[dw] add support for audio pages
authorremitamine <remitamine@gmail.com>
Fri, 11 Mar 2016 22:55:26 +0000 (23:55 +0100)
committerremitamine <remitamine@gmail.com>
Fri, 11 Mar 2016 22:55:26 +0000 (23:55 +0100)
youtube_dl/extractor/dw.py

index df901e1b27459fe7955b0b0d6eecda168f64d082..dde66b41d75c62358b7bc4b0327c94cbf0b4c55f 100644 (file)
@@ -7,7 +7,8 @@ from ..utils import int_or_none
 
 class DWIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?dw\.com/(?:[^/]+/)+av-(?P<id>\d+)'
-    _TEST = {
+    _TESTS = [{
+        # video
         'url': 'http://www.dw.com/en/intelligent-light/av-19112290',
         'md5': '7372046e1815c5a534b43f3c3c36e6e9',
         'info_dict': {
@@ -17,21 +18,36 @@ class DWIE(InfoExtractor):
             'description': 'md5:90e00d5881719f2a6a5827cb74985af1',
             'upload_date': '20160311',
         }
-    }
+    }, {
+        # audio
+        'url': 'http://www.dw.com/en/worldlink-my-business/av-19111941',
+        'md5': '2814c9a1321c3a51f8a7aeb067a360dd',
+        'info_dict': {
+            'id': '19111941',
+            'ext': 'mp3',
+            'title': 'WorldLink: My business',
+            'description': 'md5:bc9ca6e4e063361e21c920c53af12405',
+            'upload_date': '20160311',
+        }
+    }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
-        formats = self._extract_smil_formats(
-            'http://www.dw.com/smil/v-%s' % video_id, video_id,
-            transform_source=lambda s: s.replace(
-                'rtmp://tv-od.dw.de/flash/',
-                'http://tv-download.dw.de/dwtv_video/flv/'))
-
         webpage = self._download_webpage(url, video_id)
         hidden_inputs = self._hidden_inputs(webpage)
         title = hidden_inputs['media_title']
 
+        formats = []
+        if hidden_inputs.get('player_type') == 'video' and hidden_inputs.get('stream_file') == '1':
+            formats = self._extract_smil_formats(
+                'http://www.dw.com/smil/v-%s' % video_id, video_id,
+                transform_source=lambda s: s.replace(
+                    'rtmp://tv-od.dw.de/flash/',
+                    'http://tv-download.dw.de/dwtv_video/flv/'))
+        else:
+            formats = [{'url': hidden_inputs['file_name']}]
+
         return {
             'id': video_id,
             'title': title,