yt_dlp/extractor/baidu.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4
   5 from .common import InfoExtractor
   6 from ..utils import unescapeHTML
   7
   8
   9 class BaiduVideoIE(InfoExtractor):
  10     IE_DESC = '百度视频'
  11     _VALID_URL = r'https?://v\.baidu\.com/(?P<type>[a-z]+)/(?P<id>\d+)\.htm'
  12     _TESTS = [{
  13         'url': 'http://v.baidu.com/comic/1069.htm?frp=bdbrand&q=%E4%B8%AD%E5%8D%8E%E5%B0%8F%E5%BD%93%E5%AE%B6',
  14         'info_dict': {
  15             'id': '1069',
  16             'title': '中华小当家 TV版国语',
  17             'description': 'md5:51be07afe461cf99fa61231421b5397c',
  18         },
  19         'playlist_count': 52,
  20     }, {
  21         'url': 'http://v.baidu.com/show/11595.htm?frp=bdbrand',
  22         'info_dict': {
  23             'id': '11595',
  24             'title': 're:^奔跑吧兄弟',
  25             'description': 'md5:1bf88bad6d850930f542d51547c089b8',
  26         },
  27         'playlist_mincount': 12,
  28     }]
  29
  30     def _call_api(self, path, category, playlist_id, note):
  31         return self._download_json('http://app.video.baidu.com/%s/?worktype=adnative%s&id=%s' % (
  32             path, category, playlist_id), playlist_id, note)
  33
  34     def _real_extract(self, url):
  35         category, playlist_id = self._match_valid_url(url).groups()
  36         if category == 'show':
  37             category = 'tvshow'
  38         if category == 'tv':
  39             category = 'tvplay'
  40
  41         playlist_detail = self._call_api(
  42             'xqinfo', category, playlist_id, 'Download playlist JSON metadata')
  43
  44         playlist_title = playlist_detail['title']
  45         playlist_description = unescapeHTML(playlist_detail.get('intro'))
  46
  47         episodes_detail = self._call_api(
  48             'xqsingle', category, playlist_id, 'Download episodes JSON metadata')
  49
  50         entries = [self.url_result(
  51             episode['url'], video_title=episode['title']
  52         ) for episode in episodes_detail['videos']]
  53
  54         return self.playlist_result(
  55             entries, playlist_id, playlist_title, playlist_description)