Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/hark.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5
   6
   7 class HarkIE(InfoExtractor):
   8     _VALID_URL = r'https?://(?:www\.)?hark\.com/clips/(?P<id>.+?)-.+'
   9     _TEST = {
  10         'url': 'http://www.hark.com/clips/mmbzyhkgny-obama-beyond-the-afghan-theater-we-only-target-al-qaeda-on-may-23-2013',
  11         'md5': '6783a58491b47b92c7c1af5a77d4cbee',
  12         'info_dict': {
  13             'id': 'mmbzyhkgny',
  14             'ext': 'mp3',
  15             'title': 'Obama: \'Beyond The Afghan Theater, We Only Target Al Qaeda\' on May 23, 2013',
  16             'description': '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.',
  17             'duration': 11,
  18         }
  19     }
  20
  21     def _real_extract(self, url):
  22         video_id = self._match_id(url)
  23         data = self._download_json(
  24             'http://www.hark.com/clips/%s.json' % video_id, video_id)
  25
  26         return {
  27             'id': video_id,
  28             'url': data['url'],
  29             'title': data['name'],
  30             'description': data.get('description'),
  31             'thumbnail': data.get('image_original'),
  32             'duration': data.get('duration'),
  33         }