Merge 8631ff86d9 into 1d253b0a27

Closes #11483
Authored by: jshumphrey, bashonly

Co-authored-by: bashonly <88596187+bashonly@users.noreply.github.com>

test/test_traversal.py

@@ -481,7 +481,7 @@ class TestTraversalHelpers:
             'id': 'name',
             'data': 'content',
             'url': 'url',
-        }, all, {subs_list_to_dict}]) == {
+        }, all, {subs_list_to_dict(lang=None)}]) == {
             'de': [{'url': 'https://example.com/subs/de.ass'}],
             'en': [{'data': 'content'}],
         }, 'subs with mandatory items missing should be filtered'
@@ -507,6 +507,54 @@ class TestTraversalHelpers:
             {'url': 'https://example.com/subs/en1', 'ext': 'ext'},
             {'url': 'https://example.com/subs/en2', 'ext': 'ext'},
         ]}, '`quality` key should sort subtitle list accordingly'
+        assert traverse_obj([
+            {'name': 'de', 'url': 'https://example.com/subs/de.ass'},
+            {'name': 'de'},
+            {'name': 'en', 'content': 'content'},
+            {'url': 'https://example.com/subs/en'},
+        ], [..., {
+            'id': 'name',
+            'url': 'url',
+            'data': 'content',
+        }, all, {subs_list_to_dict(lang='en')}]) == {
+            'de': [{'url': 'https://example.com/subs/de.ass'}],
+            'en': [
+                {'data': 'content'},
+                {'url': 'https://example.com/subs/en'},
+            ],
+        }, 'optionally provided lang should be used if no id available'
+        assert traverse_obj([
+            {'name': 1, 'url': 'https://example.com/subs/de1'},
+            {'name': {}, 'url': 'https://example.com/subs/de2'},
+            {'name': 'de', 'ext': 1, 'url': 'https://example.com/subs/de3'},
+            {'name': 'de', 'ext': {}, 'url': 'https://example.com/subs/de4'},
+        ], [..., {
+            'id': 'name',
+            'url': 'url',
+            'ext': 'ext',
+        }, all, {subs_list_to_dict(lang=None)}]) == {
+            'de': [
+                {'url': 'https://example.com/subs/de3'},
+                {'url': 'https://example.com/subs/de4'},
+            ],
+        }, 'non str types should be ignored for id and ext'
+        assert traverse_obj([
+            {'name': 1, 'url': 'https://example.com/subs/de1'},
+            {'name': {}, 'url': 'https://example.com/subs/de2'},
+            {'name': 'de', 'ext': 1, 'url': 'https://example.com/subs/de3'},
+            {'name': 'de', 'ext': {}, 'url': 'https://example.com/subs/de4'},
+        ], [..., {
+            'id': 'name',
+            'url': 'url',
+            'ext': 'ext',
+        }, all, {subs_list_to_dict(lang='de')}]) == {
+            'de': [
+                {'url': 'https://example.com/subs/de1'},
+                {'url': 'https://example.com/subs/de2'},
+                {'url': 'https://example.com/subs/de3'},
+                {'url': 'https://example.com/subs/de4'},
+            ],
+        }, 'non str types should be replaced by default id'
 
     def test_trim_str(self):
         with pytest.raises(TypeError):
@@ -525,7 +573,7 @@ class TestTraversalHelpers:
     def test_unpack(self):
         assert unpack(lambda *x: ''.join(map(str, x)))([1, 2, 3]) == '123'
         assert unpack(join_nonempty)([1, 2, 3]) == '1-2-3'
-        assert unpack(join_nonempty(delim=' '))([1, 2, 3]) == '1 2 3'
+        assert unpack(join_nonempty, delim=' ')([1, 2, 3]) == '1 2 3'
         with pytest.raises(TypeError):
             unpack(join_nonempty)()
         with pytest.raises(TypeError):

test/test_utils.py

@@ -72,7 +72,6 @@ from yt_dlp.utils import (
     intlist_to_bytes,
     iri_to_uri,
     is_html,
-    join_nonempty,
     js_to_json,
     limit_length,
     locked_file,
@@ -2158,10 +2157,6 @@ Line 1
         assert int_or_none(v=10) == 10, 'keyword passed positional should call function'
         assert int_or_none(scale=0.1)(10) == 100, 'call after partial application should call the function'
 
-        assert callable(join_nonempty(delim=', ')), 'varargs positional should apply partially'
-        assert callable(join_nonempty()), 'varargs positional should apply partially'
-        assert join_nonempty(None, delim=', ') == '', 'passed varargs should call the function'
-
 
 if __name__ == '__main__':
     unittest.main()

yt_dlp/YoutubeDL.py

@@ -4381,7 +4381,9 @@ class YoutubeDL:
             return None
 
         for idx, t in list(enumerate(thumbnails))[::-1]:
-            thumb_ext = (f'{t["id"]}.' if multiple else '') + determine_ext(t['url'], 'jpg')
+            thumb_ext = t.get('ext') or determine_ext(t['url'], 'jpg')
+            if multiple:
+                thumb_ext = f'{t["id"]}.{thumb_ext}'
             thumb_display_id = f'{label} thumbnail {t["id"]}'
             thumb_filename = replace_extension(filename, thumb_ext, info_dict.get('ext'))
             thumb_filename_final = replace_extension(thumb_filename_base, thumb_ext, info_dict.get('ext'))

yt_dlp/extractor/_extractors.py

@@ -208,6 +208,10 @@ from .bandcamp import (
     BandcampUserIE,
     BandcampWeeklyIE,
 )
+from .bandlab import (
+    BandlabIE,
+    BandlabPlaylistIE,
+)
 from .bannedvideo import BannedVideoIE
 from .bbc import (
     BBCIE,
@@ -1649,6 +1653,7 @@ from .radiokapital import (
     RadioKapitalIE,
     RadioKapitalShowIE,
 )
+from .radioradicale import RadioRadicaleIE
 from .radiozet import RadioZetPodcastIE
 from .radlive import (
     RadLiveChannelIE,

yt_dlp/extractor/afreecatv.py

@@ -66,6 +66,14 @@ class AfreecaTVBaseIE(InfoExtractor):
             extensions={'legacy_ssl': True}), display_id,
             'Downloading API JSON', 'Unable to download API JSON')
 
+    @staticmethod
+    def _fixup_thumb(thumb_url):
+        if not url_or_none(thumb_url):
+            return None
+        # Core would determine_ext as 'php' from the url, so we need to provide the real ext
+        # See: https://github.com/yt-dlp/yt-dlp/issues/11537
+        return [{'url': thumb_url, 'ext': 'jpg'}]
+
 
 class AfreecaTVIE(AfreecaTVBaseIE):
     IE_NAME = 'soop'
@@ -155,7 +163,7 @@ class AfreecaTVIE(AfreecaTVBaseIE):
             'uploader': ('writer_nick', {str}),
             'uploader_id': ('bj_id', {str}),
             'duration': ('total_file_duration', {int_or_none(scale=1000)}),
-            'thumbnail': ('thumb', {url_or_none}),
+            'thumbnails': ('thumb', {self._fixup_thumb}),
         })
 
         entries = []
@@ -226,8 +234,7 @@ class AfreecaTVCatchStoryIE(AfreecaTVBaseIE):
 
         return self.playlist_result(self._entries(data), video_id)
 
-    @staticmethod
+    def _entries(self, data):
-    def _entries(data):
         # 'files' is always a list with 1 element
         yield from traverse_obj(data, (
             'data', lambda _, v: v['story_type'] == 'catch',
@@ -238,7 +245,7 @@ class AfreecaTVCatchStoryIE(AfreecaTVBaseIE):
                 'title': ('title', {str}),
                 'uploader': ('writer_nick', {str}),
                 'uploader_id': ('writer_id', {str}),
-                'thumbnail': ('thumb', {url_or_none}),
+                'thumbnails': ('thumb', {self._fixup_thumb}),
                 'timestamp': ('write_timestamp', {int_or_none}),
             }))
 

yt_dlp/extractor/bandlab.py

@@ -0,0 +1,438 @@
+
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+    float_or_none,
+    format_field,
+    int_or_none,
+    parse_iso8601,
+    parse_qs,
+    truncate_string,
+    url_or_none,
+)
+from ..utils.traversal import traverse_obj, value
+
+
+class BandlabBaseIE(InfoExtractor):
+    def _call_api(self, endpoint, asset_id, **kwargs):
+        headers = kwargs.pop('headers', None) or {}
+        return self._download_json(
+            f'https://www.bandlab.com/api/v1.3/{endpoint}/{asset_id}',
+            asset_id, headers={
+                'accept': 'application/json',
+                'referer': 'https://www.bandlab.com/',
+                'x-client-id': 'BandLab-Web',
+                'x-client-version': '10.1.124',
+                **headers,
+            }, **kwargs)
+
+    def _parse_revision(self, revision_data, url=None):
+        return {
+            'vcodec': 'none',
+            'media_type': 'revision',
+            'extractor_key': BandlabIE.ie_key(),
+            'extractor': BandlabIE.IE_NAME,
+            **traverse_obj(revision_data, {
+                'webpage_url': (
+                    'id', ({value(url)}, {format_field(template='https://www.bandlab.com/revision/%s')}), filter, any),
+                'id': (('revisionId', 'id'), {str}, any),
+                'title': ('song', 'name', {str}),
+                'track': ('song', 'name', {str}),
+                'url': ('mixdown', 'file', {url_or_none}),
+                'thumbnail': ('song', 'picture', 'url', {url_or_none}),
+                'description': ('description', {str}),
+                'uploader': ('creator', 'name', {str}),
+                'uploader_id': ('creator', 'username', {str}),
+                'timestamp': ('createdOn', {parse_iso8601}),
+                'duration': ('mixdown', 'duration', {float_or_none}),
+                'view_count': ('counters', 'plays', {int_or_none}),
+                'like_count': ('counters', 'likes', {int_or_none}),
+                'comment_count': ('counters', 'comments', {int_or_none}),
+                'genres': ('genres', ..., 'name', {str}),
+            }),
+        }
+
+    def _parse_track(self, track_data, url=None):
+        return {
+            'vcodec': 'none',
+            'media_type': 'track',
+            'extractor_key': BandlabIE.ie_key(),
+            'extractor': BandlabIE.IE_NAME,
+            **traverse_obj(track_data, {
+                'webpage_url': (
+                    'id', ({value(url)}, {format_field(template='https://www.bandlab.com/post/%s')}), filter, any),
+                'id': (('revisionId', 'id'), {str}, any),
+                'url': ('track', 'sample', 'audioUrl', {url_or_none}),
+                'title': ('track', 'name', {str}),
+                'track': ('track', 'name', {str}),
+                'description': ('caption', {str}),
+                'thumbnail': ('track', 'picture', ('original', 'url'), {url_or_none}, any),
+                'view_count': ('counters', 'plays', {int_or_none}),
+                'like_count': ('counters', 'likes', {int_or_none}),
+                'comment_count': ('counters', 'comments', {int_or_none}),
+                'duration': ('track', 'sample', 'duration', {float_or_none}),
+                'uploader': ('creator', 'name', {str}),
+                'uploader_id': ('creator', 'username', {str}),
+                'timestamp': ('createdOn', {parse_iso8601}),
+            }),
+        }
+
+    def _parse_video(self, video_data, url=None):
+        return {
+            'media_type': 'video',
+            'extractor_key': BandlabIE.ie_key(),
+            'extractor': BandlabIE.IE_NAME,
+            **traverse_obj(video_data, {
+                'id': ('id', {str}),
+                'webpage_url': (
+                    'id', ({value(url)}, {format_field(template='https://www.bandlab.com/post/%s')}), filter, any),
+                'url': ('video', 'url', {url_or_none}),
+                'title': ('caption', {lambda x: x.replace('\n', ' ')}, {truncate_string(left=50)}),
+                'description': ('caption', {str}),
+                'thumbnail': ('video', 'picture', 'url', {url_or_none}),
+                'view_count': ('video', 'counters', 'plays', {int_or_none}),
+                'like_count': ('video', 'counters', 'likes', {int_or_none}),
+                'comment_count': ('counters', 'comments', {int_or_none}),
+                'duration': ('video', 'duration', {float_or_none}),
+                'uploader': ('creator', 'name', {str}),
+                'uploader_id': ('creator', 'username', {str}),
+            }),
+        }
+
+
+class BandlabIE(BandlabBaseIE):
+    _VALID_URL = [
+        r'https?://(?:www\.)?bandlab.com/(?P<url_type>track|post|revision)/(?P<id>[\da-f_-]+)',
+        r'https?://(?:www\.)?bandlab.com/(?P<url_type>embed)/\?(?:[^#]*&)?id=(?P<id>[\da-f-]+)',
+    ]
+    _EMBED_REGEX = [rf'<iframe[^>]+src=[\'"](?P<url>{_VALID_URL[1]})[\'"]']
+    _TESTS = [{
+        'url': 'https://www.bandlab.com/track/04b37e88dba24967b9dac8eb8567ff39_07d7f906fc96ee11b75e000d3a428fff',
+        'md5': '46f7b43367dd268bbcf0bbe466753b2c',
+        'info_dict': {
+            'id': '02d7f906-fc96-ee11-b75e-000d3a428fff',
+            'ext': 'm4a',
+            'uploader_id': 'ender_milze',
+            'track': 'sweet black',
+            'description': 'composed by juanjn3737',
+            'timestamp': 1702171963,
+            'view_count': int,
+            'like_count': int,
+            'duration': 54.629999999999995,
+            'title': 'sweet black',
+            'upload_date': '20231210',
+            'thumbnail': 'https://bandlabimages.azureedge.net/v1.0/songs/fa082beb-b856-4730-9170-a57e4e32cc2c/',
+            'genres': ['Lofi'],
+            'uploader': 'ender milze',
+            'comment_count': int,
+            'media_type': 'revision',
+        },
+    }, {
+        # Same track as above but post URL
+        'url': 'https://www.bandlab.com/post/07d7f906-fc96-ee11-b75e-000d3a428fff',
+        'md5': '46f7b43367dd268bbcf0bbe466753b2c',
+        'info_dict': {
+            'id': '02d7f906-fc96-ee11-b75e-000d3a428fff',
+            'ext': 'm4a',
+            'uploader_id': 'ender_milze',
+            'track': 'sweet black',
+            'description': 'composed by juanjn3737',
+            'timestamp': 1702171973,
+            'view_count': int,
+            'like_count': int,
+            'duration': 54.629999999999995,
+            'title': 'sweet black',
+            'upload_date': '20231210',
+            'thumbnail': 'https://bandlabimages.azureedge.net/v1.0/songs/fa082beb-b856-4730-9170-a57e4e32cc2c/',
+            'genres': ['Lofi'],
+            'uploader': 'ender milze',
+            'comment_count': int,
+            'media_type': 'revision',
+        },
+    }, {
+        # SharedKey Example
+        'url': 'https://www.bandlab.com/track/048916c2-c6da-ee11-85f9-6045bd2e11f9?sharedKey=0NNWX8qYAEmI38lWAzCNDA',
+        'md5': '15174b57c44440e2a2008be9cae00250',
+        'info_dict': {
+            'id': '038916c2-c6da-ee11-85f9-6045bd2e11f9',
+            'ext': 'm4a',
+            'comment_count': int,
+            'genres': ['Other'],
+            'uploader_id': 'user8353034818103753',
+            'thumbnail': 'https://bandlabimages.azureedge.net/v1.0/songs/51b18363-da23-4b9b-a29c-2933a3e561ca/',
+            'timestamp': 1709625771,
+            'track': 'PodcastMaerchen4b',
+            'duration': 468.14,
+            'view_count': int,
+            'description': 'Podcast: Neues aus der Märchenwelt',
+            'like_count': int,
+            'upload_date': '20240305',
+            'uploader': 'Erna Wageneder',
+            'title': 'PodcastMaerchen4b',
+            'media_type': 'revision',
+        },
+    }, {
+        # Different Revision selected
+        'url': 'https://www.bandlab.com/track/130343fc-148b-ea11-96d2-0003ffd1fc09?revId=110343fc-148b-ea11-96d2-0003ffd1fc09',
+        'md5': '74e055ef9325d63f37088772fbfe4454',
+        'info_dict': {
+            'id': '110343fc-148b-ea11-96d2-0003ffd1fc09',
+            'ext': 'm4a',
+            'timestamp': 1588273294,
+            'thumbnail': 'https://bandlabimages.azureedge.net/v1.0/users/b612e533-e4f7-4542-9f50-3fcfd8dd822c/',
+            'description': 'Final Revision.',
+            'title': 'Replay ( Instrumental)',
+            'uploader': 'David R Sparks',
+            'uploader_id': 'davesnothome69',
+            'view_count': int,
+            'comment_count': int,
+            'track': 'Replay ( Instrumental)',
+            'genres': ['Rock'],
+            'upload_date': '20200430',
+            'like_count': int,
+            'duration': 279.43,
+            'media_type': 'revision',
+        },
+    }, {
+        # Video
+        'url': 'https://www.bandlab.com/post/5cdf9036-3857-ef11-991a-6045bd36e0d9',
+        'md5': '8caa2ef28e86c1dacf167293cfdbeba9',
+        'info_dict': {
+            'id': '5cdf9036-3857-ef11-991a-6045bd36e0d9',
+            'ext': 'mp4',
+            'duration': 44.705,
+            'thumbnail': 'https://bandlabimages.azureedge.net/v1.0/videos/67c6cef1-cef6-40d3-831e-a55bc1dcb972/',
+            'comment_count': int,
+            'title': 'backing vocals',
+            'uploader_id': 'marliashya',
+            'uploader': 'auraa',
+            'like_count': int,
+            'description': 'backing vocals',
+            'media_type': 'video',
+        },
+    }, {
+        # Embed Example
+        'url': 'https://www.bandlab.com/embed/?blur=false&id=014de0a4-7d82-ea11-a94c-0003ffd19c0f',
+        'md5': 'a4ad05cb68c54faaed9b0a8453a8cf4a',
+        'info_dict': {
+            'id': '014de0a4-7d82-ea11-a94c-0003ffd19c0f',
+            'ext': 'm4a',
+            'comment_count': int,
+            'genres': ['Electronic'],
+            'uploader': 'Charlie Henson',
+            'timestamp': 1587328674,
+            'upload_date': '20200419',
+            'view_count': int,
+            'track': 'Positronic Meltdown',
+            'duration': 318.55,
+            'thumbnail': 'https://bandlabimages.azureedge.net/v1.0/songs/87165bc3-5439-496e-b1f7-a9f13b541ff2/',
+            'description': 'Checkout my tracks at AOMX http://aomxsounds.com/',
+            'uploader_id': 'microfreaks',
+            'title': 'Positronic Meltdown',
+            'like_count': int,
+            'media_type': 'revision',
+        },
+    }, {
+        # Track without revisions available
+        'url': 'https://www.bandlab.com/track/55767ac51789ea11a94c0003ffd1fc09_2f007b0a37b94ec7a69bc25ae15108a5',
+        'md5': 'f05d68a3769952c2d9257c473e14c15f',
+        'info_dict': {
+            'id': '55767ac51789ea11a94c0003ffd1fc09_2f007b0a37b94ec7a69bc25ae15108a5',
+            'ext': 'm4a',
+            'track': 'insame',
+            'like_count': int,
+            'duration': 84.03,
+            'title': 'insame',
+            'view_count': int,
+            'comment_count': int,
+            'uploader': 'Sorakime',
+            'uploader_id': 'sorakime',
+            'thumbnail': 'https://bandlabimages.azureedge.net/v1.0/users/572a351a-0f3a-4c6a-ac39-1a5defdeeb1c/',
+            'timestamp': 1691162128,
+            'upload_date': '20230804',
+            'media_type': 'track',
+        },
+    }, {
+        'url': 'https://www.bandlab.com/revision/014de0a4-7d82-ea11-a94c-0003ffd19c0f',
+        'only_matching': True,
+    }]
+    _WEBPAGE_TESTS = [{
+        'url': 'https://phantomluigi.github.io/',
+        'info_dict': {
+            'id': 'e14223c3-7871-ef11-bdfd-000d3a980db3',
+            'ext': 'm4a',
+            'view_count': int,
+            'upload_date': '20240913',
+            'uploader_id': 'phantommusicofficial',
+            'timestamp': 1726194897,
+            'uploader': 'Phantom',
+            'comment_count': int,
+            'genres': ['Progresive Rock'],
+            'description': 'md5:a38cd668f7a2843295ef284114f18429',
+            'duration': 225.23,
+            'like_count': int,
+            'title': 'Vermilion Pt. 2 (Cover)',
+            'track': 'Vermilion Pt. 2 (Cover)',
+            'thumbnail': 'https://bandlabimages.azureedge.net/v1.0/songs/62b10750-7aef-4f42-ad08-1af52f577e97/',
+            'media_type': 'revision',
+        },
+    }]
+
+    def _real_extract(self, url):
+        display_id, url_type = self._match_valid_url(url).group('id', 'url_type')
+
+        qs = parse_qs(url)
+        revision_id = traverse_obj(qs, (('revId', 'id'), 0, any))
+        if url_type == 'revision':
+            revision_id = display_id
+
+        revision_data = None
+        if not revision_id:
+            post_data = self._call_api(
+                'posts', display_id, note='Downloading post data',
+                query=traverse_obj(qs, {'sharedKey': ('sharedKey', 0)}))
+
+            revision_id = traverse_obj(post_data, (('revisionId', ('revision', 'id')), {str}, any))
+            revision_data = traverse_obj(post_data, ('revision', {dict}))
+
+            if not revision_data and not revision_id:
+                post_type = post_data.get('type')
+                if post_type == 'Video':
+                    return self._parse_video(post_data, url=url)
+                if post_type == 'Track':
+                    return self._parse_track(post_data, url=url)
+                raise ExtractorError(f'Could not extract data for post type {post_type!r}')
+
+        if not revision_data:
+            revision_data = self._call_api(
+                'revisions', revision_id, note='Downloading revision data', query={'edit': 'false'})
+
+        return self._parse_revision(revision_data, url=url)
+
+
+class BandlabPlaylistIE(BandlabBaseIE):
+    _VALID_URL = [
+        r'https?://(?:www\.)?bandlab.com/(?:[\w]+/)?(?P<type>albums|collections)/(?P<id>[\da-f-]+)',
+        r'https?://(?:www\.)?bandlab.com/(?P<type>embed)/collection/\?(?:[^#]*&)?id=(?P<id>[\da-f-]+)',
+    ]
+    _EMBED_REGEX = [rf'<iframe[^>]+src=[\'"](?P<url>{_VALID_URL[1]})[\'"]']
+    _TESTS = [{
+        'url': 'https://www.bandlab.com/davesnothome69/albums/89b79ea6-de42-ed11-b495-00224845aac7',
+        'info_dict': {
+            'thumbnail': 'https://bl-prod-images.azureedge.net/v1.3/albums/69507ff3-579a-45be-afca-9e87eddec944/',
+            'release_date': '20221003',
+            'title': 'Remnants',
+            'album': 'Remnants',
+            'like_count': int,
+            'album_type': 'LP',
+            'description': 'A collection of some feel good, rock hits.',
+            'comment_count': int,
+            'view_count': int,
+            'id': '89b79ea6-de42-ed11-b495-00224845aac7',
+            'uploader': 'David R Sparks',
+            'uploader_id': 'davesnothome69',
+        },
+        'playlist_count': 10,
+    }, {
+        'url': 'https://www.bandlab.com/slytheband/collections/955102d4-1040-ef11-86c3-000d3a42581b',
+        'info_dict': {
+            'id': '955102d4-1040-ef11-86c3-000d3a42581b',
+            'timestamp': 1720762659,
+            'view_count': int,
+            'title': 'My Shit 🖤',
+            'uploader_id': 'slytheband',
+            'uploader': '𝓢𝓛𝓨',
+            'upload_date': '20240712',
+            'like_count': int,
+            'thumbnail': 'https://bandlabimages.azureedge.net/v1.0/collections/2c64ca12-b180-4b76-8587-7a8da76bddc8/',
+        },
+        'playlist_count': 15,
+    }, {
+        # Embeds can contain both albums and collections with the same URL pattern. This is an album
+        'url': 'https://www.bandlab.com/embed/collection/?id=12cc6f7f-951b-ee11-907c-00224844f303',
+        'info_dict': {
+            'id': '12cc6f7f-951b-ee11-907c-00224844f303',
+            'release_date': '20230706',
+            'description': 'This is a collection of songs I created when I had an Amiga computer.',
+            'view_count': int,
+            'title': 'Mark Salud The Amiga Collection',
+            'uploader_id': 'mssirmooth1962',
+            'comment_count': int,
+            'thumbnail': 'https://bl-prod-images.azureedge.net/v1.3/albums/d618bd7b-0537-40d5-bdd8-61b066e77d59/',
+            'like_count': int,
+            'uploader': 'Mark Salud',
+            'album': 'Mark Salud The Amiga Collection',
+            'album_type': 'LP',
+        },
+        'playlist_count': 24,
+    }, {
+        # Tracks without revision id
+        'url': 'https://www.bandlab.com/embed/collection/?id=e98aafb5-d932-ee11-b8f0-00224844c719',
+        'info_dict': {
+            'like_count': int,
+            'uploader_id': 'sorakime',
+            'comment_count': int,
+            'uploader': 'Sorakime',
+            'view_count': int,
+            'description': 'md5:4ec31c568a5f5a5a2b17572ea64c3825',
+            'release_date': '20230812',
+            'title': 'Art',
+            'album': 'Art',
+            'album_type': 'Album',
+            'id': 'e98aafb5-d932-ee11-b8f0-00224844c719',
+            'thumbnail': 'https://bl-prod-images.azureedge.net/v1.3/albums/20c890de-e94a-4422-828a-2da6377a13c8/',
+        },
+        'playlist_count': 13,
+    }, {
+        'url': 'https://www.bandlab.com/albums/89b79ea6-de42-ed11-b495-00224845aac7',
+        'only_matching': True,
+    }]
+
+    def _entries(self, album_data):
+        for post in traverse_obj(album_data, ('posts', lambda _, v: v['type'])):
+            post_type = post['type']
+            if post_type == 'Revision':
+                yield self._parse_revision(post.get('revision'))
+            elif post_type == 'Track':
+                yield self._parse_track(post)
+            elif post_type == 'Video':
+                yield self._parse_video(post)
+            else:
+                self.report_warning(f'Skipping unknown post type: "{post_type}"')
+
+    def _real_extract(self, url):
+        playlist_id, playlist_type = self._match_valid_url(url).group('id', 'type')
+
+        endpoints = {
+            'albums': ['albums'],
+            'collections': ['collections'],
+            'embed': ['collections', 'albums'],
+        }.get(playlist_type)
+        for endpoint in endpoints:
+            playlist_data = self._call_api(
+                endpoint, playlist_id, note=f'Downloading {endpoint[:-1]} data',
+                fatal=False, expected_status=404)
+            if not playlist_data.get('errorCode'):
+                playlist_type = endpoint
+                break
+        if error_code := playlist_data.get('errorCode'):
+            raise ExtractorError(f'Could not find playlist data. Error code: "{error_code}"')
+
+        return self.playlist_result(
+            self._entries(playlist_data), playlist_id,
+            **traverse_obj(playlist_data, {
+                'title': ('name', {str}),
+                'description': ('description', {str}),
+                'uploader': ('creator', 'name', {str}),
+                'uploader_id': ('creator', 'username', {str}),
+                'timestamp': ('createdOn', {parse_iso8601}),
+                'release_date': ('releaseDate', {lambda x: x.replace('-', '')}, filter),
+                'thumbnail': ('picture', ('original', 'url'), {url_or_none}, any),
+                'like_count': ('counters', 'likes', {int_or_none}),
+                'comment_count': ('counters', 'comments', {int_or_none}),
+                'view_count': ('counters', 'plays', {int_or_none}),
+            }),
+            **(traverse_obj(playlist_data, {
+                'album': ('name', {str}),
+                'album_type': ('type', {str}),
+            }) if playlist_type == 'albums' else {}))

yt_dlp/extractor/bilibili.py

@@ -33,6 +33,7 @@ from ..utils import (
     parse_qs,
     parse_resolution,
     qualities,
+    sanitize_url,
     smuggle_url,
     srt_subtitles_timecode,
     str_or_none,
@@ -41,6 +42,7 @@ from ..utils import (
     unsmuggle_url,
     url_or_none,
     urlencode_postdata,
+    value,
     variadic,
 )
 
@@ -66,6 +68,84 @@ class BilibiliBaseIE(InfoExtractor):
                 f'Format(s) {missing_formats} are missing; you have to login or '
                 f'become a premium member to download them. {self._login_hint()}')
 
+    def _extract_heatmap(self, cid):
+        heatmap_json = self._download_json(
+            'https://bvc.bilivideo.com/pbp/data', cid,
+            note='Downloading heatmap', errnote='Failed to download heatmap', fatal=False,
+            query={'cid': cid})
+        if not isinstance(heatmap_json, dict):
+            return
+        duration = self._parse_json(heatmap_json['debug'], cid).get('max_time')
+        step_sec = traverse_obj(heatmap_json, ('step_sec', {int}))
+        heatmap_data = traverse_obj(heatmap_json, ('events', 'default', {list}))
+        if not step_sec or not heatmap_data:
+            return
+        peak = max(heatmap_data)
+        if not peak:
+            return
+
+        for idx, heatmap_entry in enumerate(heatmap_data):
+            start_time = idx * step_sec
+            end_time = start_time + step_sec
+            if duration and end_time >= duration:
+                yield {
+                    'start_time': start_time,
+                    'end_time': duration,
+                    'value': heatmap_entry / peak,
+                }
+                break
+            yield {
+                'start_time': start_time,
+                'end_time': end_time,
+                'value': heatmap_entry / peak,
+            }
+
+    def _extract_storyboard(self, duration, aid=None, bvid=None, cid=None):
+        if not (video_id := aid or bvid) or not duration:
+            return
+        if storyboard_info := traverse_obj(self._download_json(
+                'https://api.bilibili.com/x/player/videoshot', video_id,
+                note='Downloading storyboard info', errnote='Failed to download storyboard info',
+                query=filter_dict({
+                    'index': 1,
+                    'aid': aid,
+                    'bvid': bvid,
+                    'cid': cid,
+                })), ('data', {lambda v: v if v.get('image') and v.get('index') else None})):
+            rows, cols = storyboard_info.get('img_x_len'), storyboard_info.get('img_y_len')
+            fragments = []
+            last_duration = 0.0
+            for i, url in enumerate(storyboard_info['image'], start=1):
+                if not rows or not cols:
+                    fragments.append({'url': sanitize_url(url)})
+                    continue
+                elif (duration_index := i * rows * cols - 1) < len(storyboard_info['index']) - 1:
+                    current_duration = traverse_obj(storyboard_info, ('index', duration_index))
+                else:
+                    current_duration = duration
+                if not current_duration or current_duration <= last_duration or current_duration > duration:
+                    break
+                fragments.append({
+                    'url': sanitize_url(url),
+                    'duration': current_duration - last_duration if current_duration is not None else None,
+                })
+            if fragments:
+                return {
+                    'format_id': 'sb',
+                    'format_note': 'storyboard',
+                    'ext': 'mhtml',
+                    'protocol': 'mhtml',
+                    'acodec': 'none',
+                    'vcodec': 'none',
+                    'url': 'about:invalid',
+                    'width': storyboard_info.get('img_x_size'),
+                    'height': storyboard_info.get('img_y_size'),
+                    'fps': len(storyboard_info['image']) * rows * cols / duration if rows and cols else None,
+                    'rows': rows,
+                    'columns': cols,
+                    'fragments': fragments,
+                }
+
     def extract_formats(self, play_info):
         format_names = {
             r['quality']: traverse_obj(r, 'new_description', 'display_desc')
@@ -287,14 +367,21 @@ class BilibiliBaseIE(InfoExtractor):
         cid_edges = self._get_divisions(video_id, graph_version, {1: {'cid': cid}}, 1)
         for cid, edges in cid_edges.items():
             play_info = self._download_playinfo(video_id, cid, headers=headers)
+            formats = self.extract_formats(play_info)
+            duration = float_or_none(play_info.get('timelength'), scale=1000)
+            if storyboard_format := self._extract_storyboard(
+                    duration=duration,
+                    bvid=video_id, cid=cid):
+                formats.append(storyboard_format)
             yield {
                 **metainfo,
                 'id': f'{video_id}_{cid}',
                 'title': f'{metainfo.get("title")} - {next(iter(edges.values())).get("title")}',
-                'formats': self.extract_formats(play_info),
+                'formats': formats,
                 'description': f'{json.dumps(edges, ensure_ascii=False)}\n{metainfo.get("description", "")}',
-                'duration': float_or_none(play_info.get('timelength'), scale=1000),
+                'duration': duration,
                 'subtitles': self.extract_subtitles(video_id, cid),
+                'heatmap': list(self._extract_heatmap(cid)),
             }
 
 
@@ -310,7 +397,7 @@ class BiliBiliIE(BilibiliBaseIE):
             'description': '滴妹今天唱Closer給你聽! 有史以来，被推最多次也是最久的歌曲，其实歌词跟我原本想像差蛮多的，不过还是好听！ 微博@阿滴英文',
             'uploader_id': '65880958',
             'uploader': '阿滴英文',
-            'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)$',
+            'thumbnail': r're:https?://.*\.(?:jpg|jpeg|png)$',
             'duration': 554.117,
             'tags': list,
             'comment_count': int,
@@ -319,6 +406,7 @@ class BiliBiliIE(BilibiliBaseIE):
             'like_count': int,
             'view_count': int,
             '_old_archive_ids': ['bilibili 8903802_part1'],
+            'heatmap': [],
         },
     }, {
         'note': 'old av URL version',
@@ -337,8 +425,9 @@ class BiliBiliIE(BilibiliBaseIE):
             'comment_count': int,
             'view_count': int,
             'tags': list,
-            'thumbnail': r're:^https?://.*\.(jpg|jpeg)$',
+            'thumbnail': r're:https?://.*\.(?:jpg|jpeg|png)$',
             '_old_archive_ids': ['bilibili 1074402_part1'],
+            'heatmap': [],
         },
         'params': {'skip_download': True},
     }, {
@@ -356,7 +445,7 @@ class BiliBiliIE(BilibiliBaseIE):
                 'title': '物语中的人物是如何吐槽自己的OP的 p01 Staple Stable/战场原+羽川',
                 'tags': 'count:10',
                 'timestamp': 1589601697,
-                'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)$',
+                'thumbnail': r're:https?://.*\.(?:jpg|jpeg|png)$',
                 'uploader': '打牌还是打桩',
                 'uploader_id': '150259984',
                 'like_count': int,
@@ -366,6 +455,7 @@ class BiliBiliIE(BilibiliBaseIE):
                 'description': 'md5:e3c401cf7bc363118d1783dd74068a68',
                 'duration': 90.314,
                 '_old_archive_ids': ['bilibili 498159642_part1'],
+                'heatmap': list,
             },
         }],
     }, {
@@ -377,7 +467,7 @@ class BiliBiliIE(BilibiliBaseIE):
             'title': '物语中的人物是如何吐槽自己的OP的 p01 Staple Stable/战场原+羽川',
             'tags': 'count:10',
             'timestamp': 1589601697,
-            'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)$',
+            'thumbnail': r're:https?://.*\.(?:jpg|jpeg|png)$',
             'uploader': '打牌还是打桩',
             'uploader_id': '150259984',
             'like_count': int,
@@ -387,6 +477,7 @@ class BiliBiliIE(BilibiliBaseIE):
             'description': 'md5:e3c401cf7bc363118d1783dd74068a68',
             'duration': 90.314,
             '_old_archive_ids': ['bilibili 498159642_part1'],
+            'heatmap': list,
         },
     }, {
         'url': 'https://www.bilibili.com/video/av8903802/',
@@ -399,13 +490,14 @@ class BiliBiliIE(BilibiliBaseIE):
             'timestamp': 1488353834,
             'uploader_id': '65880958',
             'uploader': '阿滴英文',
-            'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)$',
+            'thumbnail': r're:https?://.*\.(?:jpg|jpeg|png)$',
             'duration': 554.117,
             'tags': list,
             'comment_count': int,
             'view_count': int,
             'like_count': int,
             '_old_archive_ids': ['bilibili 8903802_part1'],
+            'heatmap': [],
         },
         'params': {
             'skip_download': True,
@@ -428,8 +520,9 @@ class BiliBiliIE(BilibiliBaseIE):
             'comment_count': int,
             'view_count': int,
             'like_count': int,
-            'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)$',
+            'thumbnail': r're:https?://.*\.(?:jpg|jpeg|png)$',
             '_old_archive_ids': ['bilibili 463665680_part1'],
+            'heatmap': list,
         },
         'params': {'skip_download': True},
     }, {
@@ -447,8 +540,9 @@ class BiliBiliIE(BilibiliBaseIE):
             'uploader_id': '528182630',
             'view_count': int,
             'like_count': int,
-            'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)$',
+            'thumbnail': r're:https?://.*\.(?:jpg|jpeg|png)$',
             '_old_archive_ids': ['bilibili 893839363_part1'],
+            'heatmap': [],
         },
     }, {
         'note': 'newer festival video',
@@ -465,8 +559,9 @@ class BiliBiliIE(BilibiliBaseIE):
             'uploader_id': '8469526',
             'view_count': int,
             'like_count': int,
-            'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)$',
+            'thumbnail': r're:https?://.*\.(?:jpg|jpeg|png)$',
             '_old_archive_ids': ['bilibili 778246196_part1'],
+            'heatmap': list,
         },
     }, {
         'note': 'legacy flv/mp4 video',
@@ -484,8 +579,9 @@ class BiliBiliIE(BilibiliBaseIE):
             'comment_count': int,
             'like_count': int,
             'tags': list,
-            'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)$',
+            'thumbnail': r're:https?://.*\.(?:jpg|jpeg|png)$',
             '_old_archive_ids': ['bilibili 4120229_part4'],
+            'heatmap': [],
         },
         'params': {'extractor_args': {'bilibili': {'prefer_multi_flv': ['32']}}},
         'playlist_count': 19,
@@ -514,8 +610,9 @@ class BiliBiliIE(BilibiliBaseIE):
             'view_count': int,
             'like_count': int,
             'tags': list,
-            'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)$',
+            'thumbnail': r're:https?://.*\.(?:jpg|jpeg|png)$',
             '_old_archive_ids': ['bilibili 15700301_part1'],
+            'heatmap': [],
         },
     }, {
         'note': 'interactive/split-path video',
@@ -533,7 +630,7 @@ class BiliBiliIE(BilibiliBaseIE):
             'comment_count': int,
             'view_count': int,
             'like_count': int,
-            'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)$',
+            'thumbnail': r're:https?://.*\.(?:jpg|jpeg|png)$',
             '_old_archive_ids': ['bilibili 292734508_part1'],
         },
         'playlist_count': 33,
@@ -552,10 +649,33 @@ class BiliBiliIE(BilibiliBaseIE):
                 'comment_count': int,
                 'view_count': int,
                 'like_count': int,
-                'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)$',
+                'thumbnail': r're:https?://.*\.(?:jpg|jpeg|png)$',
                 '_old_archive_ids': ['bilibili 292734508_part1'],
+                'heatmap': [],
             },
         }],
+    }, {
+        'note': 'storyboard',
+        'url': 'https://www.bilibili.com/video/av170001/',
+        'info_dict': {
+            'id': 'BV17x411w7KC_p1',
+            'title': '【MV】保加利亚妖王AZIS视频合辑 p01 Хоп',
+            'ext': 'mhtml',
+            'upload_date': '20111109',
+            'uploader_id': '122541',
+            'view_count': int,
+            '_old_archive_ids': ['bilibili 170001_part1'],
+            'thumbnail': r're:https?://.*\.(?:jpg|jpeg|png)$',
+            'uploader': '冰封.虾子',
+            'timestamp': 1320850533,
+            'comment_count': int,
+            'tags': ['Hop', '保加利亚妖王', '保加利亚', 'Азис', 'azis', 'mv'],
+            'description': 'md5:acfd7360b96547f031f7ebead9e66d9e',
+            'like_count': int,
+            'duration': 199.4,
+            'heatmap': list,
+        },
+        'params': {'format': 'sb', 'playlist_items': '1'},
     }, {
         'note': '301 redirect to bangumi link',
         'url': 'https://www.bilibili.com/video/BV1TE411f7f1',
@@ -574,7 +694,8 @@ class BiliBiliIE(BilibiliBaseIE):
             'duration': 1183.957,
             'timestamp': 1571648124,
             'upload_date': '20191021',
-            'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)$',
+            'thumbnail': r're:https?://.*\.(?:jpg|jpeg|png)$',
+            'heatmap': [],
         },
     }, {
         'note': 'video has subtitles, which requires login',
@@ -593,7 +714,7 @@ class BiliBiliIE(BilibiliBaseIE):
             'comment_count': int,
             'view_count': int,
             'like_count': int,
-            'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)$',
+            'thumbnail': r're:https?://.*\.(?:jpg|jpeg|png)$',
             'subtitles': 'count:2',  # login required for CC subtitle
             '_old_archive_ids': ['bilibili 898179753_part1'],
         },
@@ -729,6 +850,9 @@ class BiliBiliIE(BilibiliBaseIE):
                 __post_extractor=self.extract_comments(aid))
         else:
             formats = self.extract_formats(play_info)
+            formats.append(self._extract_storyboard(
+                duration=float_or_none(play_info.get('timelength'), scale=1000),
+                bvid=video_id, cid=cid))
 
             if not traverse_obj(play_info, ('dash')):
                 # we only have legacy formats and need additional work
@@ -773,6 +897,7 @@ class BiliBiliIE(BilibiliBaseIE):
                         '__post_extractor': self.extract_comments(aid) if idx == 0 else None,
                     } for idx, fragment in enumerate(formats[0]['fragments'])],
                     'duration': float_or_none(play_info.get('timelength'), scale=1000),
+                    'heatmap': list(self._extract_heatmap(cid)),
                 }
             else:
                 return {
@@ -782,6 +907,7 @@ class BiliBiliIE(BilibiliBaseIE):
                     'chapters': self._get_chapters(aid, cid),
                     'subtitles': self.extract_subtitles(video_id, cid),
                     '__post_extractor': self.extract_comments(aid),
+                    'heatmap': list(self._extract_heatmap(cid)),
                 }
 
 
@@ -805,7 +931,8 @@ class BiliBiliBangumiIE(BilibiliBaseIE):
             'duration': 1420.791,
             'timestamp': 1320412200,
             'upload_date': '20111104',
-            'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)$',
+            'thumbnail': r're:https?://.*\.(?:jpg|jpeg|png)$',
+            'heatmap': list,
         },
     }, {
         'url': 'https://www.bilibili.com/bangumi/play/ep267851',
@@ -824,7 +951,7 @@ class BiliBiliBangumiIE(BilibiliBaseIE):
             'duration': 1425.256,
             'timestamp': 1554566400,
             'upload_date': '20190406',
-            'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)$',
+            'thumbnail': r're:https?://.*\.(?:jpg|jpeg|png)$',
         },
         'skip': 'Geo-restricted',
     }, {
@@ -845,7 +972,8 @@ class BiliBiliBangumiIE(BilibiliBaseIE):
             'duration': 1922.129,
             'timestamp': 1602853860,
             'upload_date': '20201016',
-            'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)$',
+            'thumbnail': r're:https?://.*\.(?:jpg|jpeg|png)$',
+            'heatmap': list,
         },
     }]
 
@@ -865,6 +993,8 @@ class BiliBiliBangumiIE(BilibiliBaseIE):
             'Extracting episode', query={'fnval': '4048', 'ep_id': episode_id},
             headers=headers)
         premium_only = play_info.get('code') == -10403
+        episode_info = traverse_obj(play_info, ('result', 'play_view_business_info', 'episode_info'))
+        aid, cid = episode_info.get('aid'), episode_info.get('cid')
         play_info = traverse_obj(play_info, ('result', 'video_info', {dict})) or {}
 
         formats = self.extract_formats(play_info)
@@ -878,7 +1008,7 @@ class BiliBiliBangumiIE(BilibiliBaseIE):
         episode_number, episode_info = next((
             (idx, ep) for idx, ep in enumerate(traverse_obj(
                 bangumi_info, (('episodes', ('section', ..., 'episodes')), ..., {dict})), 1)
-            if str_or_none(ep.get('id')) == episode_id), (1, {}))
+            if str_or_none(ep.get('id')) == episode_id), (1, episode_info))
 
         season_id = bangumi_info.get('season_id')
         season_number, season_title = season_id and next((
@@ -887,8 +1017,10 @@ class BiliBiliBangumiIE(BilibiliBaseIE):
             if e.get('season_id') == season_id
         ), (None, None))
 
-        aid = episode_info.get('aid')
+        aid, cid = episode_info.get('aid', aid), episode_info.get('cid', cid)
-
+        duration = float_or_none(play_info.get('timelength'), scale=1000)
+        if storyboard_format := self._extract_storyboard(duration=duration, aid=aid, cid=cid):
+            formats.append(storyboard_format)
         return {
             'id': episode_id,
             'formats': formats,
@@ -907,10 +1039,11 @@ class BiliBiliBangumiIE(BilibiliBaseIE):
             'season': str_or_none(season_title),
             'season_id': str_or_none(season_id),
             'season_number': season_number,
-            'duration': float_or_none(play_info.get('timelength'), scale=1000),
+            'duration': duration,
-            'subtitles': self.extract_subtitles(episode_id, episode_info.get('cid'), aid=aid),
+            'subtitles': self.extract_subtitles(episode_id, cid, aid=aid),
             '__post_extractor': self.extract_comments(aid),
             'http_headers': {'Referer': url},
+            'heatmap': list(self._extract_heatmap(cid)),
         }
 
 
@@ -948,7 +1081,8 @@ class BiliBiliBangumiMediaIE(BilibiliBaseIE):
                 'duration': 1525.777,
                 'timestamp': 1425074413,
                 'upload_date': '20150227',
-                'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)$',
+                'thumbnail': r're:https?://.*\.(?:jpg|jpeg|png)$',
+                'heatmap': list,
             },
         }],
     }]
@@ -1003,7 +1137,8 @@ class BiliBiliBangumiSeasonIE(BilibiliBaseIE):
                 'duration': 1436.992,
                 'timestamp': 1343185080,
                 'upload_date': '20120725',
-                'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)$',
+                'thumbnail': r're:https?://.*\.(?:jpg|jpeg|png)$',
+                'heatmap': list,
             },
         }],
     }]
@@ -1037,10 +1172,14 @@ class BilibiliCheeseBaseIE(BilibiliBaseIE):
             query={'avid': aid, 'cid': cid, 'ep_id': ep_id, 'fnval': 16, 'fourk': 1},
             headers=self._HEADERS, note='Downloading playinfo')['data']
 
+        formats = self.extract_formats(play_info)
+        duration = traverse_obj(episode_info, ('duration', {int_or_none}))
+        if storyboard_format := self._extract_storyboard(duration=duration, aid=aid, cid=cid):
+            formats.append(storyboard_format)
         return {
             'id': str_or_none(ep_id),
             'episode_id': str_or_none(ep_id),
-            'formats': self.extract_formats(play_info),
+            'formats': formats,
             'extractor_key': BilibiliCheeseIE.ie_key(),
             'extractor': BilibiliCheeseIE.IE_NAME,
             'webpage_url': f'https://www.bilibili.com/cheese/play/ep{ep_id}',
@@ -1048,7 +1187,7 @@ class BilibiliCheeseBaseIE(BilibiliBaseIE):
                 'episode': ('title', {str}),
                 'title': {lambda v: v and join_nonempty('index', 'title', delim=' - ', from_dict=v)},
                 'alt_title': ('subtitle', {str}),
-                'duration': ('duration', {int_or_none}),
+                'duration': {value(duration)},
                 'episode_number': ('index', {int_or_none}),
                 'thumbnail': ('cover', {url_or_none}),
                 'timestamp': ('release_date', {int_or_none}),
@@ -1061,6 +1200,7 @@ class BilibiliCheeseBaseIE(BilibiliBaseIE):
             'subtitles': self.extract_subtitles(ep_id, cid, aid=aid),
             '__post_extractor': self.extract_comments(aid),
             'http_headers': self._HEADERS,
+            'heatmap': list(self._extract_heatmap(cid)),
         }
 
     def _download_season_info(self, query_key, video_id):
@@ -1086,8 +1226,9 @@ class BilibiliCheeseIE(BilibiliCheeseBaseIE):
             'duration': 221,
             'timestamp': 1695549606,
             'upload_date': '20230924',
-            'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)$',
+            'thumbnail': r're:https?://.*\.(?:jpg|jpeg|png)$',
             'view_count': int,
+            'heatmap': list,
         },
     }]
 
@@ -1119,8 +1260,9 @@ class BilibiliCheeseSeasonIE(BilibiliCheeseBaseIE):
                 'duration': 221,
                 'timestamp': 1695549606,
                 'upload_date': '20230924',
-                'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)$',
+                'thumbnail': r're:https?://.*\.(?:jpg|jpeg|png)$',
                 'view_count': int,
+                'heatmap': list,
             },
         }],
         'params': {'playlist_items': '1'},
@@ -1492,6 +1634,7 @@ class BilibiliPlaylistIE(BilibiliSpaceListBaseIE):
             'view_count': int,
             'like_count': int,
             '_old_archive_ids': ['bilibili 687146339_part1'],
+            'heatmap': [],
         },
         'params': {'noplaylist': True},
     }, {
@@ -1686,8 +1829,9 @@ class BiliBiliSearchIE(SearchInfoExtractor):
                 'comment_count': int,
                 'view_count': int,
                 'like_count': int,
-                'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)$',
+                'thumbnail': r're:https?://.*\.(?:jpg|jpeg|png)$',
                 '_old_archive_ids': ['bilibili 988222410_part1'],
+                'heatmap': [],
             },
         }],
     }]
@@ -1734,7 +1878,7 @@ class BilibiliAudioIE(BilibiliAudioBaseIE):
             'id': '1003142',
             'ext': 'm4a',
             'title': '【tsukimi】YELLOW / 神山羊',
-            'artist': 'tsukimi',
+            'artists': ['tsukimi'],
             'comment_count': int,
             'description': 'YELLOW的mp3版！',
             'duration': 183,
@@ -1746,7 +1890,7 @@ class BilibiliAudioIE(BilibiliAudioBaseIE):
             'thumbnail': r're:^https?://.+\.jpg',
             'timestamp': 1564836614,
             'upload_date': '20190803',
-            'uploader': 'tsukimi-つきみぐー',
+            'uploader': '十六夜tsukimiつきみぐ',
             'view_count': int,
         },
     }
@@ -1801,10 +1945,10 @@ class BilibiliAudioAlbumIE(BilibiliAudioBaseIE):
         'url': 'https://www.bilibili.com/audio/am10624',
         'info_dict': {
             'id': '10624',
-            'title': '每日新曲推荐（每日11:00更新）',
+            'title': '新曲推荐',
             'description': '每天11:00更新，为你推送最新音乐',
         },
-        'playlist_count': 19,
+        'playlist_mincount': 10,
     }
 
     def _real_extract(self, url):

yt_dlp/extractor/chaturbate.py

@@ -5,6 +5,7 @@ from ..utils import (
     ExtractorError,
     lowercase_escape,
     url_or_none,
+    urlencode_postdata,
 )
 
 
@@ -40,14 +41,48 @@ class ChaturbateIE(InfoExtractor):
         'only_matching': True,
     }]
 
-    _ROOM_OFFLINE = 'Room is currently offline'
+    _ERROR_MAP = {
+        'offline': 'Room is currently offline',
+        'private': 'Room is currently in a private show',
+        'away': 'Performer is currently away',
+        'password protected': 'Room is password protected',
+        'hidden': 'Hidden session in progress',
+    }
 
-    def _real_extract(self, url):
+    def _extract_from_api(self, video_id, tld):
-        video_id, tld = self._match_valid_url(url).group('id', 'tld')
+        response = self._download_json(
+            f'https://chaturbate.{tld}/get_edge_hls_url_ajax/', video_id,
+            data=urlencode_postdata({'room_slug': video_id}),
+            headers={
+                **self.geo_verification_headers(),
+                'X-Requested-With': 'XMLHttpRequest',
+                'Accept': 'application/json',
+            }, fatal=False, impersonate=True) or {}
 
+        status = response.get('room_status')
+        if status != 'public':
+            if error := self._ERROR_MAP.get(status):
+                raise ExtractorError(error, expected=True)
+            self.report_warning('Falling back to webpage extraction')
+            return None
+
+        m3u8_url = response.get('url')
+        if not m3u8_url:
+            self.raise_geo_restricted()
+
+        return {
+            'id': video_id,
+            'title': video_id,
+            'thumbnail': f'https://roomimg.stream.highwebmedia.com/ri/{video_id}.jpg',
+            'is_live': True,
+            'age_limit': 18,
+            'formats': self._extract_m3u8_formats(m3u8_url, video_id, ext='mp4', live=True),
+        }
+
+    def _extract_from_webpage(self, video_id, tld):
         webpage = self._download_webpage(
             f'https://chaturbate.{tld}/{video_id}/', video_id,
-            headers=self.geo_verification_headers())
+            headers=self.geo_verification_headers(), impersonate=True)
 
         found_m3u8_urls = []
 
@@ -85,8 +120,8 @@ class ChaturbateIE(InfoExtractor):
                 webpage, 'error', group='error', default=None)
             if not error:
                 if any(p in webpage for p in (
-                        self._ROOM_OFFLINE, 'offline_tipping', 'tip_offline')):
+                        self._ERROR_MAP['offline'], 'offline_tipping', 'tip_offline')):
-                    error = self._ROOM_OFFLINE
+                    error = self._ERROR_MAP['offline']
             if error:
                 raise ExtractorError(error, expected=True)
             raise ExtractorError('Unable to find stream URL')
@@ -113,3 +148,7 @@ class ChaturbateIE(InfoExtractor):
             'is_live': True,
             'formats': formats,
         }
+
+    def _real_extract(self, url):
+        video_id, tld = self._match_valid_url(url).group('id', 'tld')
+        return self._extract_from_api(video_id, tld) or self._extract_from_webpage(video_id, tld)

yt_dlp/extractor/common.py

@@ -279,6 +279,7 @@ class InfoExtractor:
     thumbnails:     A list of dictionaries, with the following entries:
                         * "id" (optional, string) - Thumbnail format ID
                         * "url"
+                        * "ext" (optional, string) - actual image extension if not given in URL
                         * "preference" (optional, int) - quality of the image
                         * "width" (optional, int)
                         * "height" (optional, int)

yt_dlp/extractor/patreon.py

@@ -16,10 +16,10 @@ from ..utils import (
     parse_iso8601,
     smuggle_url,
     str_or_none,
-    traverse_obj,
     url_or_none,
     urljoin,
 )
+from ..utils.traversal import traverse_obj, value
 
 
 class PatreonBaseIE(InfoExtractor):
@@ -252,6 +252,27 @@ class PatreonIE(PatreonBaseIE):
             'thumbnail': r're:^https?://.+',
         },
         'skip': 'Patron-only content',
+    }, {
+        # Contains a comment reply in the 'included' section
+        'url': 'https://www.patreon.com/posts/114721679',
+        'info_dict': {
+            'id': '114721679',
+            'ext': 'mp4',
+            'upload_date': '20241025',
+            'uploader': 'Japanalysis',
+            'like_count': int,
+            'thumbnail': r're:^https?://.+',
+            'comment_count': int,
+            'title': 'Karasawa Part 2',
+            'description': 'Part 2 of this video https://www.youtube.com/watch?v=Azms2-VTASk',
+            'uploader_url': 'https://www.patreon.com/japanalysis',
+            'uploader_id': '80504268',
+            'channel_url': 'https://www.patreon.com/japanalysis',
+            'channel_follower_count': int,
+            'timestamp': 1729897015,
+            'channel_id': '9346307',
+        },
+        'params': {'getcomments': True},
     }]
     _RETURN_TYPE = 'video'
 
@@ -404,26 +425,24 @@ class PatreonIE(PatreonBaseIE):
                 f'posts/{post_id}/comments', post_id, query=params, note=f'Downloading comments page {page}')
 
             cursor = None
-            for comment in traverse_obj(response, (('data', ('included', lambda _, v: v['type'] == 'comment')), ...)):
+            for comment in traverse_obj(response, (('data', 'included'), lambda _, v: v['type'] == 'comment' and v['id'])):
                 count += 1
-                comment_id = comment.get('id')
-                attributes = comment.get('attributes') or {}
-                if comment_id is None:
-                    continue
                 author_id = traverse_obj(comment, ('relationships', 'commenter', 'data', 'id'))
-                author_info = traverse_obj(
-                    response, ('included', lambda _, v: v['id'] == author_id and v['type'] == 'user', 'attributes'),
-                    get_all=False, expected_type=dict, default={})
 
                 yield {
-                    'id': comment_id,
+                    **traverse_obj(comment, {
-                    'text': attributes.get('body'),
+                        'id': ('id', {str_or_none}),
-                    'timestamp': parse_iso8601(attributes.get('created')),
+                        'text': ('attributes', 'body', {str}),
-                    'parent': traverse_obj(comment, ('relationships', 'parent', 'data', 'id'), default='root'),
+                        'timestamp': ('attributes', 'created', {parse_iso8601}),
-                    'author_is_uploader': attributes.get('is_by_creator'),
+                        'parent': ('relationships', 'parent', 'data', ('id', {value('root')}), {str}, any),
+                        'author_is_uploader': ('attributes', 'is_by_creator', {bool}),
+                    }),
+                    **traverse_obj(response, (
+                        'included', lambda _, v: v['id'] == author_id and v['type'] == 'user', 'attributes', {
+                            'author': ('full_name', {str}),
+                            'author_thumbnail': ('image_url', {url_or_none}),
+                        }), get_all=False),
                     'author_id': author_id,
-                    'author': author_info.get('full_name'),
-                    'author_thumbnail': author_info.get('image_url'),
                 }
 
             if count < traverse_obj(response, ('meta', 'count')):

yt_dlp/extractor/radioradicale.py

@@ -0,0 +1,105 @@
+from .common import InfoExtractor
+from ..utils import url_or_none
+from ..utils.traversal import traverse_obj
+
+
+class RadioRadicaleIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?radioradicale\.it/scheda/(?P<id>[0-9]+)'
+    _TESTS = [{
+        'url': 'https://www.radioradicale.it/scheda/471591',
+        'md5': 'eb0fbe43a601f1a361cbd00f3c45af4a',
+        'info_dict': {
+            'id': '471591',
+            'ext': 'mp4',
+            'title': 'md5:e8fbb8de57011a3255db0beca69af73d',
+            'description': 'md5:5e15a789a2fe4d67da8d1366996e89ef',
+            'location': 'Napoli',
+            'duration': 2852.0,
+            'timestamp': 1459987200,
+            'upload_date': '20160407',
+            'thumbnail': 'https://www.radioradicale.it/photo400/0/0/9/0/1/00901768.jpg',
+        },
+    }, {
+        'url': 'https://www.radioradicale.it/scheda/742783/parlamento-riunito-in-seduta-comune-11a-della-xix-legislatura',
+        'info_dict': {
+            'id': '742783',
+            'title': 'Parlamento riunito in seduta comune (11ª della XIX legislatura)',
+            'description': '-) Votazione per l\'elezione di un giudice della Corte Costituzionale (nono scrutinio)',
+            'location': 'CAMERA',
+            'duration': 5868.0,
+            'timestamp': 1730246400,
+            'upload_date': '20241030',
+        },
+        'playlist': [{
+            'md5': 'aa48de55dcc45478e4cd200f299aab7d',
+            'info_dict': {
+                'id': '742783-0',
+                'ext': 'mp4',
+                'title': 'Parlamento riunito in seduta comune (11ª della XIX legislatura)',
+            },
+        }, {
+            'md5': 'be915c189c70ad2920e5810f32260ff5',
+            'info_dict': {
+                'id': '742783-1',
+                'ext': 'mp4',
+                'title': 'Parlamento riunito in seduta comune (11ª della XIX legislatura)',
+            },
+        }, {
+            'md5': 'f0ee4047342baf8ed3128a8417ac5e0a',
+            'info_dict': {
+                'id': '742783-2',
+                'ext': 'mp4',
+                'title': 'Parlamento riunito in seduta comune (11ª della XIX legislatura)',
+            },
+        }],
+    }]
+
+    def _entries(self, videos_info, page_id):
+        for idx, video in enumerate(traverse_obj(
+                videos_info, ('playlist', lambda _, v: v['sources']))):
+            video_id = f'{page_id}-{idx}'
+            formats = []
+            subtitles = {}
+
+            for m3u8_url in traverse_obj(video, ('sources', ..., 'src', {url_or_none})):
+                fmts, subs = self._extract_m3u8_formats_and_subtitles(m3u8_url, video_id)
+                formats.extend(fmts)
+                self._merge_subtitles(subs, target=subtitles)
+            for sub in traverse_obj(video, ('subtitles', ..., lambda _, v: url_or_none(v['src']))):
+                self._merge_subtitles({sub.get('srclang') or 'und': [{
+                    'url': sub['src'],
+                    'name': sub.get('label'),
+                }]}, target=subtitles)
+
+            yield {
+                'id': video_id,
+                'title': video.get('title'),
+                'formats': formats,
+                'subtitles': subtitles,
+            }
+
+    def _real_extract(self, url):
+        page_id = self._match_id(url)
+        webpage = self._download_webpage(url, page_id)
+
+        videos_info = self._search_json(
+            r'jQuery\.extend\(Drupal\.settings\s*,',
+            webpage, 'videos_info', page_id)['RRscheda']
+
+        entries = list(self._entries(videos_info, page_id))
+
+        common_info = {
+            'id': page_id,
+            'title': self._og_search_title(webpage),
+            'description': self._og_search_description(webpage),
+            'location': videos_info.get('luogo'),
+            **self._search_json_ld(webpage, page_id),
+        }
+
+        if len(entries) == 1:
+            return {
+                **entries[0],
+                **common_info,
+            }
+
+        return self.playlist_result(entries, multi_video=True, **common_info)

yt_dlp/extractor/redgifs.py

@@ -213,7 +213,7 @@ class RedGifsSearchIE(RedGifsBaseInfoExtractor):
 class RedGifsUserIE(RedGifsBaseInfoExtractor):
     IE_DESC = 'Redgifs user'
     _VALID_URL = r'https?://(?:www\.)?redgifs\.com/users/(?P<username>[^/?#]+)(?:\?(?P<query>[^#]+))?'
-    _PAGE_SIZE = 30
+    _PAGE_SIZE = 80
     _TESTS = [
         {
             'url': 'https://www.redgifs.com/users/lamsinka89',
@@ -222,7 +222,7 @@ class RedGifsUserIE(RedGifsBaseInfoExtractor):
                 'title': 'lamsinka89',
                 'description': 'RedGifs user lamsinka89, ordered by recent',
             },
-            'playlist_mincount': 100,
+            'playlist_mincount': 391,
         },
         {
             'url': 'https://www.redgifs.com/users/lamsinka89?page=3',
@@ -231,7 +231,7 @@ class RedGifsUserIE(RedGifsBaseInfoExtractor):
                 'title': 'lamsinka89',
                 'description': 'RedGifs user lamsinka89, ordered by recent',
             },
-            'playlist_count': 30,
+            'playlist_count': 80,
         },
         {
             'url': 'https://www.redgifs.com/users/lamsinka89?order=best&type=g',
@@ -240,7 +240,17 @@ class RedGifsUserIE(RedGifsBaseInfoExtractor):
                 'title': 'lamsinka89',
                 'description': 'RedGifs user lamsinka89, ordered by best',
             },
-            'playlist_mincount': 100,
+            'playlist_mincount': 391,
+        },
+        {
+            'url': 'https://www.redgifs.com/users/ignored52',
+            'note': 'https://github.com/yt-dlp/yt-dlp/issues/7382',
+            'info_dict': {
+                'id': 'ignored52',
+                'title': 'ignored52',
+                'description': 'RedGifs user ignored52, ordered by recent',
+            },
+            'playlist_mincount': 121,
         },
     ]
 

yt_dlp/extractor/spankbang.py

@@ -71,9 +71,11 @@ class SpankBangIE(InfoExtractor):
     def _real_extract(self, url):
         mobj = self._match_valid_url(url)
         video_id = mobj.group('id') or mobj.group('id_2')
+        country = self.get_param('geo_bypass_country') or 'US'
+        self._set_cookie('.spankbang.com', 'country', country.upper())
         webpage = self._download_webpage(
             url.replace(f'/{video_id}/embed', f'/{video_id}/video'),
-            video_id, headers={'Cookie': 'country=US'})
+            video_id, impersonate=True)
 
         if re.search(r'<[^>]+\b(?:id|class)=["\']video_removed', webpage):
             raise ExtractorError(

yt_dlp/utils/_utils.py

@@ -216,7 +216,7 @@ def partial_application(func):
     sig = inspect.signature(func)
     required_args = [
         param.name for param in sig.parameters.values()
-        if param.kind in (inspect.Parameter.POSITIONAL_ONLY, inspect.Parameter.POSITIONAL_OR_KEYWORD, inspect.Parameter.VAR_POSITIONAL)
+        if param.kind in (inspect.Parameter.POSITIONAL_ONLY, inspect.Parameter.POSITIONAL_OR_KEYWORD)
         if param.default is inspect.Parameter.empty
     ]
 
@@ -4837,7 +4837,6 @@ def number_of_digits(number):
     return len('%d' % number)
 
 
-@partial_application
 def join_nonempty(*values, delim='-', from_dict=None):
     if from_dict is not None:
         values = (traversal.traverse_obj(from_dict, variadic(v)) for v in values)

yt_dlp/utils/traversal.py

@@ -332,14 +332,14 @@ class _RequiredError(ExtractorError):
 
 
 @typing.overload
-def subs_list_to_dict(*, ext: str | None = None) -> collections.abc.Callable[[list[dict]], dict[str, list[dict]]]: ...
+def subs_list_to_dict(*, lang: str | None = 'und', ext: str | None = None) -> collections.abc.Callable[[list[dict]], dict[str, list[dict]]]: ...
 
 
 @typing.overload
-def subs_list_to_dict(subs: list[dict] | None, /, *, ext: str | None = None) -> dict[str, list[dict]]: ...
+def subs_list_to_dict(subs: list[dict] | None, /, *, lang: str | None = 'und', ext: str | None = None) -> dict[str, list[dict]]: ...
 
 
-def subs_list_to_dict(subs: list[dict] | None = None, /, *, ext=None):
+def subs_list_to_dict(subs: list[dict] | None = None, /, *, lang='und', ext=None):
     """
     Convert subtitles from a traversal into a subtitle dict.
     The path should have an `all` immediately before this function.
@@ -352,7 +352,7 @@ def subs_list_to_dict(subs: list[dict] | None = None, /, *, ext=None):
     `quality`  The sort order for each subtitle
     """
     if subs is None:
-        return functools.partial(subs_list_to_dict, ext=ext)
+        return functools.partial(subs_list_to_dict, lang=lang, ext=ext)
 
     result = collections.defaultdict(list)
 
@@ -360,9 +360,15 @@ def subs_list_to_dict(subs: list[dict] | None = None, /, *, ext=None):
         if not url_or_none(sub.get('url')) and not sub.get('data'):
             continue
         sub_id = sub.pop('id', None)
-        if sub_id is None:
+        if not isinstance(sub_id, str):
+            if not lang:
                 continue
-        if ext is not None and not sub.get('ext'):
+            sub_id = lang
+        sub_ext = sub.get('ext')
+        if not isinstance(sub_ext, str):
+            if not ext:
+                sub.pop('ext', None)
+            else:
                 sub['ext'] = ext
         result[sub_id].append(sub)
     result = dict(result)
@@ -452,9 +458,9 @@ def trim_str(*, start=None, end=None):
     return trim
 
 
-def unpack(func):
+def unpack(func, **kwargs):
     @functools.wraps(func)
-    def inner(items, **kwargs):
+    def inner(items):
         return func(*items, **kwargs)
 
     return inner