from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
+ ExtractorError,
int_or_none,
float_or_none,
+ sanitized_Request,
+ urlencode_postdata,
)
-class YandexMusicTrackIE(InfoExtractor):
+class YandexMusicBaseIE(InfoExtractor):
+ @staticmethod
+ def _handle_error(response):
+ error = response.get('error')
+ if error:
+ raise ExtractorError(error, expected=True)
+
+ def _download_json(self, *args, **kwargs):
+ response = super(YandexMusicBaseIE, self)._download_json(*args, **kwargs)
+ self._handle_error(response)
+ return response
+
+
+class YandexMusicTrackIE(YandexMusicBaseIE):
IE_NAME = 'yandexmusic:track'
IE_DESC = 'Яндекс.Музыка - Трек'
_VALID_URL = r'https?://music\.yandex\.(?:ru|kz|ua|by)/album/(?P<album_id>\d+)/track/(?P<id>\d+)'
'info_dict': {
'id': '4878838',
'ext': 'mp3',
- 'title': 'Carlo Ambrosio - Gypsy Eyes 1',
+ 'title': 'Carlo Ambrosio & Fabio Di Bari, Carlo Ambrosio - Gypsy Eyes 1',
'filesize': 4628061,
'duration': 193.04,
+ 'track': 'Gypsy Eyes 1',
+ 'album': 'Gypsy Soul',
+ 'album_artist': 'Carlo Ambrosio',
+ 'artist': 'Carlo Ambrosio & Fabio Di Bari, Carlo Ambrosio',
+ 'release_year': '2009',
}
}
% (data['host'], key, data['ts'] + data['path'], storage[1]))
def _get_track_info(self, track):
- return {
+ thumbnail = None
+ cover_uri = track.get('albums', [{}])[0].get('coverUri')
+ if cover_uri:
+ thumbnail = cover_uri.replace('%%', 'orig')
+ if not thumbnail.startswith('http'):
+ thumbnail = 'http://' + thumbnail
+
+ track_title = track['title']
+ track_info = {
'id': track['id'],
'ext': 'mp3',
'url': self._get_track_url(track['storageDir'], track['id']),
- 'title': '%s - %s' % (track['artists'][0]['name'], track['title']),
'filesize': int_or_none(track.get('fileSize')),
'duration': float_or_none(track.get('durationMs'), 1000),
+ 'thumbnail': thumbnail,
+ 'track': track_title,
}
+ def extract_artist(artist_list):
+ if artist_list and isinstance(artist_list, list):
+ artists_names = [a['name'] for a in artist_list if a.get('name')]
+ if artists_names:
+ return ', '.join(artists_names)
+
+ albums = track.get('albums')
+ if albums and isinstance(albums, list):
+ album = albums[0]
+ if isinstance(album, dict):
+ year = album.get('year')
+ track_info.update({
+ 'album': album.get('title'),
+ 'album_artist': extract_artist(album.get('artists')),
+ 'release_year': compat_str(year) if year else None,
+ })
+
+ track_artist = extract_artist(track.get('artists'))
+ if track_artist:
+ track_info.update({
+ 'artist': track_artist,
+ 'title': '%s - %s' % (track_artist, track_title),
+ })
+ else:
+ track_info['title'] = track_title
+ return track_info
+
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
album_id, track_id = mobj.group('album_id'), mobj.group('id')
return self._get_track_info(track)
-class YandexMusicPlaylistBaseIE(InfoExtractor):
+class YandexMusicPlaylistBaseIE(YandexMusicBaseIE):
def _build_playlist(self, tracks):
return [
self.url_result(
'http://music.yandex.ru/album/%s/track/%s' % (track['albums'][0]['id'], track['id']))
- for track in tracks]
+ for track in tracks if track.get('albums') and isinstance(track.get('albums'), list)]
class YandexMusicAlbumIE(YandexMusicPlaylistBaseIE):
IE_DESC = 'Яндекс.Музыка - Плейлист'
_VALID_URL = r'https?://music\.yandex\.(?:ru|kz|ua|by)/users/[^/]+/playlists/(?P<id>\d+)'
- _TEST = {
+ _TESTS = [{
'url': 'http://music.yandex.ru/users/music.partners/playlists/1245',
'info_dict': {
'id': '1245',
'description': 'md5:3b9f27b0efbe53f2ee1e844d07155cc9',
},
'playlist_count': 6,
- }
+ }, {
+ # playlist exceeding the limit of 150 tracks shipped with webpage (see
+ # https://github.com/rg3/youtube-dl/issues/6666)
+ 'url': 'https://music.yandex.ru/users/ya.playlist/playlists/1036',
+ 'info_dict': {
+ 'id': '1036',
+ 'title': 'Музыка 90-х',
+ },
+ 'playlist_count': 310,
+ }]
def _real_extract(self, url):
playlist_id = self._match_id(url)
webpage = self._download_webpage(url, playlist_id)
- playlist = self._parse_json(
+ mu = self._parse_json(
self._search_regex(
r'var\s+Mu\s*=\s*({.+?});\s*</script>', webpage, 'player'),
- playlist_id)['pageData']['playlist']
+ playlist_id)
+
+ playlist = mu['pageData']['playlist']
+ tracks, track_ids = playlist['tracks'], playlist['trackIds']
+
+ # tracks dictionary shipped with webpage is limited to 150 tracks,
+ # missing tracks should be retrieved manually.
+ if len(tracks) < len(track_ids):
+ present_track_ids = set([compat_str(track['id']) for track in tracks if track.get('id')])
+ missing_track_ids = set(map(compat_str, track_ids)) - set(present_track_ids)
+ request = sanitized_Request(
+ 'https://music.yandex.ru/handlers/track-entries.jsx',
+ urlencode_postdata({
+ 'entries': ','.join(missing_track_ids),
+ 'lang': mu.get('settings', {}).get('lang', 'en'),
+ 'external-domain': 'music.yandex.ru',
+ 'overembed': 'false',
+ 'sign': mu.get('authData', {}).get('user', {}).get('sign'),
+ 'strict': 'true',
+ }))
+ request.add_header('Referer', url)
+ request.add_header('X-Requested-With', 'XMLHttpRequest')
+
+ missing_tracks = self._download_json(
+ request, playlist_id, 'Downloading missing tracks JSON', fatal=False)
+ if missing_tracks:
+ tracks.extend(missing_tracks)
return self.playlist_result(
- self._build_playlist(playlist['tracks']),
+ self._build_playlist(tracks),
compat_str(playlist_id),
playlist['title'], playlist.get('description'))
projects / youtube-dl / blobdiff