Merge branch 'yt-dlp:master' into handle-infinite-redirects

yt_dlp/extractor/_extractors.py

@@ -256,6 +256,7 @@
     BilibiliCheeseIE,
     BilibiliCheeseSeasonIE,
     BilibiliCollectionListIE,
+    BiliBiliDynamicIE,
     BilibiliFavoritesListIE,
     BiliBiliIE,
     BiliBiliPlayerIE,
@@ -585,6 +586,10 @@
     EggheadCourseIE,
     EggheadLessonIE,
 )
+from .eggs import (
+    EggsArtistIE,
+    EggsIE,
+)
 from .eighttracks import EightTracksIE
 from .eitb import EitbIE
 from .elementorembed import ElementorEmbedIE
@@ -1279,6 +1284,10 @@
 )
 from .nekohacker import NekoHackerIE
 from .nerdcubed import NerdCubedFeedIE
+from .nest import (
+    NestClipIE,
+    NestIE,
+)
 from .neteasemusic import (
     NetEaseMusicAlbumIE,
     NetEaseMusicDjRadioIE,
@@ -1533,6 +1542,10 @@
     PinterestCollectionIE,
     PinterestIE,
 )
+from .piramidetv import (
+    PiramideTVChannelIE,
+    PiramideTVIE,
+)
 from .pixivsketch import (
     PixivSketchIE,
     PixivSketchUserIE,

yt_dlp/extractor/bilibili.py

@@ -32,6 +32,7 @@
     parse_qs,
     parse_resolution,
     qualities,
+    sanitize_url,
     smuggle_url,
     srt_subtitles_timecode,
     str_or_none,
@@ -1861,6 +1862,47 @@ def _real_extract(self, url):
             ie=BiliBiliIE.ie_key(), video_id=video_id)
 
 
+class BiliBiliDynamicIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:t\.bilibili\.com|(?:www\.)?bilibili\.com/opus)/(?P<id>\d+)'
+    _TESTS = [{
+        'url': 'https://t.bilibili.com/998134289197432852',
+        'info_dict': {
+            'id': 'BV1TAmBYVEJr',
+            'ext': 'mp4',
+            'uploader_id': '1192648858',
+            'comment_count': int,
+            '_old_archive_ids': ['bilibili 113457567568273_part1'],
+            'thumbnail': 'http://i2.hdslb.com/bfs/archive/50091efd965d9f13ff6814f7ad374f90ab21e77d.jpg',
+            'duration': 929.238,
+            'upload_date': '20241110',
+            'uploader': '何同学工作室',
+            'like_count': int,
+            'view_count': int,
+            'title': '美国小朋友就玩这个？！何同学工作室11月开箱',
+            'description': '本期产品信息：\n机器狗\n气味模拟器\nCloudboom Strike LS\n无弦吉他\n蓝牙磁带音箱\n神奇画板',
+            'timestamp': 1731232800,
+            'tags': list,
+            'chapters': list,
+        },
+    }]
+
+    def _real_extract(self, url):
+        post_id = self._match_id(url)
+        # Without the newer chrome UA, the API will return an error (-352)
+        post_data = self._download_json(
+            'https://api.bilibili.com/x/polymer/web-dynamic/v1/detail', post_id,
+            query={'id': post_id}, headers={
+                'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/131.0.0.0 Safari/537.36',
+            })
+        video_url = traverse_obj(post_data, (
+            'data', 'item', (None, 'orig'), 'modules', 'module_dynamic',
+            (('major', ('archive', 'pgc')), ('additional', ('reserve', 'common'))),
+            'jump_url', {url_or_none}, any, {sanitize_url}))
+        if not video_url or (self.suitable(video_url) and post_id == self._match_id(video_url)):
+            raise ExtractorError('No valid video URL found', expected=True)
+        return self.url_result(video_url)
+
+
 class BiliIntlBaseIE(InfoExtractor):
     _API_URL = 'https://api.bilibili.tv/intl/gateway'
     _NETRC_MACHINE = 'biliintl'

yt_dlp/extractor/bluesky.py

@@ -88,7 +88,7 @@ class BlueskyIE(InfoExtractor):
         },
     }, {
         'url': 'https://bsky.app/profile/de1.pds.tentacle.expert/post/3l3w4tnezek2e',
-        'md5': '1af9c7fda061cf7593bbffca89e43d1c',
+        'md5': 'cc0110ed1f6b0247caac8234cc1e861d',
         'info_dict': {
             'id': '3l3w4tnezek2e',
             'ext': 'mp4',
@@ -133,6 +133,8 @@ class BlueskyIE(InfoExtractor):
             'channel_follower_count': int,
             'categories': ['Entertainment'],
             'tags': [],
+            'chapters': list,
+            'heatmap': 'count:100',
         },
         'add_ie': ['Youtube'],
     }, {
@@ -184,14 +186,14 @@ class BlueskyIE(InfoExtractor):
             },
         },
     }, {
-        'url': 'https://bsky.app/profile/alt.bun.how/post/3l7rdfxhyds2f',
+        'url': 'https://bsky.app/profile/cinny.bun.how/post/3l7rdfxhyds2f',
         'md5': '8775118b235cf9fa6b5ad30f95cda75c',
         'info_dict': {
             'id': '3l7rdfxhyds2f',
             'ext': 'mp4',
             'uploader': 'cinnamon',
-            'uploader_id': 'alt.bun.how',
+            'uploader_id': 'cinny.bun.how',
-            'uploader_url': 'https://bsky.app/profile/alt.bun.how',
+            'uploader_url': 'https://bsky.app/profile/cinny.bun.how',
             'channel_id': 'did:plc:7x6rtuenkuvxq3zsvffp2ide',
             'channel_url': 'https://bsky.app/profile/did:plc:7x6rtuenkuvxq3zsvffp2ide',
             'thumbnail': r're:https://video.bsky.app/watch/.*\.jpg$',
@@ -341,6 +343,7 @@ def _extract_videos(self, root, video_id, embed_path='embed', record_path='recor
 
             formats.append({
                 'format_id': 'blob',
+                'quality': 1,
                 'url': update_url_query(
                     self._BLOB_URL_TMPL.format(endpoint), {'did': did, 'cid': video_cid}),
                 **traverse_obj(root, (*embed_path, 'aspectRatio', {

yt_dlp/extractor/eggs.py

@@ -0,0 +1,155 @@
+import secrets
+
+from .common import InfoExtractor
+from .youtube import YoutubeIE
+from ..utils import (
+    int_or_none,
+    parse_iso8601,
+    str_or_none,
+    url_or_none,
+)
+from ..utils.traversal import traverse_obj
+
+
+class EggsBaseIE(InfoExtractor):
+    _API_HEADERS = {
+        'Accept': '*/*',
+        'apVersion': '8.2.00',
+        'deviceName': 'Android',
+    }
+
+    def _real_initialize(self):
+        self._API_HEADERS['deviceId'] = secrets.token_hex(8)
+
+    def _call_api(self, endpoint, video_id):
+        return self._download_json(
+            f'https://app-front-api.eggs.mu/v1/{endpoint}', video_id,
+            headers=self._API_HEADERS)
+
+    def _extract_music_info(self, data):
+        if yt_url := traverse_obj(data, ('youtubeUrl', {url_or_none})):
+            return self.url_result(yt_url, ie=YoutubeIE)
+
+        artist_name = traverse_obj(data, ('artist', 'artistName', {str_or_none}))
+        music_id = traverse_obj(data, ('musicId', {str_or_none}))
+        webpage_url = None
+        if artist_name and music_id:
+            webpage_url = f'https://eggs.mu/artist/{artist_name}/song/{music_id}'
+
+        return {
+            'id': music_id,
+            'vcodec': 'none',
+            'webpage_url': webpage_url,
+            'extractor_key': EggsIE.ie_key(),
+            'extractor': EggsIE.IE_NAME,
+            **traverse_obj(data, {
+                'title': ('musicTitle', {str}),
+                'url': ('musicDataPath', {url_or_none}),
+                'uploader': ('artist', 'displayName', {str}),
+                'uploader_id': ('artist', 'artistId', {str_or_none}),
+                'thumbnail': ('imageDataPath', {url_or_none}),
+                'view_count': ('numberOfMusicPlays', {int_or_none}),
+                'like_count': ('numberOfLikes', {int_or_none}),
+                'comment_count': ('numberOfComments', {int_or_none}),
+                'composers': ('composer', {str}, all),
+                'tags': ('tags', ..., {str}),
+                'timestamp': ('releaseDate', {parse_iso8601}),
+                'artist': ('artist', 'displayName', {str}),
+            })}
+
+
+class EggsIE(EggsBaseIE):
+    IE_NAME = 'eggs:single'
+    _VALID_URL = r'https?://eggs\.mu/artist/[^/?#]+/song/(?P<id>[\da-f-]+)'
+
+    _TESTS = [{
+        'url': 'https://eggs.mu/artist/32_sunny_girl/song/0e95fd1d-4d61-4d5b-8b18-6092c551da90',
+        'info_dict': {
+            'id': '0e95fd1d-4d61-4d5b-8b18-6092c551da90',
+            'ext': 'm4a',
+            'title': 'シネマと信号',
+            'uploader': 'Sunny Girl',
+            'thumbnail': r're:https?://.*\.jpg(?:\?.*)?$',
+            'uploader_id': '1607',
+            'like_count': int,
+            'timestamp': 1731327327,
+            'composers': ['橘高連太郎'],
+            'view_count': int,
+            'comment_count': int,
+            'artists': ['Sunny Girl'],
+            'upload_date': '20241111',
+            'tags': ['SunnyGirl', 'シネマと信号'],
+        },
+    }, {
+        'url': 'https://eggs.mu/artist/KAMO_3pband/song/1d4bc45f-1af6-47a9-8b30-a70cae350b4f',
+        'info_dict': {
+            'id': '80cLKA2wnoA',
+            'ext': 'mp4',
+            'title': 'KAMO「いい女だから」Audio',
+            'uploader': 'KAMO',
+            'live_status': 'not_live',
+            'channel_id': 'UCsHLBw2__5Q9y55skXPotOg',
+            'channel_follower_count': int,
+            'description': 'md5:d260da711ecbec3e720293dc11401b87',
+            'availability': 'public',
+            'uploader_id': '@KAMO_band',
+            'upload_date': '20240925',
+            'thumbnail': 'https://i.ytimg.com/vi/80cLKA2wnoA/maxresdefault.jpg',
+            'comment_count': int,
+            'channel_url': 'https://www.youtube.com/channel/UCsHLBw2__5Q9y55skXPotOg',
+            'view_count': int,
+            'duration': 151,
+            'like_count': int,
+            'channel': 'KAMO',
+            'playable_in_embed': True,
+            'uploader_url': 'https://www.youtube.com/@KAMO_band',
+            'tags': [],
+            'timestamp': 1727271121,
+            'age_limit': 0,
+            'categories': ['People & Blogs'],
+        },
+        'add_ie': ['Youtube'],
+        'params': {'skip_download': 'Youtube'},
+    }]
+
+    def _real_extract(self, url):
+        song_id = self._match_id(url)
+        json_data = self._call_api(f'musics/{song_id}', song_id)
+        return self._extract_music_info(json_data)
+
+
+class EggsArtistIE(EggsBaseIE):
+    IE_NAME = 'eggs:artist'
+    _VALID_URL = r'https?://eggs\.mu/artist/(?P<id>\w+)/?(?:[?#&]|$)'
+
+    _TESTS = [{
+        'url': 'https://eggs.mu/artist/32_sunny_girl',
+        'info_dict': {
+            'id': '32_sunny_girl',
+            'thumbnail': 'https://image-pro.eggs.mu/profile/1607.jpeg?updated_at=2024-04-03T20%3A06%3A00%2B09%3A00',
+            'description': 'Muddy Mine / 東京高田馬場CLUB PHASE / Gt.Vo 橘高 連太郎 / Ba.Cho 小野 ゆうき / Dr 大森 りゅうひこ',
+            'title': 'Sunny Girl',
+        },
+        'playlist_mincount': 18,
+    }, {
+        'url': 'https://eggs.mu/artist/KAMO_3pband',
+        'info_dict': {
+            'id': 'KAMO_3pband',
+            'description': '川崎発３ピースバンド',
+            'thumbnail': 'https://image-pro.eggs.mu/profile/35217.jpeg?updated_at=2024-11-27T16%3A31%3A50%2B09%3A00',
+            'title': 'KAMO',
+        },
+        'playlist_mincount': 2,
+    }]
+
+    def _real_extract(self, url):
+        artist_id = self._match_id(url)
+        artist_data = self._call_api(f'artists/{artist_id}', artist_id)
+        song_data = self._call_api(f'artists/{artist_id}/musics', artist_id)
+        return self.playlist_result(
+            traverse_obj(song_data, ('data', ..., {dict}, {self._extract_music_info})),
+            playlist_id=artist_id, **traverse_obj(artist_data, {
+                'title': ('displayName', {str}),
+                'description': ('profile', {str}),
+                'thumbnail': ('imageDataPath', {url_or_none}),
+            }))

yt_dlp/extractor/lbry.py

@@ -310,7 +310,13 @@ def _real_extract(self, url):
         if stream_type in self._SUPPORTED_STREAM_TYPES:
             claim_id, is_live = result['claim_id'], False
             streaming_url = self._call_api_proxy(
-                'get', claim_id, {'uri': uri}, 'streaming url')['streaming_url']
+                'get', claim_id, {
+                    'uri': uri,
+                    **traverse_obj(parse_qs(url), {
+                        'signature': ('signature', 0),
+                        'signature_ts': ('signature_ts', 0),
+                    }),
+                }, 'streaming url')['streaming_url']
 
             # GET request to v3 API returns original video/audio file if available
             direct_url = re.sub(r'/api/v\d+/', '/api/v3/', streaming_url)

yt_dlp/extractor/nest.py

@@ -0,0 +1,117 @@
+from .common import InfoExtractor
+from ..utils import ExtractorError, float_or_none, update_url_query, url_or_none
+from ..utils.traversal import traverse_obj
+
+
+class NestIE(InfoExtractor):
+    _VALID_URL = r'https?://video\.nest\.com/(?:embedded/)?live/(?P<id>\w+)'
+    _EMBED_REGEX = [rf'<iframe [^>]*\bsrc=[\'"](?P<url>{_VALID_URL})']
+    _TESTS = [{
+        'url': 'https://video.nest.com/embedded/live/4fvYdSo8AX?autoplay=0',
+        'info_dict': {
+            'id': '4fvYdSo8AX',
+            'ext': 'mp4',
+            'title': 'startswith:Outside ',
+            'alt_title': 'Outside',
+            'description': '<null>',
+            'location': 'Los Angeles',
+            'availability': 'public',
+            'thumbnail': r're:https?://',
+            'live_status': 'is_live',
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
+    }, {
+        'url': 'https://video.nest.com/live/4fvYdSo8AX',
+        'only_matching': True,
+    }]
+    _WEBPAGE_TESTS = [{
+        'url': 'https://www.pacificblue.biz/noyo-harbor-webcam/',
+        'info_dict': {
+            'id': '4fvYdSo8AX',
+            'ext': 'mp4',
+            'title': 'startswith:Outside ',
+            'alt_title': 'Outside',
+            'description': '<null>',
+            'location': 'Los Angeles',
+            'availability': 'public',
+            'thumbnail': r're:https?://',
+            'live_status': 'is_live',
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        item = self._download_json(
+            'https://video.nest.com/api/dropcam/cameras.get_by_public_token',
+            video_id, query={'token': video_id})['items'][0]
+        uuid = item.get('uuid')
+        stream_domain = item.get('live_stream_host')
+        if not stream_domain or not uuid:
+            raise ExtractorError('Unable to construct playlist URL')
+
+        thumb_domain = item.get('nexus_api_nest_domain_host')
+        return {
+            'id': video_id,
+            **traverse_obj(item, {
+                'description': ('description', {str}),
+                'title': (('title', 'name', 'where'), {str}, filter, any),
+                'alt_title': ('name', {str}),
+                'location': ((('timezone', {lambda x: x.split('/')[1].replace('_', ' ')}), 'where'), {str}, filter, any),
+            }),
+            'thumbnail': update_url_query(
+                f'https://{thumb_domain}/get_image',
+                {'uuid': uuid, 'public': video_id}) if thumb_domain else None,
+            'availability': self._availability(is_private=item.get('is_public') is False),
+            'formats': self._extract_m3u8_formats(
+                f'https://{stream_domain}/nexus_aac/{uuid}/playlist.m3u8',
+                video_id, 'mp4', live=True, query={'public': video_id}),
+            'is_live': True,
+        }
+
+
+class NestClipIE(InfoExtractor):
+    _VALID_URL = r'https?://video\.nest\.com/(?:embedded/)?clip/(?P<id>\w+)'
+    _EMBED_REGEX = [rf'<iframe [^>]*\bsrc=[\'"](?P<url>{_VALID_URL})']
+    _TESTS = [{
+        'url': 'https://video.nest.com/clip/f34c9dd237a44eca9a0001af685e3dff',
+        'info_dict': {
+            'id': 'f34c9dd237a44eca9a0001af685e3dff',
+            'ext': 'mp4',
+            'title': 'NestClip video #f34c9dd237a44eca9a0001af685e3dff',
+            'thumbnail': 'https://clips.dropcam.com/f34c9dd237a44eca9a0001af685e3dff.jpg',
+            'timestamp': 1735413474.468,
+            'upload_date': '20241228',
+        },
+    }, {
+        'url': 'https://video.nest.com/embedded/clip/34e0432adc3c46a98529443d8ad5aa76',
+        'info_dict': {
+            'id': '34e0432adc3c46a98529443d8ad5aa76',
+            'ext': 'mp4',
+            'title': 'Shootout at Veterans Boulevard at Fleur De Lis Drive',
+            'thumbnail': 'https://clips.dropcam.com/34e0432adc3c46a98529443d8ad5aa76.jpg',
+            'upload_date': '20230817',
+            'timestamp': 1692262897.191,
+        },
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        data = self._download_json(
+            'https://video.nest.com/api/dropcam/videos.get_by_filename', video_id,
+            query={'filename': f'{video_id}.mp4'})
+        return {
+            'id': video_id,
+            **traverse_obj(data, ('items', 0, {
+                'title': ('title', {str}),
+                'thumbnail': ('thumbnail_url', {url_or_none}),
+                'url': ('download_url', {url_or_none}),
+                'timestamp': ('start_time', {float_or_none}),
+            })),
+        }

yt_dlp/extractor/nrk.py

@@ -12,6 +12,7 @@
     parse_iso8601,
     str_or_none,
     try_get,
+    update_url_query,
     url_or_none,
     urljoin,
 )
@@ -171,6 +172,8 @@ def call_playback_api(item, query=None):
             format_url = url_or_none(asset.get('url'))
             if not format_url:
                 continue
+            # Remove the 'adap' query parameter
+            format_url = update_url_query(format_url, {'adap': []})
             asset_format = (asset.get('format') or '').lower()
             if asset_format == 'hls' or determine_ext(format_url) == 'm3u8':
                 formats.extend(self._extract_nrk_formats(format_url, video_id))

yt_dlp/extractor/piramidetv.py

@@ -0,0 +1,99 @@
+from .common import InfoExtractor
+from ..utils import parse_iso8601, smuggle_url, unsmuggle_url, url_or_none
+from ..utils.traversal import traverse_obj
+
+
+class PiramideTVIE(InfoExtractor):
+    _VALID_URL = r'https?://piramide\.tv/video/(?P<id>[\w-]+)'
+    _TESTS = [{
+        'url': 'https://piramide.tv/video/wWtBAORdJUTh',
+        'info_dict': {
+            'id': 'wWtBAORdJUTh',
+            'ext': 'mp4',
+            'title': 'md5:79f9c8183ea6a35c836923142cf0abcc',
+            'description': '',
+            'thumbnail': 'https://cdn.jwplayer.com/v2/media/W86PgQDn/thumbnails/B9gpIxkH.jpg',
+            'channel': 'León Picarón',
+            'channel_id': 'leonpicaron',
+            'timestamp': 1696460362,
+            'upload_date': '20231004',
+        },
+    }, {
+        'url': 'https://piramide.tv/video/wcYn6li79NgN',
+        'info_dict': {
+            'id': 'wcYn6li79NgN',
+            'ext': 'mp4',
+            'title': 'ACEPTO TENER UN BEBE CON MI NOVIA\u2026? | Parte 1',
+            'description': '',
+            'channel': 'ARTA GAME',
+            'channel_id': 'arta_game',
+            'thumbnail': 'https://cdn.jwplayer.com/v2/media/cnEdGp5X/thumbnails/rHAaWfP7.jpg',
+            'timestamp': 1703434976,
+            'upload_date': '20231224',
+        },
+    }]
+
+    def _extract_video(self, video_id):
+        video_data = self._download_json(
+            f'https://hermes.piramide.tv/video/data/{video_id}', video_id, fatal=False)
+        formats, subtitles = self._extract_m3u8_formats_and_subtitles(
+            f'https://cdn.piramide.tv/video/{video_id}/manifest.m3u8', video_id, fatal=False)
+        next_video = traverse_obj(video_data, ('video', 'next_video', 'id', {str}))
+        return next_video, {
+            'id': video_id,
+            'formats': formats,
+            'subtitles': subtitles,
+            **traverse_obj(video_data, ('video', {
+                'id': ('id', {str}),
+                'title': ('title', {str}),
+                'description': ('description', {str}),
+                'thumbnail': ('media', 'thumbnail', {url_or_none}),
+                'channel': ('channel', 'name', {str}),
+                'channel_id': ('channel', 'id', {str}),
+                'timestamp': ('date', {parse_iso8601}),
+            })),
+        }
+
+    def _entries(self, video_id):
+        visited = set()
+        while True:
+            visited.add(video_id)
+            next_video, info = self._extract_video(video_id)
+            yield info
+            if not next_video or next_video in visited:
+                break
+            video_id = next_video
+
+    def _real_extract(self, url):
+        url, smuggled_data = unsmuggle_url(url, {})
+        video_id = self._match_id(url)
+        if self._yes_playlist(video_id, video_id, smuggled_data):
+            return self.playlist_result(self._entries(video_id), video_id)
+        return self._extract_video(video_id)[1]
+
+
+class PiramideTVChannelIE(InfoExtractor):
+    _VALID_URL = r'https?://piramide\.tv/channel/(?P<id>[\w-]+)'
+    _TESTS = [{
+        'url': 'https://piramide.tv/channel/thekalo',
+        'playlist_mincount': 10,
+        'info_dict': {
+            'id': 'thekalo',
+        },
+    }]
+
+    def _entries(self, channel_name):
+        videos = self._download_json(
+            f'https://hermes.piramide.tv/channel/list/{channel_name}/date/100000', channel_name)
+        for video in traverse_obj(videos, ('videos', lambda _, v: v['id'])):
+            yield self.url_result(smuggle_url(
+                f'https://piramide.tv/video/{video["id"]}', {'force_noplaylist': True}),
+                **traverse_obj(video, {
+                    'id': ('id', {str}),
+                    'title': ('title', {str}),
+                    'description': ('description', {str}),
+                }))
+
+    def _real_extract(self, url):
+        channel_name = self._match_id(url)
+        return self.playlist_result(self._entries(channel_name), channel_name)

yt_dlp/extractor/rtvslo.py

@@ -176,6 +176,8 @@ class RTVSLOShowIE(InfoExtractor):
         'info_dict': {
             'id': '173250997',
             'title': 'Ekipa Bled',
+            'description': 'md5:c88471e27a1268c448747a5325319ab7',
+            'thumbnail': 'https://img.rtvcdn.si/_up/ava/ava_misc/show_logos/173250997/logo_wide1.jpg',
         },
         'playlist_count': 18,
     }]
@@ -187,4 +189,7 @@ def _real_extract(self, url):
         return self.playlist_from_matches(
             re.findall(r'<a [^>]*\bhref="(/arhiv/[^"]+)"', webpage),
             playlist_id, self._html_extract_title(webpage),
-            getter=urljoin('https://365.rtvslo.si'), ie=RTVSLOIE)
+            getter=urljoin('https://365.rtvslo.si'), ie=RTVSLOIE,
+            description=self._og_search_description(webpage),
+            thumbnail=self._og_search_thumbnail(webpage),
+        )

yt_dlp/extractor/senategov.py

@@ -4,43 +4,12 @@
 from .common import InfoExtractor
 from ..utils import (
     ExtractorError,
-    parse_qs,
+    UnsupportedError,
-    unsmuggle_url,
+    make_archive_id,
+    remove_end,
+    url_or_none,
 )
-
+from ..utils.traversal import traverse_obj
-_COMMITTEES = {
-    'ag': ('76440', 'http://ag-f.akamaihd.net'),
-    'aging': ('76442', 'http://aging-f.akamaihd.net'),
-    'approps': ('76441', 'http://approps-f.akamaihd.net'),
-    'arch': ('', 'http://ussenate-f.akamaihd.net'),
-    'armed': ('76445', 'http://armed-f.akamaihd.net'),
-    'banking': ('76446', 'http://banking-f.akamaihd.net'),
-    'budget': ('76447', 'http://budget-f.akamaihd.net'),
-    'cecc': ('76486', 'http://srs-f.akamaihd.net'),
-    'commerce': ('80177', 'http://commerce1-f.akamaihd.net'),
-    'csce': ('75229', 'http://srs-f.akamaihd.net'),
-    'dpc': ('76590', 'http://dpc-f.akamaihd.net'),
-    'energy': ('76448', 'http://energy-f.akamaihd.net'),
-    'epw': ('76478', 'http://epw-f.akamaihd.net'),
-    'ethics': ('76449', 'http://ethics-f.akamaihd.net'),
-    'finance': ('76450', 'http://finance-f.akamaihd.net'),
-    'foreign': ('76451', 'http://foreign-f.akamaihd.net'),
-    'govtaff': ('76453', 'http://govtaff-f.akamaihd.net'),
-    'help': ('76452', 'http://help-f.akamaihd.net'),
-    'indian': ('76455', 'http://indian-f.akamaihd.net'),
-    'intel': ('76456', 'http://intel-f.akamaihd.net'),
-    'intlnarc': ('76457', 'http://intlnarc-f.akamaihd.net'),
-    'jccic': ('85180', 'http://jccic-f.akamaihd.net'),
-    'jec': ('76458', 'http://jec-f.akamaihd.net'),
-    'judiciary': ('76459', 'http://judiciary-f.akamaihd.net'),
-    'rpc': ('76591', 'http://rpc-f.akamaihd.net'),
-    'rules': ('76460', 'http://rules-f.akamaihd.net'),
-    'saa': ('76489', 'http://srs-f.akamaihd.net'),
-    'smbiz': ('76461', 'http://smbiz-f.akamaihd.net'),
-    'srs': ('75229', 'http://srs-f.akamaihd.net'),
-    'uscc': ('76487', 'http://srs-f.akamaihd.net'),
-    'vetaff': ('76462', 'http://vetaff-f.akamaihd.net'),
-}
 
 
 class SenateISVPIE(InfoExtractor):
@@ -53,31 +22,46 @@ class SenateISVPIE(InfoExtractor):
         'info_dict': {
             'id': 'judiciary031715',
             'ext': 'mp4',
-            'title': 'Integrated Senate Video Player',
+            'title': 'ISVP',
             'thumbnail': r're:^https?://.*\.(?:jpg|png)$',
+            '_old_archive_ids': ['senategov judiciary031715'],
         },
         'params': {
             # m3u8 download
             'skip_download': True,
         },
+        'expected_warnings': ['Failed to download m3u8 information'],
     }, {
         'url': 'http://www.senate.gov/isvp/?type=live&comm=commerce&filename=commerce011514.mp4&auto_play=false',
         'info_dict': {
             'id': 'commerce011514',
             'ext': 'mp4',
             'title': 'Integrated Senate Video Player',
+            '_old_archive_ids': ['senategov commerce011514'],
         },
         'params': {
             # m3u8 download
             'skip_download': True,
         },
+        'skip': 'This video is not available.',
     }, {
         'url': 'http://www.senate.gov/isvp/?type=arch&comm=intel&filename=intel090613&hc_location=ufi',
         # checksum differs each time
         'info_dict': {
             'id': 'intel090613',
             'ext': 'mp4',
-            'title': 'Integrated Senate Video Player',
+            'title': 'ISVP',
+            '_old_archive_ids': ['senategov intel090613'],
+        },
+        'expected_warnings': ['Failed to download m3u8 information'],
+    }, {
+        'url': 'https://www.senate.gov/isvp/?auto_play=false&comm=help&filename=help090920&poster=https://www.help.senate.gov/assets/images/video-poster.png&stt=950',
+        'info_dict': {
+            'id': 'help090920',
+            'ext': 'mp4',
+            'title': 'ISVP',
+            'thumbnail': 'https://www.help.senate.gov/assets/images/video-poster.png',
+            '_old_archive_ids': ['senategov help090920'],
         },
     }, {
         # From http://www.c-span.org/video/?96791-1
@@ -85,60 +69,81 @@ class SenateISVPIE(InfoExtractor):
         'only_matching': True,
     }]
 
+    _COMMITTEES = {
+        'ag': ('76440', 'https://ag-f.akamaihd.net', '2036803', 'agriculture'),
+        'aging': ('76442', 'https://aging-f.akamaihd.net', '2036801', 'aging'),
+        'approps': ('76441', 'https://approps-f.akamaihd.net', '2036802', 'appropriations'),
+        'arch': ('', 'https://ussenate-f.akamaihd.net', '', 'arch'),
+        'armed': ('76445', 'https://armed-f.akamaihd.net', '2036800', 'armedservices'),
+        'banking': ('76446', 'https://banking-f.akamaihd.net', '2036799', 'banking'),
+        'budget': ('76447', 'https://budget-f.akamaihd.net', '2036798', 'budget'),
+        'cecc': ('76486', 'https://srs-f.akamaihd.net', '2036782', 'srs_cecc'),
+        'commerce': ('80177', 'https://commerce1-f.akamaihd.net', '2036779', 'commerce'),
+        'csce': ('75229', 'https://srs-f.akamaihd.net', '2036777', 'srs_srs'),
+        'dpc': ('76590', 'https://dpc-f.akamaihd.net', '', 'dpc'),
+        'energy': ('76448', 'https://energy-f.akamaihd.net', '2036797', 'energy'),
+        'epw': ('76478', 'https://epw-f.akamaihd.net', '2036783', 'environment'),
+        'ethics': ('76449', 'https://ethics-f.akamaihd.net', '2036796', 'ethics'),
+        'finance': ('76450', 'https://finance-f.akamaihd.net', '2036795', 'finance_finance'),
+        'foreign': ('76451', 'https://foreign-f.akamaihd.net', '2036794', 'foreignrelations'),
+        'govtaff': ('76453', 'https://govtaff-f.akamaihd.net', '2036792', 'hsgac'),
+        'help': ('76452', 'https://help-f.akamaihd.net', '2036793', 'help'),
+        'indian': ('76455', 'https://indian-f.akamaihd.net', '2036791', 'indianaffairs'),
+        'intel': ('76456', 'https://intel-f.akamaihd.net', '2036790', 'intelligence'),
+        'intlnarc': ('76457', 'https://intlnarc-f.akamaihd.net', '', 'internationalnarcoticscaucus'),
+        'jccic': ('85180', 'https://jccic-f.akamaihd.net', '2036778', 'jccic'),
+        'jec': ('76458', 'https://jec-f.akamaihd.net', '2036789', 'jointeconomic'),
+        'judiciary': ('76459', 'https://judiciary-f.akamaihd.net', '2036788', 'judiciary'),
+        'rpc': ('76591', 'https://rpc-f.akamaihd.net', '', 'rpc'),
+        'rules': ('76460', 'https://rules-f.akamaihd.net', '2036787', 'rules'),
+        'saa': ('76489', 'https://srs-f.akamaihd.net', '2036780', 'srs_saa'),
+        'smbiz': ('76461', 'https://smbiz-f.akamaihd.net', '2036786', 'smallbusiness'),
+        'srs': ('75229', 'https://srs-f.akamaihd.net', '2031966', 'srs_srs'),
+        'uscc': ('76487', 'https://srs-f.akamaihd.net', '2036781', 'srs_uscc'),
+        'vetaff': ('76462', 'https://vetaff-f.akamaihd.net', '2036785', 'veteransaffairs'),
+    }
+
     def _real_extract(self, url):
-        url, smuggled_data = unsmuggle_url(url, {})
-
         qs = urllib.parse.parse_qs(self._match_valid_url(url).group('qs'))
-        if not qs.get('filename') or not qs.get('type') or not qs.get('comm'):
+        if not qs.get('filename') or not qs.get('comm'):
             raise ExtractorError('Invalid URL', expected=True)
-
+        filename = qs['filename'][0]
-        video_id = re.sub(r'.mp4$', '', qs['filename'][0])
+        video_id = remove_end(filename, '.mp4')
 
         webpage = self._download_webpage(url, video_id)
+        committee = qs['comm'][0]
 
-        if smuggled_data.get('force_title'):
+        stream_num, stream_domain, stream_id, msl3 = self._COMMITTEES[committee]
-            title = smuggled_data['force_title']
-        else:
-            title = self._html_extract_title(webpage)
-        poster = qs.get('poster')
-        thumbnail = poster[0] if poster else None
-
-        video_type = qs['type'][0]
-        committee = video_type if video_type == 'arch' else qs['comm'][0]
-
-        stream_num, domain = _COMMITTEES[committee]
 
+        urls_alternatives = [f'https://www-senate-gov-media-srs.akamaized.net/hls/live/{stream_id}/{committee}/{filename}/master.m3u8',
+                             f'https://www-senate-gov-msl3archive.akamaized.net/{msl3}/{filename}_1/master.m3u8',
+                             f'{stream_domain}/i/{filename}_1@{stream_num}/master.m3u8',
+                             f'{stream_domain}/i/{filename}.mp4/master.m3u8']
         formats = []
-        if video_type == 'arch':
+        subtitles = {}
-            filename = video_id if '.' in video_id else video_id + '.mp4'
+        for video_url in urls_alternatives:
-            m3u8_url = urllib.parse.urljoin(domain, 'i/' + filename + '/master.m3u8')
+            formats, subtitles = self._extract_m3u8_formats_and_subtitles(video_url, video_id, ext='mp4', fatal=False)
-            formats = self._extract_m3u8_formats(m3u8_url, video_id, ext='mp4', m3u8_id='m3u8')
+            if formats:
-        else:
+                break
-            hdcore_sign = 'hdcore=3.1.0'
-            url_params = (domain, video_id, stream_num)
-            f4m_url = f'%s/z/%s_1@%s/manifest.f4m?{hdcore_sign}' % url_params
-            m3u8_url = '{}/i/{}_1@{}/master.m3u8'.format(*url_params)
-            for entry in self._extract_f4m_formats(f4m_url, video_id, f4m_id='f4m'):
-                # URLs without the extra param induce an 404 error
-                entry.update({'extra_param_to_segment_url': hdcore_sign})
-                formats.append(entry)
-            for entry in self._extract_m3u8_formats(m3u8_url, video_id, ext='mp4', m3u8_id='m3u8'):
-                mobj = re.search(r'(?P<tag>(?:-p|-b)).m3u8', entry['url'])
-                if mobj:
-                    entry['format_id'] += mobj.group('tag')
-                formats.append(entry)
 
         return {
             'id': video_id,
-            'title': title,
+            'title': self._html_extract_title(webpage),
             'formats': formats,
-            'thumbnail': thumbnail,
+            'subtitles': subtitles,
+            'thumbnail': traverse_obj(qs, ('poster', 0, {url_or_none})),
+            '_old_archive_ids': [make_archive_id(SenateGovIE, video_id)],
         }
 
 
 class SenateGovIE(InfoExtractor):
     _IE_NAME = 'senate.gov'
-    _VALID_URL = r'https?:\/\/(?:www\.)?(help|appropriations|judiciary|banking|armed-services|finance)\.senate\.gov'
+    _SUBDOMAIN_RE = '|'.join(map(re.escape, (
+        'agriculture', 'aging', 'appropriations', 'armed-services', 'banking',
+        'budget', 'commerce', 'energy', 'epw', 'finance', 'foreign', 'help',
+        'intelligence', 'inaugural', 'judiciary', 'rules', 'sbc', 'veterans',
+    )))
+    _VALID_URL = rf'https?://(?:www\.)?(?:{_SUBDOMAIN_RE})\.senate\.gov'
     _TESTS = [{
         'url': 'https://www.help.senate.gov/hearings/vaccines-saving-lives-ensuring-confidence-and-protecting-public-health',
         'info_dict': {
@@ -147,6 +152,9 @@ class SenateGovIE(InfoExtractor):
             'title': 'Vaccines: Saving Lives, Ensuring Confidence, and Protecting Public Health',
             'description': 'The U.S. Senate Committee on Health, Education, Labor & Pensions',
             'ext': 'mp4',
+            'age_limit': 0,
+            'thumbnail': 'https://www.help.senate.gov/assets/images/sharelogo.jpg',
+            '_old_archive_ids': ['senategov help090920'],
         },
         'params': {'skip_download': 'm3u8'},
     }, {
@@ -156,8 +164,12 @@ class SenateGovIE(InfoExtractor):
             'display_id': 'watch?hearingid=B8A25434-5056-A066-6020-1F68CB75F0CD',
             'title': 'Review of the FY2019 Budget Request for the U.S. Army',
             'ext': 'mp4',
+            'age_limit': 0,
+            'thumbnail': 'https://www.appropriations.senate.gov/themes/appropriations/images/video-poster-flash-fit.png',
+            '_old_archive_ids': ['senategov appropsA051518'],
         },
         'params': {'skip_download': 'm3u8'},
+        'expected_warnings': ['Failed to download m3u8 information'],
     }, {
         'url': 'https://www.banking.senate.gov/hearings/21st-century-communities-public-transportation-infrastructure-investment-and-fast-act-reauthorization',
         'info_dict': {
@@ -166,32 +178,65 @@ class SenateGovIE(InfoExtractor):
             'title': '21st Century Communities: Public Transportation Infrastructure Investment and FAST Act Reauthorization',
             'description': 'The Official website of The United States Committee on Banking, Housing, and Urban Affairs',
             'ext': 'mp4',
+            'thumbnail': 'https://www.banking.senate.gov/themes/banking/images/sharelogo.jpg',
+            'age_limit': 0,
+            '_old_archive_ids': ['senategov banking041521'],
         },
         'params': {'skip_download': 'm3u8'},
+    }, {
+        'url': 'https://www.agriculture.senate.gov/hearings/hemp-production-and-the-2018-farm-bill',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.aging.senate.gov/hearings/the-older-americans-act-the-local-impact-of-the-law-and-the-upcoming-reauthorization',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.budget.senate.gov/hearings/improving-care-lowering-costs-achieving-health-care-efficiency',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.commerce.senate.gov/2024/12/communications-networks-safety-and-security',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.energy.senate.gov/hearings/2024/2/full-committee-hearing-to-examine',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.epw.senate.gov/public/index.cfm/hearings?ID=F63083EA-2C13-498C-B548-341BED68C209',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.foreign.senate.gov/hearings/american-diplomacy-and-global-leadership-review-of-the-fy25-state-department-budget-request',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.intelligence.senate.gov/hearings/foreign-threats-elections-2024-%E2%80%93-roles-and-responsibilities-us-tech-providers',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.inaugural.senate.gov/52nd-inaugural-ceremonies/',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.rules.senate.gov/hearings/02/07/2023/business-meeting',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.sbc.senate.gov/public/index.cfm/hearings?ID=5B13AA6B-8279-45AF-B54B-94156DC7A2AB',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.veterans.senate.gov/2024/5/frontier-health-care-ensuring-veterans-access-no-matter-where-they-live',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
         display_id = self._generic_id(url)
         webpage = self._download_webpage(url, display_id)
-        parse_info = parse_qs(self._search_regex(
+        url_info = next(SenateISVPIE.extract_from_webpage(self._downloader, url, webpage), None)
-            r'<iframe class="[^>"]*streaminghearing[^>"]*"\s[^>]*\bsrc="([^">]*)', webpage, 'hearing URL'))
+        if not url_info:
-
+            raise UnsupportedError(url)
-        stream_num, stream_domain = _COMMITTEES[parse_info['comm'][-1]]
-        filename = parse_info['filename'][-1]
-
-        formats = self._extract_m3u8_formats(
-            f'{stream_domain}/i/{filename}_1@{stream_num}/master.m3u8',
-            display_id, ext='mp4')
 
         title = self._html_search_regex(
-            (*self._og_regexes('title'), r'(?s)<title>([^<]*?)</title>'), webpage, 'video title')
+            (*self._og_regexes('title'), r'(?s)<title>([^<]*?)</title>'), webpage, 'video title', fatal=False)
 
         return {
-            'id': re.sub(r'.mp4$', '', filename),
+            **url_info,
+            '_type': 'url_transparent',
             'display_id': display_id,
             'title': re.sub(r'\s+', ' ', title.split('|')[0]).strip(),
             'description': self._og_search_description(webpage, default=None),
             'thumbnail': self._og_search_thumbnail(webpage, default=None),
             'age_limit': self._rta_search(webpage),
-            'formats': formats,
         }

yt_dlp/extractor/weibo.py

@@ -124,7 +124,7 @@ def _parse_video_info(self, video_info, video_id=None):
 
 
 class WeiboIE(WeiboBaseIE):
-    _VALID_URL = r'https?://(?:m\.weibo\.cn/status|(?:www\.)?weibo\.com/\d+)/(?P<id>[a-zA-Z0-9]+)'
+    _VALID_URL = r'https?://(?:m\.weibo\.cn/(?:status|detail)|(?:www\.)?weibo\.com/\d+)/(?P<id>[a-zA-Z0-9]+)'
     _TESTS = [{
         'url': 'https://weibo.com/7827771738/N4xlMvjhI',
         'info_dict': {
@@ -164,6 +164,25 @@ class WeiboIE(WeiboBaseIE):
             'like_count': int,
             'repost_count': int,
         },
+    }, {
+        'url': 'https://m.weibo.cn/detail/4189191225395228',
+        'info_dict': {
+            'id': '4189191225395228',
+            'ext': 'mp4',
+            'display_id': 'FBqgOmDxO',
+            'title': '柴犬柴犬的秒拍视频',
+            'description': '午睡当然是要甜甜蜜蜜的啦！[坏笑]     Instagram：shibainu.gaku http://t.cn/RHbmjzW ',
+            'duration': 53,
+            'timestamp': 1514264429,
+            'upload_date': '20171226',
+            'thumbnail': r're:https://.*\.jpg',
+            'uploader': '柴犬柴犬',
+            'uploader_id': '5926682210',
+            'uploader_url': 'https://weibo.com/u/5926682210',
+            'view_count': int,
+            'like_count': int,
+            'repost_count': int,
+        },
     }, {
         'url': 'https://weibo.com/0/4224132150961381',
         'note': 'no playback_list example',

yt_dlp/extractor/xiaohongshu.py

@@ -5,6 +5,7 @@
     int_or_none,
     js_to_json,
     url_or_none,
+    urlhandle_detect_ext,
 )
 from ..utils.traversal import traverse_obj
 
@@ -46,7 +47,7 @@ def _real_extract(self, url):
             r'window\.__INITIAL_STATE__\s*=', webpage, 'initial state', display_id, transform_source=js_to_json)
 
         note_info = traverse_obj(initial_state, ('note', 'noteDetailMap', display_id, 'note'))
-        video_info = traverse_obj(note_info, ('video', 'media', 'stream', ('h264', 'av1', 'h265'), ...))
+        video_info = traverse_obj(note_info, ('video', 'media', 'stream', ..., ...))
 
         formats = []
         for info in video_info:
@@ -56,18 +57,32 @@ def _real_extract(self, url):
                 'height': ('height', {int_or_none}),
                 'vcodec': ('videoCodec', {str}),
                 'acodec': ('audioCodec', {str}),
-                'abr': ('audioBitrate', {int_or_none}),
+                'abr': ('audioBitrate', {int_or_none(scale=1000)}),
-                'vbr': ('videoBitrate', {int_or_none}),
+                'vbr': ('videoBitrate', {int_or_none(scale=1000)}),
                 'audio_channels': ('audioChannels', {int_or_none}),
-                'tbr': ('avgBitrate', {int_or_none}),
+                'tbr': ('avgBitrate', {int_or_none(scale=1000)}),
                 'format': ('qualityType', {str}),
                 'filesize': ('size', {int_or_none}),
                 'duration': ('duration', {float_or_none(scale=1000)}),
             })
 
-            formats.extend(traverse_obj(info, (('mediaUrl', ('backupUrls', ...)), {
+            formats.extend(traverse_obj(info, (('masterUrl', ('backupUrls', ...)), {
                 lambda u: url_or_none(u) and {'url': u, **format_info}})))
 
+        if origin_key := traverse_obj(note_info, ('video', 'consumer', 'originVideoKey', {str})):
+            # Not using a head request because of false negatives
+            urlh = self._request_webpage(
+                f'https://sns-video-bd.xhscdn.com/{origin_key}', display_id,
+                'Checking original video availability', 'Original video is not available', fatal=False)
+            if urlh:
+                formats.append({
+                    'format_id': 'direct',
+                    'ext': urlhandle_detect_ext(urlh, default='mp4'),
+                    'filesize': int_or_none(urlh.get_header('Content-Length')),
+                    'url': urlh.url,
+                    'quality': 1,
+                })
+
         thumbnails = []
         for image_info in traverse_obj(note_info, ('imageList', ...)):
             thumbnail_info = traverse_obj(image_info, {