Merge remote-tracking branch 'lenaten/8tracks'

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

diff --git a/youtube_dl/extractor/jeuxvideo.py b/youtube_dl/extractor/jeuxvideo.py
index d74a1c9b4ee19bcba5f322d23f5e4b8a1412d26e..8094cc2e487f2880a66178d0a07c97a2ef9432f5 100644 (file)
--- a/youtube_dl/extractor/jeuxvideo.py
+++ b/youtube_dl/extractor/jeuxvideo.py
@@ -1,33 +1,51 @@
+# coding: utf-8
+
+from __future__ import unicode_literals
+
 import json
 import re
 
 from .common import InfoExtractor
 
+
 class JeuxVideoIE(InfoExtractor):
     _VALID_URL = r'http://.*?\.jeuxvideo\.com/.*/(.*?)-\d+\.htm'
 
+    _TEST = {
+        'url': 'http://www.jeuxvideo.com/reportages-videos-jeux/0004/00046170/tearaway-playstation-vita-gc-2013-tearaway-nous-presente-ses-papiers-d-identite-00115182.htm',
+        'md5': '046e491afb32a8aaac1f44dd4ddd54ee',
+        'info_dict': {
+            'id': '5182',
+            'ext': 'mp4',
+            'title': 'GC 2013 : Tearaway nous présente ses papiers d\'identité',
+            'description': '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)
+        title = mobj.group(1)
         webpage = self._download_webpage(url, title)
-        m_download = re.search(r'<param name="flashvars" value="config=(.*?)" />', webpage)
-
-        xml_link = m_download.group(1)
-        
-        id = re.search(r'http://www.jeuxvideo.com/config/\w+/0011/(.*?)/\d+_player\.xml', xml_link).group(1)
-
-        xml_config = self._download_webpage(xml_link, title,
-                                                  'Downloading XML config')
-        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']
+        xml_link = self._html_search_regex(
+            r'<param name="flashvars" value="config=(.*?)" />',
+            webpage, 'config URL')
+
+        video_id = self._search_regex(
+            r'http://www\.jeuxvideo\.com/config/\w+/\d+/(.*?)/\d+_player\.xml',
+            xml_link, 'video ID')
 
-        track_info = {'id':id,
-                      'title' : title,
-                      'ext' :   'mp4',
-                      'url' :   video_url
-                      }
+        config = self._download_xml(
+            xml_link, title, 'Downloading XML config')
+        info_json = config.find('format.json').text
+        info = json.loads(info_json)['versions'][0]
+
+        video_url = 'http://video720.jeuxvideo.com/' + info['file']
 
-        return [track_info]
+        return {
+            'id': video_id,
+            'title': config.find('titre_video').text,
+            'ext': 'mp4',
+            'url': video_url,
+            'description': self._og_search_description(webpage),
+            'thumbnail': config.find('image').text,
+        }