fix: normalize_url preserves path/query casing, lowercasing only scheme and host

src/crawlee/_utils/requests.py

@@ -19,8 +19,10 @@ def normalize_url(url: str, *, keep_url_fragment: bool = False) -> str:
     This function cleans and standardizes a URL by removing leading and trailing whitespaces,
     converting the scheme and netloc to lower case, stripping unwanted tracking parameters
     (specifically those beginning with 'utm_'), sorting the remaining query parameters alphabetically,
-    and optionally retaining the URL fragment. The goal is to ensure that URLs that are functionally
-    identical but differ in trivial ways (such as parameter order or casing) are treated as the same.
+    and optionally retaining the URL fragment. URL paths, queries, and fragments keep their original
+    casing, since only the scheme and the host are case-insensitive (RFC 3986, section 6.2.2.1).
+    The goal is to ensure that URLs that are functionally
+    identical but differ in trivial ways (such as parameter order or scheme/host casing) are treated as the same.
 
     Args:
         url: The URL to be normalized.
@@ -44,7 +46,11 @@ def normalize_url(url: str, *, keep_url_fragment: bool = False) -> str:
         yarl_new_url.path.removesuffix('/'), keep_query=True, keep_fragment=keep_url_fragment
     )
 
-    return str(yarl_new_url).lower()
+    # Only the scheme and the host are case-insensitive (RFC 3986, section 6.2.2.1), and yarl has
+    # already lowercased both during parsing. The path, query, and fragment must keep their original
+    # casing, since lowercasing them can silently merge distinct URLs (e.g. case-sensitive paths or
+    # tokens) during deduplication.
+    return str(yarl_new_url)
 
 
 def compute_unique_key(

tests/unit/_utils/test_requests.py

@@ -15,22 +15,26 @@
             'http://example.com/?another_key=another_value&key=value',
             False,
         ),
-        ('HTTPS://EXAMPLE.COM/?KEY=VALUE', 'https://example.com/?key=value', False),
+        ('HTTPS://EXAMPLE.COM/?KEY=VALUE', 'https://example.com/?KEY=VALUE', False),
         ('', '', False),
         ('http://example.com/#fragment', 'http://example.com/#fragment', True),
         ('http://example.com/#fragment', 'http://example.com', False),
         ('  https://example.com/  ', 'https://example.com', False),
         ('http://example.com/?b=2&a=1', 'http://example.com/?a=1&b=2', False),
+        ('https://example.com/Product/ABC', 'https://example.com/Product/ABC', False),
+        ('https://example.com/?token=SeCrEt', 'https://example.com/?token=SeCrEt', False),
     ],
     ids=[
         'remove_utm_params',
         'retain_sort_non_utm_params',
-        'convert_scheme_netloc_to_lowercase',
+        'convert_scheme_netloc_to_lowercase_only',
         'handle_empty_url',
         'retain_fragment',
         'remove_fragment',
         'trim_whitespace',
         'sort_query_params',
+        'preserve_path_casing',
+        'preserve_query_casing',
     ],
 )
 def test_normalize_url(url: str, expected_output: str, *, keep_url_fragment: bool) -> None: