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

   1 import re
   2
   3 from .common import InfoExtractor
   4 from ..utils import (
   5     ExtractorError,
   6 )
   7
   8 class EmpflixIE(InfoExtractor):
   9     _VALID_URL = r'^https?://www\.empflix\.com/videos/(?P<videoid>[^\.]+)\.html'
  10     _TEST = {
  11         u'url': u'http://www.empflix.com/videos/Amateur-Finger-Fuck-33051.html',
  12         u'file': u'Amateur-Finger-Fuck-33051.flv',
  13         u'md5': u'5e5cc160f38ca9857f318eb97146e13e',
  14         u'info_dict': {
  15             u"title": u"Amateur Finger Fuck",
  16             u"age_limit": 18,
  17         }
  18     }
  19
  20     def _real_extract(self, url):
  21         mobj = re.match(self._VALID_URL, url)
  22
  23         video_id = mobj.group('videoid')
  24
  25         # Get webpage content
  26         webpage = self._download_webpage(url, video_id)
  27
  28         age_limit = self._rta_search(webpage)
  29
  30         # Get the video title
  31         video_title = self._html_search_regex(r'name="title" value="(?P<title>[^"]*)"',
  32             webpage, u'title').strip()
  33
  34         cfg_url = self._html_search_regex(r'flashvars\.config = escape\("([^"]+)"',
  35             webpage, u'flashvars.config').strip()
  36
  37         cfg_xml = self._download_xml(cfg_url, video_id, note=u'Downloading metadata')
  38         video_url = cfg_xml.find('videoLink').text
  39
  40         info = {'id': video_id,
  41                 'url': video_url,
  42                 'title': video_title,
  43                 'ext': 'flv',
  44                 'age_limit': age_limit}
  45
  46         return [info]