Adapt changes from Andreas Tille for porting to Salsa.

[youtubedl] / youtube_dl / extractor / sbs.py

diff --git a/youtube_dl/extractor/sbs.py b/youtube_dl/extractor/sbs.py
index d4bd1a0d72624e65bc9a5890f371b492451a9486..845712a7640afe9f675757c2f711830c9c79a00f 100644 (file)
--- a/youtube_dl/extractor/sbs.py
+++ b/youtube_dl/extractor/sbs.py
@@ -1,17 +1,16 @@
-# -*- coding: utf-8 -*-
+# coding: utf-8

 from __future__ import unicode_literals
 
 from __future__ import unicode_literals
 

-import re

 from .common import InfoExtractor
 from ..utils import (
 from .common import InfoExtractor
 from ..utils import (

-    js_to_json,
-    remove_end,
+    smuggle_url,
+    ExtractorError,

 )
 
 
 class SBSIE(InfoExtractor):
     IE_DESC = 'sbs.com.au'
 )
 
 
 class SBSIE(InfoExtractor):
     IE_DESC = 'sbs.com.au'

-    _VALID_URL = r'https?://(?:www\.)?sbs\.com\.au/ondemand/video/(?:single/)?(?P<id>[0-9]+)'
+    _VALID_URL = r'https?://(?:www\.)?sbs\.com\.au/(?:ondemand|news)/video/(?:single/)?(?P<id>[0-9]+)'

 
     _TESTS = [{
         # Original URL is handled by the generic IE which finds the iframe:
 
     _TESTS = [{
         # Original URL is handled by the generic IE which finds the iframe:


@@ -21,39 +20,47 @@ class SBSIE(InfoExtractor):
         'info_dict': {
             'id': '320403011771',
             'ext': 'mp4',
         'info_dict': {
             'id': '320403011771',
             'ext': 'mp4',

-            'title': 'Dingo Conservation',
-            'description': 'Dingoes are on the brink of extinction; most of the animals we think are dingoes are in fact crossbred with wild dogs. This family run a dingo conservation park to prevent their extinction',
-            'thumbnail': 're:http://.*\.jpg',
+            'title': 'Dingo Conservation (The Feed)',
+            'description': 'md5:f250a9856fca50d22dec0b5b8015f8a5',
+            'thumbnail': r're:http://.*\.jpg',
+            'duration': 308,
+            'timestamp': 1408613220,
+            'upload_date': '20140821',
+            'uploader': 'SBSC',

         },
         },

-        'add_ies': ['generic'],

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

+    }, {
+        'url': 'http://www.sbs.com.au/news/video/471395907773/The-Feed-July-9',
+        'only_matching': True,

     }]
 
     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(url, video_id)
-
-        player = self._search_regex(
-            r'(?s)playerParams\.releaseUrls\s*=\s*(\{.*?\n\});\n',
-            webpage, 'player')
-        player = re.sub(r"'\s*\+\s*[\da-zA-Z_]+\s*\+\s*'", '', player)
-
-        release_urls = self._parse_json(js_to_json(player), video_id)
-
-        theplatform_url = release_urls.get('progressive') or release_urls['standard']
+        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)

 
 

-        title = remove_end(self._og_search_title(webpage), ' (The Feed)')
-        description = self._html_search_meta('description', webpage)
-        thumbnail = self._og_search_thumbnail(webpage)
+        urls = player_params['releaseUrls']
+        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,
-            'title': title,
-            'description': description,
-            'thumbnail': thumbnail,
+            'url': smuggle_url(self._proto_relative_url(theplatform_url), {'force_smil_url': True}),

         }
         }