Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/yandexmusic.py

   1 # coding=utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5 import hashlib
   6
   7 from .common import InfoExtractor
   8 from ..compat import compat_str
   9 from ..utils import (
  10     int_or_none,
  11     float_or_none,
  12 )
  13
  14
  15 class YandexMusicBaseIE(InfoExtractor):
  16     def _get_track_url(self, storage_dir, track_id):
  17         data = self._download_json(
  18             'http://music.yandex.ru/api/v1.5/handlers/api-jsonp.jsx?action=getTrackSrc&p=download-info/%s'
  19             % storage_dir,
  20             track_id, 'Downloading track location JSON')
  21
  22         key = hashlib.md5(('XGRlBW9FXlekgbPrRHuSiA' + data['path'][1:] + data['s']).encode('utf-8')).hexdigest()
  23         storage = storage_dir.split('.')
  24
  25         return ('http://%s/get-mp3/%s/%s?track-id=%s&from=service-10-track&similarities-experiment=default'
  26                 % (data['host'], key, data['ts'] + data['path'], storage[1]))
  27
  28     def _get_track_info(self, track):
  29         return {
  30             'id': track['id'],
  31             'ext': 'mp3',
  32             'url': self._get_track_url(track['storageDir'], track['id']),
  33             'title': '%s - %s' % (track['artists'][0]['name'], track['title']),
  34             'filesize': int_or_none(track.get('fileSize')),
  35             'duration': float_or_none(track.get('durationMs'), 1000),
  36         }
  37
  38
  39 class YandexMusicTrackIE(YandexMusicBaseIE):
  40     IE_NAME = 'yandexmusic:track'
  41     IE_DESC = 'Яндекс.Музыка - Трек'
  42     _VALID_URL = r'https?://music\.yandex\.(?:ru|kz|ua|by)/album/(?P<album_id>\d+)/track/(?P<id>\d+)'
  43
  44     _TEST = {
  45         'url': 'http://music.yandex.ru/album/540508/track/4878838',
  46         'md5': 'f496818aa2f60b6c0062980d2e00dc20',
  47         'info_dict': {
  48             'id': '4878838',
  49             'ext': 'mp3',
  50             'title': 'Carlo Ambrosio - Gypsy Eyes 1',
  51             'filesize': 4628061,
  52             'duration': 193.04,
  53         }
  54     }
  55
  56     def _real_extract(self, url):
  57         mobj = re.match(self._VALID_URL, url)
  58         album_id, track_id = mobj.group('album_id'), mobj.group('id')
  59
  60         track = self._download_json(
  61             'http://music.yandex.ru/handlers/track.jsx?track=%s:%s' % (track_id, album_id),
  62             track_id, 'Downloading track JSON')['track']
  63
  64         return self._get_track_info(track)
  65
  66
  67 class YandexMusicAlbumIE(YandexMusicBaseIE):
  68     IE_NAME = 'yandexmusic:album'
  69     IE_DESC = 'Яндекс.Музыка - Альбом'
  70     _VALID_URL = r'https?://music\.yandex\.(?:ru|kz|ua|by)/album/(?P<id>\d+)/?(\?|$)'
  71
  72     _TEST = {
  73         'url': 'http://music.yandex.ru/album/540508',
  74         'info_dict': {
  75             'id': '540508',
  76             'title': 'Carlo Ambrosio - Gypsy Soul (2009)',
  77         },
  78         'playlist_count': 50,
  79     }
  80
  81     def _real_extract(self, url):
  82         album_id = self._match_id(url)
  83
  84         album = self._download_json(
  85             'http://music.yandex.ru/handlers/album.jsx?album=%s' % album_id,
  86             album_id, 'Downloading album JSON')
  87
  88         entries = [self._get_track_info(track) for track in album['volumes'][0]]
  89
  90         title = '%s - %s' % (album['artists'][0]['name'], album['title'])
  91         year = album.get('year')
  92         if year:
  93             title += ' (%s)' % year
  94
  95         return self.playlist_result(entries, compat_str(album['id']), title)
  96
  97
  98 class YandexMusicPlaylistIE(YandexMusicBaseIE):
  99     IE_NAME = 'yandexmusic:playlist'
 100     IE_DESC = 'Яндекс.Музыка - Плейлист'
 101     _VALID_URL = r'https?://music\.yandex\.(?:ru|kz|ua|by)/users/[^/]+/playlists/(?P<id>\d+)'
 102
 103     _TEST = {
 104         'url': 'http://music.yandex.ru/users/music.partners/playlists/1245',
 105         'info_dict': {
 106             'id': '1245',
 107             'title': 'Что слушают Enter Shikari',
 108             'description': 'md5:3b9f27b0efbe53f2ee1e844d07155cc9',
 109         },
 110         'playlist_count': 6,
 111     }
 112
 113     def _real_extract(self, url):
 114         playlist_id = self._match_id(url)
 115
 116         webpage = self._download_webpage(url, playlist_id)
 117
 118         playlist = self._parse_json(
 119             self._search_regex(
 120                 r'var\s+Mu\s*=\s*({.+?});\s*</script>', webpage, 'player'),
 121             playlist_id)['pageData']['playlist']
 122
 123         entries = [self._get_track_info(track) for track in playlist['tracks']]
 124
 125         return self.playlist_result(
 126             entries, compat_str(playlist_id),
 127             playlist['title'], playlist.get('description'))