[ie/onsen] Add extractor (#10971)

Closes #10902
Authored by: doe1080

.github/workflows/core.yml

@@ -37,17 +37,21 @@ jobs:
       matrix:
         os: [ubuntu-latest]
         # CPython 3.9 is in quick-test
-        python-version: ['3.10', '3.11', '3.12', '3.13', pypy-3.11]
+        python-version: ['3.10', '3.11', '3.12', '3.13', '3.14-dev', pypy-3.11]
         include:
         # atleast one of each CPython/PyPy tests must be in windows
         - os: windows-latest
           python-version: '3.9'
         - os: windows-latest
           python-version: '3.10'
+        - os: windows-latest
+          python-version: '3.11'
         - os: windows-latest
           python-version: '3.12'
         - os: windows-latest
           python-version: '3.13'
+        - os: windows-latest
+          python-version: '3.14-dev'
         - os: windows-latest
           python-version: pypy-3.11
     steps:

.github/workflows/download.yml

@@ -28,7 +28,7 @@ jobs:
       fail-fast: true
       matrix:
         os: [ubuntu-latest]
-        python-version: ['3.10', '3.11', '3.12', '3.13', pypy-3.11]
+        python-version: ['3.10', '3.11', '3.12', '3.13', '3.14-dev', pypy-3.11]
         include:
         # atleast one of each CPython/PyPy tests must be in windows
         - os: windows-latest

.github/workflows/signature-tests.yml

@@ -25,7 +25,7 @@ jobs:
       fail-fast: false
       matrix:
         os: [ubuntu-latest, windows-latest]
-        python-version: ['3.9', '3.10', '3.11', '3.12', '3.13', pypy-3.11]
+        python-version: ['3.9', '3.10', '3.11', '3.12', '3.13', '3.14-dev', pypy-3.11]
     steps:
     - uses: actions/checkout@v4
     - name: Set up Python ${{ matrix.python-version }}

pyproject.toml

@@ -35,6 +35,7 @@ classifiers = [
     "Programming Language :: Python :: 3.11",
     "Programming Language :: Python :: 3.12",
     "Programming Language :: Python :: 3.13",
+    "Programming Language :: Python :: 3.14",
     "Programming Language :: Python :: Implementation",
     "Programming Language :: Python :: Implementation :: CPython",
     "Programming Language :: Python :: Implementation :: PyPy",
@@ -173,7 +174,8 @@ python = [
     "3.11",
     "3.12",
     "3.13",
-    "pypy3.10",
+    "3.14",
+    "pypy3.11",
 ]
 
 [tool.ruff]

setup.cfg

@@ -16,7 +16,7 @@ remove-unused-variables = true
 
 [tox:tox]
 skipsdist = true
-envlist = py{39,310,311,312,313},pypy311
+envlist = py{39,310,311,312,313,314},pypy311
 skip_missing_interpreters = true
 
 [testenv]  # tox

yt_dlp/extractor/_extractors.py

@@ -1433,6 +1433,7 @@ from .onet import (
     OnetPlIE,
 )
 from .onionstudios import OnionStudiosIE
+from .onsen import OnsenIE
 from .opencast import (
     OpencastIE,
     OpencastPlaylistIE,
@@ -1779,7 +1780,6 @@ from .rutube import (
     RutubePlaylistIE,
     RutubeTagsIE,
 )
-from .rutv import RUTVIE
 from .ruutu import RuutuIE
 from .ruv import (
     RuvIE,
@@ -1877,7 +1877,12 @@ from .skynewsau import SkyNewsAUIE
 from .slideshare import SlideshareIE
 from .slideslive import SlidesLiveIE
 from .slutload import SlutloadIE
-from .smotrim import SmotrimIE
+from .smotrim import (
+    SmotrimAudioIE,
+    SmotrimIE,
+    SmotrimLiveIE,
+    SmotrimPlaylistIE,
+)
 from .snapchat import SnapchatSpotlightIE
 from .snotr import SnotrIE
 from .softwhiteunderbelly import SoftWhiteUnderbellyIE
@@ -2149,6 +2154,7 @@ from .tubitv import (
 )
 from .tumblr import TumblrIE
 from .tunein import (
+    TuneInEmbedIE,
     TuneInPodcastEpisodeIE,
     TuneInPodcastIE,
     TuneInShortenerIE,
@@ -2283,7 +2289,6 @@ from .utreon import UtreonIE
 from .varzesh3 import Varzesh3IE
 from .vbox7 import Vbox7IE
 from .veo import VeoIE
-from .vesti import VestiIE
 from .vevo import (
     VevoIE,
     VevoPlaylistIE,

yt_dlp/extractor/loco.py

@@ -37,7 +37,7 @@ class LocoIE(InfoExtractor):
         },
     }, {
         'url': 'https://loco.com/stream/c64916eb-10fb-46a9-9a19-8c4b7ed064e7',
-        'md5': '45ebc8a47ee1c2240178757caf8881b5',
+        'md5': '8b9bda03eba4d066928ae8d71f19befb',
         'info_dict': {
             'id': 'c64916eb-10fb-46a9-9a19-8c4b7ed064e7',
             'ext': 'mp4',
@@ -55,9 +55,9 @@ class LocoIE(InfoExtractor):
             'tags': ['Gameplay'],
             'series': 'GTA 5',
             'timestamp': 1740612872,
-            'modified_timestamp': 1740613037,
+            'modified_timestamp': 1750948439,
             'upload_date': '20250226',
-            'modified_date': '20250226',
+            'modified_date': '20250626',
         },
     }, {
         # Requires video authorization
@@ -123,8 +123,8 @@ class LocoIE(InfoExtractor):
     def _real_extract(self, url):
         video_type, video_id = self._match_valid_url(url).group('type', 'id')
         webpage = self._download_webpage(url, video_id)
-        stream = traverse_obj(self._search_nextjs_data(webpage, video_id), (
+        stream = traverse_obj(self._search_nextjs_v13_data(webpage, video_id), (
-            'props', 'pageProps', ('liveStreamData', 'stream', 'liveStream'), {dict}, any, {require('stream info')}))
+            ..., (None, 'ssrData'), ('liveStreamData', 'stream', 'liveStream'), {dict}, any, {require('stream info')}))
 
         if access_token := self._get_access_token(video_id):
             self._request_webpage(

yt_dlp/extractor/onsen.py

@@ -0,0 +1,151 @@
+import base64
+import json
+
+from .common import InfoExtractor
+from ..networking.exceptions import HTTPError
+from ..utils import (
+    ExtractorError,
+    clean_html,
+    int_or_none,
+    parse_qs,
+    str_or_none,
+    strftime_or_none,
+    update_url,
+    update_url_query,
+    url_or_none,
+)
+from ..utils.traversal import traverse_obj
+
+
+class OnsenIE(InfoExtractor):
+    IE_NAME = 'onsen'
+    IE_DESC = 'インターネットラジオステーション＜音泉＞'
+
+    _BASE_URL = 'https://www.onsen.ag'
+    _HEADERS = {'Referer': f'{_BASE_URL}/'}
+    _NETRC_MACHINE = 'onsen'
+    _VALID_URL = r'https?://(?:(?:share|www)\.)onsen\.ag/program/(?P<id>[^/?#]+)'
+    _TESTS = [{
+        'url': 'https://share.onsen.ag/program/onsenking?p=90&c=MTA0NjI',
+        'info_dict': {
+            'id': '10462',
+            'ext': 'm4a',
+            'title': '第SP回',
+            'cast': 'count:3',
+            'description': 'md5:de62c80a41c4c8d84da53a1ee681ad18',
+            'display_id': 'MTA0NjI=',
+            'media_type': 'sound',
+            'section_start': 0,
+            'series': '音泉キング「下野紘」のラジオ きみはもちろん、＜音泉＞ファミリーだよね？',
+            'series_id': 'onsenking',
+            'tags': 'count:2',
+            'thumbnail': r're:https?://d3bzklg4lms4gh\.cloudfront\.net/program_info/image/default/production/.+',
+            'upload_date': '20220627',
+            'webpage_url': 'https://www.onsen.ag/program/onsenking?c=MTA0NjI=',
+        },
+    }, {
+        'url': 'https://share.onsen.ag/program/girls-band-cry-radio?p=370&c=MTgwMDE',
+        'info_dict': {
+            'id': '18001',
+            'ext': 'mp4',
+            'title': '第4回',
+            'cast': 'count:5',
+            'description': 'md5:bbca8a389d99c90cbbce8f383c85fedd',
+            'display_id': 'MTgwMDE=',
+            'media_type': 'movie',
+            'section_start': 0,
+            'series': 'TVアニメ『ガールズバンドクライ』WEBラジオ「ガールズバンドクライ～ラジオにも全部ぶち込め。～」',
+            'series_id': 'girls-band-cry-radio',
+            'tags': 'count:3',
+            'thumbnail': r're:https?://d3bzklg4lms4gh\.cloudfront\.net/program_info/image/default/production/.+',
+            'upload_date': '20240425',
+            'webpage_url': 'https://www.onsen.ag/program/girls-band-cry-radio?c=MTgwMDE=',
+        },
+        'skip': 'Only available for premium supporters',
+    }, {
+        'url': 'https://www.onsen.ag/program/uma',
+        'info_dict': {
+            'id': 'uma',
+            'title': 'UMA YELL RADIO',
+        },
+        'playlist_mincount': 35,
+    }]
+
+    @staticmethod
+    def _get_encoded_id(program):
+        return base64.urlsafe_b64encode(str(program['id']).encode()).decode()
+
+    def _perform_login(self, username, password):
+        sign_in = self._download_json(
+            f'{self._BASE_URL}/web_api/signin', None, 'Logging in', headers={
+                'Accept': 'application/json',
+                'Content-Type': 'application/json',
+            }, data=json.dumps({
+                'session': {
+                    'email': username,
+                    'password': password,
+                },
+            }).encode(), expected_status=401)
+
+        if sign_in.get('error'):
+            raise ExtractorError('Invalid username or password', expected=True)
+
+    def _real_extract(self, url):
+        program_id = self._match_id(url)
+        try:
+            programs = self._download_json(
+                f'{self._BASE_URL}/web_api/programs/{program_id}', program_id)
+        except ExtractorError as e:
+            if isinstance(e.cause, HTTPError) and e.cause.status == 404:
+                raise ExtractorError('Invalid URL', expected=True)
+            raise
+
+        query = {k: v[-1] for k, v in parse_qs(url).items() if v}
+        if 'c' not in query:
+            entries = [
+                self.url_result(update_url_query(url, {'c': self._get_encoded_id(program)}), OnsenIE)
+                for program in traverse_obj(programs, ('contents', lambda _, v: v['id']))
+            ]
+
+            return self.playlist_result(
+                entries, program_id, traverse_obj(programs, ('program_info', 'title', {clean_html})))
+
+        raw_id = base64.urlsafe_b64decode(f'{query["c"]}===').decode()
+        p_keys = ('contents', lambda _, v: v['id'] == int(raw_id))
+
+        program = traverse_obj(programs, (*p_keys, any))
+        if not program:
+            raise ExtractorError(
+                'This program is no longer available', expected=True)
+        m3u8_url = traverse_obj(program, ('streaming_url', {url_or_none}))
+        if not m3u8_url:
+            self.raise_login_required(
+                'This program is only available for premium supporters')
+
+        display_id = self._get_encoded_id(program)
+        date_str = self._search_regex(
+            rf'{program_id}0?(\d{{6}})', m3u8_url, 'date string', default=None)
+
+        return {
+            'display_id': display_id,
+            'formats': self._extract_m3u8_formats(m3u8_url, raw_id, headers=self._HEADERS),
+            'http_headers': self._HEADERS,
+            'section_start': int_or_none(query.get('t', 0)),
+            'upload_date': strftime_or_none(f'20{date_str}'),
+            'webpage_url': f'{self._BASE_URL}/program/{program_id}?c={display_id}',
+            **traverse_obj(program, {
+                'id': ('id', {int}, {str_or_none}),
+                'title': ('title', {clean_html}),
+                'media_type': ('media_type', {str}),
+                'thumbnail': ('poster_image_url', {url_or_none}, {update_url(query=None)}),
+            }),
+            **traverse_obj(programs, {
+                'cast': (('performers', (*p_keys, 'guests')), ..., 'name', {str}, filter),
+                'series_id': ('directory_name', {str}),
+            }),
+            **traverse_obj(programs, ('program_info', {
+                'description': ('description', {clean_html}, filter),
+                'series': ('title', {clean_html}),
+                'tags': ('hashtag_list', ..., {str}, filter),
+            })),
+        }

yt_dlp/extractor/rutv.py

@@ -1,191 +0,0 @@
-import re
-
-from .common import InfoExtractor
-from ..utils import ExtractorError, int_or_none, str_to_int
-
-
-class RUTVIE(InfoExtractor):
-    IE_DESC = 'RUTV.RU'
-    _VALID_URL = r'''(?x)
-                    https?://
-                        (?:test)?player\.(?:rutv\.ru|vgtrk\.com)/
-                        (?P<path>
-                            flash\d+v/container\.swf\?id=|
-                            iframe/(?P<type>swf|video|live)/id/|
-                            index/iframe/cast_id/
-                        )
-                        (?P<id>\d+)
-                    '''
-    _EMBED_REGEX = [
-        r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:test)?player\.(?:rutv\.ru|vgtrk\.com)/(?:iframe/(?:swf|video|live)/id|index/iframe/cast_id)/.+?)\1',
-        r'<meta[^>]+?property=(["\'])og:video\1[^>]+?content=(["\'])(?P<url>https?://(?:test)?player\.(?:rutv\.ru|vgtrk\.com)/flash\d+v/container\.swf\?id=.+?\2)',
-    ]
-
-    _TESTS = [{
-        'url': 'http://player.rutv.ru/flash2v/container.swf?id=774471&sid=kultura&fbv=true&isPlay=true&ssl=false&i=560&acc_video_id=episode_id/972347/video_id/978186/brand_id/31724',
-        'info_dict': {
-            'id': '774471',
-            'ext': 'mp4',
-            'title': 'Монологи на все времена. Концерт',
-            'description': 'md5:18d8b5e6a41fb1faa53819471852d5d5',
-            'duration': 2906,
-            'thumbnail': r're:https?://cdn-st2\.smotrim\.ru/.+\.jpg',
-        },
-        'params': {'skip_download': 'm3u8'},
-    }, {
-        'url': 'https://player.vgtrk.com/flash2v/container.swf?id=774016&sid=russiatv&fbv=true&isPlay=true&ssl=false&i=560&acc_video_id=episode_id/972098/video_id/977760/brand_id/57638',
-        'info_dict': {
-            'id': '774016',
-            'ext': 'mp4',
-            'title': 'Чужой в семье Сталина',
-            'description': '',
-            'duration': 2539,
-        },
-        'skip': 'Invalid URL',
-    }, {
-        'url': 'http://player.rutv.ru/iframe/swf/id/766888/sid/hitech/?acc_video_id=4000',
-        'info_dict': {
-            'id': '766888',
-            'ext': 'mp4',
-            'title': 'Вести.net: интернет-гиганты начали перетягивание программных "одеял"',
-            'description': 'md5:65ddd47f9830c4f42ed6475f8730c995',
-            'duration': 279,
-            'thumbnail': r're:https?://cdn-st2\.smotrim\.ru/.+\.jpg',
-        },
-        'params': {'skip_download': 'm3u8'},
-    }, {
-        'url': 'http://player.rutv.ru/iframe/video/id/771852/start_zoom/true/showZoomBtn/false/sid/russiatv/?acc_video_id=episode_id/970443/video_id/975648/brand_id/5169',
-        'info_dict': {
-            'id': '771852',
-            'ext': 'mp4',
-            'title': 'Прямой эфир. Жертвы загадочной болезни: смерть от старости в 17 лет',
-            'description': 'md5:b81c8c55247a4bd996b43ce17395b2d8',
-            'duration': 3096,
-            'thumbnail': r're:https?://cdn-st2\.smotrim\.ru/.+\.jpg',
-        },
-        'params': {'skip_download': 'm3u8'},
-    }, {
-        'url': 'http://player.rutv.ru/iframe/live/id/51499/showZoomBtn/false/isPlay/true/sid/sochi2014',
-        'info_dict': {
-            'id': '51499',
-            'ext': 'flv',
-            'title': 'Сочи-2014. Биатлон. Индивидуальная гонка. Мужчины ',
-            'description': 'md5:9e0ed5c9d2fa1efbfdfed90c9a6d179c',
-        },
-        'skip': 'Invalid URL',
-    }, {
-        'url': 'http://player.rutv.ru/iframe/live/id/21/showZoomBtn/false/isPlay/true/',
-        'info_dict': {
-            'id': '21',
-            'ext': 'mp4',
-            'title': str,
-            'is_live': True,
-        },
-        'skip': 'Invalid URL',
-    }, {
-        'url': 'https://testplayer.vgtrk.com/iframe/live/id/19201/showZoomBtn/false/isPlay/true/',
-        'only_matching': True,
-    }]
-    _WEBPAGE_TESTS = [{
-        'url': 'http://istoriya-teatra.ru/news/item/f00/s05/n0000545/index.shtml',
-        'info_dict': {
-            'id': '1952012',
-            'ext': 'mp4',
-            'title': 'Новости культуры. Эфир от 10.10.2019 (23:30). Театр Сатиры отмечает день рождения премьерой',
-            'description': 'md5:fced27112ff01ff8fc4a452fc088bad6',
-            'duration': 191,
-            'thumbnail': r're:https?://cdn-st2\.smotrim\.ru/.+\.jpg',
-        },
-        'params': {'skip_download': 'm3u8'},
-    }]
-
-    def _real_extract(self, url):
-        mobj = self._match_valid_url(url)
-        video_id = mobj.group('id')
-        video_path = mobj.group('path')
-
-        if re.match(r'flash\d+v', video_path):
-            video_type = 'video'
-        elif video_path.startswith('iframe'):
-            video_type = mobj.group('type')
-            if video_type == 'swf':
-                video_type = 'video'
-        elif video_path.startswith('index/iframe/cast_id'):
-            video_type = 'live'
-
-        is_live = video_type == 'live'
-
-        json_data = self._download_json(
-            'http://player.vgtrk.com/iframe/data{}/id/{}'.format('live' if is_live else 'video', video_id),
-            video_id, 'Downloading JSON')
-
-        if json_data['errors']:
-            raise ExtractorError('{} said: {}'.format(self.IE_NAME, json_data['errors']), expected=True)
-
-        playlist = json_data['data']['playlist']
-        medialist = playlist['medialist']
-        media = medialist[0]
-
-        if media['errors']:
-            raise ExtractorError('{} said: {}'.format(self.IE_NAME, media['errors']), expected=True)
-
-        view_count = int_or_none(playlist.get('count_views'))
-        priority_transport = playlist['priority_transport']
-
-        thumbnail = media['picture']
-        width = int_or_none(media['width'])
-        height = int_or_none(media['height'])
-        description = media['anons']
-        title = media['title']
-        duration = int_or_none(media.get('duration'))
-
-        formats = []
-        subtitles = {}
-
-        for transport, links in media['sources'].items():
-            for quality, url in links.items():
-                preference = -1 if priority_transport == transport else -2
-                if transport == 'rtmp':
-                    mobj = re.search(r'^(?P<url>rtmp://[^/]+/(?P<app>.+))/(?P<playpath>.+)$', url)
-                    if not mobj:
-                        continue
-                    fmt = {
-                        'url': mobj.group('url'),
-                        'play_path': mobj.group('playpath'),
-                        'app': mobj.group('app'),
-                        'page_url': 'http://player.rutv.ru',
-                        'player_url': 'http://player.rutv.ru/flash3v/osmf.swf?i=22',
-                        'rtmp_live': True,
-                        'ext': 'flv',
-                        'vbr': str_to_int(quality),
-                    }
-                elif transport == 'm3u8':
-                    fmt, subs = self._extract_m3u8_formats_and_subtitles(
-                        url, video_id, 'mp4', quality=preference, m3u8_id='hls')
-                    formats.extend(fmt)
-                    self._merge_subtitles(subs, target=subtitles)
-                    continue
-                else:
-                    fmt = {
-                        'url': url,
-                    }
-                fmt.update({
-                    'width': int_or_none(quality, default=height, invscale=width, scale=height),
-                    'height': int_or_none(quality, default=height),
-                    'format_id': f'{transport}-{quality}',
-                    'source_preference': preference,
-                })
-                formats.append(fmt)
-
-        return {
-            'id': video_id,
-            'title': title,
-            'description': description,
-            'thumbnail': thumbnail,
-            'view_count': view_count,
-            'duration': duration,
-            'formats': formats,
-            'subtitles': subtitles,
-            'is_live': is_live,
-            '_format_sort_fields': ('source', ),
-        }

yt_dlp/extractor/smotrim.py

@@ -1,65 +1,403 @@
+import functools
+import json
+import re
+import urllib.parse
+
 from .common import InfoExtractor
-from ..utils import ExtractorError
+from ..utils import (
+    OnDemandPagedList,
+    clean_html,
+    determine_ext,
+    extract_attributes,
+    int_or_none,
+    parse_iso8601,
+    str_or_none,
+    unescapeHTML,
+    url_or_none,
+    urljoin,
+)
+from ..utils.traversal import (
+    find_element,
+    find_elements,
+    require,
+    traverse_obj,
+)
 
 
-class SmotrimIE(InfoExtractor):
+class SmotrimBaseIE(InfoExtractor):
-    _VALID_URL = r'https?://smotrim\.ru/(?P<type>brand|video|article|live)/(?P<id>[0-9]+)'
+    _BASE_URL = 'https://smotrim.ru'
-    _TESTS = [{  # video
+    _GEO_BYPASS = False
+    _GEO_COUNTRIES = ['RU']
+
+    def _extract_from_smotrim_api(self, typ, item_id):
+        path = f'data{typ.replace("-", "")}/{"uid" if typ == "live" else "id"}'
+        data = self._download_json(
+            f'https://player.smotrim.ru/iframe/{path}/{item_id}/sid/smotrim', item_id)
+        media = traverse_obj(data, ('data', 'playlist', 'medialist', -1, {dict}))
+        if traverse_obj(media, ('locked', {bool})):
+            self.raise_login_required()
+        if error_msg := traverse_obj(media, ('errors', {clean_html})):
+            self.raise_geo_restricted(error_msg, countries=self._GEO_COUNTRIES)
+
+        webpage_url = traverse_obj(data, ('data', 'template', 'share_url', {url_or_none}))
+        webpage = self._download_webpage(webpage_url, item_id)
+        common = {
+            'thumbnail': self._html_search_meta(['og:image', 'twitter:image'], webpage, default=None),
+            **traverse_obj(media, {
+                'id': ('id', {str_or_none}),
+                'title': (('episodeTitle', 'title'), {clean_html}, filter, any),
+                'channel_id': ('channelId', {str_or_none}),
+                'description': ('anons', {clean_html}, filter),
+                'season': ('season', {clean_html}, filter),
+                'series': (('brand_title', 'brandTitle'), {clean_html}, filter, any),
+                'series_id': ('brand_id', {str_or_none}),
+            }),
+        }
+
+        if typ == 'audio':
+            bookmark = self._search_json(
+                r'class="bookmark"[^>]+value\s*=\s*"', webpage,
+                'bookmark', item_id, default={}, transform_source=unescapeHTML)
+
+            metadata = {
+                'vcodec': 'none',
+                **common,
+                **traverse_obj(media, {
+                    'ext': ('audio_url', {determine_ext(default_ext='mp3')}),
+                    'duration': ('duration', {int_or_none}),
+                    'url': ('audio_url', {url_or_none}),
+                }),
+                **traverse_obj(bookmark, {
+                    'title': ('subtitle', {clean_html}),
+                    'timestamp': ('published', {parse_iso8601}),
+                }),
+            }
+        elif typ == 'audio-live':
+            metadata = {
+                'ext': 'mp3',
+                'url': traverse_obj(media, ('source', 'auto', {url_or_none})),
+                'vcodec': 'none',
+                **common,
+            }
+        else:
+            formats, subtitles = [], {}
+            for m3u8_url in traverse_obj(media, (
+                'sources', 'm3u8', {dict.values}, ..., {url_or_none},
+            )):
+                fmts, subs = self._extract_m3u8_formats_and_subtitles(
+                    m3u8_url, item_id, 'mp4', m3u8_id='hls', fatal=False)
+                formats.extend(fmts)
+                self._merge_subtitles(subs, target=subtitles)
+
+            metadata = {
+                'formats': formats,
+                'subtitles': subtitles,
+                **self._search_json_ld(webpage, item_id),
+                **common,
+            }
+
+        return {
+            'age_limit': traverse_obj(data, ('data', 'age_restrictions', {int_or_none})),
+            'is_live': typ in ('audio-live', 'live'),
+            'tags': traverse_obj(webpage, (
+                {find_elements(cls='tags-list__link')}, ..., {clean_html}, filter, all, filter)),
+            'webpage_url': webpage_url,
+            **metadata,
+        }
+
+
+class SmotrimIE(SmotrimBaseIE):
+    IE_NAME = 'smotrim'
+    _VALID_URL = r'(?:https?:)?//(?:(?:player|www)\.)?smotrim\.ru(?:/iframe)?/video(?:/id)?/(?P<id>\d+)'
+    _EMBED_REGEX = [fr'<iframe\b[^>]+\bsrc=["\'](?P<url>{_VALID_URL})']
+    _TESTS = [{
         'url': 'https://smotrim.ru/video/1539617',
-        'md5': 'b1923a533c8cab09679789d720d0b1c5',
         'info_dict': {
             'id': '1539617',
             'ext': 'mp4',
-            'title': 'Полиглот. Китайский с нуля за 16 часов! Урок №16',
+            'title': 'Урок №16',
-            'description': '',
+            'duration': 2631,
+            'series': 'Полиглот. Китайский с нуля за 16 часов!',
+            'series_id': '60562',
+            'tags': 'mincount:6',
+            'thumbnail': r're:https?://cdn-st\d+\.smotrim\.ru/.+\.(?:jpg|png)',
+            'timestamp': 1466771100,
+            'upload_date': '20160624',
+            'view_count': int,
         },
-        'add_ie': ['RUTV'],
+    }, {
-    }, {  # article (geo-restricted? plays fine from the US and JP)
+        'url': 'https://player.smotrim.ru/iframe/video/id/2988590',
+        'info_dict': {
+            'id': '2988590',
+            'ext': 'mp4',
+            'title': 'Трейлер',
+            'age_limit': 16,
+            'description': 'md5:6af7e68ecf4ed7b8ff6720d20c4da47b',
+            'duration': 30,
+            'series': 'Мы в разводе',
+            'series_id': '71624',
+            'tags': 'mincount:5',
+            'thumbnail': r're:https?://cdn-st\d+\.smotrim\.ru/.+\.(?:jpg|png)',
+            'timestamp': 1750670040,
+            'upload_date': '20250623',
+            'view_count': int,
+            'webpage_url': 'https://smotrim.ru/video/2988590',
+        },
+    }]
+    _WEBPAGE_TESTS = [{
         'url': 'https://smotrim.ru/article/2813445',
-        'md5': 'e0ac453952afbc6a2742e850b4dc8e77',
         'info_dict': {
             'id': '2431846',
             'ext': 'mp4',
-            'title': 'Новости культуры. Съёмки первой программы "Большие и маленькие"',
+            'title': 'Съёмки первой программы "Большие и маленькие"',
-            'description': 'md5:94a4a22472da4252bf5587a4ee441b99',
+            'description': 'md5:446c9a5d334b995152a813946353f447',
+            'duration': 240,
+            'series': 'Новости культуры',
+            'series_id': '19725',
+            'tags': 'mincount:6',
+            'thumbnail': r're:https?://cdn-st\d+\.smotrim\.ru/.+\.(?:jpg|png)',
+            'timestamp': 1656054443,
+            'upload_date': '20220624',
+            'view_count': int,
+            'webpage_url': 'https://smotrim.ru/video/2431846',
         },
-        'add_ie': ['RUTV'],
+    }, {
-    }, {  # brand, redirect
+        'url': 'https://www.vesti.ru/article/4642878',
-        'url': 'https://smotrim.ru/brand/64356',
-        'md5': '740472999ccff81d7f6df79cecd91c18',
         'info_dict': {
-            'id': '2354523',
+            'id': '3007209',
             'ext': 'mp4',
-            'title': 'Большие и маленькие. Лучшее. 4-й выпуск',
+            'title': 'Иностранные мессенджеры используют не только мошенники, но и вербовщики',
-            'description': 'md5:84089e834429008371ea41ea3507b989',
+            'description': 'md5:74ab625a0a89b87b2e0ed98d6391b182',
+            'duration': 265,
+            'series': 'Вести. Дежурная часть',
+            'series_id': '5204',
+            'tags': 'mincount:6',
+            'thumbnail': r're:https?://cdn-st\d+\.smotrim\.ru/.+\.(?:jpg|png)',
+            'timestamp': 1754756280,
+            'upload_date': '20250809',
+            'view_count': int,
+            'webpage_url': 'https://smotrim.ru/video/3007209',
         },
-        'add_ie': ['RUTV'],
-    }, {  # live
-        'url': 'https://smotrim.ru/live/19201',
-        'info_dict': {
-            'id': '19201',
-            'ext': 'mp4',
-            # this looks like a TV channel name
-            'title': 'Россия Культура. Прямой эфир',
-            'description': '',
-        },
-        'add_ie': ['RUTV'],
     }]
 
     def _real_extract(self, url):
-        video_id, typ = self._match_valid_url(url).group('id', 'type')
+        video_id = self._match_id(url)
-        rutv_type = 'video'
-        if typ not in ('video', 'live'):
-            webpage = self._download_webpage(url, video_id, f'Resolving {typ} link')
-            # there are two cases matching regex:
-            # 1. "embedUrl" in JSON LD (/brand/)
-            # 2. "src" attribute from iframe (/article/)
-            video_id = self._search_regex(
-                r'"https://player.smotrim.ru/iframe/video/id/(?P<video_id>\d+)/',
-                webpage, 'video_id', default=None)
-            if not video_id:
-                raise ExtractorError('There are no video in this page.', expected=True)
-        elif typ == 'live':
-            rutv_type = 'live'
 
-        return self.url_result(f'https://player.vgtrk.com/iframe/{rutv_type}/id/{video_id}')
+        return self._extract_from_smotrim_api('video', video_id)
+
+
+class SmotrimAudioIE(SmotrimBaseIE):
+    IE_NAME = 'smotrim:audio'
+    _VALID_URL = r'https?://(?:(?:player|www)\.)?smotrim\.ru(?:/iframe)?/audio(?:/id)?/(?P<id>\d+)'
+    _TESTS = [{
+        'url': 'https://smotrim.ru/audio/2573986',
+        'md5': 'e28d94c20da524e242b2d00caef41a8e',
+        'info_dict': {
+            'id': '2573986',
+            'ext': 'mp3',
+            'title': 'Радиоспектакль',
+            'description': 'md5:4bcaaf7d532bc78f76e478fad944e388',
+            'duration': 3072,
+            'series': 'Морис Леблан. Арсен Люпен, джентльмен-грабитель',
+            'series_id': '66461',
+            'tags': 'mincount:7',
+            'thumbnail': r're:https?://cdn-st\d+\.smotrim\.ru/.+\.(?:jpg|png)',
+            'timestamp': 1624884358,
+            'upload_date': '20210628',
+        },
+    }, {
+        'url': 'https://player.smotrim.ru/iframe/audio/id/2860468',
+        'md5': '5a6bc1fa24c7142958be1ad9cfae58a8',
+        'info_dict': {
+            'id': '2860468',
+            'ext': 'mp3',
+            'title': 'Колобок и музыкальная игра "Терем-теремок"',
+            'duration': 1501,
+            'series': 'Веселый колобок',
+            'series_id': '68880',
+            'tags': 'mincount:4',
+            'thumbnail': r're:https?://cdn-st\d+\.smotrim\.ru/.+\.(?:jpg|png)',
+            'timestamp': 1755925800,
+            'upload_date': '20250823',
+            'webpage_url': 'https://smotrim.ru/audio/2860468',
+        },
+    }]
+
+    def _real_extract(self, url):
+        audio_id = self._match_id(url)
+
+        return self._extract_from_smotrim_api('audio', audio_id)
+
+
+class SmotrimLiveIE(SmotrimBaseIE):
+    IE_NAME = 'smotrim:live'
+    _VALID_URL = r'''(?x:
+        (?:https?:)?//
+            (?:(?:(?:test)?player|www)\.)?
+            (?:
+                smotrim\.ru|
+                vgtrk\.com
+            )
+            (?:/iframe)?/
+            (?P<type>
+                channel|
+                (?:audio-)?live
+            )
+            (?:/u?id)?/(?P<id>[\da-f-]+)
+    )'''
+    _EMBED_REGEX = [fr'<iframe\b[^>]+\bsrc=["\'](?P<url>{_VALID_URL})']
+    _TESTS = [{
+        'url': 'https://smotrim.ru/channel/76',
+        'info_dict': {
+            'id': '1661',
+            'ext': 'mp4',
+            'title': str,
+            'channel_id': '76',
+            'description': 'Смотрим прямой эфир «Москва 24»',
+            'display_id': '76',
+            'live_status': 'is_live',
+            'thumbnail': r're:https?://cdn-st\d+\.smotrim\.ru/.+\.(?:jpg|png)',
+            'timestamp': int,
+            'upload_date': str,
+        },
+        'params': {'skip_download': 'Livestream'},
+    }, {
+        # Radio
+        'url': 'https://smotrim.ru/channel/81',
+        'info_dict': {
+            'id': '81',
+            'ext': 'mp3',
+            'title': str,
+            'channel_id': '81',
+            'live_status': 'is_live',
+            'thumbnail': r're:https?://cdn-st\d+\.smotrim\.ru/.+\.(?:jpg|png)',
+        },
+        'params': {'skip_download': 'Livestream'},
+    }, {
+        # Sometimes geo-restricted to Russia
+        'url': 'https://player.smotrim.ru/iframe/live/uid/381308c7-a066-4c4f-9656-83e2e792a7b4',
+        'info_dict': {
+            'id': '19201',
+            'ext': 'mp4',
+            'title': str,
+            'channel_id': '4',
+            'description': 'Смотрим прямой эфир «Россия К»',
+            'display_id': '381308c7-a066-4c4f-9656-83e2e792a7b4',
+            'live_status': 'is_live',
+            'thumbnail': r're:https?://cdn-st\d+\.smotrim\.ru/.+\.(?:jpg|png)',
+            'timestamp': int,
+            'upload_date': str,
+            'webpage_url': 'https://smotrim.ru/channel/4',
+        },
+        'params': {'skip_download': 'Livestream'},
+    }, {
+        'url': 'https://smotrim.ru/live/19201',
+        'only_matching': True,
+    }, {
+        'url': 'https://player.smotrim.ru/iframe/audio-live/id/81',
+        'only_matching': True,
+    }, {
+        'url': 'https://testplayer.vgtrk.com/iframe/live/id/19201',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        typ, display_id = self._match_valid_url(url).group('type', 'id')
+
+        if typ == 'live' and re.fullmatch(r'[0-9]+', display_id):
+            url = self._request_webpage(url, display_id).url
+            typ = self._match_valid_url(url).group('type')
+
+        if typ == 'channel':
+            webpage = self._download_webpage(url, display_id)
+            src_url = traverse_obj(webpage, ((
+                ({find_element(cls='main-player__frame', html=True)}, {extract_attributes}, 'src'),
+                ({find_element(cls='audio-play-button', html=True)},
+                    {extract_attributes}, 'value', {urllib.parse.unquote}, {json.loads}, 'source'),
+            ), any, {self._proto_relative_url}, {url_or_none}, {require('src URL')}))
+            typ, video_id = self._match_valid_url(src_url).group('type', 'id')
+        else:
+            video_id = display_id
+
+        return {
+            'display_id': display_id,
+            **self._extract_from_smotrim_api(typ, video_id),
+        }
+
+
+class SmotrimPlaylistIE(SmotrimBaseIE):
+    IE_NAME = 'smotrim:playlist'
+    _PAGE_SIZE = 15
+    _VALID_URL = r'https?://smotrim\.ru/(?P<type>brand|podcast)/(?P<id>\d+)/?(?P<season>[\w-]+)?'
+    _TESTS = [{
+        # Video
+        'url': 'https://smotrim.ru/brand/64356',
+        'info_dict': {
+            'id': '64356',
+            'title': 'Большие и маленькие',
+        },
+        'playlist_mincount': 55,
+    }, {
+        # Video, season
+        'url': 'https://smotrim.ru/brand/65293/3-sezon',
+        'info_dict': {
+            'id': '65293',
+            'title': 'Спасская',
+            'season': '3 сезон',
+        },
+        'playlist_count': 16,
+    }, {
+        # Audio
+        'url': 'https://smotrim.ru/brand/68880',
+        'info_dict': {
+            'id': '68880',
+            'title': 'Веселый колобок',
+        },
+        'playlist_mincount': 156,
+    }, {
+        # Podcast
+        'url': 'https://smotrim.ru/podcast/8021',
+        'info_dict': {
+            'id': '8021',
+            'title': 'Сила звука',
+        },
+        'playlist_mincount': 27,
+    }]
+
+    def _fetch_page(self, endpoint, key, playlist_id, page):
+        page += 1
+        items = self._download_json(
+            f'{self._BASE_URL}/api/{endpoint}', playlist_id,
+            f'Downloading page {page}', query={
+                key: playlist_id,
+                'limit': self._PAGE_SIZE,
+                'page': page,
+            },
+        )
+
+        for link in traverse_obj(items, ('contents', -1, 'list', ..., 'link', {str})):
+            yield self.url_result(urljoin(self._BASE_URL, link))
+
+    def _real_extract(self, url):
+        playlist_type, playlist_id, season = self._match_valid_url(url).group('type', 'id', 'season')
+        key = 'rubricId' if playlist_type == 'podcast' else 'brandId'
+        webpage = self._download_webpage(url, playlist_id)
+        playlist_title = self._html_search_meta(['og:title', 'twitter:title'], webpage, default=None)
+
+        if season:
+            return self.playlist_from_matches(traverse_obj(webpage, (
+                {find_elements(tag='a', attr='href', value=r'/video/\d+', html=True, regex=True)},
+                ..., {extract_attributes}, 'href', {str},
+            )), playlist_id, playlist_title, season=traverse_obj(webpage, (
+                {find_element(cls='seasons__item seasons__item--selected')}, {clean_html},
+            )), ie=SmotrimIE, getter=urljoin(self._BASE_URL))
+
+        if traverse_obj(webpage, (
+            {find_element(cls='brand-main-item__videos')}, {clean_html}, filter,
+        )):
+            endpoint = 'videos'
+        else:
+            endpoint = 'audios'
+
+        return self.playlist_result(OnDemandPagedList(
+            functools.partial(self._fetch_page, endpoint, key, playlist_id), self._PAGE_SIZE), playlist_id, playlist_title)

yt_dlp/extractor/tunein.py

@@ -1,244 +1,335 @@
+import functools
 import urllib.parse
 
 from .common import InfoExtractor
 from ..utils import (
     OnDemandPagedList,
-    determine_ext,
+    UnsupportedError,
+    clean_html,
+    int_or_none,
+    join_nonempty,
     parse_iso8601,
-    traverse_obj,
+    update_url_query,
+    url_or_none,
 )
+from ..utils.traversal import traverse_obj
 
 
 class TuneInBaseIE(InfoExtractor):
-    _VALID_URL_BASE = r'https?://(?:www\.)?tunein\.com'
+    def _call_api(self, item_id, endpoint=None, note='Downloading JSON metadata', fatal=False, query=None):
-
+        return self._download_json(
-    def _extract_metadata(self, webpage, content_id):
+            join_nonempty('https://api.tunein.com/profiles', item_id, endpoint, delim='/'),
-        return self._search_json(r'window.INITIAL_STATE=', webpage, 'hydration', content_id, fatal=False)
+            item_id, note=note, fatal=fatal, query=query) or {}
 
     def _extract_formats_and_subtitles(self, content_id):
         streams = self._download_json(
-            f'https://opml.radiotime.com/Tune.ashx?render=json&formats=mp3,aac,ogg,flash,hls&id={content_id}',
+            'https://opml.radiotime.com/Tune.ashx', content_id, query={
-            content_id)['body']
+                'formats': 'mp3,aac,ogg,flash,hls',
+                'id': content_id,
+                'render': 'json',
+            })
 
         formats, subtitles = [], {}
-        for stream in streams:
+        for stream in traverse_obj(streams, ('body', lambda _, v: url_or_none(v['url']))):
             if stream.get('media_type') == 'hls':
                 fmts, subs = self._extract_m3u8_formats_and_subtitles(stream['url'], content_id, fatal=False)
                 formats.extend(fmts)
                 self._merge_subtitles(subs, target=subtitles)
-            elif determine_ext(stream['url']) == 'pls':
-                playlist_content = self._download_webpage(stream['url'], content_id)
-                formats.append({
-                    'url': self._search_regex(r'File1=(.*)', playlist_content, 'url', fatal=False),
-                    'abr': stream.get('bitrate'),
-                    'ext': stream.get('media_type'),
-                })
             else:
-                formats.append({
+                formats.append(traverse_obj(stream, {
-                    'url': stream['url'],
+                    'abr': ('bitrate', {int_or_none}),
-                    'abr': stream.get('bitrate'),
+                    'ext': ('media_type', {str}),
-                    'ext': stream.get('media_type'),
+                    'url': ('url', {self._proto_relative_url}),
-                })
+                }))
 
         return formats, subtitles
 
 
 class TuneInStationIE(TuneInBaseIE):
-    _VALID_URL = TuneInBaseIE._VALID_URL_BASE + r'(?:/radio/[^?#]+-|/embed/player/)(?P<id>s\d+)'
+    IE_NAME = 'tunein:station'
-    _EMBED_REGEX = [r'<iframe[^>]+src=["\'](?P<url>(?:https?://)?tunein\.com/embed/player/s\d+)']
+    _VALID_URL = r'https?://tunein\.com/radio/[^/?#]+(?P<id>s\d+)'
-
     _TESTS = [{
         'url': 'https://tunein.com/radio/Jazz24-885-s34682/',
         'info_dict': {
             'id': 's34682',
-            'title': str,
-            'description': 'md5:d6d0b89063fd68d529fa7058ee98619b',
-            'thumbnail': r're:https?://cdn-profiles\.tunein\.com/.+',
-            'location': 'Seattle-Tacoma, US',
             'ext': 'mp3',
+            'title': str,
+            'alt_title': 'World Class Jazz',
+            'channel_follower_count': int,
+            'description': 'md5:d6d0b89063fd68d529fa7058ee98619b',
+            'location': r're:Seattle-Tacoma, (?:US|WA)',
             'live_status': 'is_live',
+            'thumbnail': r're:https?://.+',
         },
-        'params': {
+        'params': {'skip_download': 'Livestream'},
-            'skip_download': True,
-        },
-    }, {
-        'url': 'https://tunein.com/embed/player/s6404/',
-        'only_matching': True,
     }, {
         'url': 'https://tunein.com/radio/BBC-Radio-1-988-s24939/',
         'info_dict': {
             'id': 's24939',
-            'title': str,
-            'description': 'md5:ee2c56794844610d045f8caf5ff34d0c',
-            'thumbnail': r're:https?://cdn-profiles\.tunein\.com/.+',
-            'location': 'London, UK',
             'ext': 'm4a',
+            'title': str,
+            'alt_title': 'The biggest new pop and all-day vibes',
+            'channel_follower_count': int,
+            'description': 'md5:ee2c56794844610d045f8caf5ff34d0c',
+            'location': 'London, UK',
             'live_status': 'is_live',
+            'thumbnail': r're:https?://.+',
         },
-        'params': {
+        'params': {'skip_download': 'Livestream'},
-            'skip_download': True,
+    }]
+
+    def _real_extract(self, url):
+        station_id = self._match_id(url)
+        formats, subtitles = self._extract_formats_and_subtitles(station_id)
+
+        return {
+            'id': station_id,
+            'formats': formats,
+            'subtitles': subtitles,
+            **traverse_obj(self._call_api(station_id), ('Item', {
+                'title': ('Title', {clean_html}),
+                'alt_title': ('Subtitle', {clean_html}, filter),
+                'channel_follower_count': ('Actions', 'Follow', 'FollowerCount', {int_or_none}),
+                'description': ('Description', {clean_html}, filter),
+                'is_live': ('Actions', 'Play', 'IsLive', {bool}),
+                'location': ('Properties', 'Location', 'DisplayName', {str}),
+                'thumbnail': ('Image', {url_or_none}),
+            })),
+        }
+
+
+class TuneInPodcastIE(TuneInBaseIE):
+    IE_NAME = 'tunein:podcast:program'
+    _PAGE_SIZE = 20
+    _VALID_URL = r'https?://tunein\.com/podcasts(?:/[^/?#]+){1,2}(?P<id>p\d+)'
+    _TESTS = [{
+        'url': 'https://tunein.com/podcasts/Technology-Podcasts/Artificial-Intelligence-p1153019/',
+        'info_dict': {
+            'id': 'p1153019',
+            'title': 'Lex Fridman Podcast',
         },
+        'playlist_mincount': 200,
+    }, {
+        'url': 'https://tunein.com/podcasts/World-News/BBC-News-p14/',
+        'info_dict': {
+            'id': 'p14',
+            'title': 'BBC News',
+        },
+        'playlist_mincount': 35,
+    }]
+
+    @classmethod
+    def suitable(cls, url):
+        return False if TuneInPodcastEpisodeIE.suitable(url) else super().suitable(url)
+
+    def _fetch_page(self, url, podcast_id, page=0):
+        items = self._call_api(
+            podcast_id, 'contents', f'Downloading page {page + 1}', query={
+                'filter': 't:free',
+                'limit': self._PAGE_SIZE,
+                'offset': page * self._PAGE_SIZE,
+            },
+        )['Items']
+
+        for item in traverse_obj(items, (..., 'GuideId', {str}, filter)):
+            yield self.url_result(update_url_query(url, {'topicId': item[1:]}))
+
+    def _real_extract(self, url):
+        podcast_id = self._match_id(url)
+
+        return self.playlist_result(OnDemandPagedList(
+            functools.partial(self._fetch_page, url, podcast_id), self._PAGE_SIZE),
+            podcast_id, traverse_obj(self._call_api(podcast_id), ('Item', 'Title', {str})))
+
+
+class TuneInPodcastEpisodeIE(TuneInBaseIE):
+    IE_NAME = 'tunein:podcast'
+    _VALID_URL = r'https?://tunein\.com/podcasts(?:/[^/?#]+){1,2}(?P<series_id>p\d+)/?\?(?:[^#]+&)?(?i:topicid)=(?P<id>\d+)'
+    _TESTS = [{
+        'url': 'https://tunein.com/podcasts/Technology-Podcasts/Artificial-Intelligence-p1153019/?topicId=236404354',
+        'info_dict': {
+            'id': 't236404354',
+            'ext': 'mp3',
+            'title': '#351 – MrBeast: Future of YouTube, Twitter, TikTok, and Instagram',
+            'alt_title': 'Technology Podcasts >',
+            'cast': 'count:1',
+            'description': 'md5:1029895354ef073ff00f20b82eb6eb71',
+            'display_id': '236404354',
+            'duration': 8330,
+            'thumbnail': r're:https?://.+',
+            'timestamp': 1673458571,
+            'upload_date': '20230111',
+            'series': 'Lex Fridman Podcast',
+            'series_id': 'p1153019',
+        },
+    }, {
+        'url': 'https://tunein.com/podcasts/The-BOB--TOM-Show-Free-Podcast-p20069/?topicId=174556405',
+        'info_dict': {
+            'id': 't174556405',
+            'ext': 'mp3',
+            'title': 'B&T Extra: Ohhh Yeah, It\'s Sexy Time',
+            'alt_title': 'Westwood One >',
+            'cast': 'count:2',
+            'description': 'md5:6828234f410ab88c85655495c5fcfa88',
+            'display_id': '174556405',
+            'duration': 1203,
+            'series': 'The BOB & TOM Show Free Podcast',
+            'series_id': 'p20069',
+            'thumbnail': r're:https?://.+',
+            'timestamp': 1661799600,
+            'upload_date': '20220829',
+        },
+    }]
+
+    def _real_extract(self, url):
+        series_id, display_id = self._match_valid_url(url).group('series_id', 'id')
+        episode_id = f't{display_id}'
+        formats, subtitles = self._extract_formats_and_subtitles(episode_id)
+
+        return {
+            'id': episode_id,
+            'display_id': display_id,
+            'formats': formats,
+            'series': traverse_obj(self._call_api(series_id), ('Item', 'Title', {clean_html})),
+            'series_id': series_id,
+            'subtitles': subtitles,
+            **traverse_obj(self._call_api(episode_id), ('Item', {
+                'title': ('Title', {clean_html}),
+                'alt_title': ('Subtitle', {clean_html}, filter),
+                'cast': (
+                    'Properties', 'ParentProgram', 'Hosts', {clean_html},
+                    {lambda x: x.split(';')}, ..., {str.strip}, filter, all, filter),
+                'description': ('Description', {clean_html}, filter),
+                'duration': ('Actions', 'Play', 'Duration', {int_or_none}),
+                'thumbnail': ('Image', {url_or_none}),
+                'timestamp': ('Actions', 'Play', 'PublishTime', {parse_iso8601}),
+            })),
+        }
+
+
+class TuneInEmbedIE(TuneInBaseIE):
+    IE_NAME = 'tunein:embed'
+    _VALID_URL = r'https?://tunein\.com/embed/player/(?P<id>[^/?#]+)'
+    _EMBED_REGEX = [r'<iframe\b[^>]+\bsrc=["\'](?P<url>(?:https?:)?//tunein\.com/embed/player/[^/?#"\']+)']
+    _TESTS = [{
+        'url': 'https://tunein.com/embed/player/s6404/',
+        'info_dict': {
+            'id': 's6404',
+            'ext': 'mp3',
+            'title': str,
+            'alt_title': 'South Africa\'s News and Information Leader',
+            'channel_follower_count': int,
+            'live_status': 'is_live',
+            'location': 'Johannesburg, South Africa',
+            'thumbnail': r're:https?://.+',
+        },
+        'params': {'skip_download': 'Livestream'},
+    }, {
+        'url': 'https://tunein.com/embed/player/t236404354/',
+        'info_dict': {
+            'id': 't236404354',
+            'ext': 'mp3',
+            'title': '#351 – MrBeast: Future of YouTube, Twitter, TikTok, and Instagram',
+            'alt_title': 'Technology Podcasts >',
+            'cast': 'count:1',
+            'description': 'md5:1029895354ef073ff00f20b82eb6eb71',
+            'display_id': '236404354',
+            'duration': 8330,
+            'series': 'Lex Fridman Podcast',
+            'series_id': 'p1153019',
+            'thumbnail': r're:https?://.+',
+            'timestamp': 1673458571,
+            'upload_date': '20230111',
+        },
+    }, {
+        'url': 'https://tunein.com/embed/player/p191660/',
+        'info_dict': {
+            'id': 'p191660',
+            'title': 'SBS Tamil',
+        },
+        'playlist_mincount': 195,
     }]
     _WEBPAGE_TESTS = [{
         'url': 'https://www.martiniinthemorning.com/',
         'info_dict': {
             'id': 's55412',
             'ext': 'mp3',
-            'title': 'TuneInStation video #s55412',
+            'title': str,
+            'alt_title': 'Now that\'s music!',
+            'channel_follower_count': int,
+            'description': 'md5:41588a3e2cf34b3eafc6c33522fa611a',
+            'live_status': 'is_live',
+            'location': 'US',
+            'thumbnail': r're:https?://.+',
         },
-        'expected_warnings': ['unable to extract hydration', 'Extractor failed to obtain "title"'],
+        'params': {'skip_download': 'Livestream'},
     }]
 
     def _real_extract(self, url):
-        station_id = self._match_id(url)
+        embed_id = self._match_id(url)
+        kind = {
+            'p': 'program',
+            's': 'station',
+            't': 'topic',
+        }.get(embed_id[:1])
 
-        webpage = self._download_webpage(url, station_id)
+        return self.url_result(
-        metadata = self._extract_metadata(webpage, station_id)
+            f'https://tunein.com/{kind}/?{kind}id={embed_id[1:]}')
-
-        formats, subtitles = self._extract_formats_and_subtitles(station_id)
-        return {
-            'id': station_id,
-            'title': traverse_obj(metadata, ('profiles', station_id, 'title')),
-            'description': traverse_obj(metadata, ('profiles', station_id, 'description')),
-            'thumbnail': traverse_obj(metadata, ('profiles', station_id, 'image')),
-            'timestamp': parse_iso8601(
-                traverse_obj(metadata, ('profiles', station_id, 'actions', 'play', 'publishTime'))),
-            'location': traverse_obj(
-                metadata, ('profiles', station_id, 'metadata', 'properties', 'location', 'displayName'),
-                ('profiles', station_id, 'properties', 'location', 'displayName')),
-            'formats': formats,
-            'subtitles': subtitles,
-            'is_live': traverse_obj(metadata, ('profiles', station_id, 'actions', 'play', 'isLive')),
-        }
-
-
-class TuneInPodcastIE(TuneInBaseIE):
-    _VALID_URL = TuneInBaseIE._VALID_URL_BASE + r'/(?:podcasts/[^?#]+-|embed/player/)(?P<id>p\d+)/?(?:#|$)'
-    _EMBED_REGEX = [r'<iframe[^>]+src=["\'](?P<url>(?:https?://)?tunein\.com/embed/player/p\d+)']
-
-    _TESTS = [{
-        'url': 'https://tunein.com/podcasts/Technology-Podcasts/Artificial-Intelligence-p1153019',
-        'info_dict': {
-            'id': 'p1153019',
-            'title': 'Lex Fridman Podcast',
-            'description': 'md5:bedc4e5f1c94f7dec6e4317b5654b00d',
-        },
-        'playlist_mincount': 200,
-    }, {
-        'url': 'https://tunein.com/embed/player/p191660/',
-        'only_matching': True,
-    }, {
-        'url': 'https://tunein.com/podcasts/World-News/BBC-News-p14/',
-        'info_dict': {
-            'id': 'p14',
-            'title': 'BBC News',
-            'description': 'md5:30b9622bcc4bd101d4acd6f38f284aed',
-        },
-        'playlist_mincount': 36,
-    }]
-
-    _PAGE_SIZE = 30
-
-    def _real_extract(self, url):
-        podcast_id = self._match_id(url)
-
-        webpage = self._download_webpage(url, podcast_id, fatal=False)
-        metadata = self._extract_metadata(webpage, podcast_id)
-
-        def page_func(page_num):
-            api_response = self._download_json(
-                f'https://api.tunein.com/profiles/{podcast_id}/contents', podcast_id,
-                note=f'Downloading page {page_num + 1}', query={
-                    'filter': 't:free',
-                    'offset': page_num * self._PAGE_SIZE,
-                    'limit': self._PAGE_SIZE,
-                })
-
-            return [
-                self.url_result(
-                    f'https://tunein.com/podcasts/{podcast_id}?topicId={episode["GuideId"][1:]}',
-                    TuneInPodcastEpisodeIE, title=episode.get('Title'))
-                for episode in api_response['Items']]
-
-        entries = OnDemandPagedList(page_func, self._PAGE_SIZE)
-        return self.playlist_result(
-            entries, playlist_id=podcast_id, title=traverse_obj(metadata, ('profiles', podcast_id, 'title')),
-            description=traverse_obj(metadata, ('profiles', podcast_id, 'description')))
-
-
-class TuneInPodcastEpisodeIE(TuneInBaseIE):
-    _VALID_URL = TuneInBaseIE._VALID_URL_BASE + r'/podcasts/(?:[^?&]+-)?(?P<podcast_id>p\d+)/?\?topicId=(?P<id>\w\d+)'
-
-    _TESTS = [{
-        'url': 'https://tunein.com/podcasts/Technology-Podcasts/Artificial-Intelligence-p1153019/?topicId=236404354',
-        'info_dict': {
-            'id': 't236404354',
-            'title': '#351 – MrBeast: Future of YouTube, Twitter, TikTok, and Instagram',
-            'description': 'md5:2784533b98f8ac45c0820b1e4a8d8bb2',
-            'thumbnail': r're:https?://cdn-profiles\.tunein\.com/.+',
-            'timestamp': 1673458571,
-            'upload_date': '20230111',
-            'series_id': 'p1153019',
-            'series': 'Lex Fridman Podcast',
-            'ext': 'mp3',
-        },
-    }]
-
-    def _real_extract(self, url):
-        podcast_id, episode_id = self._match_valid_url(url).group('podcast_id', 'id')
-        episode_id = f't{episode_id}'
-
-        webpage = self._download_webpage(url, episode_id)
-        metadata = self._extract_metadata(webpage, episode_id)
-
-        formats, subtitles = self._extract_formats_and_subtitles(episode_id)
-        return {
-            'id': episode_id,
-            'title': traverse_obj(metadata, ('profiles', episode_id, 'title')),
-            'description': traverse_obj(metadata, ('profiles', episode_id, 'description')),
-            'thumbnail': traverse_obj(metadata, ('profiles', episode_id, 'image')),
-            'timestamp': parse_iso8601(
-                traverse_obj(metadata, ('profiles', episode_id, 'actions', 'play', 'publishTime'))),
-            'series_id': podcast_id,
-            'series': traverse_obj(metadata, ('profiles', podcast_id, 'title')),
-            'formats': formats,
-            'subtitles': subtitles,
-        }
 
 
 class TuneInShortenerIE(InfoExtractor):
-    _WORKING = False
     IE_NAME = 'tunein:shortener'
     IE_DESC = False  # Do not list
-    _VALID_URL = r'https?://tun\.in/(?P<id>[A-Za-z0-9]+)'
+    _VALID_URL = r'https?://tun\.in/(?P<id>[^/?#]+)'
-
     _TESTS = [{
-        # test redirection
         'url': 'http://tun.in/ser7s',
         'info_dict': {
             'id': 's34682',
             'title': str,
-            'description': 'md5:d6d0b89063fd68d529fa7058ee98619b',
-            'thumbnail': r're:https?://cdn-profiles\.tunein\.com/.+',
-            'location': 'Seattle-Tacoma, US',
             'ext': 'mp3',
+            'alt_title': 'World Class Jazz',
+            'channel_follower_count': int,
+            'description': 'md5:d6d0b89063fd68d529fa7058ee98619b',
+            'location': r're:Seattle-Tacoma, (?:US|WA)',
             'live_status': 'is_live',
+            'thumbnail': r're:https?://.+',
         },
-        'params': {
+        'params': {'skip_download': 'Livestream'},
-            'skip_download': True,  # live stream
+    }, {
+        'url': 'http://tun.in/tqeeFw',
+        'info_dict': {
+            'id': 't236404354',
+            'title': str,
+            'ext': 'mp3',
+            'alt_title': 'Technology Podcasts >',
+            'cast': 'count:1',
+            'description': 'md5:1029895354ef073ff00f20b82eb6eb71',
+            'display_id': '236404354',
+            'duration': 8330,
+            'series': 'Lex Fridman Podcast',
+            'series_id': 'p1153019',
+            'thumbnail': r're:https?://.+',
+            'timestamp': 1673458571,
+            'upload_date': '20230111',
         },
+        'params': {'skip_download': 'Livestream'},
+    }, {
+        'url': 'http://tun.in/pei6i',
+        'info_dict': {
+            'id': 'p14',
+            'title': 'BBC News',
+        },
+        'playlist_mincount': 35,
     }]
 
     def _real_extract(self, url):
         redirect_id = self._match_id(url)
         # The server doesn't support HEAD requests
-        urlh = self._request_webpage(
+        urlh = self._request_webpage(url, redirect_id, 'Downloading redirect page')
-            url, redirect_id, note='Downloading redirect page')
+        # Need to strip port from URL
-
+        parsed = urllib.parse.urlparse(urlh.url)
-        url = urlh.url
+        new_url = parsed._replace(netloc=parsed.hostname).geturl()
-        url_parsed = urllib.parse.urlparse(url)
+        # Prevent infinite loop in case redirect fails
-        if url_parsed.port == 443:
+        if self.suitable(new_url):
-            url = url_parsed._replace(netloc=url_parsed.hostname).url
+            raise UnsupportedError(new_url)
-
+        return self.url_result(new_url)
-        self.to_screen(f'Following redirect: {url}')
-        return self.url_result(url)

yt_dlp/extractor/vesti.py

@@ -1,119 +0,0 @@
-import re
-
-from .common import InfoExtractor
-from .rutv import RUTVIE
-from ..utils import ExtractorError
-
-
-class VestiIE(InfoExtractor):
-    _WORKING = False
-    IE_DESC = 'Вести.Ru'
-    _VALID_URL = r'https?://(?:.+?\.)?vesti\.ru/(?P<id>.+)'
-
-    _TESTS = [
-        {
-            'url': 'http://www.vesti.ru/videos?vid=575582&cid=1',
-            'info_dict': {
-                'id': '765035',
-                'ext': 'mp4',
-                'title': 'Вести.net: биткоины в России не являются законными',
-                'description': 'md5:d4bb3859dc1177b28a94c5014c35a36b',
-                'duration': 302,
-            },
-            'params': {
-                # m3u8 download
-                'skip_download': True,
-            },
-        },
-        {
-            'url': 'http://www.vesti.ru/doc.html?id=1349233',
-            'info_dict': {
-                'id': '773865',
-                'ext': 'mp4',
-                'title': 'Участники митинга штурмуют Донецкую областную администрацию',
-                'description': 'md5:1a160e98b3195379b4c849f2f4958009',
-                'duration': 210,
-            },
-            'params': {
-                # m3u8 download
-                'skip_download': True,
-            },
-        },
-        {
-            'url': 'http://www.vesti.ru/only_video.html?vid=576180',
-            'info_dict': {
-                'id': '766048',
-                'ext': 'mp4',
-                'title': 'США заморозило, Британию затопило',
-                'description': 'md5:f0ed0695ec05aed27c56a70a58dc4cc1',
-                'duration': 87,
-            },
-            'params': {
-                # m3u8 download
-                'skip_download': True,
-            },
-        },
-        {
-            'url': 'http://hitech.vesti.ru/news/view/id/4000',
-            'info_dict': {
-                'id': '766888',
-                'ext': 'mp4',
-                'title': 'Вести.net: интернет-гиганты начали перетягивание программных "одеял"',
-                'description': 'md5:65ddd47f9830c4f42ed6475f8730c995',
-                'duration': 279,
-            },
-            'params': {
-                # m3u8 download
-                'skip_download': True,
-            },
-        },
-        {
-            'url': 'http://sochi2014.vesti.ru/video/index/video_id/766403',
-            'info_dict': {
-                'id': '766403',
-                'ext': 'mp4',
-                'title': 'XXII зимние Олимпийские игры. Российские хоккеисты стартовали на Олимпиаде с победы',
-                'description': 'md5:55805dfd35763a890ff50fa9e35e31b3',
-                'duration': 271,
-            },
-            'params': {
-                # m3u8 download
-                'skip_download': True,
-            },
-            'skip': 'Blocked outside Russia',
-        },
-        {
-            'url': 'http://sochi2014.vesti.ru/live/play/live_id/301',
-            'info_dict': {
-                'id': '51499',
-                'ext': 'flv',
-                'title': 'Сочи-2014. Биатлон. Индивидуальная гонка. Мужчины ',
-                'description': 'md5:9e0ed5c9d2fa1efbfdfed90c9a6d179c',
-            },
-            'params': {
-                # rtmp download
-                'skip_download': True,
-            },
-            'skip': 'Translation has finished',
-        },
-    ]
-
-    def _real_extract(self, url):
-        mobj = self._match_valid_url(url)
-        video_id = mobj.group('id')
-
-        page = self._download_webpage(url, video_id, 'Downloading page')
-
-        mobj = re.search(
-            r'<meta[^>]+?property="og:video"[^>]+?content="http://www\.vesti\.ru/i/flvplayer_videoHost\.swf\?vid=(?P<id>\d+)',
-            page)
-        if mobj:
-            video_id = mobj.group('id')
-            page = self._download_webpage(f'http://www.vesti.ru/only_video.html?vid={video_id}', video_id,
-                                          'Downloading video page')
-
-        rutv_url = RUTVIE._extract_url(page)
-        if rutv_url:
-            return self.url_result(rutv_url, 'RUTV')
-
-        raise ExtractorError('No video found', expected=True)