mirrors/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-27 10:31:29 +00:00
Code Issues Packages Projects Releases Wiki Activity

[ie/suno] add fallbacks for basic page metadata

Browse source
This commit is contained in:
Michael Skyba 2024-11-04 23:54:19 -05:00
parent 10a1a93352
commit 2be0c24897
1 changed files with 29 additions and 10 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

39
yt_dlp/extractor/suno.py
View file

@ -4,7 +4,23 @@
from ..utils import ExtractorError, unescapeHTML from ..utils import ExtractorError, unescapeHTML
class SunoIE(InfoExtractor): 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]+)' _VALID_URL = r'https?://(?:www\.)?suno\.com/song/(?P<id>[-a-f0-9]+)'
_TESTS = [ _TESTS = [
{ {
@ -35,16 +51,19 @@ def _real_extract(self, url):
video_id = self._match_id(url) video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
url = self._html_search_meta(
['og:audio', 'twitter:player:stream'], webpage, 'url', default=None)
return { return {
'id': video_id, 'id': video_id,
'title': self._og_search_title(webpage), 'title': self._get_title(webpage),
'description': self._og_search_description(webpage), 'description': self._get_description(webpage),
'thumbnail': self._og_search_thumbnail(webpage), 'thumbnail': self._get_thumbnail(webpage),
'url': self._og_search_property('audio', webpage), 'url': url,
} }
class SunoPlaylistIE(InfoExtractor): class SunoPlaylistIE(SunoBaseIE):
_VALID_URL = r'https?://(?:www\.)?suno\.com/playlist/(?P<id>[-a-f0-9]+)' _VALID_URL = r'https?://(?:www\.)?suno\.com/playlist/(?P<id>[-a-f0-9]+)'
_TESTS = [ _TESTS = [
{ {
@ -69,7 +88,7 @@ class SunoPlaylistIE(InfoExtractor):
'info_dict': { 'info_dict': {
'id': '568eeaab-dfbf-4da6-aa0a-0fb1a32330de', 'id': '568eeaab-dfbf-4da6-aa0a-0fb1a32330de',
'title': 'Piano by @kunal | Suno', 'title': 'Piano by @kunal | Suno',
'description': 'Here are some good piano ', 'description': 'Here are some good piano',
'thumbnail': r're:https?://.*0ecc0956-3b17-4d4b-8504-55849dd75e22.*\.jpeg$', 'thumbnail': r're:https?://.*0ecc0956-3b17-4d4b-8504-55849dd75e22.*\.jpeg$',
}, },
'playlist': [ 'playlist': [
@ -120,9 +139,9 @@ def _real_extract(self, url):
return { return {
'_type': 'playlist', '_type': 'playlist',
'id': playlist_id, 'id': playlist_id,
'title': self._og_search_title(webpage), 'title': self._get_title(webpage),
'description': self._og_search_description(webpage), 'description': self._get_description(webpage),
'thumbnail': self._og_search_thumbnail(webpage), 'thumbnail': self._get_thumbnail(webpage),
'entries': [{ 'entries': [{
'id': song_tuple[0], 'id': song_tuple[0],