[abc] add support for audio extraction

[youtube-dl.git] / youtube_dl / extractor / abc.py

diff --git a/youtube_dl/extractor/abc.py b/youtube_dl/extractor/abc.py
index 06acf50d8294a2028cc1bb19d072293c8082e8ca..ae80dc5299d55ed0ded3f34233eb1456cb8fcffe 100644 (file)
--- a/youtube_dl/extractor/abc.py
+++ b/youtube_dl/extractor/abc.py
@@ -6,6 +6,7 @@ from .common import InfoExtractor
 from ..utils import (
     ExtractorError,
     js_to_json,
+    int_or_none,
 )
 
 
@@ -35,6 +36,15 @@ class ABCIE(InfoExtractor):
             'title': 'Marriage Equality: Warren Entsch introduces same sex marriage bill',
         },
         'add_ie': ['Youtube'],
+    }, {
+        'url': 'http://www.abc.net.au/news/2015-10-23/nab-lifts-interest-rates-following-westpac-and-cba/6880080',
+        'md5': 'b96eee7c9edf4fc5a358a0252881cc1f',
+        'info_dict': {
+            'id': '6880080',
+            'ext': 'mp3',
+            'title': 'NAB lifts interest rates, following Westpac and CBA',
+            'description': 'md5:f13d8edc81e462fce4a0437c7dc04728',
+        },
     }]
 
     def _real_extract(self, url):
@@ -42,7 +52,7 @@ class ABCIE(InfoExtractor):
         webpage = self._download_webpage(url, video_id)
 
         mobj = re.search(
-            r'inline(?P<type>Video|YouTube)Data\.push\((?P<json_data>[^)]+)\);',
+            r'inline(?P<type>Video|Audio|YouTube)Data\.push\((?P<json_data>[^)]+)\);',
             webpage)
         if mobj is None:
             raise ExtractorError('Unable to extract video urls')
@@ -59,11 +69,13 @@ class ABCIE(InfoExtractor):
 
         formats = [{
             'url': url_info['url'],
-            'width': int(url_info['width']),
-            'height': int(url_info['height']),
-            'tbr': int(url_info['bitrate']),
-            'filesize': int(url_info['filesize']),
+            'vcodec': url_info.get('codec') if mobj.group('type') == 'Video' else 'none',
+            'width': int_or_none(url_info.get('width')),
+            'height': int_or_none(url_info.get('height')),
+            'tbr': int_or_none(url_info.get('bitrate')),
+            'filesize': int_or_none(url_info.get('filesize')),
         } for url_info in urls_info]
+
         self._sort_formats(formats)
 
         return {