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

   1 import re
   2
   3 from .common import InfoExtractor
   4 from ..utils import (
   5     compat_urllib_parse,
   6
   7     ExtractorError,
   8 )
   9
  10
  11 class XNXXIE(InfoExtractor):
  12     _VALID_URL = r'^(?:https?://)?video\.xnxx\.com/video([0-9]+)/(.*)'
  13     VIDEO_URL_RE = r'flv_url=(.*?)&amp;'
  14     VIDEO_TITLE_RE = r'<title>(.*?)\s+-\s+XNXX.COM'
  15     VIDEO_THUMB_RE = r'url_bigthumb=(.*?)&amp;'
  16
  17     def _real_extract(self, url):
  18         mobj = re.match(self._VALID_URL, url)
  19         if mobj is None:
  20             raise ExtractorError(u'Invalid URL: %s' % url)
  21         video_id = mobj.group(1)
  22
  23         # Get webpage content
  24         webpage = self._download_webpage(url, video_id)
  25
  26         video_url = self._search_regex(self.VIDEO_URL_RE,
  27             webpage, u'video URL')
  28         video_url = compat_urllib_parse.unquote(video_url)
  29
  30         video_title = self._html_search_regex(self.VIDEO_TITLE_RE,
  31             webpage, u'title')
  32
  33         video_thumbnail = self._search_regex(self.VIDEO_THUMB_RE,
  34             webpage, u'thumbnail', fatal=False)
  35
  36         return [{
  37             'id': video_id,
  38             'url': video_url,
  39             'uploader': None,
  40             'upload_date': None,
  41             'title': video_title,
  42             'ext': 'flv',
  43             'thumbnail': video_thumbnail,
  44             'description': None,
  45         }]