youtube-dl

commit 063fcc9676718fc4395b92d6e9665e7f3e9c8156
parent 8403612258afb1897b82bd789cfb64ea76017688
Author: Jaime Marquínez Ferrándiz <jaime.marquinez.ferrandiz@gmail.com>
Date:   Thu, 22 Aug 2013 12:37:34 +0200

[jeuxvideo] Extract more information and add test

Diffstat:
M
youtube_dl/extractor/jeuxvideo.py
 | 
28
+++++++++++++++++++++-------

1 file changed, 21 insertions(+), 7 deletions(-)
diff --git a/youtube_dl/extractor/jeuxvideo.py b/youtube_dl/extractor/jeuxvideo.py
@@ -1,11 +1,24 @@
+# coding: utf-8
+
 import json
 import re
+import xml.etree.ElementTree
 
 from .common import InfoExtractor
 
 class JeuxVideoIE(InfoExtractor):
     _VALID_URL = r'http://.*?\.jeuxvideo\.com/.*/(.*?)-\d+\.htm'
 
+    _TEST = {
+        u'url': u'http://www.jeuxvideo.com/reportages-videos-jeux/0004/00046170/tearaway-playstation-vita-gc-2013-tearaway-nous-presente-ses-papiers-d-identite-00115182.htm',
+        u'file': u'5182.mp4',
+        u'md5': u'e0fdb0cd3ce98713ef9c1e1e025779d0',
+        u'info_dict': {
+            u'title': u'GC 2013 : Tearaway nous présente ses papiers d\'identité',
+            u'description': u'Lorsque les développeurs de LittleBigPlanet proposent un nouveau titre, on ne peut que s\'attendre à un résultat original et fort attrayant.\n',
+        },
+    }
+
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         title = re.match(self._VALID_URL, url).group(1)
@@ -18,16 +31,17 @@ class JeuxVideoIE(InfoExtractor):
 
         xml_config = self._download_webpage(xml_link, title,
                                                   'Downloading XML config')
+        config = xml.etree.ElementTree.fromstring(xml_config.encode('utf-8'))
         info = re.search(r'<format\.json>(.*?)</format\.json>',
                          xml_config, re.MULTILINE|re.DOTALL).group(1)
         info = json.loads(info)['versions'][0]
         
         video_url = 'http://video720.jeuxvideo.com/' + info['file']
 
-        track_info = {'id':id,
-                      'title' : title,
-                      'ext' :   'mp4',
-                      'url' :   video_url
-                      }
-
-        return [track_info]
+        return {'id': id,
+                'title' : config.find('titre_video').text,
+                'ext' : 'mp4',
+                'url' : video_url,
+                'description': self._og_search_description(webpage),
+                'thumbnail': config.find('image').text,
+                }