youtube_dl/extractor/hark.py

   1 # -*- coding: utf-8 -*-
   2
   3 import re
   4 import json
   5
   6 from .common import InfoExtractor
   7 from ..utils import determine_ext
   8
   9 class HarkIE(InfoExtractor):
  10     _VALID_URL = r'https?://www\.hark\.com/clips/(.+?)-.+'
  11     _TEST = {
  12         u'url': u'http://www.hark.com/clips/mmbzyhkgny-obama-beyond-the-afghan-theater-we-only-target-al-qaeda-on-may-23-2013',
  13         u'file': u'mmbzyhkgny.mp3',
  14         u'md5': u'6783a58491b47b92c7c1af5a77d4cbee',
  15         u'info_dict': {
  16             u'title': u"Obama: 'Beyond The Afghan Theater, We Only Target Al Qaeda' on May 23, 2013",
  17             u'description': u'President Barack Obama addressed the nation live on May 23, 2013 in a speech aimed at addressing counter-terrorism policies including the use of drone strikes, detainees at Guantanamo Bay prison facility, and American citizens who are terrorists.',
  18             u'duration': 11,
  19         }
  20     }
  21
  22     def _real_extract(self, url):
  23         mobj = re.match(self._VALID_URL, url)
  24         video_id = mobj.group(1)
  25         json_url = "http://www.hark.com/clips/%s.json" %(video_id)
  26         info_json = self._download_webpage(json_url, video_id)
  27         info = json.loads(info_json)
  28         final_url = info['url']
  29
  30         return {'id': video_id,
  31                 'url' : final_url,
  32                 'title': info['name'],
  33                 'ext': determine_ext(final_url),
  34                 'description': info['description'],
  35                 'thumbnail': info['image_original'],
  36                 'duration': info['duration'],
  37                 }