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

   1 # encoding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..compat import compat_urllib_parse_unquote
   6
   7
   8 class XNXXIE(InfoExtractor):
   9     _VALID_URL = r'^https?://(?:video|www)\.xnxx\.com/video(?P<id>[0-9]+)/(.*)'
  10     _TEST = {
  11         'url': 'http://video.xnxx.com/video1135332/lida_naked_funny_actress_5_',
  12         'md5': '0831677e2b4761795f68d417e0b7b445',
  13         'info_dict': {
  14             'id': '1135332',
  15             'ext': 'flv',
  16             'title': 'lida » Naked Funny Actress  (5)',
  17             'age_limit': 18,
  18         }
  19     }
  20
  21     def _real_extract(self, url):
  22         video_id = self._match_id(url)
  23         webpage = self._download_webpage(url, video_id)
  24
  25         video_url = self._search_regex(r'flv_url=(.*?)&amp;',
  26                                        webpage, 'video URL')
  27         video_url = compat_urllib_parse_unquote(video_url)
  28
  29         video_title = self._html_search_regex(r'<title>(.*?)\s+-\s+XNXX.COM',
  30                                               webpage, 'title')
  31
  32         video_thumbnail = self._search_regex(r'url_bigthumb=(.*?)&amp;',
  33                                              webpage, 'thumbnail', fatal=False)
  34
  35         return {
  36             'id': video_id,
  37             'url': video_url,
  38             'title': video_title,
  39             'ext': 'flv',
  40             'thumbnail': video_thumbnail,
  41             'age_limit': 18,
  42         }