Browse Source

Escape URLs in `sanitized_Request`, not `sanitize_url` d2558234cf5dd12d6896eed5427b7dcdb3ab7b5a added escaping of URLs while sanitizing. However, `sanitize_url` may not always receive an actual URL. Eg: When using `youtube-dl "search query" --default-search ytsearch`, `search query` gets escaped to `search%20query` before being prefixed with `ytsearch:` which is not the intended behavior. So the escaping is moved to `sanitized_Request` instead.

pukkandan 4 years ago
parent
commit
1d3751c3fe
3 changed files with 22 additions and 2 deletions
  1. 1 0
      test/test_utils.py
  2. 19 0
      youtube_dl/extractor/generic.py
  3. 2 2
      youtube_dl/utils.py

+ 1 - 0
test/test_utils.py

@@ -250,6 +250,7 @@ class TestUtil(unittest.TestCase):
         self.assertEqual(sanitize_url('httpss://foo.bar'), 'https://foo.bar')
         self.assertEqual(sanitize_url('rmtps://foo.bar'), 'rtmps://foo.bar')
         self.assertEqual(sanitize_url('https://foo.bar'), 'https://foo.bar')
+        self.assertEqual(sanitize_url('foo bar'), 'foo bar')
 
     def test_expand_path(self):
         def env(var):

+ 19 - 0
youtube_dl/extractor/generic.py

@@ -2320,6 +2320,25 @@ class GenericIE(InfoExtractor):
                 'height': 720,
                 'age_limit': 18,
             },
+        }, {
+            # would like to use the yt-dl test video but searching for
+            # '"\'/\\ä↭𝕐' fails, so using an old vid from YouTube Korea
+            'note': 'Test default search',
+            'url': 'Shorts로 허락 필요없이 놀자! (BTS편)',
+            'info_dict': {
+                'id': 'usDGO4Zb-dc',
+                'ext': 'mp4',
+                'title': 'YouTube Shorts로 허락 필요없이 놀자! (BTS편)',
+                'description': 'md5:96e31607eba81ab441567b5e289f4716',
+                'upload_date': '20211107',
+                'uploader': 'YouTube Korea',
+                'location': '대한민국',
+            },
+            'params': {
+                'default_search': 'ytsearch',
+                'skip_download': True,
+            },
+            'expected_warnings': ['uploader id'],
         },
     ]
 

+ 2 - 2
youtube_dl/utils.py

@@ -2176,11 +2176,11 @@ def sanitize_url(url):
     for mistake, fixup in COMMON_TYPOS:
         if re.match(mistake, url):
             return re.sub(mistake, fixup, url)
-    return escape_url(url)
+    return url
 
 
 def sanitized_Request(url, *args, **kwargs):
-    return compat_urllib_request.Request(sanitize_url(url), *args, **kwargs)
+    return compat_urllib_request.Request(escape_url(sanitize_url(url)), *args, **kwargs)
 
 
 def expand_path(s):