debian/control: Prefer mplayer to mplayer2 in Recommends.

[youtubedl] / youtube_dl / extractor / vgtv.py

diff --git a/youtube_dl/extractor/vgtv.py b/youtube_dl/extractor/vgtv.py
index 2f111bf7ee042de1fce790a3f0d0f13be7f1feff..f38a72fde8974a7a1ea290de04281f67079b1a16 100644 (file)
--- a/youtube_dl/extractor/vgtv.py
+++ b/youtube_dl/extractor/vgtv.py
@@ -4,11 +4,26 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
 import re
 
 from .common import InfoExtractor

-from ..utils import float_or_none
+from ..utils import (
+    ExtractorError,
+    float_or_none,
+)

 
 
 class VGTVIE(InfoExtractor):
 
 
 class VGTVIE(InfoExtractor):

-    _VALID_URL = r'http://(?:www\.)?vgtv\.no/#!/(?:.*)/(?P<id>[0-9]+)'
+    IE_DESC = 'VGTV and BTTV'
+    _VALID_URL = r'''(?x)
+                    (?:
+                        vgtv:|
+                        http://(?:www\.)?
+                    )
+                    (?P<host>vgtv|bt)
+                    (?:
+                        :|
+                        \.no/(?:tv/)?\#!/(?:video|live)/
+                    )
+                    (?P<id>[0-9]+)
+                    '''

     _TESTS = [
         {
             # streamType: vod
     _TESTS = [
         {
             # streamType: vod


@@ -47,16 +62,16 @@ class VGTVIE(InfoExtractor):
         },
         {
             # streamType: live
         },
         {
             # streamType: live

-            'url': 'http://www.vgtv.no/#!/live/100015/direkte-her-kan-du-se-laksen-live-fra-suldalslaagen',
+            'url': 'http://www.vgtv.no/#!/live/113063/direkte-v75-fra-solvalla',

             'info_dict': {
             'info_dict': {

-                'id': '100015',
+                'id': '113063',

                 'ext': 'flv',
                 'ext': 'flv',

-                'title': 'DIREKTE: Her kan du se laksen live fra Suldalslågen!',
-                'description': 'md5:9a60cc23fa349f761628924e56eeec2d',
+                'title': 're:^DIREKTE: V75 fra Solvalla [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
+                'description': 'md5:b3743425765355855f88e096acc93231',

                 'thumbnail': 're:^https?://.*\.jpg',
                 'duration': 0,
                 'thumbnail': 're:^https?://.*\.jpg',
                 'duration': 0,

-                'timestamp': 1407423348,
-                'upload_date': '20140807',
+                'timestamp': 1432975582,
+                'upload_date': '20150530',

                 'view_count': int,
             },
             'params': {
                 'view_count': int,
             },
             'params': {


@@ -64,25 +79,47 @@ class VGTVIE(InfoExtractor):
                 'skip_download': True,
             },
         },
                 'skip_download': True,
             },
         },

+        {
+            'url': 'http://www.bt.no/tv/#!/video/100250/norling-dette-er-forskjellen-paa-1-divisjon-og-eliteserien',
+            'only_matching': True,
+        },

     ]
 
     def _real_extract(self, url):
     ]
 
     def _real_extract(self, url):

-        video_id = self._match_id(url)
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        host = mobj.group('host')
+
+        HOST_WEBSITES = {
+            'vgtv': 'vgtv',
+            'bt': 'bttv',
+        }
+

         data = self._download_json(
         data = self._download_json(

-            'http://svp.vg.no/svp/api/v1/vgtv/assets/%s?appName=vgtv-website' % video_id,
+            'http://svp.vg.no/svp/api/v1/%s/assets/%s?appName=%s-website'
+            % (host, video_id, HOST_WEBSITES[host]),

             video_id, 'Downloading media JSON')
 
             video_id, 'Downloading media JSON')
 

+        if data.get('status') == 'inactive':
+            raise ExtractorError(
+                'Video %s is no longer available' % video_id, expected=True)
+

         streams = data['streamUrls']
         streams = data['streamUrls']

+        stream_type = data.get('streamType')

 
         formats = []
 
         hls_url = streams.get('hls')
         if hls_url:
 
         formats = []
 
         hls_url = streams.get('hls')
         if hls_url:

-            formats.extend(self._extract_m3u8_formats(hls_url, video_id, 'mp4'))
+            formats.extend(self._extract_m3u8_formats(
+                hls_url, video_id, 'mp4', m3u8_id='hls'))

 
         hds_url = streams.get('hds')
 
         hds_url = streams.get('hds')

-        if hds_url:
-            formats.extend(self._extract_f4m_formats(hds_url + '?hdcore=3.2.0&plugin=aasp-3.2.0.77.18', video_id))
+        # wasLive hds are always 404
+        if hds_url and stream_type != 'wasLive':
+            formats.extend(self._extract_f4m_formats(
+                hds_url + '?hdcore=3.2.0&plugin=aasp-3.2.0.77.18',
+                video_id, f4m_id='hds'))

 
         mp4_url = streams.get('mp4')
         if mp4_url:
 
         mp4_url = streams.get('mp4')
         if mp4_url:


@@ -107,11 +144,60 @@ class VGTVIE(InfoExtractor):
 
         return {
             'id': video_id,
 
         return {
             'id': video_id,

-            'title': data['title'],
+            'title': self._live_title(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'],
             'formats': formats,
             'description': data['description'],
             'thumbnail': data['images']['main'] + '?t[]=900x506q80',
             'timestamp': data['published'],
             'duration': float_or_none(data['duration'], 1000),
             'view_count': data['displays'],
             'formats': formats,

+            'is_live': True if stream_type == 'live' else False,

         }
         }

+
+
+class BTArticleIE(InfoExtractor):
+    IE_NAME = 'bt:article'
+    IE_DESC = 'Bergens Tidende Articles'
+    _VALID_URL = 'http://(?:www\.)?bt\.no/(?:[^/]+/)+(?P<id>[^/]+)-\d+\.html'
+    _TEST = {
+        'url': 'http://www.bt.no/nyheter/lokalt/Kjemper-for-internatet-1788214.html',
+        'md5': 'd055e8ee918ef2844745fcfd1a4175fb',
+        'info_dict': {
+            'id': '23199',
+            'ext': 'mp4',
+            'title': 'Alrekstad internat',
+            'description': 'md5:dc81a9056c874fedb62fc48a300dac58',
+            'thumbnail': 're:^https?://.*\.jpg',
+            'duration': 191,
+            'timestamp': 1289991323,
+            'upload_date': '20101117',
+            'view_count': int,
+        },
+    }
+
+    def _real_extract(self, url):
+        webpage = self._download_webpage(url, self._match_id(url))
+        video_id = self._search_regex(
+            r'SVP\.Player\.load\(\s*(\d+)', webpage, 'video id')
+        return self.url_result('vgtv:bt:%s' % video_id, 'VGTV')
+
+
+class BTVestlendingenIE(InfoExtractor):
+    IE_NAME = 'bt:vestlendingen'
+    IE_DESC = 'Bergens Tidende - Vestlendingen'
+    _VALID_URL = 'http://(?:www\.)?bt\.no/spesial/vestlendingen/#!/(?P<id>\d+)'
+    _TEST = {
+        'url': 'http://www.bt.no/spesial/vestlendingen/#!/86588',
+        'md5': 'd7d17e3337dc80de6d3a540aefbe441b',
+        'info_dict': {
+            'id': '86588',
+            'ext': 'mov',
+            'title': 'Otto Wollertsen',
+            'description': 'Vestlendingen Otto Fredrik Wollertsen',
+            'timestamp': 1430473209,
+            'upload_date': '20150501',
+        },
+    }
+
+    def _real_extract(self, url):
+        return self.url_result('xstream:btno:%s' % self._match_id(url), 'Xstream')