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

   1 import re
   2
   3 from .common import InfoExtractor
   4 from ..utils import compat_urllib_parse
   5
   6
   7 class PornHdIE(InfoExtractor):
   8     _VALID_URL = r'(?:http://)?(?:www\.)?pornhd\.com/(?:[a-z]{2,4}/)?videos/(?P<video_id>[0-9]+)/(?P<video_title>.+)'
   9     _TEST = {
  10         u'url': u'http://www.pornhd.com/videos/1962/sierra-day-gets-his-cum-all-over-herself-hd-porn-video',
  11         u'file': u'1962.flv',
  12         u'md5': u'35272469887dca97abd30abecc6cdf75',
  13         u'info_dict': {
  14             u"title": u"sierra-day-gets-his-cum-all-over-herself-hd-porn-video",
  15             u"age_limit": 18,
  16         }
  17     }
  18
  19     def _real_extract(self, url):
  20         mobj = re.match(self._VALID_URL, url)
  21
  22         video_id = mobj.group('video_id')
  23         video_title = mobj.group('video_title')
  24
  25         webpage = self._download_webpage(url, video_id)
  26
  27         video_url = self._html_search_regex(
  28             r'&hd=(http.+?)&', webpage, u'video URL')
  29         video_url = compat_urllib_parse.unquote(video_url)
  30         age_limit = 18
  31
  32         return {
  33             'id': video_id,
  34             'url': video_url,
  35             'ext': 'flv',
  36             'title': video_title,
  37             'age_limit': age_limit,
  38         }