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

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7
   8 class GorillaVidIE(InfoExtractor):
   9     _VALID_URL = r'https?://(?:www.)?gorillavid.in/(?:embed-)?(?P<id>\w+)(?:\-\d+x\d+)?(?:.html)?'
  10     _TEST = {
  11         'url': "http://gorillavid.in/z08zf8le23c6",
  12         'md5': 'c9e293ca74d46cad638e199c3f3fe604',
  13         'info_dict': {
  14             'id': 'z08zf8le23c6',
  15             'ext': 'mp4',
  16             'title': 'Say something nice',
  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._html_search_regex(r"name=['\"]fname['\"]\s+value=['\"](.*?)['\"]", webpage, u"video title")
  26
  27         # download embed page again with cookies to get url
  28         embed_url = "http://gorillavid.in/embed-{0}-960x480.html".format(video_id)
  29         webpage = self._download_webpage(embed_url, video_id, note=u'Downloading webpage again (with cookie)')
  30         url = self._html_search_regex(r'file:\s+["\'](http://.*?video.\w{3})["\']', webpage, url)
  31
  32         info_dict = {
  33             'id': video_id,
  34             'title': title,
  35             'url': url,
  36         }
  37
  38         return info_dict