Update upstream source from tag 'upstream/2019.09.28'

[youtubedl] / youtube_dl / extractor / vgtv.py

diff --git a/youtube_dl/extractor/vgtv.py b/youtube_dl/extractor/vgtv.py
index 3b38ac700296a2eef8c12f0b45406f54785d7684..fe7a26b620deeff53a5443beea96e109f7685dc8 100644 (file)
--- a/youtube_dl/extractor/vgtv.py
+++ b/youtube_dl/extractor/vgtv.py
@@ -14,6 +14,7 @@ from ..utils import (
 
 class VGTVIE(XstreamIE):
     IE_DESC = 'VGTV, BTTV, FTV, Aftenposten and Aftonbladet'
+    _GEO_BYPASS = False
 
     _HOST_TO_APPNAME = {
         'vgtv.no': 'vgtv',
@@ -23,6 +24,7 @@ class VGTVIE(XstreamIE):
         'aftenposten.no/webtv': 'aptv',
         'ap.vgtv.no/webtv': 'aptv',
         'tv.aftonbladet.se/abtv': 'abtv',
+        'www.aftonbladet.se/tv': 'abtv',
     }
 
     _APP_NAME_TO_VENDOR = {
@@ -41,9 +43,9 @@ class VGTVIE(XstreamIE):
                     )
                     /?
                     (?:
-                        \#!/(?:video|live)/|
+                        (?:\#!/)?(?:video|live)/|
                         embed?.*id=|
-                        articles/
+                        a(?:rticles)?/
                     )|
                     (?P<appname>
                         %s
@@ -61,7 +63,7 @@ class VGTVIE(XstreamIE):
                 'ext': 'mp4',
                 'title': 'Hevnen er søt: Episode 10 - Abu',
                 'description': 'md5:e25e4badb5f544b04341e14abdc72234',
-                'thumbnail': 're:^https?://.*\.jpg',
+                'thumbnail': r're:^https?://.*\.jpg',
                 'duration': 648.000,
                 'timestamp': 1404626400,
                 'upload_date': '20140706',
@@ -76,7 +78,7 @@ class VGTVIE(XstreamIE):
                 'ext': 'flv',
                 'title': 'OPPTAK: VGTV følger EM-kvalifiseringen',
                 'description': 'md5:3772d9c0dc2dff92a886b60039a7d4d3',
-                'thumbnail': 're:^https?://.*\.jpg',
+                'thumbnail': r're:^https?://.*\.jpg',
                 'duration': 9103.0,
                 'timestamp': 1410113864,
                 'upload_date': '20140907',
@@ -96,7 +98,7 @@ class VGTVIE(XstreamIE):
                 'ext': 'mp4',
                 'title': 'V75 fra Solvalla 30.05.15',
                 'description': 'md5:b3743425765355855f88e096acc93231',
-                'thumbnail': 're:^https?://.*\.jpg',
+                'thumbnail': r're:^https?://.*\.jpg',
                 'duration': 25966,
                 'timestamp': 1432975582,
                 'upload_date': '20150530',
@@ -142,10 +144,18 @@ class VGTVIE(XstreamIE):
             'url': 'http://tv.aftonbladet.se/abtv/articles/36015',
             'only_matching': True,
         },
+        {
+            'url': 'https://www.aftonbladet.se/tv/a/36015',
+            'only_matching': True,
+        },
         {
             'url': 'abtv:140026',
             'only_matching': True,
-        }
+        },
+        {
+            'url': 'http://www.vgtv.no/video/84196/hevnen-er-soet-episode-10-abu',
+            'only_matching': True,
+        },
     ]
 
     def _real_extract(self, url):
@@ -173,13 +183,15 @@ class VGTVIE(XstreamIE):
 
         streams = data['streamUrls']
         stream_type = data.get('streamType')
-
+        is_live = stream_type == 'live'
         formats = []
 
         hls_url = streams.get('hls')
         if hls_url:
             formats.extend(self._extract_m3u8_formats(
-                hls_url, video_id, 'mp4', m3u8_id='hls', fatal=False))
+                hls_url, video_id, 'mp4',
+                entry_protocol='m3u8' if is_live else 'm3u8_native',
+                m3u8_id='hls', fatal=False))
 
         hds_url = streams.get('hds')
         if hds_url:
@@ -200,7 +212,7 @@ class VGTVIE(XstreamIE):
             format_info = {
                 'url': mp4_url,
             }
-            mobj = re.search('(\d+)_(\d+)_(\d+)', mp4_url)
+            mobj = re.search(r'(\d+)_(\d+)_(\d+)', mp4_url)
             if mobj:
                 tbr = int(mobj.group(3))
                 format_info.update({
@@ -217,19 +229,20 @@ class VGTVIE(XstreamIE):
             properties = try_get(
                 data, lambda x: x['streamConfiguration']['properties'], list)
             if properties and 'geoblocked' in properties:
-                raise self.raise_geo_restricted()
+                raise self.raise_geo_restricted(
+                    countries=[host.rpartition('.')[-1].partition('/')[0].upper()])
 
         self._sort_formats(info['formats'])
 
         info.update({
             'id': video_id,
-            'title': self._live_title(data['title']) if stream_type == 'live' else data['title'],
+            'title': self._live_title(data['title']) if is_live else data['title'],
             'description': data['description'],
             'thumbnail': data['images']['main'] + '?t[]=900x506q80',
             'timestamp': data['published'],
             'duration': float_or_none(data['duration'], 1000),
             'view_count': data['displays'],
-            'is_live': True if stream_type == 'live' else False,
+            'is_live': is_live,
         })
         return info
 
@@ -246,7 +259,7 @@ class BTArticleIE(InfoExtractor):
             'ext': 'mp4',
             'title': 'Alrekstad internat',
             'description': 'md5:dc81a9056c874fedb62fc48a300dac58',
-            'thumbnail': 're:^https?://.*\.jpg',
+            'thumbnail': r're:^https?://.*\.jpg',
             'duration': 191,
             'timestamp': 1289991323,
             'upload_date': '20101117',