Merge remote-tracking branch 'jaimeMF/yt-toplists'
[youtube-dl] / youtube_dl / extractor / wimp.py
index a548e0fa0668c154a7b3a36f48fe192d11c4e4d7..3635691e7a15cbed6957cc7757138f3179c318f3 100644 (file)
@@ -1,26 +1,34 @@
 import re
 import base64
+
 from .common import InfoExtractor
 
 
 class WimpIE(InfoExtractor):
     _VALID_URL = r'(?:http://)?(?:www\.)?wimp\.com/([^/]+)/'
+    _TEST = {
+        u'url': u'http://www.wimp.com/deerfence/',
+        u'file': u'deerfence.flv',
+        u'md5': u'8b215e2e0168c6081a1cf84b2846a2b5',
+        u'info_dict': {
+            u"title": u"Watch Till End: Herd of deer jump over a fence.",
+            u"description": u"These deer look as fluid as running water when they jump over this fence as a herd. This video is one that needs to be watched until the very end for the true majesty to be witnessed, but once it comes, it's sure to take your breath away.",
+        }
+    }
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group(1)
         webpage = self._download_webpage(url, video_id)
-        title = self._search_regex('\<meta name\="description" content="(.+?)" \/\>',webpage, 'video title')
-        thumbnail_url = self._search_regex('\<meta property\=\"og\:image" content\=\"(.+?)\" />',webpage,'video thumbnail')
-        googleString = self._search_regex("googleCode = '(.*?)'", webpage,'file url')
+        title = self._html_search_meta('description', webpage, u'video title')
+        googleString = self._search_regex("googleCode = '(.*?)'", webpage, 'file url')
         googleString = base64.b64decode(googleString).decode('ascii')
         final_url = self._search_regex('","(.*?)"', googleString,'final video url')
-        ext = final_url.split('.')[-1]
-        return [{
-            'id':        video_id,
-            'url':       final_url,
-            'ext':       ext,
-            'title':     title,
-            'thumbnail': thumbnail_url,
-        }]
 
+        return {
+            'id': video_id,
+            'url': final_url,
+            'title': self._og_search_title(webpage),
+            'thumbnail': self._og_search_thumbnail(webpage),
+            'description': self._og_search_description(webpage),
+        }