youtube_dl/extractor/sprout.py

@@ -3,62 +3,50 @@ from __future__ import unicode_literals
 
 from .adobepass import AdobePassIE
 from ..utils import (
-    int_or_none,
+    extract_attributes,
-    smuggle_url,
     update_url_query,
+    smuggle_url,
 )
 
 
 class SproutIE(AdobePassIE):
-    _VALID_URL = r'https?://(?:www\.)?(?:sproutonline|universalkids)\.com/(?:watch|(?:[^/]+/)*videos)/(?P<id>[^/?#]+)'
+    _VALID_URL = r'https?://(?:www\.)?sproutonline\.com/watch/(?P<id>[^/?#]+)'
-    _TESTS = [{
+    _TEST = {
-        'url': 'https://www.universalkids.com/shows/remy-and-boo/season/1/videos/robot-bike-race',
-        'info_dict': {
-            'id': 'bm0foJFaTKqb',
-            'ext': 'mp4',
-            'title': 'Robot Bike Race',
-            'description': 'md5:436b1d97117cc437f54c383f4debc66d',
-            'timestamp': 1606148940,
-            'upload_date': '20201123',
-            'uploader': 'NBCU-MPAT',
-        },
-        'params': {
-            'skip_download': True,
-        },
-    }, {
         'url': 'http://www.sproutonline.com/watch/cowboy-adventure',
-        'only_matching': True,
+        'md5': '74bf14128578d1e040c3ebc82088f45f',
-    }, {
+        'info_dict': {
-        'url': 'https://www.universalkids.com/watch/robot-bike-race',
+            'id': '9dexnwtmh8_X',
-        'only_matching': True,
+            'ext': 'mp4',
-    }]
+            'title': 'A Cowboy Adventure',
-    _GEO_COUNTRIES = ['US']
+            'description': 'Ruff-Ruff, Tweet and Dave get to be cowboys for the day at Six Cow Corral.',
+            'timestamp': 1437758640,
+            'upload_date': '20150724',
+            'uploader': 'NBCU-SPROUT-NEW',
+        }
+    }
 
     def _real_extract(self, url):
-        display_id = self._match_id(url)
+        video_id = self._match_id(url)
-        mpx_metadata = self._download_json(
+        webpage = self._download_webpage(url, video_id)
-            # http://nbcuunikidsprod.apps.nbcuni.com/networks/universalkids/content/videos/
+        video_component = self._search_regex(
-            'https://www.universalkids.com/_api/videos/' + display_id,
+            r'(?s)(<div[^>]+data-component="video"[^>]*?>)',
-            display_id)['mpxMetadata']
+            webpage, 'video component', default=None)
-        media_pid = mpx_metadata['mediaPid']
+        if video_component:
-        theplatform_url = 'https://link.theplatform.com/s/HNK2IC/' + media_pid
+            options = self._parse_json(extract_attributes(
+                video_component)['data-options'], video_id)
+            theplatform_url = options['video']
             query = {
                 'mbr': 'true',
                 'manifest': 'm3u',
             }
-        if mpx_metadata.get('entitlement') == 'auth':
+            if options.get('protected'):
-            query['auth'] = self._extract_mvpd_auth(url, media_pid, 'sprout', 'sprout')
+                query['auth'] = self._extract_mvpd_auth(url, options['pid'], 'sprout', 'sprout')
-        theplatform_url = smuggle_url(
+            theplatform_url = smuggle_url(update_url_query(
-            update_url_query(theplatform_url, query), {
+                theplatform_url, query), {'force_smil_url': True})
-                'force_smil_url': True,
+        else:
-                'geo_countries': self._GEO_COUNTRIES,
+            iframe = self._search_regex(
-            })
+                r'(<iframe[^>]+id="sproutVideoIframe"[^>]*?>)',
-        return {
+                webpage, 'iframe')
-            '_type': 'url_transparent',
+            theplatform_url = extract_attributes(iframe)['src']
-            'id': media_pid,
+
-            'url': theplatform_url,
+        return self.url_result(theplatform_url, 'ThePlatform')
-            'series': mpx_metadata.get('seriesName'),
-            'season_number': int_or_none(mpx_metadata.get('seasonNumber')),
-            'episode_number': int_or_none(mpx_metadata.get('episodeNumber')),
-            'ie_key': 'ThePlatform',
-        }

youtube_dl/extractor/theplatform.py

@@ -234,9 +234,6 @@ class ThePlatformIE(ThePlatformBaseIE, AdobePassIE):
 
     def _real_extract(self, url):
         url, smuggled_data = unsmuggle_url(url, {})
-        self._initialize_geo_bypass({
-            'countries': smuggled_data.get('geo_countries'),
-        })
 
         mobj = re.match(self._VALID_URL, url)
         provider_id = mobj.group('provider_id')