youtube_dl/extractor/ku6.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6
   7
   8 class Ku6IE(InfoExtractor):
   9     _VALID_URL = r'http://v\.ku6\.com/show/(?P<id>[a-zA-Z0-9\-\_]+)(?:\.)*html'
  10     _TEST = {
  11         'url': 'http://v.ku6.com/show/JG-8yS14xzBr4bCn1pu0xw...html',
  12         'md5': '01203549b9efbb45f4b87d55bdea1ed1',
  13         'info_dict': {
  14             'id': 'JG-8yS14xzBr4bCn1pu0xw',
  15             'ext': 'f4v',
  16             'title': 'techniques test',
  17         }
  18     }
  19
  20     def _real_extract(self, url):
  21         mobj = re.match(self._VALID_URL, url)
  22         video_id = mobj.group('id')
  23
  24         webpage = self._download_webpage(url, video_id)
  25         title = self._search_regex(r'<h1 title=.*>(.*?)</h1>', webpage, 'title')
  26         dataUrl = 'http://v.ku6.com/fetchVideo4Player/%s.html' % video_id
  27         jsonData = self._download_json(dataUrl, video_id)
  28         downloadUrl = jsonData['data']['f']
  29
  30         return {
  31             'id': video_id,
  32             'title': title,
  33             'url': downloadUrl
  34         }
  35