Merge 049862b803 into 1d253b0a27

Closes #11483
Authored by: jshumphrey, bashonly

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

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/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/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/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/rtp.py

@@ -4,40 +4,97 @@ import re
 import urllib.parse
 
 from .common import InfoExtractor
-from ..utils import js_to_json
+from ..utils import (
+    ExtractorError,
+    determine_ext,
+    join_nonempty,
+    js_to_json,
+)
 
 
 class RTPIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?rtp\.pt/play/(?:(?:estudoemcasa|palco|zigzag)/)?p(?P<program_id>[0-9]+)/(?P<id>[^/?#]+)'
+    _VALID_URL = r'https?://(?:(?:www\.)?rtp\.pt/play/(?P<subarea>.*/)?p(?P<program_id>\d+)/|arquivos\.rtp\.pt/conteudos/)(?P<id>[^/?#]+)'
     _TESTS = [{
-        'url': 'http://www.rtp.pt/play/p405/e174042/paixoes-cruzadas',
+        'url': 'https://www.rtp.pt/play/p9165/e562949/por-do-sol',
-        'md5': 'e736ce0c665e459ddb818546220b4ef8',
         'info_dict': {
-            'id': 'e174042',
+            'id': 'e562949',
-            'ext': 'mp3',
-            'title': 'Paixões Cruzadas',
-            'description': 'As paixões musicais de António Cartaxo e António Macedo',
-            'thumbnail': r're:^https?://.*\.jpg',
-        },
-    }, {
-        'url': 'https://www.rtp.pt/play/zigzag/p13166/e757904/25-curiosidades-25-de-abril',
-        'md5': '9a81ed53f2b2197cfa7ed455b12f8ade',
-        'info_dict': {
-            'id': 'e757904',
             'ext': 'mp4',
-            'title': '25 Curiosidades, 25 de Abril',
+            'title': 'Pôr do Sol Episódio 1',
-            'description': 'Estudar ou não estudar - Em cada um dos episódios descobrimos uma curiosidade acerca de como era viver em Portugal antes da revolução do 25 de abr',
+            'description': 'Madalena Bourbon de Linhaça vive atormentada pelo segredo que esconde desde 1990. Matilde Bourbon de Linhaça sonha fugir com o seu amor proibido. O',
-            'thumbnail': r're:^https?://.*\.jpg',
+            'thumbnail': r're:https?://.*\.(?:jpg|png)',
         },
     }, {
-        'url': 'http://www.rtp.pt/play/p831/a-quimica-das-coisas',
+        'url': 'https://www.rtp.pt/play/p12646/e738493/telejornal',
-        'only_matching': True,
+        'info_dict': {
+            'id': 'e738493',
+            'ext': 'mp4',
+            'title': 'Telejornal de 01 jan 2024 PARTE 1',
+            'description': 'A mais rigorosa seleção de notícias, todos os dias às 20h00. De segunda a domingo, João Adelino Faria, José Rodrigues dos Santos e Ana Lourenço',
+            'thumbnail': r're:https?://.*\.(?:jpg|png)',
+        },
     }, {
-        'url': 'https://www.rtp.pt/play/estudoemcasa/p7776/portugues-1-ano',
+        'url': 'https://www.rtp.pt/play/p6646/e457262/grande-entrevista',
-        'only_matching': True,
+        'info_dict': {
+            'id': 'e457262',
+            'ext': 'mp4',
+            'title': 'Grande Entrevista Episódio 7 - de 19 fev 2020',
+            'description': 'Bruno Nogueira - É um dos mais originais humoristas portugueses e de maior êxito! Bruno Nogueira na Grande Entrevista com Vítor Gonçalves.',
+            'thumbnail': r're:https?://.*\.(?:jpg|png)',
+        },
     }, {
-        'url': 'https://www.rtp.pt/play/palco/p13785/l7nnon',
+        'url': 'https://www.rtp.pt/play/p1525/e738522/a-mosca',
-        'only_matching': True,
+        'info_dict': {
+            'id': 'e738522',
+            'ext': 'mp4',
+            'title': 'A Mosca de 02 jan 2024',
+            'description': 'Ano novo, vida nova - Ano novo, vida nova',
+            'thumbnail': r're:https?://.*\.(?:jpg|png)',
+        },
+    }, {
+        'url': 'https://www.rtp.pt/play/estudoemcasa/p7776/e539826/portugues-1-ano',
+        'info_dict': {
+            'id': 'e539826',
+            'ext': 'mp4',
+            'title': 'Português - 1.º ano , aula 45 - 27 abr 2021',
+            'description': 'A História do Pedrito Coelho, de Beatrix Potter. O dígrafo \'lh\' - A História do Pedrito Coelho, de Beatrix Potter. O dígrafo \'lh\'.',
+            'thumbnail': r're:https?://.*\.(?:jpg|png)',
+        },
+    }, {
+        'url': 'https://www.rtp.pt/play/zigzag/p13857/e794575/zig-zag-zzz-e-amigos',
+        'info_dict': {
+            'id': 'e794575',
+            'ext': 'mp4',
+            'title': 'Zig, Zag, Zzz e Amigos Episódio 1 - de 16 set 2024',
+            'description': 'O Brinquedo Perdido - Zig, Zag e Zzz são três amigos inseparáveis que partilham aventuras emocionantes e cheias de imaginação. Exploram o mundo <20>',
+            'thumbnail': r're:https?://.*\.(?:jpg|png)',
+        },
+    }, {
+        'url': 'https://www.rtp.pt/play/palco/p13151/premio-miguel-rovisco-2023-requiem-por-isabel',
+        'info_dict': {
+            'id': 'premio-miguel-rovisco-2023-requiem-por-isabel',
+            'ext': 'mp4',
+            'title': 'Prémio Miguel Rovisco 23: Requiem Por Isabel de 30 mar 2024',
+            'description': 'Lucrécia foi a atriz mais famosa e requisitada do seu tempo. Este já não é o seu tempo. A debater-se com a decrepitude física e financeira, foi o',
+            'thumbnail': r're:https?://.*\.(?:jpg|png)',
+        },
+    }, {
+        'url': 'https://arquivos.rtp.pt/conteudos/liga-dos-ultimos-152/',
+        'info_dict': {
+            'id': 'liga-dos-ultimos-152',
+            'ext': 'mp4',
+            'title': 'Liga dos Últimos – RTP Arquivos',
+            'description': 'Magazine desportivo, com apresentação de Álvaro Costa e comentários em estúdio do professor Hernâni Gonçalves e do sociólogo João Nuno Coelho. Destaque para os jogos de futebol das equipas dos escalões secundários de Portugal, com momentos dos jogos: Agrário de Lamas vs Pampilhoense e Apúlia vs Fragoso.',
+            'thumbnail': r're:https?://.*\.(?:jpg|png)',
+        },
+    }, {
+        'url': 'https://www.rtp.pt/play/p510/e786608/aleixo-fm',
+        'info_dict': {
+            'id': 'e786608',
+            'ext': 'mp3',
+            'title': 'Aleixo FM de 31 jul 2024',
+            'description': 'Melhor dia pra casar - Já o diz Joaquim de Magalhães Fernandes Barreiros, comummente conhecido como Quim Barreiros. Mas será mesmo este o melhor di',
+            'thumbnail': r're:https?://.*\.(?:jpg|png)',
+        },
     }]
 
     _RX_OBFUSCATION = re.compile(r'''(?xs)
@@ -60,42 +117,77 @@ class RTPIE(InfoExtractor):
         video_id = self._match_id(url)
 
         webpage = self._download_webpage(url, video_id)
-        title = self._html_search_meta(
-            'twitter:title', webpage, display_name='title', fatal=True)
 
+        # Title tag includes relevant data
+        title = self._html_search_regex(r'<title>(.+?)</title>', webpage, 'title', default='')
+
+        # Raise error if episode is unavailable
+        if 'Este episódio não se encontra disponível' in title:
+            raise ExtractorError('Episode unavailable', expected=True)
+
+        # Replace irrelevant text in title
+        title = re.sub(r' -  ?(RTP Play|Estudo Em Casa|Zig Zag Play|RTP Palco)( - RTP)?', '', title)
+
+        # Check if it's a episode split in parts
+        part = self._html_search_regex(r'section\-parts.*<span.*>(.+?)</span>.*</ul>', webpage, 'part', default=None)
+
+        # Add episode part identification to title if it exists
+        title = join_nonempty(title, part, delim=' ')
+
+        # Extract f and config from page
         f, config = self._search_regex(
             r'''(?sx)
                 (?:var\s+f\s*=\s*(?P<f>".*?"|{[^;]+?});\s*)?
-                var\s+player1\s+=\s+new\s+RTPPlayer\s*\((?P<config>{(?:(?!\*/).)+?})\);(?!\s*\*/)
+                var\s+player1?\s+=\s+new\s+RTPPlayer\s*\((?P<config>{(?:(?!\*/).)+?})\);(?!\s*\*/)
             ''', webpage,
             'player config', group=('f', 'config'))
 
         config = self._parse_json(
             config, video_id,
             lambda data: self.__unobfuscate(data, video_id=video_id))
+
+        # Estudo em Casa / Zig Zag / Palco / RTP Arquivos subareas don't include f
         f = config['file'] if not f else self._parse_json(
             f, video_id,
             lambda data: self.__unobfuscate(data, video_id=video_id))
 
         formats = []
         if isinstance(f, dict):
-            f_hls = f.get('hls')
+            file_hls = f.get('hls')
-            if f_hls is not None:
+            file_fps = f.get('fps')
-                formats.extend(self._extract_m3u8_formats(
-                    f_hls, video_id, 'mp4', 'm3u8_native', m3u8_id='hls'))
 
-            f_dash = f.get('dash')
+            if file_fps is not None:
-            if f_dash is not None:
+                # RTP Arquivos specific use case
-                formats.extend(self._extract_mpd_formats(f_dash, video_id, mpd_id='dash'))
+                if '/arquivo/' in file_fps:
+                    file_key = config['fileKey']
+                    split_file_key = file_key.split('/')
+                    filename = split_file_key[-1]
+                    del split_file_key[-1]
+                    split_file_key.extend([f'index.m3u8?tlm=hls&streams={filename}.m3u8'])
+
+                    path = '/'.join(split_file_key)
+
+                    file_hls = f'https://streaming-arquivo-ondemand.rtp.pt/nas2.share{path}'
+                elif file_hls is None:
+                    file_hls = file_fps.replace('drm-fps', 'hls')
+
+            formats.extend(self._extract_m3u8_formats(
+                file_hls, video_id, 'mp4', 'm3u8_native', m3u8_id='hls'))
         else:
-            formats.append({
+            ext = determine_ext(f)
-                'format_id': 'f',
+
-                'url': f,
+            if ext == 'm3u8':
-                'vcodec': 'none' if config.get('mediaType') == 'audio' else None,
+                formats.extend(self._extract_m3u8_formats(
-            })
+                    f, video_id, 'mp4', 'm3u8_native', m3u8_id='hls'))
+
+            else:
+                formats.append({
+                    'format_id': 'f',
+                    'url': f,
+                    'vcodec': 'none' if config.get('mediaType') == 'audio' else None,
+                })
 
         subtitles = {}
-
         vtt = config.get('vtt')
         if vtt is not None:
             for lcode, lname, url in vtt:
@@ -108,7 +200,7 @@ class RTPIE(InfoExtractor):
             'id': video_id,
             'title': title,
             'formats': formats,
-            'description': self._html_search_meta(['description', 'twitter:description'], webpage),
+            'description': self._html_search_meta(['og:description', 'description'], webpage),
             'thumbnail': config.get('poster') or self._og_search_thumbnail(webpage),
             'subtitles': subtitles,
         }

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(