From 8ccecfe699b46eae685f186ab6b33c7601627161 Mon Sep 17 00:00:00 2001
From: mamad <mamad@fedora>
Date: Fri, 28 Aug 2026 22:08:03 +0330
Subject: [PATCH] fix: clean html tag stripping regex

---
 services/website_collector.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/services/website_collector.py b/services/website_collector.py
index b1e84fb..2fd9ae7 100644
--- a/services/website_collector.py
+++ b/services/website_collector.py
@@ -18,7 +18,7 @@ logger = logging.getLogger(__name__)
 def _clean_html(raw_html: str) -> str:
     if not raw_html:
         return ""
-    text = re.sub(r'<[^>]+>', ' ', raw_html)
+    text = re.sub(r'<[^>]+>', '', raw_html)
     text = html.unescape(text)
     return re.sub(r'\s+', ' ', text).strip()