'LOCKUP_CONTENT_TYPE_PODCAST':
+            yield self.url_result(
+                f'https://www.youtube.com/playlist?list={content_id}',
+                ie=YoutubeTabIE, video_id=content_id,
+                **traverse_obj(renderer, {
+                    'title': ('metadata', 'lockupMetadataViewModel', 'title', 'content', {str}),
+                }),
+                thumbnails=self._extract_thumbnails(renderer, (
+                    'contentImage', 'collectionThumbnailViewModel', 'primaryThumbnail', 'thumbnailViewModel', 'image'), final_key='sources'))
+            return
 
     def _video_entry(self, video_renderer):
         video_id = video_renderer.get('videoId')
@@ -6706,22 +6718,22 @@ class YoutubeTabIE(YoutubeTabBaseInfoExtractor):
         },
         'playlist_count': 0,
     }, {
-        # Podcasts tab, with rich entry playlistRenderers
+        # Podcasts tab, with rich entry lockupViewModel
         'url': 'https://www.youtube.com/@99percentinvisiblepodcast/podcasts',
         'info_dict': {
             'id': 'UCVMF2HD4ZgC0QHpU9Yq5Xrw',
             'channel_id': 'UCVMF2HD4ZgC0QHpU9Yq5Xrw',
             'uploader_url': 'https://www.youtube.com/@99percentinvisiblepodcast',
             'description': 'md5:3a0ed38f1ad42a68ef0428c04a15695c',
-            'title': '99 Percent Invisible - Podcasts',
+            'title': '99% Invisible - Podcasts',
-            'uploader': '99 Percent Invisible',
+            'uploader': '99% Invisible',
             'channel_follower_count': int,
             'channel_url': 'https://www.youtube.com/channel/UCVMF2HD4ZgC0QHpU9Yq5Xrw',
             'tags': [],
-            'channel': '99 Percent Invisible',
+            'channel': '99% Invisible',
             'uploader_id': '@99percentinvisiblepodcast',
         },
-        'playlist_count': 0,
+        'playlist_count': 5,
     }, {
         # Releases tab, with rich entry playlistRenderers (same as Podcasts tab)
         'url': 'https://www.youtube.com/@AHimitsu/releases',