1.小说搜索重定向首页

2.伪造小说恢复修改前，直接使用小说详情同一个html
3.限制伪造谷歌爬虫ua

code/app/services/SiteContext.php

@@ -505,14 +505,7 @@ class SiteContext
     {
 
         $arrVisitInfo = [
-            //'vil_ip'         => $this->Request->ip(),
             'vil_user_agent' => $this->Request->server('HTTP_USER_AGENT'),
-            // 'vil_url'        => $this->Request->url(true),
-            // 'vil_method'     => $this->Request->method(),
-            // 'vil_headers'    => json_encode($this->Request->header()), // 保存所有 HTTP 头信息
-            // 'vil_timestamp'  => date('Y-m-d H:i:s'), // 获取当前时间
-            // 'vil_content_type' => 'page',
-            // 'vil_content_id' => $this->Request->url(true),
         ];
 
         // 判断是否为爬虫
@@ -538,7 +531,6 @@ class SiteContext
             Cache::store('redis')->handler()->expire($strKeyLimit100, 60 * 10); // 设置 10分钟 过期
         }
 
-        // var_dump($intRequestTotalLimit10);
         // 检查请求次数是否超过限制
         if ($intRequestTotalLimit10 > 60 && !$arrVisitInfo['vil_is_spider']) {
             throw new HttpException(404, 'Too Many Requests');
@@ -555,14 +547,30 @@ class SiteContext
             //abort(403, 'Too Many Requests100');
         }
 
-        $strAGEN = 'Mozilla/5.0 AppleWebKit/537.36 (KHTML, like Gecko; compatible; Amazonbot/0.1; +https://developer.amazon.com/support/amazonbot) Chrome/119.0.6045.214 Safari/537.36';
-        if ($arrVisitInfo['vil_user_agent'] == $strAGEN) {
-            throw new HttpException(404, 'Too Many Requests100');
-            //abort(403, 'Too Many Requests100');
+        /**
+         * 不会拦掉真的 Googlebot（因为真的只会是 Chrome/41.0 固定 UA）。
+        * 但是 如果你要更精准一点，可以只拦截 Googlebot + Chrome 但不是 Chrome/41
+         */
+        if (stripos($arrVisitInfo['vil_user_agent'], 'Googlebot/2.1') !== false 
+            && stripos($arrVisitInfo['vil_user_agent'], 'Chrome/') !== false 
+            && stripos($arrVisitInfo['vil_user_agent'], 'Chrome/41.0.2272.96') === false) {
+            throw new HttpException(403, 'HTTP/1.1 403 Forbidden');
         }
-        if (preg_match('/Chrome\/119\.0\.6045\.214/', $arrVisitInfo['vil_user_agent'])) {
-            throw new HttpException(404, 'Too Many Requests100');
-            //abort(403, 'Too Many Requests100');
+
+        // 定义需要屏蔽的 UA 关键字 / 正则
+        $arrDenyUserAgents = [
+            'Amazonbot',                    // 屏蔽 Amazon 爬虫
+            'zgrab',                        // 安全扫描工具
+            'crawler',                      // 明示 crawler
+            'Chrome\/119\.0\.6045\.214',    // 特定版本号 UA
+        ];
+
+        // 遍历检查 UA
+        foreach ($arrDenyUserAgents as $strPattern) {
+            if (preg_match("/$strPattern/i", $arrVisitInfo['vil_user_agent'])) {
+                throw new HttpException(404, 'Too Many Requests100');
+                // 或者用 abort(403, 'Too Many Requests100');
+            }
         }
     }
 
@@ -577,8 +585,8 @@ class SiteContext
         # ✅ 主流搜索引擎爬虫（按需维护）
         $arrSpiders = [
             'Baiduspider',
-            'Googlebot',
-            'Googlebot-Mobile',
+            // 'Googlebot',
+            // 'Googlebot-Mobile',
             '360Spider',
             'HaosouSpider',
             'Sogou',