youtube-dl/youtube_dl/extractor/yandexmusic.py

133 lines
4.4 KiB
Python
Raw Normal View History

# coding: utf-8
2015-03-09 06:06:49 -07:00
from __future__ import unicode_literals
import re
import hashlib
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
int_or_none,
float_or_none,
)
2015-03-09 06:06:49 -07:00
class YandexMusicTrackIE(InfoExtractor):
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+)'
_TEST = {
'url': 'http://music.yandex.ru/album/540508/track/4878838',
'md5': 'f496818aa2f60b6c0062980d2e00dc20',
'info_dict': {
'id': '4878838',
'ext': 'mp3',
'title': 'Carlo Ambrosio - Gypsy Eyes 1',
'filesize': 4628061,
'duration': 193.04,
}
}
2015-03-09 06:06:49 -07:00
def _get_track_url(self, storage_dir, track_id):
data = self._download_json(
'http://music.yandex.ru/api/v1.5/handlers/api-jsonp.jsx?action=getTrackSrc&p=download-info/%s'
% storage_dir,
track_id, 'Downloading track location JSON')
2015-03-09 06:06:49 -07:00
key = hashlib.md5(('XGRlBW9FXlekgbPrRHuSiA' + data['path'][1:] + data['s']).encode('utf-8')).hexdigest()
2015-03-09 06:06:49 -07:00
storage = storage_dir.split('.')
return ('http://%s/get-mp3/%s/%s?track-id=%s&from=service-10-track&similarities-experiment=default'
% (data['host'], key, data['ts'] + data['path'], storage[1]))
2015-03-09 06:06:49 -07:00
def _get_track_info(self, track):
return {
'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),
}
2015-03-09 06:06:49 -07:00
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
album_id, track_id = mobj.group('album_id'), mobj.group('id')
2015-03-09 06:06:49 -07:00
track = self._download_json(
'http://music.yandex.ru/handlers/track.jsx?track=%s:%s' % (track_id, album_id),
track_id, 'Downloading track JSON')['track']
2015-03-09 06:06:49 -07:00
return self._get_track_info(track)
2015-03-09 06:06:49 -07:00
class YandexMusicPlaylistBaseIE(InfoExtractor):
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]
class YandexMusicAlbumIE(YandexMusicPlaylistBaseIE):
IE_NAME = 'yandexmusic:album'
IE_DESC = 'Яндекс.Музыка - Альбом'
2015-03-14 00:56:04 -07:00
_VALID_URL = r'https?://music\.yandex\.(?:ru|kz|ua|by)/album/(?P<id>\d+)/?(\?|$)'
2015-03-09 06:06:49 -07:00
_TEST = {
'url': 'http://music.yandex.ru/album/540508',
'info_dict': {
'id': '540508',
'title': 'Carlo Ambrosio - Gypsy Soul (2009)',
},
'playlist_count': 50,
}
2015-03-09 06:06:49 -07:00
def _real_extract(self, url):
album_id = self._match_id(url)
2015-03-09 06:06:49 -07:00
album = self._download_json(
'http://music.yandex.ru/handlers/album.jsx?album=%s' % album_id,
album_id, 'Downloading album JSON')
2015-03-09 06:06:49 -07:00
entries = self._build_playlist(album['volumes'][0])
title = '%s - %s' % (album['artists'][0]['name'], album['title'])
year = album.get('year')
if year:
title += ' (%s)' % year
return self.playlist_result(entries, compat_str(album['id']), title)
2015-03-09 06:06:49 -07:00
class YandexMusicPlaylistIE(YandexMusicPlaylistBaseIE):
IE_NAME = 'yandexmusic:playlist'
IE_DESC = 'Яндекс.Музыка - Плейлист'
2015-03-14 00:56:04 -07:00
_VALID_URL = r'https?://music\.yandex\.(?:ru|kz|ua|by)/users/[^/]+/playlists/(?P<id>\d+)'
2015-03-09 06:06:49 -07:00
_TEST = {
'url': 'http://music.yandex.ru/users/music.partners/playlists/1245',
2015-03-09 06:06:49 -07:00
'info_dict': {
'id': '1245',
'title': 'Что слушают Enter Shikari',
'description': 'md5:3b9f27b0efbe53f2ee1e844d07155cc9',
},
'playlist_count': 6,
2015-03-09 06:06:49 -07:00
}
def _real_extract(self, url):
playlist_id = self._match_id(url)
2015-03-09 06:06:49 -07:00
webpage = self._download_webpage(url, playlist_id)
2015-03-09 06:06:49 -07:00
playlist = self._parse_json(
self._search_regex(
r'var\s+Mu\s*=\s*({.+?});\s*</script>', webpage, 'player'),
playlist_id)['pageData']['playlist']
return self.playlist_result(
self._build_playlist(playlist['tracks']),
compat_str(playlist_id),
playlist['title'], playlist.get('description'))