Tidy up cleanup rule and keep lintian happy.

[youtubedl] / youtube_dl / extractor / newgrounds.py

diff --git a/youtube_dl/extractor/newgrounds.py b/youtube_dl/extractor/newgrounds.py
index 2e72e8915aab601b6916fd18e4f64090a613986e..7059403239ce19ac8b2861fa4af0dde93c98467b 100644 (file)
--- a/youtube_dl/extractor/newgrounds.py
+++ b/youtube_dl/extractor/newgrounds.py
@@ -7,8 +7,8 @@ from .common import InfoExtractor
 
 
 class NewgroundsIE(InfoExtractor):
 
 
 class NewgroundsIE(InfoExtractor):

-    _VALID_URL = r'https?://(?:www\.)?newgrounds\.com/audio/listen/(?P<id>[0-9]+)'
-    _TEST = {
+    _VALID_URL = r'https?://(?:www\.)?newgrounds\.com/(?:audio/listen|portal/view)/(?P<id>[0-9]+)'
+    _TESTS = [{

         'url': 'http://www.newgrounds.com/audio/listen/549479',
         'md5': 'fe6033d297591288fa1c1f780386f07a',
         'info_dict': {
         'url': 'http://www.newgrounds.com/audio/listen/549479',
         'md5': 'fe6033d297591288fa1c1f780386f07a',
         'info_dict': {


@@ -17,18 +17,29 @@ class NewgroundsIE(InfoExtractor):
             'title': 'B7 - BusMode',
             'uploader': 'Burn7',
         }
             'title': 'B7 - BusMode',
             'uploader': 'Burn7',
         }

-    }
+    }, {
+        'url': 'http://www.newgrounds.com/portal/view/673111',
+        'md5': '3394735822aab2478c31b1004fe5e5bc',
+        'info_dict': {
+            'id': '673111',
+            'ext': 'mp4',
+            'title': 'Dancin',
+            'uploader': 'Squirrelman82',
+        },
+    }]

 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         music_id = mobj.group('id')
         webpage = self._download_webpage(url, music_id)
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         music_id = mobj.group('id')
         webpage = self._download_webpage(url, music_id)

-        
+

         title = self._html_search_regex(
         title = self._html_search_regex(

-            r',"name":"([^"]+)",', webpage, 'music title')
+            r'<title>([^>]+)</title>', webpage, 'title')
+

         uploader = self._html_search_regex(
         uploader = self._html_search_regex(

-            r',"artist":"([^"]+)",', webpage, 'music uploader')
-        
+            [r',"artist":"([^"]+)",', r'[\'"]owner[\'"]\s*:\s*[\'"]([^\'"]+)[\'"],'],
+            webpage, 'uploader')
+

         music_url_json_string = self._html_search_regex(
             r'({"url":"[^"]+"),', webpage, 'music url') + '}'
         music_url_json = json.loads(music_url_json_string)
         music_url_json_string = self._html_search_regex(
             r'({"url":"[^"]+"),', webpage, 'music url') + '}'
         music_url_json = json.loads(music_url_json_string)