youtube_dl/extractor/ku6.py

   1 from __future__ import unicode_literals
   2
   3 from .common import InfoExtractor
   4
   5
   6 class Ku6IE(InfoExtractor):
   7     _VALID_URL = r'https?://v\.ku6\.com/show/(?P<id>[a-zA-Z0-9\-\_]+)(?:\.)*html'
   8     _TEST = {
   9         'url': 'http://v.ku6.com/show/JG-8yS14xzBr4bCn1pu0xw...html',
  10         'md5': '01203549b9efbb45f4b87d55bdea1ed1',
  11         'info_dict': {
  12             'id': 'JG-8yS14xzBr4bCn1pu0xw',
  13             'ext': 'f4v',
  14             'title': 'techniques test',
  15         }
  16     }
  17
  18     def _real_extract(self, url):
  19         video_id = self._match_id(url)
  20         webpage = self._download_webpage(url, video_id)
  21
  22         title = self._html_search_regex(
  23             r'<h1 title=.*>(.*?)</h1>', webpage, 'title')
  24         dataUrl = 'http://v.ku6.com/fetchVideo4Player/%s.html' % video_id
  25         jsonData = self._download_json(dataUrl, video_id)
  26         downloadUrl = jsonData['data']['f']
  27
  28         return {
  29             'id': video_id,
  30             'title': title,
  31             'url': downloadUrl
  32         }