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

   1 import re
   2 import base64
   3
   4 from .common import InfoExtractor
   5
   6
   7 class WimpIE(InfoExtractor):
   8     _VALID_URL = r'(?:http://)?(?:www\.)?wimp\.com/([^/]+)/'
   9     _TEST = {
  10         u'url': u'http://www.wimp.com/deerfence/',
  11         u'file': u'deerfence.flv',
  12         u'md5': u'8b215e2e0168c6081a1cf84b2846a2b5',
  13         u'info_dict': {
  14             u"title": u"Watch Till End: Herd of deer jump over a fence."
  15         }
  16     }
  17
  18     def _real_extract(self, url):
  19         mobj = re.match(self._VALID_URL, url)
  20         video_id = mobj.group(1)
  21         webpage = self._download_webpage(url, video_id)
  22         title = self._search_regex(r'<meta name="description" content="(.+?)" />',webpage, 'video title')
  23         thumbnail_url = self._search_regex(r'<meta property="og\:image" content="(.+?)" />', webpage,'video thumbnail')
  24         googleString = self._search_regex("googleCode = '(.*?)'", webpage, 'file url')
  25         googleString = base64.b64decode(googleString).decode('ascii')
  26         final_url = self._search_regex('","(.*?)"', googleString,'final video url')
  27         ext = final_url.rpartition(u'.')[2]
  28
  29         return [{
  30             'id':        video_id,
  31             'url':       final_url,
  32             'ext':       ext,
  33             'title':     title,
  34             'thumbnail': thumbnail_url,
  35         }]
  36