增强 agent-browser 反爬虫支持

- 自动设置 AGENT_BROWSER_SOCKET_DIR 环境变量
- 添加真实 User-Agent 绕过反爬虫检测
- 增加 403 错误检测和提示
- 解决 techpowerup.com 等网站拦截问题

app.py

@@ -59,12 +59,17 @@ class AgentBrowserSession:
     def run(self, cmd, timeout=60000):
         """执行 agent-browser 命令"""
         full_cmd = self.base_cmd + cmd
+        # 设置必要的环境变量
+        env = os.environ.copy()
+        env['AGENT_BROWSER_SOCKET_DIR'] = '/tmp/agent-browser-sockets'
+        env['AGENT_BROWSER_USER_AGENT'] = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36'
         try:
             result = subprocess.run(
                 full_cmd,
                 capture_output=True,
                 text=True,
-                timeout=timeout / 1000
+                timeout=timeout / 1000,
+                env=env
             )
             return result.returncode == 0, result.stdout, result.stderr
         except subprocess.TimeoutExpired:
@@ -74,6 +79,9 @@ class AgentBrowserSession:
     
     def open(self, url):
         """打开网页"""
+        # 添加反爬虫检测的 User-Agent
+        env = os.environ.copy()
+        env['AGENT_BROWSER_USER_AGENT'] = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36'
         return self.run(["open", url], timeout=30000)
     
     def set_viewport(self, width, height):
@@ -134,6 +142,9 @@ def capture_with_agent_browser(
         # 打开网页
         success, stdout, stderr = session.open(url)
         if not success:
+            # 检查是否是反爬虫拦截
+            if "403" in stdout or "Access Denied" in stdout:
+                return {"success": False, "error": "网站反爬虫拦截 (403)，建议使用 Playwright 后端或手动添加请求头"}
             return {"success": False, "error": f"Failed to open URL: {stderr}"}
         
         # 等待页面加载