Unify coding cookie

[youtube-dl] / youtube_dl / extractor / hark.py

diff --git a/youtube_dl/extractor/hark.py b/youtube_dl/extractor/hark.py
index ab0a69697ed0dcc07ecd50ec04c3ed4ef264a4d6..342a6130ea10325d4b7e7ecee7ee86b130e90173 100644 (file)
--- a/youtube_dl/extractor/hark.py
+++ b/youtube_dl/extractor/hark.py
@@ -1,35 +1,33 @@
-# -*- coding: utf-8 -*-
-
-import re
+# coding: utf-8
+from __future__ import unicode_literals
 
 from .common import InfoExtractor
-from ..utils import determine_ext
+
 
 class HarkIE(InfoExtractor):
-    _VALID_URL = r'https?://www\.hark\.com/clips/(.+?)-.+'
+    _VALID_URL = r'https?://(?:www\.)?hark\.com/clips/(?P<id>.+?)-.+'
     _TEST = {
-        u'url': u'http://www.hark.com/clips/mmbzyhkgny-obama-beyond-the-afghan-theater-we-only-target-al-qaeda-on-may-23-2013',
-        u'file': u'mmbzyhkgny.mp3',
-        u'md5': u'6783a58491b47b92c7c1af5a77d4cbee',
-        u'info_dict': {
-            u"title": u"Obama: 'Beyond The Afghan Theater, We Only Target Al Qaeda' On May 23, 2013 ",
+        'url': 'http://www.hark.com/clips/mmbzyhkgny-obama-beyond-the-afghan-theater-we-only-target-al-qaeda-on-may-23-2013',
+        'md5': '6783a58491b47b92c7c1af5a77d4cbee',
+        'info_dict': {
+            'id': 'mmbzyhkgny',
+            'ext': 'mp3',
+            'title': 'Obama: \'Beyond The Afghan Theater, We Only Target Al Qaeda\' on May 23, 2013',
+            '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.',
+            'duration': 11,
         }
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group(1)
-        embed_url = "http://www.hark.com/clips/%s/homepage_embed" %(video_id)
-        webpage = self._download_webpage(embed_url, video_id)
+        video_id = self._match_id(url)
+        data = self._download_json(
+            'http://www.hark.com/clips/%s.json' % video_id, video_id)
 
-        final_url = self._search_regex(r'src="(.+?).mp3"',
-                                webpage, 'video url')+'.mp3'
-        title = self._html_search_regex(r'<title>(.+?)</title>',
-                                webpage, 'video title').replace(' Sound Clip and Quote - Hark','').replace(
-                                'Sound Clip , Quote, MP3, and Ringtone - Hark','')
-
-        return {'id': video_id,
-                'url' : final_url,
-                'title': title,
-                'ext': determine_ext(final_url),
-                }
+        return {
+            'id': video_id,
+            'url': data['url'],
+            'title': data['name'],
+            'description': data.get('description'),
+            'thumbnail': data.get('image_original'),
+            'duration': data.get('duration'),
+        }