git.bitcoin.ninja 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_parse_qs,
   8     compat_urllib_request,
   9 )
  10 from ..utils import (
  11     qualities,
  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]+))(?:[/?&]|$)'
  18     _TESTS = [{
  19         'url': 'http://www.extremetube.com/video/music-video-14-british-euro-brit-european-cumshots-swallow-652431',
  20         'md5': '344d0c6d50e2f16b06e49ca011d8ac69',
  21         'info_dict': {
  22             'id': '652431',
  23             'ext': 'mp4',
  24             'title': 'Music Video 14 british euro brit european cumshots swallow',
  25             'uploader': 'unknown',
  26             'view_count': int,
  27             'age_limit': 18,
  28         }
  29     }, {
  30         'url': 'http://www.extremetube.com/gay/video/abcde-1234',
  31         'only_matching': True,
  32     }]
  33
  34     def _real_extract(self, url):
  35         mobj = re.match(self._VALID_URL, url)
  36         video_id = mobj.group('id')
  37         url = 'http://www.' + mobj.group('url')
  38
  39         req = compat_urllib_request.Request(url)
  40         req.add_header('Cookie', 'age_verified=1')
  41         webpage = self._download_webpage(req, video_id)
  42
  43         video_title = self._html_search_regex(
  44             r'<h1 [^>]*?title="([^"]+)"[^>]*>', webpage, 'title')
  45         uploader = self._html_search_regex(
  46             r'Uploaded by:\s*</strong>\s*(.+?)\s*</div>',
  47             webpage, 'uploader', fatal=False)
  48         view_count = str_to_int(self._html_search_regex(
  49             r'Views:\s*</strong>\s*<span>([\d,\.]+)</span>',
  50             webpage, 'view count', fatal=False))
  51
  52         flash_vars = compat_parse_qs(self._search_regex(
  53             r'<param[^>]+?name="flashvars"[^>]+?value="([^"]+)"', webpage, 'flash vars'))
  54
  55         formats = []
  56         quality = qualities(['180p', '240p', '360p', '480p', '720p', '1080p'])
  57         for k, vals in flash_vars.items():
  58             m = re.match(r'quality_(?P<quality>[0-9]+p)$', k)
  59             if m is not None:
  60                 formats.append({
  61                     'format_id': m.group('quality'),
  62                     'quality': quality(m.group('quality')),
  63                     'url': vals[0],
  64                 })
  65
  66         self._sort_formats(formats)
  67
  68         return {
  69             'id': video_id,
  70             'title': video_title,
  71             'formats': formats,
  72             'uploader': uploader,
  73             'view_count': view_count,
  74             'age_limit': 18,
  75         }