Annotate changelog with bug closed.

[youtubedl] / youtube_dl / extractor / aftonbladet.py

diff --git a/youtube_dl/extractor/aftonbladet.py b/youtube_dl/extractor/aftonbladet.py
index 8442019eac3eaa0a373140d494ffa2ca420f4606..e0518cf261fbffc4dd23bc4a3800d04eae324139 100644 (file)
--- a/youtube_dl/extractor/aftonbladet.py
+++ b/youtube_dl/extractor/aftonbladet.py
@@ -2,14 +2,15 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
 from __future__ import unicode_literals
 
 from .common import InfoExtractor

+from ..utils import int_or_none

 
 
 class AftonbladetIE(InfoExtractor):
 
 
 class AftonbladetIE(InfoExtractor):

-    _VALID_URL = r'^http://tv\.aftonbladet\.se/webbtv.+?(?P<video_id>article[0-9]+)\.ab(?:$|[?#])'
+    _VALID_URL = r'http://tv\.aftonbladet\.se/abtv/articles/(?P<id>[0-9]+)'

     _TEST = {
     _TEST = {

-        'url': 'http://tv.aftonbladet.se/webbtv/nyheter/vetenskap/rymden/article36015.ab',
+        'url': 'http://tv.aftonbladet.se/abtv/articles/36015',

         'info_dict': {
         'info_dict': {

-            'id': 'article36015',
+            'id': '36015',

             'ext': 'mp4',
             'title': 'Vulkanutbrott i rymden - nu släpper NASA bilderna',
             'description': 'Jupiters måne mest aktiv av alla himlakroppar',
             'ext': 'mp4',
             'title': 'Vulkanutbrott i rymden - nu släpper NASA bilderna',
             'description': 'Jupiters måne mest aktiv av alla himlakroppar',


@@ -24,8 +25,9 @@ class AftonbladetIE(InfoExtractor):
 
         # find internal video meta data
         meta_url = 'http://aftonbladet-play.drlib.aptoma.no/video/%s.json'
 
         # find internal video meta data
         meta_url = 'http://aftonbladet-play.drlib.aptoma.no/video/%s.json'

-        internal_meta_id = self._html_search_regex(
-            r'data-aptomaId="([\w\d]+)"', webpage, 'internal_meta_id')
+        player_config = self._parse_json(self._html_search_regex(
+            r'data-player-config="([^"]+)"', webpage, 'player config'), video_id)
+        internal_meta_id = player_config['videoId']

         internal_meta_url = meta_url % internal_meta_id
         internal_meta_json = self._download_json(
             internal_meta_url, video_id, 'Downloading video meta data')
         internal_meta_url = meta_url % internal_meta_id
         internal_meta_json = self._download_json(
             internal_meta_url, video_id, 'Downloading video meta data')


@@ -43,9 +45,9 @@ class AftonbladetIE(InfoExtractor):
             formats.append({
                 'url': 'http://%s:%d/%s/%s' % (p['address'], p['port'], p['path'], p['filename']),
                 'ext': 'mp4',
             formats.append({
                 'url': 'http://%s:%d/%s/%s' % (p['address'], p['port'], p['path'], p['filename']),
                 'ext': 'mp4',

-                'width': fmt['width'],
-                'height': fmt['height'],
-                'tbr': fmt['bitrate'],
+                'width': int_or_none(fmt.get('width')),
+                'height': int_or_none(fmt.get('height')),
+                'tbr': int_or_none(fmt.get('bitrate')),

                 'protocol': 'http',
             })
         self._sort_formats(formats)
                 'protocol': 'http',
             })
         self._sort_formats(formats)


@@ -54,9 +56,9 @@ class AftonbladetIE(InfoExtractor):
             'id': video_id,
             'title': internal_meta_json['title'],
             'formats': formats,
             'id': video_id,
             'title': internal_meta_json['title'],
             'formats': formats,

-            'thumbnail': internal_meta_json['imageUrl'],
-            'description': internal_meta_json['shortPreamble'],
-            'timestamp': internal_meta_json['timePublished'],
-            'duration': internal_meta_json['duration'],
-            'view_count': internal_meta_json['views'],
+            'thumbnail': internal_meta_json.get('imageUrl'),
+            'description': internal_meta_json.get('shortPreamble'),
+            'timestamp': int_or_none(internal_meta_json.get('timePublished')),
+            'duration': int_or_none(internal_meta_json.get('duration')),
+            'view_count': int_or_none(internal_meta_json.get('views')),

         }
         }