Merge tag 'upstream/2017.02.07'

[youtubedl] / youtube_dl / extractor / vgtv.py

diff --git a/youtube_dl/extractor/vgtv.py b/youtube_dl/extractor/vgtv.py
index 14e945d494cd2f6e5f3b3e6a03ff6ebb076826dd..8a574bc269789e14f3dcadd6167c5caaa46e49e3 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,
 )
 
 
@@ -20,6 +21,8 @@ class VGTVIE(XstreamIE):
         'aftenbladet.no/tv': 'satv',
         'fvn.no/fvntv': 'fvntv',
         'aftenposten.no/webtv': 'aptv',
+        'ap.vgtv.no/webtv': 'aptv',
+        'tv.aftonbladet.se/abtv': 'abtv',
     }
 
     _APP_NAME_TO_VENDOR = {
@@ -28,6 +31,7 @@ class VGTVIE(XstreamIE):
         'satv': 'sa',
         'fvntv': 'fvn',
         'aptv': 'ap',
+        'abtv': 'ab',
     }
 
     _VALID_URL = r'''(?x)
@@ -35,10 +39,11 @@ class VGTVIE(XstreamIE):
                     (?P<host>
                         %s
                     )
-                    /
+                    /?
                     (?:
                         \#!/(?:video|live)/|
-                        embed?.*id=
+                        embed?.*id=|
+                        articles/
                     )|
                     (?P<appname>
                         %s
@@ -56,7 +61,7 @@ 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',
@@ -71,7 +76,7 @@ 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',
@@ -91,7 +96,7 @@ 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',
@@ -107,19 +112,40 @@ class VGTVIE(XstreamIE):
             'md5': 'fd828cd29774a729bf4d4425fe192972',
             'info_dict': {
                 'id': '21039',
-                'ext': 'mov',
+                'ext': 'mp4',
                 'title': 'TRAILER: «SWEATSHOP» - I can´t take any more',
                 'description': 'md5:21891f2b0dd7ec2f78d84a50e54f8238',
                 'duration': 66,
                 'timestamp': 1417002452,
                 'upload_date': '20141126',
                 'view_count': int,
-            }
+            },
+            'params': {
+                # m3u8 download
+                'skip_download': True,
+            },
         },
         {
             'url': 'http://www.bt.no/tv/#!/video/100250/norling-dette-er-forskjellen-paa-1-divisjon-og-eliteserien',
             'only_matching': True,
         },
+        {
+            '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,
+        },
+        {
+            'url': 'http://tv.aftonbladet.se/abtv/articles/36015',
+            'only_matching': True,
+        },
+        {
+            'url': 'abtv:140026',
+            'only_matching': True,
+        }
     ]
 
     def _real_extract(self, url):
@@ -144,8 +170,6 @@ class VGTVIE(XstreamIE):
         if len(video_id) == 5:
             if appname == 'bttv':
                 info = self._extract_video_info('btno', video_id)
-            elif appname == 'aptv':
-                info = self._extract_video_info('ap', video_id)
 
         streams = data['streamUrls']
         stream_type = data.get('streamType')
@@ -176,7 +200,7 @@ 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({
@@ -189,6 +213,12 @@ 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({
@@ -207,7 +237,7 @@ 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',
@@ -216,7 +246,7 @@ 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',
@@ -234,7 +264,7 @@ 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',