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

   1 import re
   2
   3 from .common import InfoExtractor
   4
   5
   6 class FunnyOrDieIE(InfoExtractor):
   7     _VALID_URL = r'^(?:https?://)?(?:www\.)?funnyordie\.com/videos/(?P<id>[0-9a-f]+)/.*$'
   8
   9     def _real_extract(self, url):
  10         mobj = re.match(self._VALID_URL, url)
  11
  12         video_id = mobj.group('id')
  13         webpage = self._download_webpage(url, video_id)
  14
  15         video_url = self._html_search_regex(r'<video[^>]*>\s*<source[^>]*>\s*<source src="(?P<url>[^"]+)"',
  16             webpage, u'video URL', flags=re.DOTALL)
  17
  18         title = self._html_search_regex((r"<h1 class='player_page_h1'.*?>(?P<title>.*?)</h1>",
  19             r'<title>(?P<title>[^<]+?)</title>'), webpage, 'title', flags=re.DOTALL)
  20
  21         video_description = self._html_search_regex(r'<meta property="og:description" content="(?P<desc>.*?)"',
  22             webpage, u'description', fatal=False, flags=re.DOTALL)
  23
  24         info = {
  25             'id': video_id,
  26             'url': video_url,
  27             'ext': 'mp4',
  28             'title': title,
  29             'description': video_description,
  30         }
  31         return [info]