[myspace] Improve _VALID_URL (closes #13040)

youtube_dl/extractor/myspace.py

@@ -12,10 +12,16 @@ from ..utils import (
 
 
 class MySpaceIE(InfoExtractor):
-    _VALID_URL = r'https?://myspace\.com/([^/]+)/(?P<mediatype>video/[^/]+/|music/song/.*?)(?P<id>\d+)'
+    _VALID_URL = r'''(?x)
+                    https?://
+                        myspace\.com/[^/]+/
+                        (?P<mediatype>
+                            video/[^/]+/(?P<video_id>\d+)|
+                            music/song/[^/?#&]+-(?P<song_id>\d+)-\d+(?:[/?#&]|$)
+                        )
+                    '''
 
-    _TESTS = [
+    _TESTS = [{
-        {
         'url': 'https://myspace.com/fiveminutestothestage/video/little-big-town/109594919',
         'md5': '9c1483c106f4a695c47d2911feed50a7',
         'info_dict': {
@@ -28,9 +34,8 @@ class MySpaceIE(InfoExtractor):
             'timestamp': 1414108751,
             'upload_date': '20141023',
         },
-        },
+    }, {
         # songs
-        {
         'url': 'https://myspace.com/killsorrow/music/song/of-weakened-soul...-93388656-103880681',
         'md5': '1d7ee4604a3da226dd69a123f748b262',
         'info_dict': {
@@ -53,23 +58,16 @@ class MySpaceIE(InfoExtractor):
             'upload_date': '20091002',
         },
     }, {
-            'add_ie': ['Youtube'],
         'url': 'https://myspace.com/starset2/music/song/first-light-95799905-106964426',
-            'info_dict': {
+        'only_matching': True,
-                'id': 'ypWvQgnJrSU',
+    }, {
-                'ext': 'mp4',
+        'url': 'https://myspace.com/thelargemouthbassband/music/song/02-pure-eyes.mp3-94422330-105113388',
-                'title': 'Starset - First Light',
+        'only_matching': True,
-                'description': 'md5:2d5db6c9d11d527683bcda818d332414',
+    }]
-                'uploader': 'Yumi K',
-                'uploader_id': 'SorenPromotions',
-                'upload_date': '20140725',
-            }
-        },
-    ]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
+        video_id = mobj.group('video_id') or mobj.group('song_id')
         is_song = mobj.group('mediatype').startswith('music/song')
         webpage = self._download_webpage(url, video_id)
         player_url = self._search_regex(