test/test_utils.py

@@ -1835,6 +1835,8 @@ def test_iri_to_uri(self):
     def test_clean_podcast_url(self):
         self.assertEqual(clean_podcast_url('https://www.podtrac.com/pts/redirect.mp3/chtbl.com/track/5899E/traffic.megaphone.fm/HSW7835899191.mp3'), 'https://traffic.megaphone.fm/HSW7835899191.mp3')
         self.assertEqual(clean_podcast_url('https://play.podtrac.com/npr-344098539/edge1.pod.npr.org/anon.npr-podcasts/podcast/npr/waitwait/2020/10/20201003_waitwait_wwdtmpodcast201003-015621a5-f035-4eca-a9a1-7c118d90bc3c.mp3'), 'https://edge1.pod.npr.org/anon.npr-podcasts/podcast/npr/waitwait/2020/10/20201003_waitwait_wwdtmpodcast201003-015621a5-f035-4eca-a9a1-7c118d90bc3c.mp3')
+        self.assertEqual(clean_podcast_url('https://pdst.fm/e/2.gum.fm/chtbl.com/track/chrt.fm/track/34D33/pscrb.fm/rss/p/traffic.megaphone.fm/ITLLC7765286967.mp3?updated=1687282661'), 'https://traffic.megaphone.fm/ITLLC7765286967.mp3?updated=1687282661')
+        self.assertEqual(clean_podcast_url('https://pdst.fm/e/https://mgln.ai/e/441/www.buzzsprout.com/1121972/13019085-ep-252-the-deep-life-stack.mp3'), 'https://www.buzzsprout.com/1121972/13019085-ep-252-the-deep-life-stack.mp3')
 
     def test_LazyList(self):
         it = list(range(10))

yt_dlp/extractor/_extractors.py

@@ -214,6 +214,7 @@
 from .bilibili import (
     BiliBiliIE,
     BiliBiliBangumiIE,
+    BiliBiliBangumiSeasonIE,
     BiliBiliBangumiMediaIE,
     BiliBiliSearchIE,
     BilibiliCategoryIE,
@@ -1870,7 +1871,6 @@
     StoryFireSeriesIE,
 )
 from .streamable import StreamableIE
-from .streamanity import StreamanityIE
 from .streamcloud import StreamcloudIE
 from .streamcz import StreamCZIE
 from .streamff import StreamFFIE

yt_dlp/extractor/bilibili.py

@@ -18,6 +18,7 @@
     float_or_none,
     format_field,
     int_or_none,
+    join_nonempty,
     make_archive_id,
     merge_dicts,
     mimetype2ext,
@@ -135,6 +136,17 @@ def _get_all_children(self, reply):
         for children in map(self._get_all_children, traverse_obj(reply, ('replies', ...))):
             yield from children
 
+    def _get_episodes_from_season(self, ss_id, url):
+        season_info = self._download_json(
+            'https://api.bilibili.com/pgc/web/season/section', ss_id,
+            note='Downloading season info', query={'season_id': ss_id},
+            headers={'Referer': url, **self.geo_verification_headers()})
+
+        for entry in traverse_obj(season_info, (
+                'result', 'main_section', 'episodes',
+                lambda _, v: url_or_none(v['share_url']) and v['id'])):
+            yield self.url_result(entry['share_url'], BiliBiliBangumiIE, f'ep{entry["id"]}')
+
 
 class BiliBiliIE(BilibiliBaseIE):
     _VALID_URL = r'https?://www\.bilibili\.com/(?:video/|festival/\w+\?(?:[^#]*&)?bvid=)[aAbB][vV](?P<id>[^/?#&]+)'
@@ -403,76 +415,93 @@ def _real_extract(self, url):
 
 
 class BiliBiliBangumiIE(BilibiliBaseIE):
-    _VALID_URL = r'(?x)https?://www\.bilibili\.com/bangumi/play/(?P<id>(?:ss|ep)\d+)'
+    _VALID_URL = r'https?://(?:www\.)?bilibili\.com/bangumi/play/(?P<id>ep\d+)'
 
     _TESTS = [{
-        'url': 'https://www.bilibili.com/bangumi/play/ss897',
+        'url': 'https://www.bilibili.com/bangumi/play/ep267851',
         'info_dict': {
-            'id': 'ss897',
+            'id': '267851',
             'ext': 'mp4',
-            'series': '神的记事本',
-            'season': '神的记事本',
-            'season_id': 897,
+            'series': '鬼灭之刃',
+            'series_id': '4358',
+            'season': '鬼灭之刃',
+            'season_id': '26801',
             'season_number': 1,
-            'episode': '你与旅行包',
-            'episode_number': 2,
-            'title': '神的记事本：第2话 你与旅行包',
-            'duration': 1428.487,
-            'timestamp': 1310809380,
-            'upload_date': '20110716',
-            'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)$',
+            'episode': '残酷',
+            'episode_id': '267851',
+            'episode_number': 1,
+            'title': '1 残酷',
+            'duration': 1425.256,
+            'timestamp': 1554566400,
+            'upload_date': '20190406',
+            'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)$'
         },
-    }, {
-        'url': 'https://www.bilibili.com/bangumi/play/ep508406',
-        'only_matching': True,
+        'skip': 'According to the copyright owner\'s request, you may only watch the video after you are premium member.'
     }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
+        episode_id = video_id[2:]
         webpage = self._download_webpage(url, video_id)
 
         if '您所在的地区无法观看本片' in webpage:
             raise GeoRestrictedError('This video is restricted')
-        elif ('开通大会员观看' in webpage and '__playinfo__' not in webpage
-                or '正在观看预览，大会员免费看全片' in webpage):
+        elif '正在观看预览，大会员免费看全片' in webpage:
             self.raise_login_required('This video is for premium members only')
 
-        play_info = self._search_json(r'window\.__playinfo__\s*=', webpage, 'play info', video_id)['data']
+        headers = {'Referer': url, **self.geo_verification_headers()}
+        play_info = self._download_json(
+            'https://api.bilibili.com/pgc/player/web/v2/playurl', video_id,
+            'Extracting episode', query={'fnval': '4048', 'ep_id': episode_id},
+            headers=headers)
+        premium_only = play_info.get('code') == -10403
+        play_info = traverse_obj(play_info, ('result', 'video_info', {dict})) or {}
+
         formats = self.extract_formats(play_info)
-        if (not formats and '成为大会员抢先看' in webpage
-                and play_info.get('durl') and not play_info.get('dash')):
+        if not formats and (premium_only or '成为大会员抢先看' in webpage or '开通大会员观看' in webpage):
             self.raise_login_required('This video is for premium members only')
 
-        initial_state = self._search_json(r'window\.__INITIAL_STATE__\s*=', webpage, 'initial state', video_id)
+        bangumi_info = self._download_json(
+            'https://api.bilibili.com/pgc/view/web/season', video_id, 'Get episode details',
+            query={'ep_id': episode_id}, headers=headers)['result']
 
-        season_id = traverse_obj(initial_state, ('mediaInfo', 'season_id'))
+        episode_number, episode_info = next((
+            (idx, ep) for idx, ep in enumerate(traverse_obj(
+                bangumi_info, ('episodes', ..., {dict})), 1)
+            if str_or_none(ep.get('id')) == episode_id), (1, {}))
+
+        season_id = bangumi_info.get('season_id')
         season_number = season_id and next((
             idx + 1 for idx, e in enumerate(
-                traverse_obj(initial_state, ('mediaInfo', 'seasons', ...)))
+                traverse_obj(bangumi_info, ('seasons', ...)))
             if e.get('season_id') == season_id
         ), None)
 
+        aid = episode_info.get('aid')
+
         return {
             'id': video_id,
             'formats': formats,
-            'title': traverse_obj(initial_state, 'h1Title'),
-            'episode': traverse_obj(initial_state, ('epInfo', 'long_title')),
-            'episode_number': int_or_none(traverse_obj(initial_state, ('epInfo', 'title'))),
-            'series': traverse_obj(initial_state, ('mediaInfo', 'series')),
-            'season': traverse_obj(initial_state, ('mediaInfo', 'season_title')),
-            'season_id': season_id,
+            **traverse_obj(bangumi_info, {
+                'series': ('series', 'series_title', {str}),
+                'series_id': ('series', 'series_id', {str_or_none}),
+                'thumbnail': ('square_cover', {url_or_none}),
+            }),
+            'title': join_nonempty('title', 'long_title', delim=' ', from_dict=episode_info),
+            'episode': episode_info.get('long_title'),
+            'episode_id': episode_id,
+            'episode_number': int_or_none(episode_info.get('title')) or episode_number,
+            'season_id': str_or_none(season_id),
             'season_number': season_number,
-            'thumbnail': traverse_obj(initial_state, ('epInfo', 'cover')),
-            'timestamp': traverse_obj(initial_state, ('epInfo', 'pub_time')),
+            'timestamp': int_or_none(episode_info.get('pub_time')),
             'duration': float_or_none(play_info.get('timelength'), scale=1000),
-            'subtitles': self.extract_subtitles(
-                video_id, initial_state, traverse_obj(initial_state, ('epInfo', 'cid'))),
-            '__post_extractor': self.extract_comments(traverse_obj(initial_state, ('epInfo', 'aid'))),
-            'http_headers': {'Referer': url, **self.geo_verification_headers()},
+            'subtitles': self.extract_subtitles(video_id, aid, episode_info.get('cid')),
+            '__post_extractor': self.extract_comments(aid),
+            'http_headers': headers,
         }
 
 
-class BiliBiliBangumiMediaIE(InfoExtractor):
+class BiliBiliBangumiMediaIE(BilibiliBaseIE):
     _VALID_URL = r'https?://www\.bilibili\.com/bangumi/media/md(?P<id>\d+)'
     _TESTS = [{
         'url': 'https://www.bilibili.com/bangumi/media/md24097891',
@@ -485,16 +514,26 @@ class BiliBiliBangumiMediaIE(InfoExtractor):
     def _real_extract(self, url):
         media_id = self._match_id(url)
         webpage = self._download_webpage(url, media_id)
+        ss_id = self._search_json(
+            r'window\.__INITIAL_STATE__\s*=', webpage, 'initial_state', media_id)['mediaInfo']['season_id']
+
+        return self.playlist_result(self._get_episodes_from_season(ss_id, url), media_id)
+
+
+class BiliBiliBangumiSeasonIE(BilibiliBaseIE):
+    _VALID_URL = r'(?x)https?://www\.bilibili\.com/bangumi/play/ss(?P<id>\d+)'
+    _TESTS = [{
+        'url': 'https://www.bilibili.com/bangumi/play/ss26801',
+        'info_dict': {
+            'id': '26801'
+        },
+        'playlist_mincount': 26
+    }]
 
-        initial_state = self._search_json(r'window\.__INITIAL_STATE__\s*=', webpage, 'initial_state', media_id)
-        episode_list = self._download_json(
-            'https://api.bilibili.com/pgc/web/season/section', media_id,
-            query={'season_id': initial_state['mediaInfo']['season_id']},
-            note='Downloading season info')['result']['main_section']['episodes']
+    def _real_extract(self, url):
+        ss_id = self._match_id(url)
 
-        return self.playlist_result((
-            self.url_result(entry['share_url'], BiliBiliBangumiIE, entry['aid'])
-            for entry in episode_list), media_id)
+        return self.playlist_result(self._get_episodes_from_season(ss_id, url), ss_id)
 
 
 class BilibiliSpaceBaseIE(InfoExtractor):

yt_dlp/extractor/streamanity.py

-from .common import InfoExtractor
-
-
-class StreamanityIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?streamanity\.com/video/(?P<id>[A-Za-z0-9]+)'
-    _TESTS = [{
-        'url': 'https://streamanity.com/video/9DFPTnuYi8f2',
-        'md5': '6ab171e8d4a02ad5dcbff6bea44cf5a1',
-        'info_dict': {
-            'id': '9DFPTnuYi8f2',
-            'ext': 'mp4',
-            'title': 'Bitcoin vs The Lighting Network',
-            'thumbnail': r're:https://res\.cloudinary\.com/.+\.png',
-            'description': '',
-            'uploader': 'Tom Bombadil (Freddy78)',
-        }
-    }, {
-        'url': 'https://streamanity.com/video/JktOUjSlfzTD',
-        'md5': '31f131e28abd3377c38be586a59532dc',
-        'info_dict': {
-            'id': 'JktOUjSlfzTD',
-            'ext': 'mp4',
-            'title': 'Share data when you see it',
-            'thumbnail': r're:https://res\.cloudinary\.com/.+\.png',
-            'description': 'Reposting as data should be public and stored on blockchain',
-            'uploader': 'digitalcurrencydaily',
-        }
-    }]
-
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-        video_info = self._download_json(
-            f'https://app.streamanity.com/api/video/{video_id}', video_id)['data']['video']
-
-        formats = self._extract_m3u8_formats(
-            f'https://stream.mux.com/{video_info["play_id"]}.m3u8?token={video_info["token"]}',
-            video_id, ext='mp4', m3u8_id='hls')
-
-        return {
-            'id': video_id,
-            'title': video_info['title'],
-            'description': video_info.get('description'),
-            'uploader': video_info.get('author_name'),
-            'is_live': False,
-            'thumbnail': video_info.get('thumb'),
-            'formats': formats,
-        }

yt_dlp/extractor/vrt.py

@@ -44,9 +44,11 @@ class VRTBaseIE(GigyaBaseIE):
             'version': '2.7.4-prod-2023-04-19T06:05:45'
         }
     }
-    # From https://player.vrt.be/vrtnws/js/main.js & https://player.vrt.be/ketnet/js/main.fd1de01a40a1e3d842ea.js
+    # From https://player.vrt.be/vrtnws/js/main.js & https://player.vrt.be/ketnet/js/main.8cdb11341bcb79e4cd44.js
     _JWT_KEY_ID = '0-0Fp51UZykfaiCJrfTE3+oMI8zvDteYfPtR+2n1R+z8w='
-    _JWT_SIGNING_KEY = '2a9251d782700769fb856da5725daf38661874ca6f80ae7dc2b05ec1a81a24ae'
+    _JWT_SIGNING_KEY = 'b5f500d55cb44715107249ccd8a5c0136cfb2788dbb71b90a4f142423bacaf38'  # -dev
+    # player-stag.vrt.be key:    d23987504521ae6fbf2716caca6700a24bb1579477b43c84e146b279de5ca595
+    # player.vrt.be key:         2a9251d782700769fb856da5725daf38661874ca6f80ae7dc2b05ec1a81a24ae
 
     def _extract_formats_and_subtitles(self, data, video_id):
         if traverse_obj(data, 'drm'):

yt_dlp/postprocessor/embedthumbnail.py

@@ -114,7 +114,7 @@ def run(self, info):
             self._report_run('ffmpeg', filename)
             self.run_ffmpeg(filename, temp_filename, options)
 
-        elif info['ext'] in ['m4a', 'mp4', 'mov']:
+        elif info['ext'] in ['m4a', 'mp4', 'm4v', 'mov']:
             prefer_atomicparsley = 'embed-thumbnail-atomicparsley' in self.get_param('compat_opts', [])
             # Method 1: Use mutagen
             if not mutagen or prefer_atomicparsley:
@@ -213,7 +213,7 @@ def run(self, info):
             temp_filename = filename
 
         else:
-            raise EmbedThumbnailPPError('Supported filetypes for thumbnail embedding are: mp3, mkv/mka, ogg/opus/flac, m4a/mp4/mov')
+            raise EmbedThumbnailPPError('Supported filetypes for thumbnail embedding are: mp3, mkv/mka, ogg/opus/flac, m4a/mp4/m4v/mov')
 
         if success and temp_filename != filename:
             os.replace(temp_filename, filename)

yt_dlp/utils/_utils.py

@@ -5123,14 +5123,18 @@ def clean_podcast_url(url):
             (?:
                 chtbl\.com/track|
                 media\.blubrry\.com| # https://create.blubrry.com/resources/podcast-media-download-statistics/getting-started/
-                play\.podtrac\.com
-            )/[^/]+|
+                play\.podtrac\.com|
+                chrt\.fm/track|
+                mgln\.ai/e
+            )(?:/[^/.]+)?|
             (?:dts|www)\.podtrac\.com/(?:pts/)?redirect\.[0-9a-z]{3,4}| # http://analytics.podtrac.com/how-to-measure
             flex\.acast\.com|
             pd(?:
                 cn\.co| # https://podcorn.com/analytics-prefix/
                 st\.fm # https://podsights.com/docs/
-            )/e
+            )/e|
+            [0-9]\.gum\.fm|
+            pscrb\.fm/rss/p
         )/''', '', url)
     return re.sub(r'^\w+://(\w+://)', r'\1', url)