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

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