[jwplatform] Use js_to_json to detect more JWPlayers

[youtube-dl] / youtube_dl / extractor / vgtv.py

diff --git a/youtube_dl/extractor/vgtv.py b/youtube_dl/extractor/vgtv.py
index e148b1ef513321376efe1795056503ea2a8bcad8..185756301c3a9b0afe440254d3d2051ca97730d7 100644 (file)
--- a/youtube_dl/extractor/vgtv.py
+++ b/youtube_dl/extractor/vgtv.py
@@ -8,6 +8,7 @@ from .xstream import XstreamIE
 from ..utils import (
     ExtractorError,
     float_or_none,
+    try_get,
 )
 
 
@@ -129,6 +130,11 @@ class VGTVIE(XstreamIE):
             'url': 'http://ap.vgtv.no/webtv#!/video/111084/de-nye-bysyklene-lettere-bedre-gir-stoerre-hjul-og-feste-til-mobil',
             'only_matching': True,
         },
+        {
+            # geoblocked
+            'url': 'http://www.vgtv.no/#!/video/127205/inside-the-mind-of-favela-funk',
+            'only_matching': True,
+        },
     ]
 
     def _real_extract(self, url):
@@ -196,6 +202,12 @@ class VGTVIE(XstreamIE):
 
         info['formats'].extend(formats)
 
+        if not info['formats']:
+            properties = try_get(
+                data, lambda x: x['streamConfiguration']['properties'], list)
+            if properties and 'geoblocked' in properties:
+                raise self.raise_geo_restricted()
+
         self._sort_formats(info['formats'])
 
         info.update({
@@ -214,7 +226,7 @@ class VGTVIE(XstreamIE):
 class BTArticleIE(InfoExtractor):
     IE_NAME = 'bt:article'
     IE_DESC = 'Bergens Tidende Articles'
-    _VALID_URL = 'http://(?:www\.)?bt\.no/(?:[^/]+/)+(?P<id>[^/]+)-\d+\.html'
+    _VALID_URL = r'https?://(?:www\.)?bt\.no/(?:[^/]+/)+(?P<id>[^/]+)-\d+\.html'
     _TEST = {
         'url': 'http://www.bt.no/nyheter/lokalt/Kjemper-for-internatet-1788214.html',
         'md5': '2acbe8ad129b3469d5ae51b1158878df',
@@ -241,7 +253,7 @@ class BTArticleIE(InfoExtractor):
 class BTVestlendingenIE(InfoExtractor):
     IE_NAME = 'bt:vestlendingen'
     IE_DESC = 'Bergens Tidende - Vestlendingen'
-    _VALID_URL = 'http://(?:www\.)?bt\.no/spesial/vestlendingen/#!/(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:www\.)?bt\.no/spesial/vestlendingen/#!/(?P<id>\d+)'
     _TESTS = [{
         'url': 'http://www.bt.no/spesial/vestlendingen/#!/86588',
         'md5': 'd7d17e3337dc80de6d3a540aefbe441b',