优化爬虫，增加缓存，线程池，保存浏览器用户信息

_php_code/AbstractScrmSpider.class.php

@@ -112,14 +112,21 @@ abstract class AbstractScrmSpider
 //             'apiUrls'     => $apiUrlsToIntercept,
 //             'authActions' => $config['authActions']
 //         ]);
+        $antiBot = $config['antiBot'] ?? null;
+
         // 【阶段一】：初始化并首屏拦截
         $initResult = $this->requestNode('/api/auth-and-intercept', [
             'pageUrl'     => $config['pageUrl'],
             'apiUrls'     => $apiUrlsToIntercept,
-            'authActions' => $config['authActions']
-        ]);
+            'authActions' => $config['authActions'],
+            'antiBot'     => $antiBot,
+        ], $this->resolveAuthInterceptTimeout($antiBot));
 
         if (empty($initResult['success'])) {
+            $cfCode = (string) ($initResult['code'] ?? '');
+            if ($cfCode === 'CF_TURNSTILE_FAILED') {
+                throw new Exception('Cloudflare Turnstile 验证失败: ' . ($initResult['stage'] ?? 'timeout'));
+            }
             throw new Exception("初始化失败: " . ($initResult['error'] ?? '未知'));
         }
 
@@ -161,7 +168,8 @@ abstract class AbstractScrmSpider
                         'paramList' => $paramList,
                         'method'    => $config['listMethod'] ?? 'GET'
                     ]],
-                    'cookies' => $cookies
+                    'cookies' => $cookies,
+                    'antiBot' => $antiBot,
                 ], 120);
 
                 if (!empty($fetchResult['success'])) {
@@ -189,7 +197,8 @@ abstract class AbstractScrmSpider
                     'cookies'         => $cookies,
                     'firstPageData'   => $firstPageData, // 传递原始数据源
                     // 🔥 核心补充：把登录剧本原封不动地传给翻页引擎！
-                    'authActions'     => $config['authActions'] 
+                    'authActions'     => $config['authActions'],
+                    'antiBot'         => $antiBot,
                 ], 1200); // 增加 PHP 端的 cURL 超时时间到 400 秒，以包容多次重试产生的耗时
                 
                 if (!empty($uiResult['success']) && !empty($uiResult['data'])) {
@@ -220,6 +229,19 @@ abstract class AbstractScrmSpider
         return $unifiedData;
     }
 
+    /**
+     * Real Browser + Turnstile 首屏耗时较长，单独放宽 auth-and-intercept 超时
+     *
+     * @param array<string, mixed>|null $antiBot
+     */
+    private function resolveAuthInterceptTimeout($antiBot)
+    {
+        if (!is_array($antiBot) || empty($antiBot['enabled'])) {
+            return 120;
+        }
+        return 180;
+    }
+
     private function requestNode($endpoint, $payload, $timeout = 60)
     {
         $ch = curl_init($this->nodeHost . $endpoint);
@@ -227,6 +249,7 @@ abstract class AbstractScrmSpider
         curl_setopt($ch, CURLOPT_POST, true);
         curl_setopt($ch, CURLOPT_POSTFIELDS, json_encode($payload));
         curl_setopt($ch, CURLOPT_HTTPHEADER, ['Content-Type: application/json']);
+        curl_setopt($ch, CURLOPT_CONNECTTIMEOUT, 5);
         curl_setopt($ch, CURLOPT_TIMEOUT, $timeout);
         $response = curl_exec($ch);
         if (curl_errno($ch)) throw new Exception(curl_error($ch));