mirrors/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2025-06-27 17:08:32 +00:00
Code Issues Projects Releases Wiki Activity

Review changes

Browse Source
This commit is contained in:
Iuri Campos 2025-06-18 17:17:33 +01:00
parent c34129c354
commit a5778de413
1 changed files with 64 additions and 70 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

134
yt_dlp/extractor/udio.py
View File

@ -1,4 +1,7 @@
import re
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import determine_ext, urljoin
class UdioIE(InfoExtractor): class UdioIE(InfoExtractor):
@ -6,74 +9,84 @@ class UdioIE(InfoExtractor):
_TESTS = [{ _TESTS = [{
'url': 'https://www.udio.com/songs/ehJuLz9DuCtVapQMVMcA7N', 'url': 'https://www.udio.com/songs/ehJuLz9DuCtVapQMVMcA7N',
'info_dict': 'info_dict':
{'id': 'ehJuLz9DuCtVapQMVMcA7N', {
'title': 'Lost Love | Udio', 'id': 'ehJuLz9DuCtVapQMVMcA7N',
'description': "Listen to Lost Love by The I Don't Knows on Udio. Discover, create, and share music with the world. Use the latest technology to create AI music in seconds.", 'title': 'Lost Love',
'uploader': "The I Don't Knows", 'description': "Listen to Lost Love by The I Don't Knows on Udio. Discover, create, and share music with the world. Use the latest technology to create AI music in seconds.",
'uploader_url': "https://udio.com/artist/The I Don't Knows"}, 'uploader': "The I Don't Knows",
'uploader_url': "https://udio.com/artist/The I Don't Knows",
},
'playlist_count': 1, 'playlist_count': 1,
}, { }, {
'url': 'https://www.udio.com/songs/hGZqWy3bPMrN3tosf5QZqt', 'url': 'https://www.udio.com/songs/hGZqWy3bPMrN3tosf5QZqt',
'info_dict': 'info_dict':
{'id': 'hGZqWy3bPMrN3tosf5QZqt', {
'title': 'Batou - What is this love thing? (feat. EchoShadow) | Udio', 'id': 'hGZqWy3bPMrN3tosf5QZqt',
'description': 'Listen to Batou - What is this love thing? (feat. EchoShadow) by DigitalScribe on Udio. Discover, create, and share music with the world. Use the latest technology to create AI music in seconds.', 'title': 'Batou - What is this love thing? (feat. EchoShadow)',
'uploader': 'DigitalScribe', 'description': 'Listen to Batou - What is this love thing? (feat. EchoShadow) by DigitalScribe on Udio. Discover, create, and share music with the world. Use the latest technology to create AI music in seconds.',
'uploader_url': 'https://udio.com/artist/DigitalScribe'}, 'uploader': 'DigitalScribe',
'uploader_url': 'https://udio.com/artist/DigitalScribe',
},
'playlist_count': 1, 'playlist_count': 1,
}, { }, {
'url': 'https://www.udio.com/songs/dRFAMqCzqkTAX13F4MTKCb', 'url': 'https://www.udio.com/songs/dRFAMqCzqkTAX13F4MTKCb',
'info_dict': {'id': 'dRFAMqCzqkTAX13F4MTKCb', 'info_dict': {
'title': 'Évasion en Route | Udio', 'id': 'dRFAMqCzqkTAX13F4MTKCb',
'description': 'Listen to Évasion en Route by aveiro on Udio. Discover, create, and share music with the world. Use the latest technology to create AI music in seconds.', 'title': 'Évasion en Route',
'uploader': 'aveiro', 'description': 'Listen to Évasion en Route by aveiro on Udio. Discover, create, and share music with the world. Use the latest technology to create AI music in seconds.',
'uploader_url': 'https://udio.com/artist/aveiro'}, 'uploader': 'aveiro',
'uploader_url': 'https://udio.com/artist/aveiro',
},
'playlist_count': 1, 'playlist_count': 1,
}, { }, {
'url': 'https://www.udio.com/songs/edMsDRvAiFosixHHTVbJ1L', 'url': 'https://www.udio.com/songs/edMsDRvAiFosixHHTVbJ1L',
'info_dict': {'id': 'edMsDRvAiFosixHHTVbJ1L', 'info_dict': {
'title': 'Charlie e la Felicità ext v2.2 | Udio', 'id': 'edMsDRvAiFosixHHTVbJ1L',
'description': 'Listen to Charlie e la Felicità ext v2.2 by GIANI_curzioilGRANDE on Udio. Discover, create, and share music with the world. Use the latest technology to create AI music in seconds.', 'title': 'Charlie e la Felicità ext v2.2',
'uploader': 'GIANI_curzioilGRANDE', 'description': 'Listen to Charlie e la Felicità ext v2.2 by GIANI_curzioilGRANDE on Udio. Discover, create, and share music with the world. Use the latest technology to create AI music in seconds.',
'uploader_url': 'https://udio.com/artist/GIANI_curzioilGRANDE'}, 'uploader': 'GIANI_curzioilGRANDE',
'uploader_url': 'https://udio.com/artist/GIANI_curzioilGRANDE',
},
'playlist_count': 1, 'playlist_count': 1,
}, { }, {
'url': 'https://www.udio.com/songs/fPoZ7yLUv8orY2sNzeYNFp', 'url': 'https://www.udio.com/songs/fPoZ7yLUv8orY2sNzeYNFp',
'info_dict': {'id': 'fPoZ7yLUv8orY2sNzeYNFp', 'info_dict': {
'title': 'Nocturnal Vibes | Udio', 'id': 'fPoZ7yLUv8orY2sNzeYNFp',
'description': 'Listen to Nocturnal Vibes by RaulKong898 on Udio. Discover, create, and share music with the world. Use the latest technology to create AI music in seconds.', 'title': 'Nocturnal Vibes',
'uploader': 'RaulKong898', 'description': 'Listen to Nocturnal Vibes by RaulKong898 on Udio. Discover, create, and share music with the world. Use the latest technology to create AI music in seconds.',
'uploader_url': 'https://udio.com/artist/RaulKong898'}, 'uploader': 'RaulKong898',
'uploader_url': 'https://udio.com/artist/RaulKong898',
},
'playlist_count': 1, 'playlist_count': 1,
}, { }, {
'url': 'https://www.udio.com/songs/pzGGivV6oAR76ZxsnkbVw2', 'url': 'https://www.udio.com/songs/pzGGivV6oAR76ZxsnkbVw2',
'info_dict': {'id': 'pzGGivV6oAR76ZxsnkbVw2', 'info_dict': {
'title': 'Eternal Darkness | Udio', 'id': 'pzGGivV6oAR76ZxsnkbVw2',
'description': 'Listen to Eternal Darkness by Para$Graf0815 on Udio. Discover, create, and share music with the world. Use the latest technology to create AI music in seconds.', 'title': 'Eternal Darkness',
'uploader': 'Para$Graf0815', 'description': 'Listen to Eternal Darkness by Para$Graf0815 on Udio. Discover, create, and share music with the world. Use the latest technology to create AI music in seconds.',
'uploader_url': 'https://udio.com/artist/Para$Graf0815'}, 'uploader': 'Para$Graf0815',
'uploader_url': 'https://udio.com/artist/Para$Graf0815',
},
'playlist_count': 1, 'playlist_count': 1,
}, { }, {
'url': 'https://www.udio.com/songs/hSzvdEyBjBXF2CdsJP4zYr', 'url': 'https://www.udio.com/songs/hSzvdEyBjBXF2CdsJP4zYr',
'info_dict': {'id': 'hSzvdEyBjBXF2CdsJP4zYr', 'info_dict': {
'title': 'Revenge of the Dreamer | Udio', 'id': 'hSzvdEyBjBXF2CdsJP4zYr',
'description': 'Listen to Revenge of the Dreamer by Doc Immortal on Udio. Discover, create, and share music with the world. Use the latest technology to create AI music in seconds.', 'title': 'Revenge of the Dreamer',
'uploader': 'Doc Immortal', 'description': 'Listen to Revenge of the Dreamer by Doc Immortal on Udio. Discover, create, and share music with the world. Use the latest technology to create AI music in seconds.',
'uploader_url': 'https://udio.com/artist/Doc Immortal'}, 'uploader': 'Doc Immortal',
'uploader_url': 'https://udio.com/artist/Doc Immortal',
},
'playlist_count': 1, 'playlist_count': 1,
}, },
] ]
def _real_extract(self, url): def _real_extract(self, url):
artist_id = self._match_id(url) song_id = self._match_id(url)
webpage = self._download_webpage(url, artist_id) webpage = self._download_webpage(url, song_id)
media_url = self._og_search_video_url(webpage, default=None)
# Extract the audio URL from the <meta> tag
audio_src = self._html_search_meta('og:audio', webpage, 'audio src', fatal=True)
artist_name, title = self._html_extract_title(webpage, default=None).split('-', 1) artist_name, title = self._html_extract_title(webpage, default=None).split('-', 1)
description = self._og_search_description(webpage, default=None) title = title.split('|', 1)
# Create a single entry for the playlist
# Extract lyrics from the pre tag with specific classes
lyrics = self._search_regex( lyrics = self._search_regex(
r'<pre>\s*(.*?)\s*</pre>', r'<pre>\s*(.*?)\s*</pre>',
webpage, webpage,
@ -82,12 +95,15 @@ def _real_extract(self, url):
) )
return { return {
'id': artist_id, 'id': song_id,
'title': title.strip(), 'title': title[0].strip(),
'description': lyrics, 'description': lyrics,
'uploader': artist_name.strip(), 'uploader': artist_name.strip(),
'uploader_url': f'https://udio.com/artist/{artist_name.strip()}', 'uploader_url': urljoin('https://udio.com/artist/', artist_name.strip()),
'url': audio_src, 'formats': [{
'url': media_url,
'ext': determine_ext(media_url),
}],
} }
@ -135,32 +151,17 @@ class UdioListIE(InfoExtractor):
}] }]
def _find_links(self, webpage, base_url=None): def _find_links(self, webpage, base_url=None):
"""
Find all song links in the webpage.
Returns a list of absolute URLs.
Args:
webpage: The HTML content of the webpage
base_url: Base URL to prepend to relative links (optional)
Returns:
List of absolute song URLs
"""
import re
# Look for href attributes with relative song links
relative_links = re.findall(r'href="(/songs/[^"?&/]+)"', webpage) relative_links = re.findall(r'href="(/songs/[^"?&/]+)"', webpage)
# Convert relative URLs to absolute URLs
if not base_url: if not base_url:
base_url = 'https://www.udio.com' base_url = 'https://www.udio.com'
return [f'{base_url}{relative_link}' for relative_link in relative_links] return [f'{base_url}{relative_link}' for relative_link in relative_links]
def _real_extract(self, url): def _real_extract(self, url):
import re
list_type, list_id = self._match_valid_url(url).group('list_type', 'id') list_type, list_id = self._match_valid_url(url).group('list_type', 'id')
webpage = self._download_webpage(url, list_id) webpage = self._download_webpage(url, list_id)
# Look for song cards in the webpage
song_cards = re.findall(r'<div[^>]*class="[^"]*song-card[^"]*"[^>]*>(.*?)</div>\s*</div>', song_cards = re.findall(r'<div[^>]*class="[^"]*song-card[^"]*"[^>]*>(.*?)</div>\s*</div>',
webpage, re.DOTALL) webpage, re.DOTALL)
@ -168,31 +169,26 @@ def _real_extract(self, url):
entries = [] entries = []
for card in song_cards: for card in song_cards:
# Extract song URL
song_url_match = re.search(r'href="(/songs/([^"?&/]+))"', card) song_url_match = re.search(r'href="(/songs/([^"?&/]+))"', card)
if not song_url_match: if not song_url_match:
continue continue
song_path = song_url_match.group(1) song_path = song_url_match.group(1)
song_id = song_url_match.group(2) song_id = song_url_match.group(2)
song_url = f'https://www.udio.com{song_path}' song_url = urljoin('https://www.udio.com/', song_path)
# Extract song title
song_title = self._search_regex( song_title = self._search_regex(
r'<div[^>]*class="[^"]*song-title[^"]*"[^>]*>(.*?)</div>', r'<div[^>]*class="[^"]*song-title[^"]*"[^>]*>(.*?)</div>',
card, 'song title', default=None) card, 'song title', default=None)
# Extract artist name
artist_name = self._search_regex( artist_name = self._search_regex(
r'<div[^>]*class="[^"]*artist-name[^"]*"[^>]*>(.*?)</div>', r'<div[^>]*class="[^"]*artist-name[^"]*"[^>]*>(.*?)</div>',
card, 'artist name', default=None) card, 'artist name', default=None)
# Extract thumbnail
thumbnail = self._search_regex( thumbnail = self._search_regex(
r'<img[^>]*src="([^"]+)"[^>]*class="[^"]*song-cover[^"]*"', r'<img[^>]*src="([^"]+)"[^>]*class="[^"]*song-cover[^"]*"',
card, 'thumbnail', default=None) card, 'thumbnail', default=None)
# If we found detailed metadata, create a more detailed entry
if song_title or artist_name or thumbnail: if song_title or artist_name or thumbnail:
self.to_screen(f'Found metadata for song {song_id}: {song_title} by {artist_name}') self.to_screen(f'Found metadata for song {song_id}: {song_title} by {artist_name}')
entry = { entry = {
@ -211,10 +207,8 @@ def _real_extract(self, url):
entries.append(entry) entries.append(entry)
else: else:
# Fall back to simple URL result if no metadata found
entries.append(self.url_result(song_url, 'Udio', song_id)) entries.append(self.url_result(song_url, 'Udio', song_id))
# If no entries found using song cards, fall back to our existing method
if not entries: if not entries:
self.to_screen('No song cards found, trying alternative methods') self.to_screen('No song cards found, trying alternative methods')
song_urls = self._find_links(webpage) song_urls = self._find_links(webpage)