[ustream] Try to extract uploader from JSON data (#5128)
[youtube-dl] / youtube_dl / extractor / dreisat.py
index 69ca75423cb1d4692f1958829dc61bcf5c2bac73..05bb22ddf3f0a3b095e1108b88d47f6766484d09 100644 (file)
@@ -3,22 +3,25 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..utils import unified_strdate
+from ..utils import (
+    ExtractorError,
+    unified_strdate,
+)
 
 
 class DreiSatIE(InfoExtractor):
     IE_NAME = '3sat'
     _VALID_URL = r'(?:http://)?(?:www\.)?3sat\.de/mediathek/(?:index\.php)?\?(?:(?:mode|display)=[^&]+&)*obj=(?P<id>[0-9]+)$'
     _TEST = {
-        'url': 'http://www.3sat.de/mediathek/index.php?obj=36983',
-        'md5': '9dcfe344732808dbfcc901537973c922',
+        'url': 'http://www.3sat.de/mediathek/index.php?mode=play&obj=45918',
+        'md5': 'be37228896d30a88f315b638900a026e',
         'info_dict': {
-            'id': '36983',
+            'id': '45918',
             'ext': 'mp4',
-            'title': 'Kaffeeland Schweiz',
-            'description': 'md5:cc4424b18b75ae9948b13929a0814033',
+            'title': 'Waidmannsheil',
+            'description': 'md5:cce00ca1d70e21425e72c86a98a56817',
             'uploader': '3sat',
-            'upload_date': '20130622'
+            'upload_date': '20140913'
         }
     }
 
@@ -28,6 +31,15 @@ class DreiSatIE(InfoExtractor):
         details_url = 'http://www.3sat.de/mediathek/xmlservice/web/beitragsDetails?ak=web&id=%s' % video_id
         details_doc = self._download_xml(details_url, video_id, 'Downloading video details')
 
+        status_code = details_doc.find('./status/statuscode')
+        if status_code is not None and status_code.text != 'ok':
+            code = status_code.text
+            if code == 'notVisibleAnymore':
+                message = 'Video %s is not available' % video_id
+            else:
+                message = '%s returned error: %s' % (self.IE_NAME, code)
+            raise ExtractorError(message, expected=True)
+
         thumbnail_els = details_doc.findall('.//teaserimage')
         thumbnails = [{
             'width': int(te.attrib['key'].partition('x')[0]),