github/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-07 20:30:41 -05:00
Code Issues Projects Releases Packages Wiki Activity

[audiomack] Update album and song VALID_URL (#1203)

Browse source 
Original PR: https://github.com/ytdl-org/youtube-dl/pull/29810
Closes #1352, https://github.com/ytdl-org/youtube-dl/issues/29800
Authored by: abdullah-if, dirkf
This commit is contained in:
Abdullah Ibn Fulan 2021-12-20 07:53:42 +06:00 committed by GitHub
parent c2dedf12e8
commit 2aae2c91ff
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
1 changed files with 19 additions and 15 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

34
yt_dlp/extractor/audiomack.py
View file

@ -14,7 +14,7 @@
class AudiomackIE(InfoExtractor): class AudiomackIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?audiomack\.com/song/(?P<id>[\w/-]+)' _VALID_URL = r'https?://(?:www\.)?audiomack\.com/(?:song/|(?=.+/song/))(?P<id>[\w/-]+)'
IE_NAME = 'audiomack' IE_NAME = 'audiomack'
_TESTS = [ _TESTS = [
# hosted on audiomack # hosted on audiomack
@ -39,15 +39,16 @@ class AudiomackIE(InfoExtractor):
'title': 'Black Mamba Freestyle [Prod. By Danny Wolf]', 'title': 'Black Mamba Freestyle [Prod. By Danny Wolf]',
'uploader': 'ILOVEMAKONNEN', 'uploader': 'ILOVEMAKONNEN',
'upload_date': '20160414', 'upload_date': '20160414',
} },
'skip': 'Song has been removed from the site',
}, },
] ]
def _real_extract(self, url): def _real_extract(self, url):
# URLs end with [uploader name]/[uploader title] # URLs end with [uploader name]/song/[uploader title]
# this title is whatever the user types in, and is rarely # this title is whatever the user types in, and is rarely
# the proper song title. Real metadata is in the api response # the proper song title. Real metadata is in the api response
album_url_tag = self._match_id(url) album_url_tag = self._match_id(url).replace('/song/', '/')
# Request the extended version of the api for extra fields like artist and title # Request the extended version of the api for extra fields like artist and title
api_response = self._download_json( api_response = self._download_json(
@ -73,13 +74,13 @@ def _real_extract(self, url):
class AudiomackAlbumIE(InfoExtractor): class AudiomackAlbumIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?audiomack\.com/album/(?P<id>[\w/-]+)' _VALID_URL = r'https?://(?:www\.)?audiomack\.com/(?:album/|(?=.+/album/))(?P<id>[\w/-]+)'
IE_NAME = 'audiomack:album' IE_NAME = 'audiomack:album'
_TESTS = [ _TESTS = [
# Standard album playlist # Standard album playlist
{ {
'url': 'http://www.audiomack.com/album/flytunezcom/tha-tour-part-2-mixtape', 'url': 'http://www.audiomack.com/album/flytunezcom/tha-tour-part-2-mixtape',
'playlist_count': 15, 'playlist_count': 11,
'info_dict': 'info_dict':
{ {
'id': '812251', 'id': '812251',
@ -95,24 +96,27 @@ class AudiomackAlbumIE(InfoExtractor):
}, },
'playlist': [{ 'playlist': [{
'info_dict': { 'info_dict': {
'title': 'PPP (Pistol P Project) - 9. Heaven or Hell (CHIMACA) ft Zuse (prod by DJ FU)', 'title': 'PPP (Pistol P Project) - 8. Real (prod by SYK SENSE )',
'id': '837577', 'id': '837576',
'ext': 'mp3',
'uploader': 'Lil Herb a.k.a. G Herbo',
}
}, {
'info_dict': {
'title': 'PPP (Pistol P Project) - 10. 4 Minutes Of Hell Part 4 (prod by DY OF 808 MAFIA)',
'id': '837580',
'ext': 'mp3', 'ext': 'mp3',
'uploader': 'Lil Herb a.k.a. G Herbo', 'uploader': 'Lil Herb a.k.a. G Herbo',
} }
}], }],
'params': {
'playliststart': 9,
'playlistend': 9,
}
} }
] ]
def _real_extract(self, url): def _real_extract(self, url):
# URLs end with [uploader name]/[uploader title] # URLs end with [uploader name]/album/[uploader title]
# this title is whatever the user types in, and is rarely # this title is whatever the user types in, and is rarely
# the proper song title. Real metadata is in the api response # the proper song title. Real metadata is in the api response
album_url_tag = self._match_id(url) album_url_tag = self._match_id(url).replace('/album/', '/')
result = {'_type': 'playlist', 'entries': []} result = {'_type': 'playlist', 'entries': []}
# There is no one endpoint for album metadata - instead it is included/repeated in each song's metadata # There is no one endpoint for album metadata - instead it is included/repeated in each song's metadata
# Therefore we don't know how many songs the album has and must infi-loop until failure # Therefore we don't know how many songs the album has and must infi-loop until failure
@ -134,7 +138,7 @@ def _real_extract(self, url):
# Pull out the album metadata and add to result (if it exists) # Pull out the album metadata and add to result (if it exists)
for resultkey, apikey in [('id', 'album_id'), ('title', 'album_title')]: for resultkey, apikey in [('id', 'album_id'), ('title', 'album_title')]:
if apikey in api_response and resultkey not in result: if apikey in api_response and resultkey not in result:
result[resultkey] = api_response[apikey] result[resultkey] = compat_str(api_response[apikey])
song_id = url_basename(api_response['url']).rpartition('.')[0] song_id = url_basename(api_response['url']).rpartition('.')[0]
result['entries'].append({ result['entries'].append({
'id': compat_str(api_response.get('id', song_id)), 'id': compat_str(api_response.get('id', song_id)),