Merge tag 'upstream/2014.12.01'

[youtubedl] / youtube_dl / extractor / wistia.py

diff --git a/youtube_dl/extractor/wistia.py b/youtube_dl/extractor/wistia.py
index bc31c2e64f22999adf575e60d59bde3d903bb9cc..748443f811f184d4276d4628cd13ed1e2bf92d9c 100644 (file)
--- a/youtube_dl/extractor/wistia.py
+++ b/youtube_dl/extractor/wistia.py
@@ -1,18 +1,23 @@
-import json
+from __future__ import unicode_literals
+

 import re
 
 from .common import InfoExtractor
 import re
 
 from .common import InfoExtractor

+from ..utils import ExtractorError, compat_urllib_request

 
 
 class WistiaIE(InfoExtractor):
 
 
 class WistiaIE(InfoExtractor):

-    _VALID_URL = r'^https?://(?:fast\.)?wistia\.net/embed/iframe/(?P<id>[a-z0-9]+)'
+    _VALID_URL = r'https?://(?:fast\.)?wistia\.net/embed/iframe/(?P<id>[a-z0-9]+)'
+    _API_URL = 'http://fast.wistia.com/embed/medias/{0:}.json'

 
     _TEST = {
 
     _TEST = {

-        u"url": u"http://fast.wistia.net/embed/iframe/sh7fpupwlt",
-        u"file": u"sh7fpupwlt.mov",
-        u"md5": u"cafeb56ec0c53c18c97405eecb3133df",
-        u"info_dict": {
-            u"title": u"cfh_resourceful_zdkh_final_1"
+        'url': 'http://fast.wistia.net/embed/iframe/sh7fpupwlt',
+        'md5': 'cafeb56ec0c53c18c97405eecb3133df',
+        'info_dict': {
+            'id': 'sh7fpupwlt',
+            'ext': 'mov',
+            'title': 'Being Resourceful',
+            'duration': 117,

         },
     }
 
         },
     }
 


@@ -20,11 +25,13 @@ class WistiaIE(InfoExtractor):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('id')
 
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('id')
 

-        webpage = self._download_webpage(url, video_id)
-        data_json = self._html_search_regex(
-            r'Wistia.iframeInit\((.*?), {}\);', webpage, u'video data')
-
-        data = json.loads(data_json)
+        request = compat_urllib_request.Request(self._API_URL.format(video_id))
+        request.add_header('Referer', url)  # Some videos require this.
+        data_json = self._download_json(request, video_id)
+        if data_json.get('error'):
+            raise ExtractorError('Error while getting the playlist',
+                                 expected=True)
+        data = data_json['media']

 
         formats = []
         thumbnails = []
 
         formats = []
         thumbnails = []


@@ -54,4 +61,5 @@ class WistiaIE(InfoExtractor):
             'title': data['name'],
             'formats': formats,
             'thumbnails': thumbnails,
             'title': data['name'],
             'formats': formats,
             'thumbnails': thumbnails,

+            'duration': data.get('duration'),

         }
         }