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

   1 import re
   2
   3 from .common import InfoExtractor
   4 from ..utils import (
   5     compat_urllib_parse,
   6 )
   7
   8
   9 class XVideosIE(InfoExtractor):
  10     _VALID_URL = r'^(?:https?://)?(?:www\.)?xvideos\.com/video([0-9]+)(?:.*)'
  11
  12     def _real_extract(self, url):
  13         mobj = re.match(self._VALID_URL, url)
  14         video_id = mobj.group(1)
  15
  16         webpage = self._download_webpage(url, video_id)
  17
  18         self.report_extraction(video_id)
  19
  20         # Extract video URL
  21         video_url = compat_urllib_parse.unquote(self._search_regex(r'flv_url=(.+?)&',
  22             webpage, u'video URL'))
  23
  24         # Extract title
  25         video_title = self._html_search_regex(r'<title>(.*?)\s+-\s+XVID',
  26             webpage, u'title')
  27
  28         # Extract video thumbnail
  29         video_thumbnail = self._search_regex(r'http://(?:img.*?\.)xvideos.com/videos/thumbs/[a-fA-F0-9]+/[a-fA-F0-9]+/[a-fA-F0-9]+/[a-fA-F0-9]+/([a-fA-F0-9.]+jpg)',
  30             webpage, u'thumbnail', fatal=False)
  31
  32         info = {
  33             'id': video_id,
  34             'url': video_url,
  35             'uploader': None,
  36             'upload_date': None,
  37             'title': video_title,
  38             'ext': 'flv',
  39             'thumbnail': video_thumbnail,
  40             'description': None,
  41         }
  42
  43         return [info]