yt_dlp/extractor/ku6.py

   1 from .common import InfoExtractor
   2
   3
   4 class Ku6IE(InfoExtractor):
   5     _VALID_URL = r'https?://v\.ku6\.com/show/(?P<id>[a-zA-Z0-9\-\_]+)(?:\.)*html'
   6     _TEST = {
   7         'url': 'http://v.ku6.com/show/JG-8yS14xzBr4bCn1pu0xw...html',
   8         'md5': '01203549b9efbb45f4b87d55bdea1ed1',
   9         'info_dict': {
  10             'id': 'JG-8yS14xzBr4bCn1pu0xw',
  11             'ext': 'f4v',
  12             'title': 'techniques test',
  13         },
  14     }
  15
  16     def _real_extract(self, url):
  17         video_id = self._match_id(url)
  18         webpage = self._download_webpage(url, video_id)
  19
  20         title = self._html_search_regex(
  21             r'<h1 title=.*>(.*?)</h1>', webpage, 'title')
  22         data_url = f'http://v.ku6.com/fetchVideo4Player/{video_id}.html'
  23         json_data = self._download_json(data_url, video_id)
  24         download_url = json_data['data']['f']
  25
  26         return {
  27             'id': video_id,
  28             'title': title,
  29             'url': download_url,
  30         }