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

   1 import re
   2
   3 from .common import InfoExtractor
   4 from ..utils import (
   5     ExtractorError,
   6 )
   7
   8
   9 class FunnyOrDieIE(InfoExtractor):
  10     _VALID_URL = r'^(?:https?://)?(?:www\.)?funnyordie\.com/videos/(?P<id>[0-9a-f]+)/.*$'
  11
  12     def _real_extract(self, url):
  13         mobj = re.match(self._VALID_URL, url)
  14
  15         video_id = mobj.group('id')
  16         webpage = self._download_webpage(url, video_id)
  17
  18         video_url = self._html_search_regex(r'<video[^>]*>\s*<source[^>]*>\s*<source src="(?P<url>[^"]+)"',
  19             webpage, u'video URL', flags=re.DOTALL)
  20
  21         title = self._html_search_regex((r"<h1 class='player_page_h1'.*?>(?P<title>.*?)</h1>",
  22             r'<title>(?P<title>[^<]+?)</title>'), webpage, 'title', flags=re.DOTALL)
  23
  24         video_description = self._html_search_regex(r'<meta property="og:description" content="(?P<desc>.*?)"',
  25             webpage, u'description', fatal=False, flags=re.DOTALL)
  26
  27         info = {
  28             'id': video_id,
  29             'url': video_url,
  30             'ext': 'mp4',
  31             'title': title,
  32             'description': video_description,
  33         }
  34         return [info]