_ Git - youtube-dl/blob - youtube_dl/extractor/yamusic.py

   1 # coding=utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5 import hashlib
   6 import time
   7
   8 from .common import InfoExtractor
   9
  10 class YandexMusicAlbumIE(InfoExtractor):
  11     _VALID_URL = r'http://music.yandex.ru/album/(?P<id>\d+)'
  12
  13     def _get_track_url(self, storage_dir, track_id):
  14         data = self._download_json('http://music.yandex.ru/api/v1.5/handlers/api-jsonp.jsx?requestId=2&nc=%d&action=getTrackSrc&p=download-info/%s/2.mp3' % (time.time(), storage_dir), track_id)
  15
  16         hsh = hashlib.md5()
  17         hsh.update('XGRlBW9FXlekgbPrRHuSiA' + data['path'][1:] + data['s'])
  18         hash = hsh.hexdigest()
  19         storage = storage_dir.split('.')
  20
  21         return 'http://%s/get-mp3/%s/%s?track-id=%s&from=service-10-track&similarities-experiment=default' % (data['host'], hash, data['ts'] + data['path'], storage[1])
  22
  23     def _get_album_id_and_data(self, url):
  24         matched = re.match(self._VALID_URL, url)
  25         id = matched.group('id')
  26
  27         webpage = self._download_webpage(url, id)
  28         data = self._parse_json(
  29             self._search_regex(
  30                 r'var\s+Mu\s+=\s+(.+?);\s+<\/script>', webpage, 'player'),
  31             id)
  32         return id, data['pageData']
  33
  34     def _real_extract(self, url):
  35
  36         id, data = self._get_album_id_and_data(url)
  37
  38         entries = []
  39
  40         for track in data['volumes'][0]:
  41             entries.append({
  42                 'id': track['id'],
  43                 'ext': 'mp3',
  44                 'url': self._get_track_url(track['storageDir'], track['id']),
  45                 'title': track['artists'][0]['name'] + ' - ' + track['title'],
  46             })
  47
  48         return {
  49             '_type': 'playlist',
  50             'entries': entries,
  51             'id': id,
  52             'title': data['title'],
  53         }
  54
  55 class YandexMusicPlaylistIE(YandexMusicAlbumIE):
  56     _VALID_URL = r'http://music.yandex.ru/users/(?P<user_name>[^/]+)/playlists/(?P<id>\d+)'
  57
  58     def _real_extract(self, url):
  59         id, data = self._get_album_id_and_data(url)
  60         data = data['playlist']
  61
  62         entries = []
  63
  64         for track in data['tracks']:
  65             entries.append({
  66                 'id': track['id'],
  67                 'ext': 'mp3',
  68                 'url': self._get_track_url(track['storageDir'], track['id']),
  69                 'title': track['artists'][0]['name'] + ' - ' + track['title'],
  70             })
  71
  72         return {
  73             '_type': 'playlist',
  74             'entries': entries,
  75             'id': id,
  76             'title': data['title'],
  77         }
  78
  79 class YandexMusicTrackIE(YandexMusicAlbumIE):
  80     _VALID_URL = r'http://music.yandex.ru/album/(?P<album_id>\d+)/track/(?P<id>\d+)'
  81     _TEST = {
  82         'url': 'http://music.yandex.ru/album/540508/track/4878838',
  83         'info_dict': {
  84             'id': '4878838',
  85             'ext': 'mp3',
  86             'title': 'Carlo Ambrosio - Gypsy Eyes 1',
  87         }
  88     }
  89
  90     def _real_extract(self, url):
  91
  92         id, data = self._get_album_id_and_data(url)
  93
  94         for track in data['volumes'][0]:
  95             if track['id'] == id:
  96                 track_url = self._get_track_url(track['storageDir'], id)
  97                 break
  98
  99         return {
 100             'id': id,
 101             'ext': 'mp3',
 102             'url': track_url,
 103             'title': track['artists'][0]['name'] + ' - ' + track['title'],
 104         }