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

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..utils import (
   7     compat_urllib_parse_urlparse,
   8     compat_urllib_request,
   9     compat_urllib_parse,
  10 )
  11
  12
  13 class ExtremeTubeIE(InfoExtractor):
  14     _VALID_URL = r'^(?:https?://)?(?:www\.)?(?P<url>extremetube\.com/.*?video/.+?(?P<videoid>[0-9]+))(?:[/?&]|$)'
  15     _TESTS = [{
  16         'url': 'http://www.extremetube.com/video/music-video-14-british-euro-brit-european-cumshots-swallow-652431',
  17         'md5': '1fb9228f5e3332ec8c057d6ac36f33e0',
  18         'info_dict': {
  19             'id': '652431',
  20             'ext': 'mp4',
  21             'title': 'Music Video 14 british euro brit european cumshots swallow',
  22             'uploader': 'unknown',
  23             'age_limit': 18,
  24         }
  25     }, {
  26         'url': 'http://www.extremetube.com/gay/video/abcde-1234',
  27         'only_matching': True,
  28     }]
  29
  30     def _real_extract(self, url):
  31         mobj = re.match(self._VALID_URL, url)
  32         video_id = mobj.group('videoid')
  33         url = 'http://www.' + mobj.group('url')
  34
  35         req = compat_urllib_request.Request(url)
  36         req.add_header('Cookie', 'age_verified=1')
  37         webpage = self._download_webpage(req, video_id)
  38
  39         video_title = self._html_search_regex(
  40             r'<h1 [^>]*?title="([^"]+)"[^>]*>', webpage, 'title')
  41         uploader = self._html_search_regex(
  42             r'>Posted by:(?=<)(?:\s|<[^>]*>)*(.+?)\|', webpage, 'uploader',
  43             fatal=False)
  44         video_url = compat_urllib_parse.unquote(self._html_search_regex(
  45             r'video_url=(.+?)&amp;', webpage, 'video_url'))
  46         path = compat_urllib_parse_urlparse(video_url).path
  47         format = path.split('/')[5].split('_')[:2]
  48         format = "-".join(format)
  49
  50         return {
  51             'id': video_id,
  52             'title': video_title,
  53             'uploader': uploader,
  54             'url': video_url,
  55             'format': format,
  56             'format_id': format,
  57             'age_limit': 18,
  58         }