_ 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 ..compat import (
   7     compat_urllib_parse_urlparse,
   8     compat_urllib_request,
   9     compat_urllib_parse,
  10 )
  11 from ..utils import (
  12     str_to_int,
  13 )
  14
  15
  16 class ExtremeTubeIE(InfoExtractor):
  17     _VALID_URL = r'https?://(?:www\.)?(?P<url>extremetube\.com/.*?video/.+?(?P<id>[0-9]+))(?:[/?&]|$)'
  18     _TESTS = [{
  19         'url': 'http://www.extremetube.com/video/music-video-14-british-euro-brit-european-cumshots-swallow-652431',
  20         'md5': '1fb9228f5e3332ec8c057d6ac36f33e0',
  21         'info_dict': {
  22             'id': '652431',
  23             'ext': 'mp4',
  24             'title': 'Music Video 14 british euro brit european cumshots swallow',
  25             'uploader': 'unknown',
  26             'view_count': int,
  27             'age_limit': 18,
  28         }
  29     }, {
  30         'url': 'http://www.extremetube.com/gay/video/abcde-1234',
  31         'only_matching': True,
  32     }]
  33
  34     def _real_extract(self, url):
  35         mobj = re.match(self._VALID_URL, url)
  36         video_id = mobj.group('id')
  37         url = 'http://www.' + mobj.group('url')
  38
  39         req = compat_urllib_request.Request(url)
  40         req.add_header('Cookie', 'age_verified=1')
  41         webpage = self._download_webpage(req, video_id)
  42
  43         video_title = self._html_search_regex(
  44             r'<h1 [^>]*?title="([^"]+)"[^>]*>', webpage, 'title')
  45         uploader = self._html_search_regex(
  46             r'Uploaded by:\s*</strong>\s*(.+?)\s*</div>',
  47             webpage, 'uploader', fatal=False)
  48         view_count = str_to_int(self._html_search_regex(
  49             r'Views:\s*</strong>\s*<span>([\d,\.]+)</span>',
  50             webpage, 'view count', fatal=False))
  51
  52         video_url = compat_urllib_parse.unquote(self._html_search_regex(
  53             r'video_url=(.+?)&amp;', webpage, 'video_url'))
  54         path = compat_urllib_parse_urlparse(video_url).path
  55         format = path.split('/')[5].split('_')[:2]
  56         format = "-".join(format)
  57
  58         return {
  59             'id': video_id,
  60             'title': video_title,
  61             'uploader': uploader,
  62             'view_count': view_count,
  63             'url': video_url,
  64             'format': format,
  65             'format_id': format,
  66             'age_limit': 18,
  67         }