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

   1 # -*- coding: utf-8 -*-
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..utils import determine_ext
   7
   8 class HarkIE(InfoExtractor):
   9     _VALID_URL = r'https?://www\.hark\.com/clips/(.+?)-.+'
  10     _TEST = {
  11         u'url': u'http://www.hark.com/clips/mmbzyhkgny-obama-beyond-the-afghan-theater-we-only-target-al-qaeda-on-may-23-2013',
  12         u'file': u'mmbzyhkgny.mp3',
  13         u'md5': u'6783a58491b47b92c7c1af5a77d4cbee',
  14         u'info_dict': {
  15             u"title": u"Obama: 'Beyond The Afghan Theater, We Only Target Al Qaeda' On May 23, 2013 ",
  16         }
  17     }
  18
  19     def _real_extract(self, url):
  20         mobj = re.match(self._VALID_URL, url)
  21         video_id = mobj.group(1)
  22         embed_url = "http://www.hark.com/clips/%s/homepage_embed" %(video_id)
  23         webpage = self._download_webpage(embed_url, video_id)
  24
  25         final_url = self._search_regex(r'src="(.+?).mp3"',
  26                                 webpage, 'video url')+'.mp3'
  27         title = self._html_search_regex(r'<title>(.+?)</title>',
  28                                 webpage, 'video title').replace(' Sound Clip and Quote - Hark','').replace(
  29                                 'Sound Clip , Quote, MP3, and Ringtone - Hark','')
  30
  31         return {'id': video_id,
  32                 'url' : final_url,
  33                 'title': title,
  34                 'ext': determine_ext(final_url),
  35                 }