Use canonical URL in Vcs-Git.

[youtubedl] / youtube_dl / extractor / sbs.py

diff --git a/youtube_dl/extractor/sbs.py b/youtube_dl/extractor/sbs.py
index d6ee2d9e2245475d236c12fb6967af68558d8598..0e623ff7b7039e541754088d606c33855ca5a01b 100644 (file)
--- a/youtube_dl/extractor/sbs.py
+++ b/youtube_dl/extractor/sbs.py
@@ -1,7 +1,11 @@
-# -*- coding: utf-8 -*-
+# coding: utf-8

 from __future__ import unicode_literals
 
 from .common import InfoExtractor
 from __future__ import unicode_literals
 
 from .common import InfoExtractor

+from ..utils import (
+    smuggle_url,
+    ExtractorError,
+)

 
 
 class SBSIE(InfoExtractor):
 
 
 class SBSIE(InfoExtractor):


@@ -18,8 +22,11 @@ class SBSIE(InfoExtractor):
             'ext': 'mp4',
             'title': 'Dingo Conservation (The Feed)',
             'description': 'md5:f250a9856fca50d22dec0b5b8015f8a5',
             'ext': 'mp4',
             'title': 'Dingo Conservation (The Feed)',
             'description': 'md5:f250a9856fca50d22dec0b5b8015f8a5',

-            'thumbnail': 're:http://.*\.jpg',
+            'thumbnail': r're:http://.*\.jpg',

             'duration': 308,
             'duration': 308,

+            'timestamp': 1408613220,
+            'upload_date': '20140821',
+            'uploader': 'SBSC',

         },
     }, {
         'url': 'http://www.sbs.com.au/ondemand/video/320403011771/Dingo-Conservation-The-Feed',
         },
     }, {
         'url': 'http://www.sbs.com.au/ondemand/video/320403011771/Dingo-Conservation-The-Feed',


@@ -31,21 +38,29 @@ class SBSIE(InfoExtractor):
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
     def _real_extract(self, url):
         video_id = self._match_id(url)

+        player_params = self._download_json(
+            'http://www.sbs.com.au/api/video_pdkvars/id/%s?form=json' % video_id, video_id)

 
 

-        webpage = self._download_webpage(
-            'http://www.sbs.com.au/ondemand/video/single/%s?context=web' % video_id, video_id)
-
-        player_params = self._parse_json(
-            self._search_regex(
-                r'(?s)var\s+playerParams\s*=\s*({.+?});', webpage, 'playerParams'),
-            video_id)
+        error = player_params.get('error')
+        if error:
+            error_message = 'Sorry, The video you are looking for does not exist.'
+            video_data = error.get('results') or {}
+            error_code = error.get('errorCode')
+            if error_code == 'ComingSoon':
+                error_message = '%s is not yet available.' % video_data.get('title', '')
+            elif error_code in ('Forbidden', 'intranetAccessOnly'):
+                error_message = 'Sorry, This video cannot be accessed via this website'
+            elif error_code == 'Expired':
+                error_message = 'Sorry, %s is no longer available.' % video_data.get('title', '')
+            raise ExtractorError('%s said: %s' % (self.IE_NAME, error_message), expected=True)

 
         urls = player_params['releaseUrls']
 
         urls = player_params['releaseUrls']

-        theplatform_url = (urls.get('progressive') or urls.get('standard') or
-                           urls.get('html') or player_params['relatedItemsURL'])
+        theplatform_url = (urls.get('progressive') or urls.get('html')
+                           or urls.get('standard') or player_params['relatedItemsURL'])

 
         return {
             '_type': 'url_transparent',
 
         return {
             '_type': 'url_transparent',

+            'ie_key': 'ThePlatform',

             'id': video_id,
             'id': video_id,

-            'url': theplatform_url,
+            'url': smuggle_url(self._proto_relative_url(theplatform_url), {'force_smil_url': True}),

         }
         }