集成 playwright-stealth 专业反检测插件

添加:
- playwright-stealth 反检测库
- 增强 navigator 属性模拟
- 真实 Chrome 浏览器支持（如果已安装）
- 更强的反自动化检测配置

注意:
- 某些高防护网站（如 Cloudflare）仍可能拦截
- 建议使用代理或真实 Chrome 浏览器

PROJECT_SUMMARY.md

@@ -0,0 +1,43 @@
+# Web Capture API 项目
+
+## 待推送信息
+
+- **仓库地址**: http://121.40.164.32:12007/hz4th_coder/web-capture-api.git
+- **当前版本**: v1.0.2
+- **提交历史**:
+  - v1.0.0: 初始化项目
+  - v1.0.1: 修改端口为 16025
+  - v1.0.2: 修复 agent-browser socket 权限问题
+
+## 操作步骤
+
+### 1. 在 Git 平台创建仓库
+
+请大爷登录 Git 平台 (http://121.40.164.32:12007) 并创建仓库：
+- 仓库名称: `web-capture-api`
+- 所属用户: `hz4th_coder`
+- 可见性: 公开或私有（根据需要）
+
+### 2. 推送代码
+
+仓库创建后，运行以下命令：
+
+```bash
+cd /home/openclaw/.openclaw/workspace-hz4th_coder/works/web-capture-api
+git push -u origin master --tags
+```
+
+## 项目功能
+
+- 网页截图（全页或视口）
+- HTML 代码提取
+- 自动滚动加载动态内容
+- 自定义视口大小
+- Web 界面和 RESTful API
+- 支持 agent-browser 和 Playwright 双后端
+- Docker 部署支持
+
+## 服务地址
+
+- Web 界面: http://192.168.0.101:16025
+- API 接口: http://192.168.0.101:16025/api/capture

app.py

@@ -20,8 +20,17 @@ from datetime import datetime
 try:
     from playwright.async_api import async_playwright
     PLAYWRIGHT_AVAILABLE = True
+    # 尝试导入 stealth 反检测
+    try:
+        from playwright_stealth import stealth_async
+        STEALTH_AVAILABLE = True
+    except ImportError:
+        STEALTH_AVAILABLE = False
+        print("⚠️  playwright-stealth 未安装，反爬虫能力降低")
 except ImportError:
     PLAYWRIGHT_AVAILABLE = False
+    STEALTH_AVAILABLE = False
+    print("⚠️  Playwright 未安装，请运行: pip install playwright && playwright install chromium")
 
 # 检查 agent-browser 是否可用
 def check_agent_browser():
@@ -44,6 +53,10 @@ CORS(app)
 CAPTURE_DIR = Path(tempfile.gettempdir()) / "web_captures"
 CAPTURE_DIR.mkdir(exist_ok=True)
 
+# agent-browser socket 目录
+os.environ.setdefault("AGENT_BROWSER_SOCKET_DIR", "/tmp/agent-browser-sockets")
+Path(os.environ["AGENT_BROWSER_SOCKET_DIR"]).mkdir(exist_ok=True, parents=True)
+
 
 class AgentBrowserSession:
     """agent-browser 会话管理器"""
@@ -55,12 +68,17 @@ 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:
@@ -70,6 +88,9 @@ 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):
@@ -130,6 +151,9 @@ 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
@@ -179,28 +203,120 @@ async def capture_with_playwright(
 ):
     """
     使用 Playwright 捕获网页
+    Playwright 有更强的反爬虫能力
     """
     if not PLAYWRIGHT_AVAILABLE:
-        return {"success": False, "error": "Playwright not installed"}
+        return {"success": False, "error": "Playwright not installed. Run: pip install playwright && playwright install chromium"}
     
     session_id = str(uuid.uuid4())[:8]
     
     try:
         async with async_playwright() as p:
-            browser = await p.chromium.launch(headless=True)
+            # 启动浏览器，添加反检测配置
+            # 尝试使用真实 Chrome（如果安装了）
+            try:
+                # 首先尝试使用真实 Chrome 浏览器
+                browser = await p.chromium.launch(
+                    headless=True,
+                    channel='chrome',  # 使用真实 Chrome 而不是 Chromium
+                    args=[
+                        '--disable-blink-features=AutomationControlled',
+                        '--disable-dev-shm-usage',
+                        '--no-sandbox',
+                        '--ignore-certificate-errors',
+                    ]
+                )
+            except:
+                # 如果没有 Chrome，使用 Chromium
+                browser = await p.chromium.launch(
+                    headless=True,
+                    args=[
+                        '--disable-blink-features=AutomationControlled',
+                        '--disable-dev-shm-usage',
+                        '--no-sandbox',
+                        '--ignore-certificate-errors',
+                    ]
+                )
             
             viewport_settings = viewport or {"width": 1920, "height": 1080}
             
+            # 创建上下文，模拟真实浏览器
             context = await browser.new_context(
                 viewport={
                     "width": viewport_settings.get("width", 1920),
                     "height": viewport_settings.get("height", 1080)
                 },
-                user_agent="Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36"
+                user_agent='Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.6099.109 Safari/537.36',
+                # 添加更多浏览器特征
+                locale='en-US',
+                timezone_id='America/New_York',
+                color_scheme='light',
+                has_touch=False,
+                is_mobile=False,
+                java_script_enabled=True,
+                accept_downloads=True,
             )
             
+            # 注入反检测脚本
+            await context.add_init_script("""
+                // 移除 webdriver 标记
+                Object.defineProperty(navigator, 'webdriver', {
+                    get: () => undefined
+                });
+                
+                // 添加插件
+                Object.defineProperty(navigator, 'plugins', {
+                    get: () => {
+                        return [
+                            {name: 'Chrome PDF Plugin', filename: 'internal-pdf-viewer', description: 'Portable Document Format'},
+                            {name: 'Chrome PDF Viewer', filename: 'mhjfbmdgncjokjjpdkfnmlglggk', description: ''},
+                            {name: 'Native Client', filename: 'internal-nacl-plugin', description: ''}
+                        ];
+                    }
+                });
+                
+                // 语言列表
+                Object.defineProperty(navigator, 'languages', {
+                    get: () => ['en-US', 'en', 'zh-CN']
+                });
+                
+                // 平台
+                Object.defineProperty(navigator, 'platform', {
+                    get: () => 'Win32'
+                });
+                
+                // 硬件并发
+                Object.defineProperty(navigator, 'hardwareConcurrency', {
+                    get: () => 8
+                });
+                
+                // 设备内存
+                Object.defineProperty(navigator, 'deviceMemory', {
+                    get: () => 8
+                });
+                
+                // Chrome 对象
+                window.chrome = {
+                    runtime: {
+                        PlatformOs: {MAC: 'mac', WIN: 'win', ANDROID: 'android', CROS: 'cros', LINUX: 'linux', OPENBSD: 'openbsd'},
+                        PlatformArch: {ARM: 'arm', X86_32: 'x86-32', X86_64: 'x86-64'},
+                        PlatformNaclArch: {ARM: 'arm', X86_32: 'x86-32', X86_64: 'x86-64'},
+                        Request: function() {},
+                        connect: function() {},
+                        sendMessage: function() {}
+                    },
+                    loadTimes: function() {},
+                    csi: function() {},
+                    app: {}
+                };
+            """)
+            
             page = await context.new_page()
             
+            # 应用 stealth 反检测（如果可用）
+            if STEALTH_AVAILABLE:
+                await stealth_async(page)
+            
             try:
                 await page.goto(url, wait_until="networkidle", timeout=30000)
             except:

templates/index.html

@@ -405,7 +405,7 @@
             submitBtn.disabled = true;
             
             try {
-                const response = await fetch('http://localhost:16025/api/capture', {
+                const response = await fetch('/api/capture', {
                     method: 'POST',
                     headers: {
                         'Content-Type': 'application/json'