Compare commits

...

7 Commits

Author SHA1 Message Date
Michael Skyba
21d74b49fd
Merge 2be0c24897 into 6365e92589 2024-11-16 17:57:18 +01:00
sepro
6365e92589
[ie/bandlab] Add extractors (#11535)
Closes #7750
Authored by: seproDev
2024-11-16 17:56:43 +01:00
Alessandro Campolo
70c55cb08f
[ie/RadioRadicale] Add extractor (#5607)
Authored by: a13ssandr0, pzhlkj6612

Co-authored-by: Mozi <29089388+pzhlkj6612@users.noreply.github.com>
2024-11-16 13:56:15 +01:00
Michael Skyba
2be0c24897 [ie/suno] add fallbacks for basic page metadata 2024-11-04 23:54:46 -05:00
Michael Skyba
10a1a93352 [ie/suno] use regexes for thumbnail match tests 2024-11-04 23:54:45 -05:00
Michael Skyba
6ec19e942d [ie/suno] add playlist extractor 2024-11-04 23:54:43 -05:00
Michael Skyba
3c59d3e7a2 [ie/suno] add /song mp3 extractor 2024-11-04 20:18:18 -05:00
4 changed files with 701 additions and 0 deletions

View File

@ -208,6 +208,10 @@ from .bandcamp import (
BandcampUserIE, BandcampUserIE,
BandcampWeeklyIE, BandcampWeeklyIE,
) )
from .bandlab import (
BandlabIE,
BandlabPlaylistIE,
)
from .bannedvideo import BannedVideoIE from .bannedvideo import BannedVideoIE
from .bbc import ( from .bbc import (
BBCIE, BBCIE,
@ -1649,6 +1653,7 @@ from .radiokapital import (
RadioKapitalIE, RadioKapitalIE,
RadioKapitalShowIE, RadioKapitalShowIE,
) )
from .radioradicale import RadioRadicaleIE
from .radiozet import RadioZetPodcastIE from .radiozet import RadioZetPodcastIE
from .radlive import ( from .radlive import (
RadLiveChannelIE, RadLiveChannelIE,
@ -1983,6 +1988,7 @@ from .stretchinternet import StretchInternetIE
from .stripchat import StripchatIE from .stripchat import StripchatIE
from .stv import STVPlayerIE from .stv import STVPlayerIE
from .substack import SubstackIE from .substack import SubstackIE
from .suno import SunoIE, SunoPlaylistIE
from .sunporno import SunPornoIE from .sunporno import SunPornoIE
from .sverigesradio import ( from .sverigesradio import (
SverigesRadioEpisodeIE, SverigesRadioEpisodeIE,

438
yt_dlp/extractor/bandlab.py Normal file
View File

@ -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 {}))

View File

@ -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)

152
yt_dlp/extractor/suno.py Normal file
View File

@ -0,0 +1,152 @@
import re
from .common import InfoExtractor
from ..utils import ExtractorError, unescapeHTML
class SunoBaseIE(InfoExtractor):
def _get_title(self, webpage):
return self._html_search_meta(
['og:title', 'twitter:title'], webpage, 'title',
default=None) or self._html_extract_title(webpage)
def _get_description(self, webpage):
return self._html_search_meta(
['og:description', 'description', 'twitter:description'],
webpage, 'description', default=None)
def _get_thumbnail(self, webpage):
return self._html_search_meta(
['og:image', 'twitter:image'], webpage, 'thumbnail', default=None)
class SunoIE(SunoBaseIE):
_VALID_URL = r'https?://(?:www\.)?suno\.com/song/(?P<id>[-a-f0-9]+)'
_TESTS = [
{
'url': 'https://suno.com/song/ab39a04d-b2e6-463b-9b8e-ddea725422f5',
'md5': 'ef850763b175d8a3c7fba5e2dbdc6bc5',
'info_dict': {
'id': 'ab39a04d-b2e6-463b-9b8e-ddea725422f5',
'title': 'Life\'s a Soundtrack · AI Funk Factory @ YT by @funk | Suno',
'description': 'groovy funk, melodic song. Listen and make your own with Suno.',
'thumbnail': r're:https?://.*903f2bd7-ccc0-4029-a76a-887f07ebc2df.*\.jpeg$',
'ext': 'mp3',
},
},
{
'url': 'https://suno.com/song/9cbcb5f4-f367-4f1c-8a32-23ec62bdc47e',
'md5': '2f038badef88d189891d5f8cd8d8804d',
'info_dict': {
'id': '9cbcb5f4-f367-4f1c-8a32-23ec62bdc47e',
'title': 'Pequenos Prazeres da Vida by @groovebot | Suno',
'description': 'pop bossa nova song. Listen and make your own with Suno.',
'thumbnail': r're:https?://.*9cbcb5f4-f367-4f1c-8a32-23ec62bdc47e.*\.jpeg$',
'ext': 'mp3',
},
},
]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
url = self._html_search_meta(
['og:audio', 'twitter:player:stream'], webpage, 'url', default=None)
return {
'id': video_id,
'title': self._get_title(webpage),
'description': self._get_description(webpage),
'thumbnail': self._get_thumbnail(webpage),
'url': url,
}
class SunoPlaylistIE(SunoBaseIE):
_VALID_URL = r'https?://(?:www\.)?suno\.com/playlist/(?P<id>[-a-f0-9]+)'
_TESTS = [
{
'url': 'https://suno.com/playlist/01f2ac32-c32e-4d26-b10c-221107c02946',
'info_dict': {
'id': '01f2ac32-c32e-4d26-b10c-221107c02946',
'title': 'Main 0 by @contemplativetranspositions367 | Suno',
'description': 'Hopefully the test case passed',
'thumbnail': r're:https?://.*19d6d518-1b87-43b3-90b9-2a476ca5824a.*\.jpeg$',
},
'playlist': [{
'info_dict': {
'id': '19d6d518-1b87-43b3-90b9-2a476ca5824a',
'title': 'Ceaseless <Echoes>',
'ext': 'mp3',
},
}],
'playlist_count': 1,
},
{
'url': 'https://www.suno.com/playlist/568eeaab-dfbf-4da6-aa0a-0fb1a32330de',
'info_dict': {
'id': '568eeaab-dfbf-4da6-aa0a-0fb1a32330de',
'title': 'Piano by @kunal | Suno',
'description': 'Here are some good piano',
'thumbnail': r're:https?://.*0ecc0956-3b17-4d4b-8504-55849dd75e22.*\.jpeg$',
},
'playlist': [
{
'info_dict': {
'id': '0ecc0956-3b17-4d4b-8504-55849dd75e22',
'title': 'ST',
'ext': 'mp3',
},
},
{
'info_dict': {
'id': '3fef7d44-c5a3-4181-9de3-d81542af23ef',
'title': 'ST',
'ext': 'mp3',
},
},
{
'info_dict': {
'id': '15e797fa-06c0-4e11-8cc0-3b2580476039',
'title': 'ST - 2',
'ext': 'mp3',
},
},
],
'playlist_count': 3,
},
]
def _real_extract(self, url):
playlist_id = self._match_id(url)
webpage = self._download_webpage(url, playlist_id)
# There are <a>s whose href is a song/ID path. The <span>s directly
# within them have the respective song title as their innerHTML.
# Alternatively, this info can be extracted through parsing an escaped
# JSON object inside a <script> array, though that seems even less stable
# than this HTML.
songs_regex = r'/song/(?P<id>[-a-f0-9]+)["\'][^>]*>\s*<span[^>]*>\s*(?P<title>[^<]+)</span>'
songs = re.findall(songs_regex, webpage)
og_audio_regex = self._og_regexes('audio')[0]
audio_urls = [matches[0] for matches in re.findall(og_audio_regex, webpage)]
if len(songs) != len(audio_urls):
raise ExtractorError('Unexpected mismatch between song HTML list and og audio URLs')
return {
'_type': 'playlist',
'id': playlist_id,
'title': self._get_title(webpage),
'description': self._get_description(webpage),
'thumbnail': self._get_thumbnail(webpage),
'entries': [{
'id': song_tuple[0],
'title': unescapeHTML(song_tuple[1]),
'url': audio_urls[i],
} for i, song_tuple in enumerate(songs)],
}