_ Git - youtube-dl/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     str_to_int,
  11 )
  12
  13
  14 class ExtremeTubeIE(InfoExtractor):
  15     _VALID_URL = r'^(?:https?://)?(?:www\.)?(?P<url>extremetube\.com/.*?video/.+?(?P<videoid>[0-9]+))(?:[/?&]|$)'
  16     _TESTS = [{
  17         'url': 'http://www.extremetube.com/video/music-video-14-british-euro-brit-european-cumshots-swallow-652431',
  18         'md5': '1fb9228f5e3332ec8c057d6ac36f33e0',
  19         'info_dict': {
  20             'id': '652431',
  21             'ext': 'mp4',
  22             'title': 'Music Video 14 british euro brit european cumshots swallow',
  23             'uploader': 'unknown',
  24             'view_count': int,
  25             'age_limit': 18,
  26         }
  27     }, {
  28         'url': 'http://www.extremetube.com/gay/video/abcde-1234',
  29         'only_matching': True,
  30     }]
  31
  32     def _real_extract(self, url):
  33         mobj = re.match(self._VALID_URL, url)
  34         video_id = mobj.group('videoid')
  35         url = 'http://www.' + mobj.group('url')
  36
  37         req = compat_urllib_request.Request(url)
  38         req.add_header('Cookie', 'age_verified=1')
  39         webpage = self._download_webpage(req, video_id)
  40
  41         video_title = self._html_search_regex(
  42             r'<h1 [^>]*?title="([^"]+)"[^>]*>', webpage, 'title')
  43         uploader = self._html_search_regex(
  44             r'Uploaded by:\s*</strong>\s*(.+?)\s*</div>',
  45             webpage, 'uploader', fatal=False)
  46         view_count = str_to_int(self._html_search_regex(
  47             r'Views:\s*</strong>\s*<span>([\d,\.]+)</span>',
  48             webpage, 'view count', fatal=False))
  49
  50         video_url = compat_urllib_parse.unquote(self._html_search_regex(
  51             r'video_url=(.+?)&amp;', webpage, 'video_url'))
  52         path = compat_urllib_parse_urlparse(video_url).path
  53         format = path.split('/')[5].split('_')[:2]
  54         format = "-".join(format)
  55
  56         return {
  57             'id': video_id,
  58             'title': video_title,
  59             'uploader': uploader,
  60             'view_count': view_count,
  61             'url': video_url,
  62             'format': format,
  63             'format_id': format,
  64             'age_limit': 18,
  65         }