_ 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 compat_urllib_request
   7 from ..utils import (
   8     int_or_none,
   9     str_to_int,
  10 )
  11
  12
  13 class ExtremeTubeIE(InfoExtractor):
  14     _VALID_URL = r'https?://(?:www\.)?(?P<url>extremetube\.com/.*?video/.+?(?P<id>[0-9]+))(?:[/?&]|$)'
  15     _TESTS = [{
  16         'url': 'http://www.extremetube.com/video/music-video-14-british-euro-brit-european-cumshots-swallow-652431',
  17         'md5': '344d0c6d50e2f16b06e49ca011d8ac69',
  18         'info_dict': {
  19             'id': '652431',
  20             'ext': 'mp4',
  21             'title': 'Music Video 14 british euro brit european cumshots swallow',
  22             'uploader': 'unknown',
  23             'view_count': int,
  24             'age_limit': 18,
  25         }
  26     }, {
  27         'url': 'http://www.extremetube.com/gay/video/abcde-1234',
  28         'only_matching': True,
  29     }]
  30
  31     def _real_extract(self, url):
  32         mobj = re.match(self._VALID_URL, url)
  33         video_id = mobj.group('id')
  34         url = 'http://www.' + mobj.group('url')
  35
  36         req = compat_urllib_request.Request(url)
  37         req.add_header('Cookie', 'age_verified=1')
  38         webpage = self._download_webpage(req, video_id)
  39
  40         video_title = self._html_search_regex(
  41             r'<h1 [^>]*?title="([^"]+)"[^>]*>', webpage, 'title')
  42         uploader = self._html_search_regex(
  43             r'Uploaded by:\s*</strong>\s*(.+?)\s*</div>',
  44             webpage, 'uploader', fatal=False)
  45         view_count = str_to_int(self._html_search_regex(
  46             r'Views:\s*</strong>\s*<span>([\d,\.]+)</span>',
  47             webpage, 'view count', fatal=False))
  48
  49         flash_vars = self._parse_json(
  50             self._search_regex(
  51                 r'var\s+flashvars\s*=\s*({.+?});', webpage, 'flash vars'),
  52             video_id)
  53
  54         formats = []
  55         for quality_key, video_url in flash_vars.items():
  56             height = int_or_none(self._search_regex(
  57                 r'quality_(\d+)[pP]$', quality_key, 'height', default=None))
  58             if not height:
  59                 continue
  60             f = {
  61                 'url': video_url,
  62             }
  63             mobj = re.search(
  64                 r'/(?P<height>\d{3,4})[pP]_(?P<bitrate>\d+)[kK]_\d+', video_url)
  65             if mobj:
  66                 height = int(mobj.group('height'))
  67                 bitrate = int(mobj.group('bitrate'))
  68                 f.update({
  69                     'format_id': '%dp-%dk' % (height, bitrate),
  70                     'height': height,
  71                     'tbr': bitrate,
  72                 })
  73             else:
  74                 f.update({
  75                     'format_id': '%dp' % height,
  76                     'height': height,
  77                 })
  78             formats.append(f)
  79         self._sort_formats(formats)
  80
  81         return {
  82             'id': video_id,
  83             'title': video_title,
  84             'formats': formats,
  85             'uploader': uploader,
  86             'view_count': view_count,
  87             'age_limit': 18,
  88         }