youtube_dl/extractor/xnxx.py

   1 # encoding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..utils import (
   8     compat_urllib_parse,
   9 )
  10
  11
  12 class XNXXIE(InfoExtractor):
  13     _VALID_URL = r'^https?://(?:video|www)\.xnxx\.com/video(?P<id>[0-9]+)/(.*)'
  14     _TEST = {
  15         'url': 'http://video.xnxx.com/video1135332/lida_naked_funny_actress_5_',
  16         'md5': '0831677e2b4761795f68d417e0b7b445',
  17         'info_dict': {
  18             'id': '1135332',
  19             'ext': 'flv',
  20             'title': 'lida » Naked Funny Actress  (5)',
  21             'age_limit': 18,
  22         }
  23     }
  24
  25     def _real_extract(self, url):
  26         mobj = re.match(self._VALID_URL, url)
  27         video_id = mobj.group('id')
  28
  29         # Get webpage content
  30         webpage = self._download_webpage(url, video_id)
  31
  32         video_url = self._search_regex(r'flv_url=(.*?)&amp;',
  33             webpage, 'video URL')
  34         video_url = compat_urllib_parse.unquote(video_url)
  35
  36         video_title = self._html_search_regex(r'<title>(.*?)\s+-\s+XNXX.COM',
  37             webpage, 'title')
  38
  39         video_thumbnail = self._search_regex(r'url_bigthumb=(.*?)&amp;',
  40             webpage, 'thumbnail', fatal=False)
  41
  42         return {
  43             'id': video_id,
  44             'url': video_url,
  45             'title': video_title,
  46             'ext': 'flv',
  47             'thumbnail': video_thumbnail,
  48             'age_limit': 18,
  49         }