Merge c59ce7d6a6 into a9f85670d0

Closes #10594
Authored by: manavchaudhary1

.github/workflows/build.yml

@@ -411,7 +411,7 @@ jobs:
         run: | # Custom pyinstaller built with https://github.com/yt-dlp/pyinstaller-builds
           python devscripts/install_deps.py -o --include build
           python devscripts/install_deps.py --include curl-cffi
-          python -m pip install -U "https://yt-dlp.github.io/Pyinstaller-Builds/x86_64/pyinstaller-6.10.0-py3-none-any.whl"
+          python -m pip install -U "https://yt-dlp.github.io/Pyinstaller-Builds/x86_64/pyinstaller-6.11.1-py3-none-any.whl"
 
       - name: Prepare
         run: |
@@ -460,7 +460,7 @@ jobs:
         run: |
           python devscripts/install_deps.py -o --include build
           python devscripts/install_deps.py
-          python -m pip install -U "https://yt-dlp.github.io/Pyinstaller-Builds/i686/pyinstaller-6.10.0-py3-none-any.whl"
+          python -m pip install -U "https://yt-dlp.github.io/Pyinstaller-Builds/i686/pyinstaller-6.11.1-py3-none-any.whl"
 
       - name: Prepare
         run: |

pyproject.toml

@@ -83,7 +83,7 @@ test = [
     "pytest-rerunfailures~=14.0",
 ]
 pyinstaller = [
-    "pyinstaller>=6.10.0",  # Windows temp cleanup fixed in 6.10.0
+    "pyinstaller>=6.11.1",  # Windows temp cleanup fixed in 6.11.1
 ]
 
 [project.urls]

yt_dlp/extractor/_extractors.py

@@ -281,6 +281,16 @@ from .bloomberg import BloombergIE
 from .bluesky import BlueskyIE
 from .bokecc import BokeCCIE
 from .bongacams import BongaCamsIE
+from .boomplay import (
+    BoomplayEpisodeIE,
+    BoomplayGenericPlaylistIE,
+    BoomplayMusicIE,
+    BoomplayPlaylistIE,
+    BoomplayPodcastIE,
+    BoomplaySearchIE,
+    BoomplaySearchURLIE,
+    BoomplayVideoIE,
+)
 from .boosty import BoostyIE
 from .bostonglobe import BostonGlobeIE
 from .box import BoxIE
@@ -1156,6 +1166,7 @@ from .mitele import MiTeleIE
 from .mixch import (
     MixchArchiveIE,
     MixchIE,
+    MixchMovieIE,
 )
 from .mixcloud import (
     MixcloudIE,
@@ -1939,9 +1950,7 @@ from .spotify import (
 )
 from .spreaker import (
     SpreakerIE,
-    SpreakerPageIE,
     SpreakerShowIE,
-    SpreakerShowPageIE,
 )
 from .springboardplatform import SpringboardPlatformIE
 from .sprout import SproutIE

yt_dlp/extractor/boomplay.py

@@ -0,0 +1,511 @@
+import base64
+import functools
+import json
+import re
+import urllib.parse
+
+from .common import InfoExtractor, SearchInfoExtractor
+from ..aes import aes_cbc_decrypt_bytes, aes_cbc_encrypt_bytes, unpad_pkcs7
+from ..utils import (
+    ExtractorError,
+    classproperty,
+    clean_html,
+    extract_attributes,
+    get_elements_text_and_html_by_attribute,
+    int_or_none,
+    join_nonempty,
+    merge_dicts,
+    parse_count,
+    parse_duration,
+    smuggle_url,
+    strip_or_none,
+    unified_strdate,
+    unsmuggle_url,
+    url_or_none,
+    urlencode_postdata,
+    urljoin,
+    variadic,
+)
+from ..utils.traversal import traverse_obj
+
+
+class BoomplayBaseIE(InfoExtractor):
+    # Calculated from const values, see lhx.AESUtils.encrypt in public.js
+    # Note that the real key/iv differs from `lhx.AESUtils.key`/`lhx.AESUtils.iv`
+    _KEY = b'boomplayVr3xopAM'
+    _IV = b'boomplay8xIsKTn9'
+    _BASE = 'https://www.boomplay.com'
+    _MEDIA_TYPES = ('songs', 'video', 'episode', 'podcasts', 'playlists', 'artists', 'albums')
+    _GEO_COUNTRIES = ['NG']
+
+    @staticmethod
+    def __yield_elements_text_and_html_by_class_and_tag(class_, tag, html):
+        """
+        Yields content of all element matching `tag.class_` in html
+        class_ must be re escaped
+        """
+        # get_elements_text_and_html_by_attribute returns a generator
+        return get_elements_text_and_html_by_attribute(
+            attribute='class', value=rf'''[^'"]*(?<=['"\s]){class_}(?=['"\s])[^'"]*''', html=html,
+            tag=tag, escape_value=False)
+
+    @classmethod
+    def __yield_elements_by_class_and_tag(cls, *args, **kwargs):
+        return (content for content, _ in cls.__yield_elements_text_and_html_by_class_and_tag(*args, **kwargs))
+
+    @classmethod
+    def __yield_elements_html_by_class_and_tag(cls, *args, **kwargs):
+        return (whole for _, whole in cls.__yield_elements_text_and_html_by_class_and_tag(*args, **kwargs))
+
+    @classmethod
+    def _get_elements_by_class_and_tag(cls, class_, tag, html):
+        return list(cls.__yield_elements_by_class_and_tag(class_, tag, html))
+
+    @classmethod
+    def _get_element_by_class_and_tag(cls, class_, tag, html):
+        return next(cls.__yield_elements_by_class_and_tag(class_, tag, html), None)
+
+    @classmethod
+    def _urljoin(cls, path):
+        return url_or_none(urljoin(base=cls._BASE, path=path))
+
+    def _get_playurl(self, item_id, item_type):
+        resp = self._download_json(
+            'https://www.boomplay.com/getResourceAddr', item_id,
+            note='Downloading play URL', errnote='Failed to download play URL',
+            data=urlencode_postdata({
+                'param': base64.b64encode(aes_cbc_encrypt_bytes(json.dumps({
+                    'itemID': item_id,
+                    'itemType': item_type,
+                }).encode(), self._KEY, self._IV)).decode(),
+            }), headers={
+                'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8',
+            })
+        if not (source := resp.get('source')) and (code := resp.get('code')):
+            if 'unavailable in your country' in (desc := resp.get('desc')) or '':
+                # since NG must have failed ...
+                self.raise_geo_restricted(countries=['GH', 'KE', 'TZ', 'CM', 'CI'])
+            else:
+                raise ExtractorError(desc or f'Failed to get play url, code: {code}')
+        return unpad_pkcs7(aes_cbc_decrypt_bytes(
+            base64.b64decode(source),
+            self._KEY, self._IV)).decode()
+
+    def _extract_formats(self, item_id, item_type='MUSIC', **kwargs):
+        if url := url_or_none(self._get_playurl(item_id, item_type)):
+            return [{
+                'format_id': '0',
+                'url': url,
+                'http_headers': {
+                    'Origin': 'https://www.boomplay.com',
+                    'Referer': 'https://www.boomplay.com',
+                    'X-Boomplay-Ref': 'Boomplay_WEBV1',
+                },
+                **kwargs,
+            }]
+        else:
+            self.raise_no_formats('No formats found')
+
+    def _extract_page_metadata(self, webpage, item_id):
+        metadata_div = self._get_element_by_class_and_tag('summary', 'div', webpage) or ''
+        metadata_entries = re.findall(r'(?si)<strong>(?P<entry>.*?)</strong>', metadata_div) or []
+        description = re.sub(
+            r'(?i)Listen and download music for free on Boomplay!', '',
+            clean_html(self._get_element_by_class_and_tag(
+                'description_content', 'span', webpage)) or '') or None
+
+        details_section = self._get_element_by_class_and_tag('songDetailInfo', 'section', webpage) or ''
+        metadata_entries.extend(re.findall(r'(?si)<li>(?P<entry>.*?)</li>', details_section) or [])
+        page_metadata = {
+            'id': item_id,
+            **self._extract_title_from_webpage(webpage),
+            'thumbnail': self._html_search_meta(['og:image', 'twitter:image'],
+                                                webpage, 'thumbnail', default=None),
+            'like_count': parse_count(self._get_element_by_class_and_tag('btn_favorite', 'button', metadata_div)),
+            'repost_count': parse_count(self._get_element_by_class_and_tag('btn_share', 'button', metadata_div)),
+            'comment_count': parse_count(self._get_element_by_class_and_tag('btn_comment', 'button', metadata_div)),
+            'duration': parse_duration(self._get_element_by_class_and_tag('btn_duration', 'button', metadata_div)),
+            'upload_date': unified_strdate(strip_or_none(
+                self._get_element_by_class_and_tag('btn_pubDate', 'button', metadata_div))),
+            'description': description,
+        }
+        for metadata_entry in metadata_entries:
+            if ':' not in metadata_entry:
+                continue
+            k, v = clean_html(metadata_entry).split(':', 1)
+            v = v.strip()
+            if 'artist' in k.lower():
+                page_metadata['artists'] = [v]
+            elif 'album' in k.lower():
+                page_metadata['album'] = v
+            elif 'genre' in k.lower():
+                page_metadata['genres'] = [v]
+            elif 'year of release' in k.lower():
+                page_metadata['release_year'] = int_or_none(v)
+        return page_metadata
+
+    def _extract_title_from_webpage(self, webpage):
+        if h1_title := self._html_search_regex(r'(?i)<h1[^>]*>([^<]+)</h1>', webpage, 'title', default=None):
+            return {'title': h1_title}
+        else:
+            return self._fix_title(
+                self._html_search_meta(['og:title', 'twitter:title'], webpage, 'title', default=None)
+                or self._html_search_regex(r'(?i)<title[^>]*>([^<]+)</title>', webpage, 'title', default=None))
+
+    @staticmethod
+    def _fix_title(title):
+        """
+        fix various types of titles(og:title, twitter:title, title tag in html head)
+        """
+        if not title:
+            return {}
+
+        title_patterns = (
+            r'^(?P<title>(?P<artist>.+)) Songs MP3 Download, New Songs \& Albums \| Boomplay$',  # artists
+            r'^(?P<artist>.+?) - (?P<title>.+) MP3\ Download \& Lyrics \| Boomplay$',  # music
+            r'^Download (?P<artist>.+) album songs: (?P<title>.+?) \| Boomplay Music$',  # album
+            r'^Search:(?P<title>.+) \| Boomplay Music$',  # search url
+            r'^(?P<title>.+) \| Podcast \| Boomplay$',  # podcast, episode
+            r'^(?P<title>.+) \| Boomplay(?: Music)?$',  # video, playlist, generic playlists
+        )
+
+        for pattern in title_patterns:
+            if match := re.search(pattern, title):
+                return {
+                    'title': match.group('title'),
+                    'artists': [match.group('artist')] if 'artist' in match.groupdict() else None,
+                }
+
+        return {'title': title}
+
+    @classmethod
+    def _extract_from_webpage(cls, url, webpage, **kwargs):
+        if kwargs:
+            url = smuggle_url(url, kwargs)
+        return super()._extract_from_webpage(url, webpage)
+
+    @classmethod
+    def _extract_embed_urls(cls, url, webpage):
+        url, smuggled_data = unsmuggle_url(url)
+        media_types = variadic(smuggled_data.get('media_types', cls._MEDIA_TYPES))
+        media_types = join_nonempty(*(
+            re.escape(v)for v in media_types if v in cls._MEDIA_TYPES),
+            delim='|')
+
+        for mobj in re.finditer(
+                rf'''(?ix)
+                <a
+                    (?:\s(?:[^>"']|"[^"]*"|'[^']*')*)?
+                        (?<=\s)href\s*=\s*(?P<_q>['"])
+                            (?P<href>/(?:{media_types})/\d+/?[\-\w=?&#:;@]*)
+                        (?P=_q)
+                    (?:\s(?:[^>"']|"[^"]*"|'[^']*')*)?
+                >''', webpage):
+            if url := cls._urljoin(mobj.group('href')):
+                yield url
+
+    @classmethod
+    def _extract_playlist_entries(cls, webpage, media_types, warn=True):
+        song_list = strip_or_none(
+            cls._get_element_by_class_and_tag('morePart_musics', 'ol', webpage)
+            or cls._get_element_by_class_and_tag('morePart', 'ol', webpage)
+            or '')
+
+        entries = traverse_obj(cls.__yield_elements_html_by_class_and_tag(
+            'songName', 'a', song_list),
+            (..., {extract_attributes}, 'href', {cls._urljoin}, {cls.url_result}))
+        if not entries:
+            if warn:
+                cls.report_warning('Failed to extract playlist entries, finding suitable links instead!')
+
+            def strip_ie(entry):
+                # All our IEs have a _VALID_URL and set a key: don't use it
+                entry.pop('ie_key', None)
+                return entry
+
+            return (strip_ie(result) for result in
+                    cls._extract_from_webpage(cls._BASE, webpage, media_types=media_types))
+
+        return entries
+
+
+class BoomplayMusicIE(BoomplayBaseIE):
+    _VALID_URL = r'https?://(?:www\.)?boomplay\.com/songs/(?P<id>\d+)'
+    _TESTS = [{
+        'url': 'https://www.boomplay.com/songs/165481965',
+        'md5': 'c5fb4f23e6aae98064230ef3c39c2178',
+        'info_dict': {
+            'title': 'Rise of the Fallen Heroes',
+            'ext': 'mp3',
+            'id': '165481965',
+            'artists': ['fatbunny'],
+            'thumbnail': 'https://source.boomplaymusic.com/group10/M00/04/29/375ecda38f6f48179a93c72ab909118f_464_464.jpg',
+            'channel_url': 'https://www.boomplay.com/artists/52723101',
+            'duration': 125.0,
+            'release_year': 2024,
+            'comment_count': int,
+            'like_count': int,
+            'repost_count': int,
+            'album': 'Legendary Battle',
+            'genres': ['Metal'],
+        },
+    }]
+
+    def _real_extract(self, url):
+        song_id = self._match_id(url)
+        webpage = self._download_webpage(url, song_id)
+        ld_json_meta = next(self._yield_json_ld(webpage, song_id))
+        # TODO: extract comments(and lyrics? they don't have timestamps)
+        # example: https://www.boomplay.com/songs/96352673?from=home
+        return merge_dicts(
+            self._extract_page_metadata(webpage, song_id),
+            traverse_obj(ld_json_meta, {
+                'title': 'name',
+                'thumbnail': 'image',
+                'channel_url': ('byArtist', 0, '@id'),
+                'artists': ('byArtist', ..., 'name'),
+                'duration': ('duration', {parse_duration}),
+            }), {
+                'formats': self._extract_formats(song_id, 'MUSIC', vcodec='none'),
+            })
+
+
+class BoomplayVideoIE(BoomplayBaseIE):
+    _VALID_URL = r'https?://(?:www\.)?boomplay\.com/video/(?P<id>\d+)'
+    _TESTS = [{
+        'url': 'https://www.boomplay.com/video/1154892',
+        'md5': 'd9b67ad333d2292a82922062d065352d',
+        'info_dict': {
+            'id': '1154892',
+            'ext': 'mp4',
+            'title': 'Autumn blues',
+            'thumbnail': 'https://source.boomplaymusic.com/group10/M00/10/10/2171dee9e1f8452e84021560729edb88.jpg',
+            'upload_date': '20241010',
+            'timestamp': 1728599214,
+            'view_count': int,
+            'duration': 177.0,
+            'description': 'Autumn blues by Lugo',
+        },
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+        return merge_dicts(
+            self._extract_page_metadata(webpage, video_id),
+            self._search_json_ld(webpage, video_id), {
+                'formats': self._extract_formats(video_id, 'VIDEO', ext='mp4'),
+            })
+
+
+class BoomplayEpisodeIE(BoomplayBaseIE):
+    _VALID_URL = r'https?://(?:www\.)?boomplay\.com/episode/(?P<id>\d+)'
+    _TESTS = [{
+        'url': 'https://www.boomplay.com/episode/7132706',
+        'md5': 'f26e236b764baa53d7a2cbb7e9ce6dc4',
+        'info_dict': {
+            'id': '7132706',
+            'ext': 'mp3',
+            'title': 'Letting Go',
+            'repost_count': int,
+            'thumbnail': 'https://source.boomplaymusic.com/group10/M00/05/06/fc535eaa25714b43a47185a9831887a5_320_320.jpg',
+            'comment_count': int,
+            'duration': 921.0,
+            'upload_date': '20240506',
+            'description': 'md5:5ec684b281fa0f9e4c31b3ee20c5e57a',
+        },
+    }]
+
+    def _real_extract(self, url):
+        ep_id = self._match_id(url)
+        webpage = self._download_webpage(url, ep_id)
+        return merge_dicts(
+            self._extract_page_metadata(webpage, ep_id), {
+                'description': self._html_search_meta(
+                    ['description', 'og:description', 'twitter:description'], webpage),
+                'formats': self._extract_formats(ep_id, 'EPISODE', vcodec='none'),
+            })
+
+
+class BoomplayPodcastIE(BoomplayBaseIE):
+    _VALID_URL = r'https?://(?:www\.)?boomplay\.com/podcasts/(?P<id>\d+)'
+    _TESTS = [{
+        'url': 'https://www.boomplay.com/podcasts/5372',
+        'playlist_count': 200,
+        'info_dict': {
+            'id': '5372',
+            'title': 'TED Talks Daily',
+            'description': r're:(?s)Every weekday, TED Talks Daily brings you the latest talks .{328} learn something new\.$',
+            'thumbnail': 'https://source.boomplaymusic.com/group10/M00/12/22/6f9cf97ad6f846a0a7882c98dfcf4f8c_320_320.jpg',
+            'repost_count': int,
+            'comment_count': int,
+            'like_count': int,
+        },
+    }]
+
+    def _real_extract(self, url):
+        playlist_id = self._match_id(url)
+        webpage = self._download_webpage(url, playlist_id)
+        song_list = self._get_element_by_class_and_tag('morePart_musics', 'ol', webpage)
+        song_list = traverse_obj(re.finditer(
+            r'''(?ix)
+            <li
+                (?:\s(?:[^>"']|"[^"]*"|'[^']*')*)?
+                    \sdata-id\s*=\s*
+                        (?P<_q>['"]?)
+                            (?P<id>\d+)
+                        (?P=_q)
+                (?:\s(?:[^>"']|"[^"]*"|'[^']*')*)?
+            >''',
+            song_list),
+            (..., 'id', {
+                lambda x: self.url_result(
+                    f'https://www.boomplay.com/episode/{x}', BoomplayEpisodeIE, x),
+            }))
+        return self.playlist_result(
+            song_list, playlist_id,
+            **self._extract_page_metadata(webpage, playlist_id))
+
+
+class BoomplayPlaylistIE(BoomplayBaseIE):
+    _VALID_URL = r'https?://(?:www\.)?boomplay\.com/(?:playlists|artists|albums)/(?P<id>\d+)'
+    _TESTS = [{
+        'url': 'https://www.boomplay.com/playlists/33792494',
+        'info_dict': {
+            'id': '33792494',
+            'title': 'Daily Trending Indonesia',
+            'thumbnail': 'https://source.boomplaymusic.com/group10/M00/08/19/d05d431ee616412caeacd7f78f4f68f5_320_320.jpeg',
+            'repost_count': int,
+            'comment_count': int,
+            'like_count': int,
+            'description': 'md5:7ebdffc5137c77acb62acb3c89248445',
+        },
+        'playlist_count': 10,
+    }, {
+        'url': 'https://www.boomplay.com/artists/52723101',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.boomplay.com/albums/89611238?from=home#google_vignette',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        playlist_id = self._match_id(url)
+        webpage = self._download_webpage(url, playlist_id)
+        json_ld_metadata = next(self._yield_json_ld(webpage, playlist_id))
+        # schema `MusicGroup` not supported by self._json_ld()
+
+        return self.playlist_result(**merge_dicts(
+            self._extract_page_metadata(webpage, playlist_id),
+            traverse_obj(json_ld_metadata, {
+                'entries': ('track', ..., 'url', {
+                    functools.partial(self.url_result, ie=BoomplayMusicIE),
+                }),
+                'playlist_title': 'name',
+                'thumbnail': 'image',
+                'artists': ('byArtist', ..., 'name'),
+                'channel_url': ('byArtist', 0, '@id'),
+            })))
+
+
+class BoomplayGenericPlaylistIE(BoomplayBaseIE):
+    _VALID_URL = r'https?://(?:www\.)?boomplay\.com/.+'
+    _TESTS = [{
+        'url': 'https://www.boomplay.com/new-songs',
+        'playlist_mincount': 20,
+        'info_dict': {
+            'id': 'new-songs',
+            'title': 'New Songs',
+            'thumbnail': 'http://www.boomplay.com/pc/img/og_default_v3.jpg',
+        },
+    }, {
+        'url': 'https://www.boomplay.com/trending-songs',
+        'playlist_mincount': 20,
+        'info_dict': {
+            'id': 'trending-songs',
+            'title': 'Trending Songs',
+            'thumbnail': 'http://www.boomplay.com/pc/img/og_default_v3.jpg',
+        },
+    }]
+
+    @classmethod
+    def suitable(cls, url):
+        return super().suitable(url) and all(not ie.suitable(url) for ie in (
+            BoomplayEpisodeIE,
+            BoomplayMusicIE,
+            BoomplayPlaylistIE,
+            BoomplayPodcastIE,
+            BoomplaySearchURLIE,
+            BoomplayVideoIE,
+        ))
+
+    def _real_extract(self, url):
+        playlist_id = self._generic_id(url)
+        webpage = self._download_webpage(url, playlist_id)
+        return self.playlist_result(
+            self._extract_playlist_entries(webpage, self._MEDIA_TYPES),
+            **self._extract_page_metadata(webpage, playlist_id))
+
+
+class BoomplaySearchURLIE(BoomplayBaseIE):
+    _TESTS = [{
+        'url': 'https://www.boomplay.com/search/default/%20Rise%20of%20the%20Falletesn%20Heroes%20fatbunny',
+        'md5': 'c5fb4f23e6aae98064230ef3c39c2178',
+        'info_dict': {
+            'id': '165481965',
+            'ext': 'mp3',
+            'title': 'Rise of the Fallen Heroes',
+            'duration': 125.0,
+            'genres': ['Metal'],
+            'artists': ['fatbunny'],
+            'thumbnail': 'https://source.boomplaymusic.com/group10/M00/04/29/375ecda38f6f48179a93c72ab909118f_464_464.jpg',
+            'channel_url': 'https://www.boomplay.com/artists/52723101',
+            'comment_count': int,
+            'repost_count': int,
+            'album': 'Legendary Battle',
+            'release_year': 2024,
+            'like_count': int,
+        },
+    }, {
+        'url': 'https://www.boomplay.com/search/video/%20Autumn%20blues',
+        'md5': 'd9b67ad333d2292a82922062d065352d',
+        'info_dict': {
+            'id': '1154892',
+            'title': 'Autumn blues',
+            'ext': 'mp4',
+            'timestamp': 1728599214,
+            'view_count': int,
+            'thumbnail': 'https://source.boomplaymusic.com/group10/M00/10/10/2171dee9e1f8452e84021560729edb88.jpg',
+            'description': 'Autumn blues by Lugo',
+            'upload_date': '20241010',
+            'duration': 177.0,
+        },
+        'params': {'playlist_items': '1'},
+    }]
+
+    @classproperty
+    def _VALID_URL(cls):
+        return r'https?://(?:www\.)?boomplay\.com/search/(?P<media_type>default|video|episode|podcasts|playlists|artists|albums)/(?P<query>[^?&#/]+)'
+
+    def _real_extract(self, url):
+        media_type, query = self._match_valid_url(url).group('media_type', 'query')
+        if media_type == 'default':
+            media_type = 'songs'
+        webpage = self._download_webpage(url, query)
+        return self.playlist_result(
+            self._extract_playlist_entries(webpage, media_type, warn=media_type == 'songs'),
+            **self._extract_page_metadata(webpage, query))
+
+
+class BoomplaySearchIE(SearchInfoExtractor):
+    _SEARCH_KEY = 'boomplaysearch'
+    _RETURN_TYPE = 'url'
+    _TESTS = [{
+        'url': 'boomplaysearch:rise of the fallen heroes',
+        'only_matching': True,
+    }]
+
+    def _search_results(self, query):
+        yield self.url_result(
+            f'https://www.boomplay.com/search/default/{urllib.parse.quote(query)}',
+            BoomplaySearchURLIE)

yt_dlp/extractor/chaturbate.py

@@ -9,7 +9,7 @@ from ..utils import (
 
 
 class ChaturbateIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:[^/]+\.)?chaturbate\.com/(?:fullvideo/?\?.*?\bb=)?(?P<id>[^/?&#]+)'
+    _VALID_URL = r'https?://(?:[^/]+\.)?chaturbate\.(?P<tld>com|eu|global)/(?:fullvideo/?\?.*?\bb=)?(?P<id>[^/?&#]+)'
     _TESTS = [{
         'url': 'https://www.chaturbate.com/siswet19/',
         'info_dict': {
@@ -29,15 +29,24 @@ class ChaturbateIE(InfoExtractor):
     }, {
         'url': 'https://en.chaturbate.com/siswet19/',
         'only_matching': True,
+    }, {
+        'url': 'https://chaturbate.eu/siswet19/',
+        'only_matching': True,
+    }, {
+        'url': 'https://chaturbate.eu/fullvideo/?b=caylin',
+        'only_matching': True,
+    }, {
+        'url': 'https://chaturbate.global/siswet19/',
+        'only_matching': True,
     }]
 
     _ROOM_OFFLINE = 'Room is currently offline'
 
     def _real_extract(self, url):
-        video_id = self._match_id(url)
+        video_id, tld = self._match_valid_url(url).group('id', 'tld')
 
         webpage = self._download_webpage(
-            f'https://chaturbate.com/{video_id}/', video_id,
+            f'https://chaturbate.{tld}/{video_id}/', video_id,
             headers=self.geo_verification_headers())
 
         found_m3u8_urls = []

yt_dlp/extractor/cloudflarestream.py

@@ -8,7 +8,7 @@ class CloudflareStreamIE(InfoExtractor):
     _DOMAIN_RE = r'(?:cloudflarestream\.com|(?:videodelivery|bytehighway)\.net)'
     _EMBED_RE = rf'(?:embed\.|{_SUBDOMAIN_RE}){_DOMAIN_RE}/embed/[^/?#]+\.js\?(?:[^#]+&)?video='
     _ID_RE = r'[\da-f]{32}|eyJ[\w-]+\.[\w-]+\.[\w-]+'
-    _VALID_URL = rf'https?://(?:{_SUBDOMAIN_RE}{_DOMAIN_RE}/|{_EMBED_RE})(?P<id>{_ID_RE})'
+    _VALID_URL = rf'https?://(?:{_SUBDOMAIN_RE}(?P<domain>{_DOMAIN_RE})/|{_EMBED_RE})(?P<id>{_ID_RE})'
     _EMBED_REGEX = [
         rf'<script[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//{_EMBED_RE}(?:{_ID_RE})(?:(?!\1).)*)\1',
         rf'<iframe[^>]+\bsrc=["\'](?P<url>https?://{_SUBDOMAIN_RE}{_DOMAIN_RE}/[\da-f]{{32}})',
@@ -19,7 +19,7 @@ class CloudflareStreamIE(InfoExtractor):
             'id': '31c9291ab41fac05471db4e73aa11717',
             'ext': 'mp4',
             'title': '31c9291ab41fac05471db4e73aa11717',
-            'thumbnail': 'https://videodelivery.net/31c9291ab41fac05471db4e73aa11717/thumbnails/thumbnail.jpg',
+            'thumbnail': 'https://cloudflarestream.com/31c9291ab41fac05471db4e73aa11717/thumbnails/thumbnail.jpg',
         },
         'params': {
             'skip_download': 'm3u8',
@@ -30,7 +30,7 @@ class CloudflareStreamIE(InfoExtractor):
             'id': '0e8e040aec776862e1d632a699edf59e',
             'ext': 'mp4',
             'title': '0e8e040aec776862e1d632a699edf59e',
-            'thumbnail': 'https://videodelivery.net/0e8e040aec776862e1d632a699edf59e/thumbnails/thumbnail.jpg',
+            'thumbnail': 'https://cloudflarestream.com/0e8e040aec776862e1d632a699edf59e/thumbnails/thumbnail.jpg',
         },
     }, {
         'url': 'https://watch.cloudflarestream.com/9df17203414fd1db3e3ed74abbe936c1',
@@ -54,7 +54,7 @@ class CloudflareStreamIE(InfoExtractor):
             'id': 'eaef9dea5159cf968be84241b5cedfe7',
             'ext': 'mp4',
             'title': 'eaef9dea5159cf968be84241b5cedfe7',
-            'thumbnail': 'https://videodelivery.net/eaef9dea5159cf968be84241b5cedfe7/thumbnails/thumbnail.jpg',
+            'thumbnail': 'https://cloudflarestream.com/eaef9dea5159cf968be84241b5cedfe7/thumbnails/thumbnail.jpg',
         },
         'params': {
             'skip_download': 'm3u8',
@@ -62,8 +62,9 @@ class CloudflareStreamIE(InfoExtractor):
     }]
 
     def _real_extract(self, url):
-        video_id = self._match_id(url)
-        domain = 'bytehighway.net' if 'bytehighway.net/' in url else 'videodelivery.net'
+        video_id, domain = self._match_valid_url(url).group('id', 'domain')
+        if domain != 'bytehighway.net':
+            domain = 'cloudflarestream.com'
         base_url = f'https://{domain}/{video_id}/'
         if '.' in video_id:
             video_id = self._parse_json(base64.urlsafe_b64decode(

yt_dlp/extractor/goplay.py

@@ -5,56 +5,63 @@ import hashlib
 import hmac
 import json
 import os
+import re
+import urllib.parse
 
 from .common import InfoExtractor
 from ..utils import (
     ExtractorError,
+    int_or_none,
+    js_to_json,
+    remove_end,
     traverse_obj,
-    unescapeHTML,
 )
 
 
 class GoPlayIE(InfoExtractor):
-    _VALID_URL = r'https?://(www\.)?goplay\.be/video/([^/]+/[^/]+/|)(?P<display_id>[^/#]+)'
+    _VALID_URL = r'https?://(www\.)?goplay\.be/video/([^/?#]+/[^/?#]+/|)(?P<id>[^/#]+)'
 
     _NETRC_MACHINE = 'goplay'
 
     _TESTS = [{
-        'url': 'https://www.goplay.be/video/de-container-cup/de-container-cup-s3/de-container-cup-s3-aflevering-2#autoplay',
+        'url': 'https://www.goplay.be/video/de-slimste-mens-ter-wereld/de-slimste-mens-ter-wereld-s22/de-slimste-mens-ter-wereld-s22-aflevering-1',
         'info_dict': {
-            'id': '9c4214b8-e55d-4e4b-a446-f015f6c6f811',
+            'id': '2baa4560-87a0-421b-bffc-359914e3c387',
             'ext': 'mp4',
-            'title': 'S3 - Aflevering 2',
-            'series': 'De Container Cup',
-            'season': 'Season 3',
-            'season_number': 3,
-            'episode': 'Episode 2',
-            'episode_number': 2,
+            'title': 'S22 - Aflevering 1',
+            'description': r're:In aflevering 1 nemen Daan Alferink, Tess Elst en Xander De Rycke .{66}',
+            'series': 'De Slimste Mens ter Wereld',
+            'episode': 'Episode 1',
+            'season_number': 22,
+            'episode_number': 1,
+            'season': 'Season 22',
         },
+        'params': {'skip_download': True},
         'skip': 'This video is only available for registered users',
     }, {
-        'url': 'https://www.goplay.be/video/a-family-for-thr-holidays-s1-aflevering-1#autoplay',
+        'url': 'https://www.goplay.be/video/1917',
         'info_dict': {
-            'id': '74e3ed07-748c-49e4-85a0-393a93337dbf',
+            'id': '40cac41d-8d29-4ef5-aa11-75047b9f0907',
             'ext': 'mp4',
-            'title': 'A Family for the Holidays',
+            'title': '1917',
+            'description': r're:Op het hoogtepunt van de Eerste Wereldoorlog krijgen twee jonge .{94}',
         },
+        'params': {'skip_download': True},
         'skip': 'This video is only available for registered users',
     }, {
         'url': 'https://www.goplay.be/video/de-mol/de-mol-s11/de-mol-s11-aflevering-1#autoplay',
         'info_dict': {
-            'id': '03eb8f2f-153e-41cb-9805-0d3a29dab656',
+            'id': 'ecb79672-92b9-4cd9-a0d7-e2f0250681ee',
             'ext': 'mp4',
             'title': 'S11 - Aflevering 1',
+            'description': r're:Tien kandidaten beginnen aan hun verovering van Amerika en ontmoeten .{102}',
             'episode': 'Episode 1',
             'series': 'De Mol',
             'season_number': 11,
             'episode_number': 1,
             'season': 'Season 11',
         },
-        'params': {
-            'skip_download': True,
-        },
+        'params': {'skip_download': True},
         'skip': 'This video is only available for registered users',
     }]
 
@@ -69,27 +76,42 @@ class GoPlayIE(InfoExtractor):
         if not self._id_token:
             raise self.raise_login_required(method='password')
 
-    def _real_extract(self, url):
-        url, display_id = self._match_valid_url(url).group(0, 'display_id')
-        webpage = self._download_webpage(url, display_id)
-        video_data_json = self._html_search_regex(r'<div\s+data-hero="([^"]+)"', webpage, 'video_data')
-        video_data = self._parse_json(unescapeHTML(video_data_json), display_id).get('data')
+    def _find_json(self, s):
+        return self._search_json(
+            r'\w+\s*:\s*', s, 'next js data', None, contains_pattern=r'\[(?s:.+)\]', default=None)
 
-        movie = video_data.get('movie')
-        if movie:
-            video_id = movie['videoUuid']
-            info_dict = {
-                'title': movie.get('title'),
-            }
-        else:
-            episode = traverse_obj(video_data, ('playlists', ..., 'episodes', lambda _, v: v['pageInfo']['url'] == url), get_all=False)
-            video_id = episode['videoUuid']
-            info_dict = {
-                'title': episode.get('episodeTitle'),
-                'series': traverse_obj(episode, ('program', 'title')),
-                'season_number': episode.get('seasonNumber'),
-                'episode_number': episode.get('episodeNumber'),
-            }
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_id)
+
+        nextjs_data = traverse_obj(
+            re.findall(r'<script[^>]*>\s*self\.__next_f\.push\(\s*(\[.+?\])\s*\);?\s*</script>', webpage),
+            (..., {js_to_json}, {json.loads}, ..., {self._find_json}, ...))
+        meta = traverse_obj(nextjs_data, (
+            ..., lambda _, v: v['meta']['path'] == urllib.parse.urlparse(url).path, 'meta', any))
+
+        video_id = meta['uuid']
+        info_dict = traverse_obj(meta, {
+            'title': ('title', {str}),
+            'description': ('description', {str.strip}),
+        })
+
+        if traverse_obj(meta, ('program', 'subtype')) != 'movie':
+            for season_data in traverse_obj(nextjs_data, (..., 'children', ..., 'playlists', ...)):
+                episode_data = traverse_obj(
+                    season_data, ('videos', lambda _, v: v['videoId'] == video_id, any))
+                if not episode_data:
+                    continue
+
+                episode_title = traverse_obj(
+                    episode_data, 'contextualTitle', 'episodeTitle', expected_type=str)
+                info_dict.update({
+                    'title': episode_title or info_dict.get('title'),
+                    'series': remove_end(info_dict.get('title'), f' - {episode_title}'),
+                    'season_number': traverse_obj(season_data, ('season', {int_or_none})),
+                    'episode_number': traverse_obj(episode_data, ('episodeNumber', {int_or_none})),
+                })
+                break
 
         api = self._download_json(
             f'https://api.goplay.be/web/v1/videos/long-form/{video_id}',

yt_dlp/extractor/mixch.py

@@ -12,7 +12,7 @@ from ..utils.traversal import traverse_obj
 
 class MixchIE(InfoExtractor):
     IE_NAME = 'mixch'
-    _VALID_URL = r'https?://(?:www\.)?mixch\.tv/u/(?P<id>\d+)'
+    _VALID_URL = r'https?://mixch\.tv/u/(?P<id>\d+)'
 
     _TESTS = [{
         'url': 'https://mixch.tv/u/16943797/live',
@@ -74,7 +74,7 @@ class MixchIE(InfoExtractor):
 
 class MixchArchiveIE(InfoExtractor):
     IE_NAME = 'mixch:archive'
-    _VALID_URL = r'https?://(?:www\.)?mixch\.tv/archive/(?P<id>\d+)'
+    _VALID_URL = r'https?://mixch\.tv/archive/(?P<id>\d+)'
 
     _TESTS = [{
         'url': 'https://mixch.tv/archive/421',
@@ -116,3 +116,56 @@ class MixchArchiveIE(InfoExtractor):
             'formats': self._extract_m3u8_formats(info_json['archiveURL'], video_id),
             'thumbnail': traverse_obj(info_json, ('thumbnailURL', {url_or_none})),
         }
+
+
+class MixchMovieIE(InfoExtractor):
+    IE_NAME = 'mixch:movie'
+    _VALID_URL = r'https?://mixch\.tv/m/(?P<id>\w+)'
+
+    _TESTS = [{
+        'url': 'https://mixch.tv/m/Ve8KNkJ5',
+        'info_dict': {
+            'id': 'Ve8KNkJ5',
+            'title': '夏☀️\nムービーへのポイントは本イベントに加算されないので配信にてお願い致します🙇🏻\u200d♀️\n#TGCCAMPUS #ミス東大 #ミス東大2024 ',
+            'ext': 'mp4',
+            'uploader': 'ミス東大No.5 松藤百香🍑💫',
+            'uploader_id': '12299174',
+            'channel_follower_count': int,
+            'view_count': int,
+            'like_count': int,
+            'comment_count': int,
+            'timestamp': 1724070828,
+            'uploader_url': 'https://mixch.tv/u/12299174',
+            'live_status': 'not_live',
+            'upload_date': '20240819',
+        },
+    }, {
+        'url': 'https://mixch.tv/m/61DzpIKE',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        data = self._download_json(
+            f'https://mixch.tv/api-web/movies/{video_id}', video_id)
+        return {
+            'id': video_id,
+            'formats': [{
+                'format_id': 'mp4',
+                'url': data['movie']['file'],
+                'ext': 'mp4',
+            }],
+            **traverse_obj(data, {
+                'title': ('movie', 'title', {str}),
+                'thumbnail': ('movie', 'thumbnailURL', {url_or_none}),
+                'uploader': ('ownerInfo', 'name', {str}),
+                'uploader_id': ('ownerInfo', 'id', {int}, {str_or_none}),
+                'channel_follower_count': ('ownerInfo', 'fan', {int_or_none}),
+                'view_count': ('ownerInfo', 'view', {int_or_none}),
+                'like_count': ('movie', 'favCount', {int_or_none}),
+                'comment_count': ('movie', 'commentCount', {int_or_none}),
+                'timestamp': ('movie', 'published', {int_or_none}),
+                'uploader_url': ('ownerInfo', 'id', {lambda x: x and f'https://mixch.tv/u/{x}'}, filter),
+            }),
+            'live_status': 'not_live',
+        }

yt_dlp/extractor/rutube.py

@@ -2,15 +2,18 @@ import itertools
 
 from .common import InfoExtractor
 from ..utils import (
+    UnsupportedError,
     bool_or_none,
     determine_ext,
     int_or_none,
+    js_to_json,
     parse_qs,
-    traverse_obj,
+    str_or_none,
     try_get,
     unified_timestamp,
     url_or_none,
 )
+from ..utils.traversal import traverse_obj
 
 
 class RutubeBaseIE(InfoExtractor):
@@ -19,7 +22,7 @@ class RutubeBaseIE(InfoExtractor):
             query = {}
         query['format'] = 'json'
         return self._download_json(
-            f'http://rutube.ru/api/video/{video_id}/',
+            f'https://rutube.ru/api/video/{video_id}/',
             video_id, 'Downloading video JSON',
             'Unable to download video JSON', query=query)
 
@@ -61,18 +64,21 @@ class RutubeBaseIE(InfoExtractor):
             query = {}
         query['format'] = 'json'
         return self._download_json(
-            f'http://rutube.ru/api/play/options/{video_id}/',
+            f'https://rutube.ru/api/play/options/{video_id}/',
             video_id, 'Downloading options JSON',
             'Unable to download options JSON',
             headers=self.geo_verification_headers(), query=query)
 
-    def _extract_formats(self, options, video_id):
+    def _extract_formats_and_subtitles(self, options, video_id):
         formats = []
+        subtitles = {}
         for format_id, format_url in options['video_balancer'].items():
             ext = determine_ext(format_url)
             if ext == 'm3u8':
-                formats.extend(self._extract_m3u8_formats(
-                    format_url, video_id, 'mp4', m3u8_id=format_id, fatal=False))
+                fmts, subs = self._extract_m3u8_formats_and_subtitles(
+                    format_url, video_id, 'mp4', m3u8_id=format_id, fatal=False)
+                formats.extend(fmts)
+                self._merge_subtitles(subs, target=subtitles)
             elif ext == 'f4m':
                 formats.extend(self._extract_f4m_formats(
                     format_url, video_id, f4m_id=format_id, fatal=False))
@@ -82,11 +88,19 @@ class RutubeBaseIE(InfoExtractor):
                     'format_id': format_id,
                 })
         for hls_url in traverse_obj(options, ('live_streams', 'hls', ..., 'url', {url_or_none})):
-            formats.extend(self._extract_m3u8_formats(hls_url, video_id, ext='mp4', fatal=False))
-        return formats
+            fmts, subs = self._extract_m3u8_formats_and_subtitles(
+                hls_url, video_id, 'mp4', fatal=False, m3u8_id='hls')
+            formats.extend(fmts)
+            self._merge_subtitles(subs, target=subtitles)
+        for caption in traverse_obj(options, ('captions', lambda _, v: url_or_none(v['file']))):
+            subtitles.setdefault(caption.get('code') or 'ru', []).append({
+                'url': caption['file'],
+                'name': caption.get('langTitle'),
+            })
+        return formats, subtitles
 
-    def _download_and_extract_formats(self, video_id, query=None):
-        return self._extract_formats(
+    def _download_and_extract_formats_and_subtitles(self, video_id, query=None):
+        return self._extract_formats_and_subtitles(
             self._download_api_options(video_id, query=query), video_id)
 
 
@@ -97,8 +111,8 @@ class RutubeIE(RutubeBaseIE):
     _EMBED_REGEX = [r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//rutube\.ru/(?:play/)?embed/[\da-z]{32}.*?)\1']
 
     _TESTS = [{
-        'url': 'http://rutube.ru/video/3eac3b4561676c17df9132a9a1e62e3e/',
-        'md5': 'e33ac625efca66aba86cbec9851f2692',
+        'url': 'https://rutube.ru/video/3eac3b4561676c17df9132a9a1e62e3e/',
+        'md5': '3d73fdfe5bb81b9aef139e22ef3de26a',
         'info_dict': {
             'id': '3eac3b4561676c17df9132a9a1e62e3e',
             'ext': 'mp4',
@@ -111,26 +125,25 @@ class RutubeIE(RutubeBaseIE):
             'upload_date': '20131016',
             'age_limit': 0,
             'view_count': int,
-            'thumbnail': 'http://pic.rutubelist.ru/video/d2/a0/d2a0aec998494a396deafc7ba2c82add.jpg',
+            'thumbnail': 'https://pic.rutubelist.ru/video/d2/a0/d2a0aec998494a396deafc7ba2c82add.jpg',
             'categories': ['Новости и СМИ'],
             'chapters': [],
         },
-        'expected_warnings': ['Unable to download f4m'],
     }, {
-        'url': 'http://rutube.ru/play/embed/a10e53b86e8f349080f718582ce4c661',
+        'url': 'https://rutube.ru/play/embed/a10e53b86e8f349080f718582ce4c661',
         'only_matching': True,
     }, {
-        'url': 'http://rutube.ru/embed/a10e53b86e8f349080f718582ce4c661',
+        'url': 'https://rutube.ru/embed/a10e53b86e8f349080f718582ce4c661',
         'only_matching': True,
     }, {
-        'url': 'http://rutube.ru/video/3eac3b4561676c17df9132a9a1e62e3e/?pl_id=4252',
+        'url': 'https://rutube.ru/video/3eac3b4561676c17df9132a9a1e62e3e/?pl_id=4252',
         'only_matching': True,
     }, {
         'url': 'https://rutube.ru/video/10b3a03fc01d5bbcc632a2f3514e8aab/?pl_type=source',
         'only_matching': True,
     }, {
         'url': 'https://rutube.ru/video/private/884fb55f07a97ab673c7d654553e0f48/?p=x2QojCumHTS3rsKHWXN8Lg',
-        'md5': 'd106225f15d625538fe22971158e896f',
+        'md5': '4fce7b4fcc7b1bcaa3f45eb1e1ad0dd7',
         'info_dict': {
             'id': '884fb55f07a97ab673c7d654553e0f48',
             'ext': 'mp4',
@@ -143,11 +156,10 @@ class RutubeIE(RutubeBaseIE):
             'upload_date': '20221210',
             'age_limit': 0,
             'view_count': int,
-            'thumbnail': 'http://pic.rutubelist.ru/video/f2/d4/f2d42b54be0a6e69c1c22539e3152156.jpg',
+            'thumbnail': 'https://pic.rutubelist.ru/video/f2/d4/f2d42b54be0a6e69c1c22539e3152156.jpg',
             'categories': ['Видеоигры'],
             'chapters': [],
         },
-        'expected_warnings': ['Unable to download f4m'],
     }, {
         'url': 'https://rutube.ru/video/c65b465ad0c98c89f3b25cb03dcc87c6/',
         'info_dict': {
@@ -156,17 +168,16 @@ class RutubeIE(RutubeBaseIE):
             'chapters': 'count:4',
             'categories': ['Бизнес и предпринимательство'],
             'description': 'md5:252feac1305257d8c1bab215cedde75d',
-            'thumbnail': 'http://pic.rutubelist.ru/video/71/8f/718f27425ea9706073eb80883dd3787b.png',
+            'thumbnail': 'https://pic.rutubelist.ru/video/71/8f/718f27425ea9706073eb80883dd3787b.png',
             'duration': 782,
             'age_limit': 0,
             'uploader_id': '23491359',
             'timestamp': 1677153329,
             'view_count': int,
             'upload_date': '20230223',
-            'title': 'Бизнес с нуля: найм сотрудников. Интервью с директором строительной компании',
+            'title': 'Бизнес с нуля: найм сотрудников. Интервью с директором строительной компании #1',
             'uploader': 'Стас Быков',
         },
-        'expected_warnings': ['Unable to download f4m'],
     }, {
         'url': 'https://rutube.ru/live/video/c58f502c7bb34a8fcdd976b221fca292/',
         'info_dict': {
@@ -174,7 +185,7 @@ class RutubeIE(RutubeBaseIE):
             'ext': 'mp4',
             'categories': ['Телепередачи'],
             'description': '',
-            'thumbnail': 'http://pic.rutubelist.ru/video/14/19/14190807c0c48b40361aca93ad0867c7.jpg',
+            'thumbnail': 'https://pic.rutubelist.ru/video/14/19/14190807c0c48b40361aca93ad0867c7.jpg',
             'live_status': 'is_live',
             'age_limit': 0,
             'uploader_id': '23460655',
@@ -184,6 +195,24 @@ class RutubeIE(RutubeBaseIE):
             'title': r're:Первый канал. Прямой эфир \d{4}-\d{2}-\d{2} \d{2}:\d{2}$',
             'uploader': 'Первый канал',
         },
+    }, {
+        'url': 'https://rutube.ru/play/embed/03a9cb54bac3376af4c5cb0f18444e01/',
+        'info_dict': {
+            'id': '03a9cb54bac3376af4c5cb0f18444e01',
+            'ext': 'mp4',
+            'age_limit': 0,
+            'description': '',
+            'title': 'Церемония начала торгов акциями ПАО «ЕвроТранс»',
+            'chapters': [],
+            'upload_date': '20240829',
+            'duration': 293,
+            'uploader': 'MOEX - Московская биржа',
+            'timestamp': 1724946628,
+            'thumbnail': 'https://pic.rutubelist.ru/video/2e/24/2e241fddb459baf0fa54acfca44874f4.jpg',
+            'view_count': int,
+            'uploader_id': '38420507',
+            'categories': ['Интервью'],
+        },
     }, {
         'url': 'https://rutube.ru/video/5ab908fccfac5bb43ef2b1e4182256b0/',
         'only_matching': True,
@@ -192,40 +221,46 @@ class RutubeIE(RutubeBaseIE):
         'only_matching': True,
     }]
 
-    @classmethod
-    def suitable(cls, url):
-        return False if RutubePlaylistIE.suitable(url) else super().suitable(url)
-
     def _real_extract(self, url):
         video_id = self._match_id(url)
         query = parse_qs(url)
         info = self._download_and_extract_info(video_id, query)
-        info['formats'] = self._download_and_extract_formats(video_id, query)
-        return info
+        formats, subtitles = self._download_and_extract_formats_and_subtitles(video_id, query)
+        return {
+            **info,
+            'formats': formats,
+            'subtitles': subtitles,
+        }
 
 
 class RutubeEmbedIE(RutubeBaseIE):
     IE_NAME = 'rutube:embed'
     IE_DESC = 'Rutube embedded videos'
-    _VALID_URL = r'https?://rutube\.ru/(?:video|play)/embed/(?P<id>[0-9]+)'
+    _VALID_URL = r'https?://rutube\.ru/(?:video|play)/embed/(?P<id>[0-9]+)(?:[?#/]|$)'
 
     _TESTS = [{
-        'url': 'http://rutube.ru/video/embed/6722881?vk_puid37=&vk_puid38=',
+        'url': 'https://rutube.ru/video/embed/6722881?vk_puid37=&vk_puid38=',
         'info_dict': {
             'id': 'a10e53b86e8f349080f718582ce4c661',
             'ext': 'mp4',
             'timestamp': 1387830582,
             'upload_date': '20131223',
             'uploader_id': '297833',
-            'description': 'Видео группы ★http://vk.com/foxkidsreset★ музей Fox Kids и Jetix<br/><br/> восстановлено и сделано в шикоформате subziro89 http://vk.com/subziro89',
             'uploader': 'subziro89 ILya',
             'title': 'Мистический городок Эйри в Индиан 5 серия озвучка subziro89',
+            'age_limit': 0,
+            'duration': 1395,
+            'chapters': [],
+            'description': 'md5:a5acea57bbc3ccdc3cacd1f11a014b5b',
+            'view_count': int,
+            'thumbnail': 'https://pic.rutubelist.ru/video/d3/03/d3031f4670a6e6170d88fb3607948418.jpg',
+            'categories': ['Сериалы'],
         },
         'params': {
             'skip_download': True,
         },
     }, {
-        'url': 'http://rutube.ru/play/embed/8083783',
+        'url': 'https://rutube.ru/play/embed/8083783',
         'only_matching': True,
     }, {
         # private video
@@ -240,11 +275,12 @@ class RutubeEmbedIE(RutubeBaseIE):
         query = parse_qs(url)
         options = self._download_api_options(embed_id, query)
         video_id = options['effective_video']
-        formats = self._extract_formats(options, video_id)
+        formats, subtitles = self._extract_formats_and_subtitles(options, video_id)
         info = self._download_and_extract_info(video_id, query)
         info.update({
             'extractor_key': 'Rutube',
             'formats': formats,
+            'subtitles': subtitles,
         })
         return info
 
@@ -295,14 +331,14 @@ class RutubeTagsIE(RutubePlaylistBaseIE):
     IE_DESC = 'Rutube tags'
     _VALID_URL = r'https?://rutube\.ru/tags/video/(?P<id>\d+)'
     _TESTS = [{
-        'url': 'http://rutube.ru/tags/video/1800/',
+        'url': 'https://rutube.ru/tags/video/1800/',
         'info_dict': {
             'id': '1800',
         },
         'playlist_mincount': 68,
     }]
 
-    _PAGE_TEMPLATE = 'http://rutube.ru/api/tags/video/%s/?page=%s&format=json'
+    _PAGE_TEMPLATE = 'https://rutube.ru/api/tags/video/%s/?page=%s&format=json'
 
 
 class RutubeMovieIE(RutubePlaylistBaseIE):
@@ -310,8 +346,8 @@ class RutubeMovieIE(RutubePlaylistBaseIE):
     IE_DESC = 'Rutube movies'
     _VALID_URL = r'https?://rutube\.ru/metainfo/tv/(?P<id>\d+)'
 
-    _MOVIE_TEMPLATE = 'http://rutube.ru/api/metainfo/tv/%s/?format=json'
-    _PAGE_TEMPLATE = 'http://rutube.ru/api/metainfo/tv/%s/video?page=%s&format=json'
+    _MOVIE_TEMPLATE = 'https://rutube.ru/api/metainfo/tv/%s/?format=json'
+    _PAGE_TEMPLATE = 'https://rutube.ru/api/metainfo/tv/%s/video?page=%s&format=json'
 
     def _real_extract(self, url):
         movie_id = self._match_id(url)
@@ -327,62 +363,82 @@ class RutubePersonIE(RutubePlaylistBaseIE):
     IE_DESC = 'Rutube person videos'
     _VALID_URL = r'https?://rutube\.ru/video/person/(?P<id>\d+)'
     _TESTS = [{
-        'url': 'http://rutube.ru/video/person/313878/',
+        'url': 'https://rutube.ru/video/person/313878/',
         'info_dict': {
             'id': '313878',
         },
-        'playlist_mincount': 37,
+        'playlist_mincount': 36,
     }]
 
-    _PAGE_TEMPLATE = 'http://rutube.ru/api/video/person/%s/?page=%s&format=json'
+    _PAGE_TEMPLATE = 'https://rutube.ru/api/video/person/%s/?page=%s&format=json'
 
 
 class RutubePlaylistIE(RutubePlaylistBaseIE):
     IE_NAME = 'rutube:playlist'
     IE_DESC = 'Rutube playlists'
-    _VALID_URL = r'https?://rutube\.ru/(?:video|(?:play/)?embed)/[\da-z]{32}/\?.*?\bpl_id=(?P<id>\d+)'
+    _VALID_URL = r'https?://rutube\.ru/plst/(?P<id>\d+)'
     _TESTS = [{
-        'url': 'https://rutube.ru/video/cecd58ed7d531fc0f3d795d51cee9026/?pl_id=3097&pl_type=tag',
+        'url': 'https://rutube.ru/plst/308547/',
         'info_dict': {
-            'id': '3097',
+            'id': '308547',
         },
-        'playlist_count': 27,
-    }, {
-        'url': 'https://rutube.ru/video/10b3a03fc01d5bbcc632a2f3514e8aab/?pl_id=4252&pl_type=source',
-        'only_matching': True,
+        'playlist_mincount': 22,
     }]
-
-    _PAGE_TEMPLATE = 'http://rutube.ru/api/playlist/%s/%s/?page=%s&format=json'
-
-    @classmethod
-    def suitable(cls, url):
-        from ..utils import int_or_none, parse_qs
-
-        if not super().suitable(url):
-            return False
-        params = parse_qs(url)
-        return params.get('pl_type', [None])[0] and int_or_none(params.get('pl_id', [None])[0])
-
-    def _next_page_url(self, page_num, playlist_id, item_kind):
-        return self._PAGE_TEMPLATE % (item_kind, playlist_id, page_num)
-
-    def _real_extract(self, url):
-        qs = parse_qs(url)
-        playlist_kind = qs['pl_type'][0]
-        playlist_id = qs['pl_id'][0]
-        return self._extract_playlist(playlist_id, item_kind=playlist_kind)
+    _PAGE_TEMPLATE = 'https://rutube.ru/api/playlist/custom/%s/videos?page=%s&format=json'
 
 
 class RutubeChannelIE(RutubePlaylistBaseIE):
     IE_NAME = 'rutube:channel'
     IE_DESC = 'Rutube channel'
-    _VALID_URL = r'https?://rutube\.ru/channel/(?P<id>\d+)/videos'
+    _VALID_URL = r'https?://rutube\.ru/(?:channel/(?P<id>\d+)|u/(?P<slug>\w+))(?:/(?P<section>videos|shorts|playlists))?'
     _TESTS = [{
         'url': 'https://rutube.ru/channel/639184/videos/',
         'info_dict': {
-            'id': '639184',
+            'id': '639184_videos',
         },
-        'playlist_mincount': 133,
+        'playlist_mincount': 129,
+    }, {
+        'url': 'https://rutube.ru/channel/25902603/shorts/',
+        'info_dict': {
+            'id': '25902603_shorts',
+        },
+        'playlist_mincount': 277,
+    }, {
+        'url': 'https://rutube.ru/channel/25902603/',
+        'info_dict': {
+            'id': '25902603',
+        },
+        'playlist_mincount': 406,
+    }, {
+        'url': 'https://rutube.ru/u/rutube/videos/',
+        'info_dict': {
+            'id': '23704195_videos',
+        },
+        'playlist_mincount': 113,
     }]
 
-    _PAGE_TEMPLATE = 'http://rutube.ru/api/video/person/%s/?page=%s&format=json'
+    _PAGE_TEMPLATE = 'https://rutube.ru/api/video/person/%s/?page=%s&format=json&origin__type=%s'
+
+    def _next_page_url(self, page_num, playlist_id, section):
+        origin_type = {
+            'videos': 'rtb,rst,ifrm,rspa',
+            'shorts': 'rshorts',
+            None: '',
+        }.get(section)
+        return self._PAGE_TEMPLATE % (playlist_id, page_num, origin_type)
+
+    def _real_extract(self, url):
+        playlist_id, slug, section = self._match_valid_url(url).group('id', 'slug', 'section')
+        if section == 'playlists':
+            raise UnsupportedError(url)
+        if slug:
+            webpage = self._download_webpage(url, slug)
+            redux_state = self._search_json(
+                r'window\.reduxState\s*=', webpage, 'redux state', slug, transform_source=js_to_json)
+            playlist_id = traverse_obj(redux_state, (
+                'api', 'queries', lambda k, _: k.startswith('channelIdBySlug'),
+                'data', 'channel_id', {int}, {str_or_none}, any))
+        playlist = self._extract_playlist(playlist_id, section=section)
+        if section:
+            playlist['id'] = f'{playlist_id}_{section}'
+        return playlist

yt_dlp/extractor/spreaker.py

@@ -2,13 +2,16 @@ import itertools
 
 from .common import InfoExtractor
 from ..utils import (
+    filter_dict,
     float_or_none,
     int_or_none,
+    parse_qs,
     str_or_none,
     try_get,
     unified_timestamp,
     url_or_none,
 )
+from ..utils.traversal import traverse_obj
 
 
 def _extract_episode(data, episode_id=None):
@@ -58,15 +61,10 @@ def _extract_episode(data, episode_id=None):
 
 
 class SpreakerIE(InfoExtractor):
-    _VALID_URL = r'''(?x)
-                    https?://
-                        api\.spreaker\.com/
-                        (?:
-                            (?:download/)?episode|
-                            v2/episodes
-                        )/
-                        (?P<id>\d+)
-                    '''
+    _VALID_URL = [
+        r'https?://api\.spreaker\.com/(?:(?:download/)?episode|v2/episodes)/(?P<id>\d+)',
+        r'https?://(?:www\.)?spreaker\.com/episode/[^#?/]*?(?P<id>\d+)/?(?:[?#]|$)',
+    ]
     _TESTS = [{
         'url': 'https://api.spreaker.com/episode/12534508',
         'info_dict': {
@@ -83,7 +81,9 @@ class SpreakerIE(InfoExtractor):
             'view_count': int,
             'like_count': int,
             'comment_count': int,
-            'series': 'Success With Music (SWM)',
+            'series': 'Success With Music | SWM',
+            'thumbnail': 'https://d3wo5wojvuv7l.cloudfront.net/t_square_limited_160/images.spreaker.com/original/777ce4f96b71b0e1b7c09a5e625210e3.jpg',
+            'creators': ['SWM'],
         },
     }, {
         'url': 'https://api.spreaker.com/download/episode/12534508/swm_ep15_how_to_market_your_music_part_2.mp3',
@@ -91,52 +91,75 @@ class SpreakerIE(InfoExtractor):
     }, {
         'url': 'https://api.spreaker.com/v2/episodes/12534508?export=episode_segments',
         'only_matching': True,
+    }, {
+        'note': 'episode',
+        'url': 'https://www.spreaker.com/episode/grunge-music-origins-the-raw-sound-that-defined-a-generation--60269615',
+        'info_dict': {
+            'id': '60269615',
+            'display_id': 'grunge-music-origins-the-raw-sound-that-',
+            'ext': 'mp3',
+            'title': 'Grunge Music Origins - The Raw Sound that Defined a Generation',
+            'description': str,
+            'timestamp': 1717468905,
+            'upload_date': '20240604',
+            'uploader': 'Katie Brown 2',
+            'uploader_id': '17733249',
+            'duration': 818.83,
+            'view_count': int,
+            'like_count': int,
+            'comment_count': int,
+            'series': '90s Grunge',
+            'thumbnail': 'https://d3wo5wojvuv7l.cloudfront.net/t_square_limited_160/images.spreaker.com/original/bb0d4178f7cf57cc8786dedbd9c5d969.jpg',
+            'creators': ['Katie Brown 2'],
+        },
+    }, {
+        'url': 'https://www.spreaker.com/episode/60269615',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
         episode_id = self._match_id(url)
         data = self._download_json(
-            f'https://api.spreaker.com/v2/episodes/{episode_id}',
-            episode_id)['response']['episode']
+            f'https://api.spreaker.com/v2/episodes/{episode_id}', episode_id,
+            query=traverse_obj(parse_qs(url), {'key': ('key', 0)}))['response']['episode']
         return _extract_episode(data, episode_id)
 
 
-class SpreakerPageIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?spreaker\.com/user/[^/]+/(?P<id>[^/?#&]+)'
-    _TESTS = [{
-        'url': 'https://www.spreaker.com/user/9780658/swm-ep15-how-to-market-your-music-part-2',
-        'only_matching': True,
-    }]
-
-    def _real_extract(self, url):
-        display_id = self._match_id(url)
-        webpage = self._download_webpage(url, display_id)
-        episode_id = self._search_regex(
-            (r'data-episode_id=["\'](?P<id>\d+)',
-             r'episode_id\s*:\s*(?P<id>\d+)'), webpage, 'episode id')
-        return self.url_result(
-            f'https://api.spreaker.com/episode/{episode_id}',
-            ie=SpreakerIE.ie_key(), video_id=episode_id)
-
-
 class SpreakerShowIE(InfoExtractor):
-    _VALID_URL = r'https?://api\.spreaker\.com/show/(?P<id>\d+)'
+    _VALID_URL = [
+        r'https?://api\.spreaker\.com/show/(?P<id>\d+)',
+        r'https?://(?:www\.)?spreaker\.com/podcast/[\w-]+--(?P<id>[\d]+)',
+        r'https?://(?:www\.)?spreaker\.com/show/(?P<id>\d+)/episodes/feed',
+    ]
     _TESTS = [{
         'url': 'https://api.spreaker.com/show/4652058',
         'info_dict': {
             'id': '4652058',
         },
         'playlist_mincount': 118,
+    }, {
+        'url': 'https://www.spreaker.com/podcast/health-wealth--5918323',
+        'info_dict': {
+            'id': '5918323',
+        },
+        'playlist_mincount': 60,
+    }, {
+        'url': 'https://www.spreaker.com/show/5887186/episodes/feed',
+        'info_dict': {
+            'id': '5887186',
+        },
+        'playlist_mincount': 290,
     }]
 
-    def _entries(self, show_id):
+    def _entries(self, show_id, key=None):
         for page_num in itertools.count(1):
             episodes = self._download_json(
                 f'https://api.spreaker.com/show/{show_id}/episodes',
-                show_id, note=f'Downloading JSON page {page_num}', query={
+                show_id, note=f'Downloading JSON page {page_num}', query=filter_dict({
                     'page': page_num,
                     'max_per_page': 100,
-                })
+                    'key': key,
+                }))
             pager = try_get(episodes, lambda x: x['response']['pager'], dict)
             if not pager:
                 break
@@ -152,21 +175,5 @@ class SpreakerShowIE(InfoExtractor):
 
     def _real_extract(self, url):
         show_id = self._match_id(url)
-        return self.playlist_result(self._entries(show_id), playlist_id=show_id)
-
-
-class SpreakerShowPageIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?spreaker\.com/show/(?P<id>[^/?#&]+)'
-    _TESTS = [{
-        'url': 'https://www.spreaker.com/show/success-with-music',
-        'only_matching': True,
-    }]
-
-    def _real_extract(self, url):
-        display_id = self._match_id(url)
-        webpage = self._download_webpage(url, display_id)
-        show_id = self._search_regex(
-            r'show_id\s*:\s*(?P<id>\d+)', webpage, 'show id')
-        return self.url_result(
-            f'https://api.spreaker.com/show/{show_id}',
-            ie=SpreakerShowIE.ie_key(), video_id=show_id)
+        key = traverse_obj(parse_qs(url), ('key', 0))
+        return self.playlist_result(self._entries(show_id, key), playlist_id=show_id)