0
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-12-05 04:17:27 +00:00
yt-dlp/yt_dlp/extractor/musicdex.py
sepro add96eb9f8
[cleanup] Add more ruff rules (#10149)
Authored by: seproDev

Reviewed-by: bashonly <88596187+bashonly@users.noreply.github.com>
Reviewed-by: Simon Sawicki <contact@grub4k.xyz>
2024-06-12 01:09:58 +02:00

174 lines
7.2 KiB
Python

from .common import InfoExtractor
from ..utils import (
date_from_str,
format_field,
try_get,
unified_strdate,
)
class MusicdexBaseIE(InfoExtractor):
def _return_info(self, track_json, album_json, video_id):
return {
'id': str(video_id),
'title': track_json.get('name'),
'track': track_json.get('name'),
'description': track_json.get('description'),
'track_number': track_json.get('number'),
'url': format_field(track_json, 'url', 'https://www.musicdex.org/%s'),
'duration': track_json.get('duration'),
'genres': [genre.get('name') for genre in track_json.get('genres') or []],
'like_count': track_json.get('likes_count'),
'view_count': track_json.get('plays'),
'artists': [artist.get('name') for artist in track_json.get('artists') or []],
'album_artists': [artist.get('name') for artist in album_json.get('artists') or []],
'thumbnail': format_field(album_json, 'image', 'https://www.musicdex.org/%s'),
'album': album_json.get('name'),
'release_year': try_get(album_json, lambda x: date_from_str(unified_strdate(x['release_date'])).year),
'extractor_key': MusicdexSongIE.ie_key(),
'extractor': 'MusicdexSong',
}
class MusicdexSongIE(MusicdexBaseIE):
_VALID_URL = r'https?://(?:www\.)?musicdex\.org/track/(?P<id>\d+)'
_TESTS = [{
'url': 'https://www.musicdex.org/track/306/dual-existence',
'info_dict': {
'id': '306',
'ext': 'mp3',
'title': 'dual existence',
'description': '#NIPPONSEI @ IRC.RIZON.NET',
'track': 'dual existence',
'track_number': 1,
'duration': 266000,
'genres': ['Anime'],
'like_count': int,
'view_count': int,
'artists': ['fripSide'],
'album_artists': ['fripSide'],
'thumbnail': 'https://www.musicdex.org/storage/album/9iDIam1DHTVqUG4UclFIEq1WAFGXfPW4y0TtZa91.png',
'album': 'To Aru Kagaku no Railgun T OP2 Single - dual existence',
'release_year': 2020,
},
'params': {'skip_download': True},
}]
def _real_extract(self, url):
video_id = self._match_id(url)
data_json = self._download_json(
f'https://www.musicdex.org/secure/tracks/{video_id}?defaultRelations=true', video_id)['track']
return self._return_info(data_json, data_json.get('album') or {}, video_id)
class MusicdexAlbumIE(MusicdexBaseIE):
_VALID_URL = r'https?://(?:www\.)?musicdex\.org/album/(?P<id>\d+)'
_TESTS = [{
'url': 'https://www.musicdex.org/album/56/tenmon-and-eiichiro-yanagi-minori/ef-a-tale-of-memories-original-soundtrack-2-fortissimo',
'playlist_mincount': 28,
'info_dict': {
'id': '56',
'genres': ['OST'],
'view_count': int,
'artists': ['TENMON & Eiichiro Yanagi / minori'],
'title': 'ef - a tale of memories Original Soundtrack 2 ~fortissimo~',
'release_year': 2008,
'thumbnail': 'https://www.musicdex.org/storage/album/2rSHkyYBYfB7sbvElpEyTMcUn6toY7AohOgJuDlE.jpg',
},
}]
def _real_extract(self, url):
playlist_id = self._match_id(url)
data_json = self._download_json(
f'https://www.musicdex.org/secure/albums/{playlist_id}?defaultRelations=true', playlist_id)['album']
entries = [self._return_info(track, data_json, track['id'])
for track in data_json.get('tracks') or [] if track.get('id')]
return {
'_type': 'playlist',
'id': playlist_id,
'title': data_json.get('name'),
'description': data_json.get('description'),
'genres': [genre.get('name') for genre in data_json.get('genres') or []],
'view_count': data_json.get('plays'),
'artists': [artist.get('name') for artist in data_json.get('artists') or []],
'thumbnail': format_field(data_json, 'image', 'https://www.musicdex.org/%s'),
'release_year': try_get(data_json, lambda x: date_from_str(unified_strdate(x['release_date'])).year),
'entries': entries,
}
class MusicdexPageIE(MusicdexBaseIE): # XXX: Conventionally, base classes should end with BaseIE/InfoExtractor
def _entries(self, playlist_id):
next_page_url = self._API_URL % playlist_id
while next_page_url:
data_json = self._download_json(next_page_url, playlist_id)['pagination']
yield from data_json.get('data') or []
next_page_url = data_json.get('next_page_url')
class MusicdexArtistIE(MusicdexPageIE):
_VALID_URL = r'https?://(?:www\.)?musicdex\.org/artist/(?P<id>\d+)'
_API_URL = 'https://www.musicdex.org/secure/artists/%s/albums?page=1'
_TESTS = [{
'url': 'https://www.musicdex.org/artist/11/fripside',
'playlist_mincount': 28,
'info_dict': {
'id': '11',
'view_count': int,
'title': 'fripSide',
'thumbnail': 'https://www.musicdex.org/storage/artist/ZmOz0lN2vsweegB660em3xWffCjLPmTQHqJls5Xx.jpg',
},
}]
def _real_extract(self, url):
playlist_id = self._match_id(url)
data_json = self._download_json(f'https://www.musicdex.org/secure/artists/{playlist_id}', playlist_id)['artist']
entries = []
for album in self._entries(playlist_id):
entries.extend(self._return_info(track, album, track['id']) for track in album.get('tracks') or [] if track.get('id'))
return {
'_type': 'playlist',
'id': playlist_id,
'title': data_json.get('name'),
'view_count': data_json.get('plays'),
'thumbnail': format_field(data_json, 'image_small', 'https://www.musicdex.org/%s'),
'entries': entries,
}
class MusicdexPlaylistIE(MusicdexPageIE):
_VALID_URL = r'https?://(?:www\.)?musicdex\.org/playlist/(?P<id>\d+)'
_API_URL = 'https://www.musicdex.org/secure/playlists/%s/tracks?perPage=10000&page=1'
_TESTS = [{
'url': 'https://www.musicdex.org/playlist/9/test',
'playlist_mincount': 73,
'info_dict': {
'id': '9',
'view_count': int,
'title': 'Test',
'thumbnail': 'https://www.musicdex.org/storage/album/jXATI79f0IbQ2sgsKYOYRCW3zRwF3XsfHhzITCuJ.jpg',
'description': 'Test 123 123 21312 32121321321321312',
},
}]
def _real_extract(self, url):
playlist_id = self._match_id(url)
data_json = self._download_json(f'https://www.musicdex.org/secure/playlists/{playlist_id}', playlist_id)['playlist']
entries = [self._return_info(track, track.get('album') or {}, track['id'])
for track in self._entries(playlist_id) or [] if track.get('id')]
return {
'_type': 'playlist',
'id': playlist_id,
'title': data_json.get('name'),
'description': data_json.get('description'),
'view_count': data_json.get('plays'),
'thumbnail': format_field(data_json, 'image', 'https://www.musicdex.org/%s'),
'entries': entries,
}