yt_dlp/extractor/tudou.py

   1 from .common import InfoExtractor
   2
   3
   4 class TudouPlaylistIE(InfoExtractor):
   5     IE_NAME = 'tudou:playlist'
   6     _VALID_URL = r'https?://(?:www\.)?tudou\.com/listplay/(?P<id>[\w-]{11})\.html'
   7     _TESTS = [{
   8         'url': 'http://www.tudou.com/listplay/zzdE77v6Mmo.html',
   9         'info_dict': {
  10             'id': 'zzdE77v6Mmo',
  11         },
  12         'playlist_mincount': 209,
  13     }]
  14
  15     def _real_extract(self, url):
  16         playlist_id = self._match_id(url)
  17         playlist_data = self._download_json(
  18             'http://www.tudou.com/tvp/plist.action?lcode=%s' % playlist_id, playlist_id)
  19         entries = [self.url_result(
  20             'http://www.tudou.com/programs/view/%s' % item['icode'],
  21             'Tudou', item['icode'],
  22             item['kw']) for item in playlist_data['items']]
  23         return self.playlist_result(entries, playlist_id)
  24
  25
  26 class TudouAlbumIE(InfoExtractor):
  27     IE_NAME = 'tudou:album'
  28     _VALID_URL = r'https?://(?:www\.)?tudou\.com/album(?:cover|play)/(?P<id>[\w-]{11})'
  29     _TESTS = [{
  30         'url': 'http://www.tudou.com/albumplay/v5qckFJvNJg.html',
  31         'info_dict': {
  32             'id': 'v5qckFJvNJg',
  33         },
  34         'playlist_mincount': 45,
  35     }]
  36
  37     def _real_extract(self, url):
  38         album_id = self._match_id(url)
  39         album_data = self._download_json(
  40             'http://www.tudou.com/tvp/alist.action?acode=%s' % album_id, album_id)
  41         entries = [self.url_result(
  42             'http://www.tudou.com/programs/view/%s' % item['icode'],
  43             'Tudou', item['icode'],
  44             item['kw']) for item in album_data['items']]
  45         return self.playlist_result(entries, album_id)