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

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5
   6
   7 class TMZIE(InfoExtractor):
   8     _VALID_URL = r'https?://(?:www\.)?tmz\.com/videos/(?P<id>[^/]+)/?'
   9     _TEST = {
  10         'url': 'http://www.tmz.com/videos/0_okj015ty/',
  11         'md5': '791204e3bf790b1426cb2db0706184c0',
  12         'info_dict': {
  13             'id': '0_okj015ty',
  14             'url': 'http://tmz.vo.llnwd.net/o28/2014-03/13/0_okj015ty_0_rt8ro3si_2.mp4',
  15             'ext': 'mp4',
  16             'title': 'Kim Kardashian\'s Boobs Unlock a Mystery!',
  17             'description': 'Did Kim Kardasain try to one-up Khloe by one-upping Kylie???  Or is she just showing off her amazing boobs?',
  18             'thumbnail': 'http://cdnbakmi.kaltura.com/p/591531/sp/59153100/thumbnail/entry_id/0_okj015ty/version/100002/acv/182/width/640',
  19         }
  20     }
  21
  22     def _real_extract(self, url):
  23         video_id = self._match_id(url)
  24
  25         webpage = self._download_webpage(url, video_id)
  26
  27         url = self._html_search_regex(r'<meta name="VideoURL" content="(.+)"', webpage, 'url')
  28         title = self._html_search_regex(r'<meta property="og:title" content="(.+)"', webpage, 'title')
  29         description = self._html_search_regex(r'<meta property="og:description" content="(.+)"', webpage, 'description')
  30         thumbnail_url = self._html_search_regex(r'<meta name="ThumbURL" content="(.+)"', webpage, 'thumbnail url')
  31
  32         return {
  33             'id': video_id,
  34             'url': url,
  35             'ext': 'mp4',
  36             'title': title,
  37             'description': description,
  38             'thumbnail': thumbnail_url,
  39         }