From 39fe41eb8382dfec4b7ebf4d76887c94957d35e3 Mon Sep 17 00:00:00 2001
From: wood <wood@czl.net>
Date: Thu, 5 Sep 2024 13:28:28 +0800
Subject: [PATCH] =?UTF-8?q?=E4=BC=98=E5=8C=96=E9=93=BE=E6=8E=A5=E8=BF=87?=
 =?UTF-8?q?=E6=BB=A4=E5=99=A8=E4=B8=AD=E7=9A=84=E9=93=BE=E6=8E=A5=E6=A0=87?=
 =?UTF-8?q?=E5=87=86=E5=8C=96=E5=87=BD=E6=95=B0?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

链接过滤器功能已增强，可消除链接中不必要的协议部分和初始斜线。该更新有助于更清晰地处理链接，同时保持其基本标识不变。
---
 src/link_filter.py | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/src/link_filter.py b/src/link_filter.py
index bf0ac55..56f09df 100644
--- a/src/link_filter.py
+++ b/src/link_filter.py
@@ -54,13 +54,20 @@ class LinkFilter:
         logger.info(f"Reloaded {len(self.keywords)} keywords and {len(self.whitelist)} whitelist entries")
 
     def normalize_link(self, link):
+    # 移除协议部分（如 http:// 或 https://）
         link = re.sub(r'^https?://', '', link)
+        
+        # 移除开头的双斜杠
+        link = link.lstrip('/')
+        
         parsed = urllib.parse.urlparse(f"http://{link}")
         normalized = urllib.parse.urlunparse(('', parsed.netloc, parsed.path, parsed.params, parsed.query, ''))
         result = normalized.rstrip('/')
+        
         logger.debug(f"Normalized link: {link} -> {result}")
         return result
 
+
     def is_whitelisted(self, link):
         extracted = tldextract.extract(link)
         domain = f"{extracted.domain}.{extracted.suffix}"