Merge tag 'upstream/2014.07.11'

[youtubedl] / youtube_dl / extractor / jeuxvideo.py

diff --git a/youtube_dl/extractor/jeuxvideo.py b/youtube_dl/extractor/jeuxvideo.py
index 6bb54b932298395b8f07554b12ad6091cca140d3..1881659665b415714d1315f6d52bc93dbe324a2c 100644 (file)
--- a/youtube_dl/extractor/jeuxvideo.py
+++ b/youtube_dl/extractor/jeuxvideo.py
@@ -1,8 +1,9 @@
 # coding: utf-8
 
 # coding: utf-8
 

+from __future__ import unicode_literals
+

 import json
 import re
 import json
 import re

-import xml.etree.ElementTree

 
 from .common import InfoExtractor
 
 
 from .common import InfoExtractor
 


@@ -11,33 +12,31 @@ class JeuxVideoIE(InfoExtractor):
     _VALID_URL = r'http://.*?\.jeuxvideo\.com/.*/(.*?)-\d+\.htm'
 
     _TEST = {
     _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'046e491afb32a8aaac1f44dd4ddd54ee',
-        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',
+        '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)
         },
     }
 
     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)
         xml_link = self._html_search_regex(
             r'<param name="flashvars" value="config=(.*?)" />',
         webpage = self._download_webpage(url, title)
         xml_link = self._html_search_regex(
             r'<param name="flashvars" value="config=(.*?)" />',

-            webpage, u'config URL')
+            webpage, 'config URL')

         
         video_id = self._search_regex(
             r'http://www\.jeuxvideo\.com/config/\w+/\d+/(.*?)/\d+_player\.xml',
         
         video_id = self._search_regex(
             r'http://www\.jeuxvideo\.com/config/\w+/\d+/(.*?)/\d+_player\.xml',

-            xml_link, u'video ID')
-
-        xml_config = self._download_webpage(
-            xml_link, title, u'Downloading XML config')
-        config = xml.etree.ElementTree.fromstring(xml_config.encode('utf-8'))
-        info_json = self._search_regex(
-            r'(?sm)<format\.json>(.*?)</format\.json>',
-            xml_config, u'JSON information')
+            xml_link, 'video ID')
+
+        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']
         info = json.loads(info_json)['versions'][0]
         
         video_url = 'http://video720.jeuxvideo.com/' + info['file']