Merge branch 'seamusphelan-sbs_website_changes'

youtube_dl/extractor/sbs.py

@@ -1,17 +1,12 @@
 # -*- coding: utf-8 -*-
 from __future__ import unicode_literals
 
-import re
 from .common import InfoExtractor
-from ..utils import (
-    js_to_json,
-    remove_end,
-)
 
 
 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:
@@ -21,39 +16,36 @@ class SBSIE(InfoExtractor):
         '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',
+            'title': 'Dingo Conservation (The Feed)',
+            'description': 'md5:f250a9856fca50d22dec0b5b8015f8a5',
             'thumbnail': 're:http://.*\.jpg',
+            'duration': 308,
         },
-        '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/news/video/471395907773/The-Feed-July-9',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
-        webpage = self._download_webpage(url, video_id)
+        webpage = self._download_webpage(
+            'http://www.sbs.com.au/ondemand/video/single/%s?context=web' % video_id, 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)
+        player_params = self._parse_json(
+            self._search_regex(
+                r'(?s)var\s+playerParams\s*=\s*({.+?});', webpage, 'playerParams'),
+            video_id)
 
-        release_urls = self._parse_json(js_to_json(player), video_id)
-
-        theplatform_url = release_urls.get('progressive') or release_urls['standard']
-
-        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('standard') or
+                           urls.get('html') or player_params['relatedItemsURL'])
 
         return {
             '_type': 'url_transparent',
             'id': video_id,
             'url': theplatform_url,
-            'title': title,
-            'description': description,
-            'thumbnail': thumbnail,
         }