Merge 1ef35f1c00 into 6365e92589

Closes #7750
Authored by: seproDev

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/googledrive.py

@@ -3,6 +3,7 @@ import urllib.parse
 
 from .common import InfoExtractor
 from .youtube import YoutubeIE
+from ..networking.exceptions import HTTPError
 from ..utils import (
     ExtractorError,
     bug_reports_message,
@@ -12,6 +13,7 @@ from ..utils import (
     get_element_html_by_id,
     int_or_none,
     lowercase_escape,
+    traverse_obj,
     try_get,
     update_url_query,
 )
@@ -51,6 +53,17 @@ class GoogleDriveIE(InfoExtractor):
             'duration': 184,
             'thumbnail': 'https://drive.google.com/thumbnail?id=1IP0o8dHcQrIHGgVyp0Ofvx2cGfLzyO1x',
         },
+    }, {
+        # shortcut url
+        'url': 'https://drive.google.com/file/d/1_n3-8ZwEUV4OniMsLAJ_C1JEjuT2u5Pk/view?usp=drivesdk',
+        'md5': '43d34f7be1acc0262f337a039d1ad12d',
+        'info_dict': {
+            'id': '1J1RCw2jcgUngrZRdpza-IHXYkardZ-4l',
+            'ext': 'webm',
+            'title': 'Forrest walk with Best Mind Refresh Music Mithran [tEvJKrE4cS0].webm',
+            'duration': 512,
+            'thumbnail': 'https://drive.google.com/thumbnail?id=1J1RCw2jcgUngrZRdpza-IHXYkardZ-4l',
+        },
     }, {
         # video can't be watched anonymously due to view count limit reached,
         # but can be downloaded (see https://github.com/ytdl-org/youtube-dl/issues/14046)
@@ -166,6 +179,17 @@ class GoogleDriveIE(InfoExtractor):
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
+        try:
+            _, webpage_urlh = self._download_webpage_handle(url, video_id)
+        except ExtractorError as e:
+            if isinstance(e.cause, HTTPError):
+                if e.cause.status in (401, 403):
+                    self.raise_login_required('Access Denied')
+                raise
+        if webpage_urlh.url != url:
+            url = webpage_urlh.url
+            video_id = self._match_id(url)
+
         video_info = urllib.parse.parse_qs(self._download_webpage(
             'https://drive.google.com/get_video_info',
             video_id, 'Downloading video webpage', query={'docid': video_id}))
@@ -289,7 +313,7 @@ class GoogleDriveIE(InfoExtractor):
 
 class GoogleDriveFolderIE(InfoExtractor):
     IE_NAME = 'GoogleDrive:Folder'
-    _VALID_URL = r'https?://(?:docs|drive)\.google\.com/drive/folders/(?P<id>[\w-]{28,})'
+    _VALID_URL = r'https?://(?:docs|drive)\.google\.com/drive/(?:folders/(?P<id>[\w-]{19,})|my-drive)'
     _TESTS = [{
         'url': 'https://drive.google.com/drive/folders/1dQ4sx0-__Nvg65rxTSgQrl7VyW_FZ9QI',
         'info_dict': {
@@ -297,47 +321,83 @@ class GoogleDriveFolderIE(InfoExtractor):
             'title': 'Forrest',
         },
         'playlist_count': 3,
+    }, {
+        'note': 'Contains various formats and a subfolder, folder name was formerly mismatched.'
+                'also contains loop shortcut, shortcut to non-downloadable files, etc.',
+        'url': 'https://docs.google.com/drive/folders/1jjrhqi94d8TSHSVMSdBjD49MOiHYpHfF',
+        'info_dict': {
+            'id': '1jjrhqi94d8TSHSVMSdBjD49MOiHYpHfF',
+            'title': '], sideChannel: {}});',
+        },
+        'playlist_count': 8,
     }]
-    _BOUNDARY = '=====vc17a3rwnndj====='
-    _REQUEST = "/drive/v2beta/files?openDrive=true&reason=102&syncType=0&errorRecovery=false&q=trashed%20%3D%20false%20and%20'{folder_id}'%20in%20parents&fields=kind%2CnextPageToken%2Citems(kind%2CmodifiedDate%2CmodifiedByMeDate%2ClastViewedByMeDate%2CfileSize%2Cowners(kind%2CpermissionId%2Cid)%2ClastModifyingUser(kind%2CpermissionId%2Cid)%2ChasThumbnail%2CthumbnailVersion%2Ctitle%2Cid%2CresourceKey%2Cshared%2CsharedWithMeDate%2CuserPermission(role)%2CexplicitlyTrashed%2CmimeType%2CquotaBytesUsed%2Ccopyable%2CfileExtension%2CsharingUser(kind%2CpermissionId%2Cid)%2Cspaces%2Cversion%2CteamDriveId%2ChasAugmentedPermissions%2CcreatedDate%2CtrashingUser(kind%2CpermissionId%2Cid)%2CtrashedDate%2Cparents(id)%2CshortcutDetails(targetId%2CtargetMimeType%2CtargetLookupStatus)%2Ccapabilities(canCopy%2CcanDownload%2CcanEdit%2CcanAddChildren%2CcanDelete%2CcanRemoveChildren%2CcanShare%2CcanTrash%2CcanRename%2CcanReadTeamDrive%2CcanMoveTeamDriveItem)%2Clabels(starred%2Ctrashed%2Crestricted%2Cviewed))%2CincompleteSearch&appDataFilter=NO_APP_DATA&spaces=drive&pageToken={page_token}&maxResults=50&supportsTeamDrives=true&includeItemsFromAllDrives=true&corpora=default&orderBy=folder%2Ctitle_natural%20asc&retryCount=0&key={key} HTTP/1.1"
-    _DATA = f'''--{_BOUNDARY}
-content-type: application/http
-content-transfer-encoding: binary
 
-GET %s
+    def _extract_json_meta(self, webpage, video_id, dsval=None, hashval=None, name=None, **kwargs):
-
+        """
---{_BOUNDARY}
+        Uses regex to search for json metadata with 'ds' value(0-5) or 'hash' value(1-6)
-'''
+        from the webpage.
-
+            logged out  folder info:ds0hash1;          items:ds4hash6
-    def _call_api(self, folder_id, key, data, **kwargs):
+            logged in   folder info:ds0hash1;          items:ds5hash6
-        response = self._download_webpage(
+            my-drive    folder info:ds0hash1/ds0hash4; items:ds5hash6
-            'https://clients6.google.com/batch/drive/v2beta',
+        For example, if the webpage contains the line below, the empty data array
-            folder_id, data=data.encode(),
+        can be got by passing dsval=3 or hashval=2 to this method.
-            headers={
+            AF_initDataCallback({key: 'ds:3', hash: '2', data:[], sideChannel: {}});
-                'Content-Type': 'text/plain;charset=UTF-8;',
+        """
-                'Origin': 'https://drive.google.com',
+        _ARRAY_RE = r'\[(?s:.+)\]'
-            }, query={
+        _META_END_RE = r', sideChannel: \{\}\}\);'  # greedy match to deal with the 2nd test case
-                '$ct': f'multipart/mixed; boundary="{self._BOUNDARY}"',
+        if dsval is not None:
-                'key': key,
+            if not name:
-            }, **kwargs)
+                name = f'webpage JSON metadata ds:{dsval}'
-        return self._search_json('', response, 'api response', folder_id, **kwargs) or {}
+            return self._search_json(
-
+                rf'''key\s*?:\s*?(['"])ds:\s*?{dsval}\1,[^\[]*?data:''', webpage, name, video_id,
-    def _get_folder_items(self, folder_id, key):
+                end_pattern=_META_END_RE, contains_pattern=_ARRAY_RE, **kwargs)
-        page_token = ''
+        elif hashval is not None:
-        while page_token is not None:
+            if not name:
-            request = self._REQUEST.format(folder_id=folder_id, page_token=page_token, key=key)
+                name = f'webpage JSON metadata hash:{hashval}'
-            page = self._call_api(folder_id, key, self._DATA % request)
+            return self._search_json(
-            yield from page['items']
+                rf'''hash\s*?:\s*?(['"]){hashval}\1,[^\[]*?data:''', webpage, name, video_id,
-            page_token = page.get('nextPageToken')
+                end_pattern=_META_END_RE, contains_pattern=_ARRAY_RE, **kwargs)
 
     def _real_extract(self, url):
-        folder_id = self._match_id(url)
+        def item_url_getter(item, video_id):
+            if not isinstance(item, list):
+                return None
+            available_IEs = (GoogleDriveFolderIE, GoogleDriveIE)  # subfolder or item
+            if 'application/vnd.google-apps.shortcut' in item:  # extract real link
+                entry_url = traverse_obj(
+                    item,
+                    (..., ..., lambda _, v: any(ie.suitable(v) for ie in available_IEs), any))
+            else:
+                entry_url = traverse_obj(
+                    item,
+                    (lambda _, v: any(ie.suitable(v) for ie in available_IEs), any))
+            if not entry_url:
+                return None
+            return self.url_result(entry_url, video_id=video_id, video_title=item[2])
 
-        webpage = self._download_webpage(url, folder_id)
+        folder_id = self._match_id(url) or 'my-drive'
-        key = self._search_regex(r'"(\w{39})"', webpage, 'key')
+        headers = self.geo_verification_headers()
 
-        folder_info = self._call_api(folder_id, key, self._DATA % f'/drive/v2beta/files/{folder_id} HTTP/1.1', fatal=False)
+        try:
+            webpage, urlh = self._download_webpage_handle(url, folder_id, headers=headers)
+        except ExtractorError as e:
+            if isinstance(e.cause, HTTPError):
+                if e.cause.status == 404:
+                    self.raise_no_formats(e.cause.msg, expected=True)
+                elif e.cause.status == 403:
+                    # logged in with an account without access
+                    self.raise_login_required('Access Denied')
+            raise
+        if urllib.parse.urlparse(urlh.url).netloc == 'accounts.google.com':
+            # not logged in when visiting a private folder
+            self.raise_login_required('Access Denied')
 
-        return self.playlist_from_matches(
+        title = self._extract_json_meta(webpage, folder_id, dsval=0, name='folder info')[1][2]
-            self._get_folder_items(folder_id, key), folder_id, folder_info.get('title'),
+        items = self._extract_json_meta(webpage, folder_id, hashval=6, name='folder items')[-1]
-            ie=GoogleDriveIE, getter=lambda item: f'https://drive.google.com/file/d/{item["id"]}')
+
+        if items is False:  # empty folder
+            return self.playlist_result([], folder_id, title)
+
+        return self.playlist_result(
+            (entry for item in items if (entry := item_url_getter(item, folder_id))),
+            folder_id, title)

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)