youtube_dl/extractor/tudou.py

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