_ Git - youtube-dl/blob - youtube_dl/extractor/ku6.py

   1 from __future__ import unicode_literals
   2 import re
   3 from .common import InfoExtractor
   4
   5 class Ku6IE(InfoExtractor):
   6     _VALID_URL = r'http://v\.ku6\.com/show/(?P<id>[a-zA-Z0-9\-\_]+)(?:\.)*html'
   7     _TEST = {
   8         'url': 'http://v.ku6.com/show/JG-8yS14xzBr4bCn1pu0xw...html',
   9         'info_dict': {
  10             'id': 'JG-8yS14xzBr4bCn1pu0xw',
  11             'ext': 'f4v',
  12             u'title': u'techniques test',
  13         }
  14     }
  15
  16
  17
  18     def _real_extract(self, url):
  19         mobj = re.match(self._VALID_URL, url)
  20         video_id = mobj.group('id')
  21
  22         webpage = self._download_webpage(url, video_id)
  23         #title = self._html_search_meta('title', webpage, 'title')
  24         title = self._search_regex(r'<h1 title=.*>(.*?)</h1>', webpage, 'title')
  25         self.to_screen('title: '+title)
  26
  27         dataUrl = 'http://v.ku6.com/fetchVideo4Player/'+video_id+'.html'
  28         jsonData = self._download_json(dataUrl, video_id)
  29         downloadUrl = jsonData['data']['f']
  30
  31         return {
  32             'id': video_id,
  33             'title': title,
  34             'url': downloadUrl
  35             # TODO more properties (see youtube_dl/extractor/common.py)
  36
  37         }
  38