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

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7
   8 class CrackedIE(InfoExtractor):
   9     _VALID_URL = r'http?://.*?\.cracked\.com/video_+(?P<id>.*)_.*'
  10     _TEST = {
  11         'url': 'http://www.cracked.com/video_18803_4-social-criticisms-hidden-in-sonic-hedgehog-games.html',
  12
  13         'info_dict': {
  14             'id': '18803',
  15             'ext': 'mp4',
  16             'title': "4 Social Criticisms Hidden in 'Sonic the Hedgehog' Games | Cracked.com",
  17             'height': 375,
  18             'width': 666,
  19
  20
  21         }
  22     }
  23
  24     def _real_extract(self, url):
  25         mobj = re.match(self._VALID_URL, url)
  26         video_id = mobj.group('id')
  27
  28         webpage = self._download_webpage(url, video_id)
  29         title = self._search_regex(r'<title>(.*?)</title>',webpage,'title')
  30         video_url = self._search_regex(r'var CK_vidSrc = "+(.*)"',webpage,'url')
  31         width = self._search_regex(r'width="(.*?)"',webpage,'width')
  32         height = re.findall(r'height="(.*?)"',webpage)[1]
  33
  34
  35
  36
  37         return {
  38             'url':video_url,
  39             'id': video_id,
  40             'ext':'mp4',
  41             'title':title,
  42             'height':int(height),
  43             'width':int(width)
  44
  45
  46         }