From 40ab287c9087bf6701072558427d974510335bc0 Mon Sep 17 00:00:00 2001
From: ntohidi <nasrin@kidocode.com>
Date: Fri, 22 Aug 2025 12:05:21 +0800
Subject: [PATCH] fix(utils): Improve URL normalization by avoiding
 quote/unquote to preserve '+' signs. ref #1332

---
 crawl4ai/utils.py | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/crawl4ai/utils.py b/crawl4ai/utils.py
index 73f1d2a3..09e6e4b7 100644
--- a/crawl4ai/utils.py
+++ b/crawl4ai/utils.py
@@ -2184,8 +2184,10 @@ def normalize_url(
     netloc = parsed.netloc.lower()
 
     # ── path ──
-    # Strip duplicate slashes and trailing “/” (except root)
-    path = quote(unquote(parsed.path))
+    # Strip duplicate slashes and trailing "/" (except root)
+    # IMPORTANT: Don't use quote(unquote()) as it mangles + signs in URLs
+    # The path from urlparse is already properly encoded
+    path = parsed.path
     if path.endswith('/') and path != '/':
         path = path.rstrip('/')