[youtube] Fix extraction.

[youtube-dl] / youtube_dl / extractor / kusi.py

diff --git a/youtube_dl/extractor/kusi.py b/youtube_dl/extractor/kusi.py
index 5d458e31ecf2967596e96b656e289b7a105c8364..6a7e3baa70cc019b497828ab84d176e55216356f 100644 (file)
--- a/youtube_dl/extractor/kusi.py
+++ b/youtube_dl/extractor/kusi.py
@@ -16,30 +16,22 @@ from ..utils import (
 
 
 class KUSIIE(InfoExtractor):
-    _VALID_URL = r'http://(?:www\.)?kusi\.com/(?P<path>story/.+|video\?clipId=(?P<clipId>\d+))'
+    _VALID_URL = r'https?://(?:www\.)?kusi\.com/(?P<path>story/.+|video\?clipId=(?P<clipId>\d+))'
     _TESTS = [{
-        'url': 'http://www.kusi.com/story/31183873/turko-files-case-closed-put-on-hold',
-        'md5': 'f926e7684294cf8cb7bdf8858e1b3988',
+        'url': 'http://www.kusi.com/story/32849881/turko-files-refused-to-help-it-aint-right',
+        'md5': '4e76ce8e53660ce9697d06c0ba6fc47d',
         'info_dict': {
-            'id': '12203019',
+            'id': '12689020',
             'ext': 'mp4',
-            'title': 'Turko Files: Case Closed! & Put On Hold!',
-            'duration': 231,
+            'title': "Turko Files: Refused to Help, It Ain't Right!",
+            'duration': 223.586,
+            'upload_date': '20160826',
+            'timestamp': 1472233118,
+            'thumbnail': r're:^https?://.*\.jpg$'
         },
     }, {
         'url': 'http://kusi.com/video?clipId=12203019',
-        'info_dict': {
-            'id': '12203019',
-            'ext': 'mp4',
-            'title': 'Turko Files: Case Closed! & Put On Hold!',
-            'duration': 231.0,
-            'upload_date': '20160210',
-            'timestamp': 1455087571,
-            'thumbnail': 're:^https?://.*\.jpg$'
-        },
-        'params': {
-            'skip_download': True,  # Same as previous one
-        },
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
@@ -68,13 +60,11 @@ class KUSIIE(InfoExtractor):
 
         doc = self._download_xml(xml_url, video_id)
 
-        video_title = xpath_text(doc, 'HEADLINE')
-        duration = float_or_none(
-            xpath_text(doc, 'DURATION', fatal=False), scale=1000)
-        description = xpath_text(doc, 'ABSTRACT', fatal=False)
-        thumbnail = xpath_text(doc, './THUMBNAILIMAGE/FILENAME', fatal=False)
-        createtion_time = timeconvert(
-            xpath_text(doc, 'rfc822creationdate', fatal=False))
+        video_title = xpath_text(doc, 'HEADLINE', fatal=True)
+        duration = float_or_none(xpath_text(doc, 'DURATION'), scale=1000)
+        description = xpath_text(doc, 'ABSTRACT')
+        thumbnail = xpath_text(doc, './THUMBNAILIMAGE/FILENAME')
+        createtion_time = timeconvert(xpath_text(doc, 'rfc822creationdate'))
 
         quality_options = doc.find('{http://search.yahoo.com/mrss/}group').findall('{http://search.yahoo.com/mrss/}content')
         formats = []
@@ -83,7 +73,7 @@ class KUSIIE(InfoExtractor):
                 'url': compat_urllib_parse_unquote_plus(quality.attrib['url']),
                 'height': int_or_none(quality.attrib.get('height')),
                 'width': int_or_none(quality.attrib.get('width')),
-                'vbr': float_or_none(quality.attrib.get('bitratebits'), scale=1024),
+                'vbr': float_or_none(quality.attrib.get('bitratebits'), scale=1000),
             })
         self._sort_formats(formats)