[franceinter] Minor improvements (#2152)
authorPhilipp Hagemeister <phihag@phihag.de>
Fri, 17 Jan 2014 02:09:07 +0000 (03:09 +0100)
committerPhilipp Hagemeister <phihag@phihag.de>
Fri, 17 Jan 2014 02:09:07 +0000 (03:09 +0100)
youtube_dl/extractor/franceinter.py

index 932a1f161794a8b89487e2d7483f651c0c3b1551..7728410da93d17d4bdd112ab3091512c2e335554 100644 (file)
@@ -1,31 +1,40 @@
+# coding: utf-8
 from __future__ import unicode_literals
 
 import re
 
 from .common import InfoExtractor
+
+
 class FranceInterIE(InfoExtractor):
-    
-    _VALID_URL=r'http://(?:www\.)?franceinter\.fr/player/reecouter\?play=(?P<id>[0-9]{6})'
-    _TEST={
-           u'url':u'http://www.franceinter.fr/player/reecouter?play=793962',
-           u'file':u'793962.mp3'
-                  
-           }
-           
-   
-        
-   
-    def _real_extract(self,url):
+    _VALID_URL = r'http://(?:www\.)?franceinter\.fr/player/reecouter\?play=(?P<id>[0-9]{6})'
+    _TEST = {
+        'url': 'http://www.franceinter.fr/player/reecouter?play=793962',
+        'file': '793962.mp3',
+        'md5': '4764932e466e6f6c79c317d2e74f6884',
+        "info_dict": {
+            "title": "L’Histoire dans les jeux vidéo",
+        },
+    }
 
+    def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('id')
         
-        webpage=self._download_webpage(url,video_id)
-        
-        title=self._search_regex(u'(?<=<span class="roll_overflow">)(.*)(?=</span></h1>)', webpage, u'title')
-        
-        video_url='http://www.franceinter.fr/'+self._search_regex(u'(?<=&urlAOD=)(.*)(?=&startTime)', webpage, u'video url')
-        
-        return{'id': video_id,u'url': video_url,u'title': title}
-        
+        webpage = self._download_webpage(url, video_id)
+        title = self._html_search_regex(
+            r'<span class="roll_overflow">(.*?)</span></h1>', webpage, 'title')
+        path = self._search_regex(
+            r'&urlAOD=(.*?)&startTime', webpage, 'video url')
+        video_url = 'http://www.franceinter.fr/' + path
+
+        return {
+            'id': video_id,
+            'formats': [{
+                'url': video_url,
+                'vcodec': 'none',
+            }],
+            'title': title,
+        }
+
         
\ No newline at end of file