_ Git - youtube-dl/blob - youtube_dl/extractor/nuvid.py

   1 import re
   2
   3 from .common import InfoExtractor
   4
   5 class NuvidIE(InfoExtractor):
   6     _VALID_URL = r'^https?://(?:www|m)\.nuvid\.com/video/(?P<videoid>\d+)'
   7     _TEST = {
   8         u'url': u'http://m.nuvid.com/video/1310741/',
   9         u'file': u'1310741.mp4',
  10         u'md5': u'eab207b7ac4fccfb4e23c86201f11277',
  11         u'info_dict': {
  12             u"title": u"Horny babes show their awesome bodeis and",
  13             u"age_limit": 18,
  14         }
  15     }
  16
  17     def _real_extract(self, url):
  18         mobj = re.match(self._VALID_URL, url)
  19
  20         video_id = mobj.group('videoid')
  21
  22         # Get webpage content
  23         murl = url.replace('//www.', '//m.')
  24         webpage = self._download_webpage(murl, video_id)
  25
  26         video_title = self._html_search_regex(r'<div class="title">\s+<h2[^>]*>([^<]+)</h2>', webpage, 'video_title').strip()
  27
  28         video_url = 'http://m.nuvid.com'+self._html_search_regex(r'href="(/mp4/[^"]+)"[^>]*data-link_type="mp4"', webpage, 'video_url')
  29
  30         video_thumb = self._html_search_regex(r'href="(/thumbs/[^"]+)"[^>]*data-link_type="thumbs"', webpage, 'video_thumb')
  31
  32         info = {'id': video_id,
  33                 'url': video_url,
  34                 'title': video_title,
  35                 'thumbnail': video_thumb,
  36                 'ext': 'mp4',
  37                 'age_limit': 18}
  38
  39         return [info]