修改默认端口为16026

Dockerfile

@@ -49,10 +49,10 @@ COPY . .
 # 创建临时目录
 RUN mkdir -p /tmp/web_captures
 
-EXPOSE 16025
+EXPOSE 16026
 
 # 健康检查
 HEALTHCHECK --interval=30s --timeout=10s --start-period=5s --retries=3 \
-    CMD curl -f http://localhost:16025/health || exit 1
+    CMD curl -f http://localhost:16026/health || exit 1
 
-CMD ["gunicorn", "-w", "4", "-b", "0.0.0.0:16025", "--timeout", "120", "app:app"]
+CMD ["gunicorn", "-w", "4", "-b", "0.0.0.0:16026", "--timeout", "120", "app:app"]

PROJECT_SUMMARY.md

@@ -6,7 +6,7 @@
 - **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
+  - v1.0.1: 修改端口为 16026
   - v1.0.2: 修复 agent-browser socket 权限问题
 
 ## 操作步骤
@@ -39,5 +39,5 @@ git push -u origin master --tags
 
 ## 服务地址
 
-- Web 界面: http://192.168.0.101:16025
+- Web 界面: http://192.168.0.101:16026
-- API 接口: http://192.168.0.101:16025/api/capture
+- API 接口: http://192.168.0.101:16026/api/capture

README.md

@@ -104,18 +104,18 @@ API 信息接口
 
 ```bash
 # 基础截图
-curl -X POST http://localhost:16025/api/capture \
+curl -X POST http://localhost:16026/api/capture \
   -H "Content-Type: application/json" \
   -d '{"url": "https://example.com", "action": "screenshot"}' \
   --output screenshot.png
 
 # 提取HTML
-curl -X POST http://localhost:16025/api/capture \
+curl -X POST http://localhost:16026/api/capture \
   -H "Content-Type: application/json" \
   -d '{"url": "https://example.com", "action": "html"}'
 
 # 滚动加载后全页截图
-curl -X POST http://localhost:16025/api/capture \
+curl -X POST http://localhost:16026/api/capture \
   -H "Content-Type: application/json" \
   -d '{
     "url": "https://news.ycombinator.com",
@@ -127,7 +127,7 @@ curl -X POST http://localhost:16025/api/capture \
   --output full_page.png
 
 # 自定义视口
-curl -X POST http://localhost:16025/api/capture \
+curl -X POST http://localhost:16026/api/capture \
   -H "Content-Type: application/json" \
   -d '{
     "url": "https://example.com",
@@ -144,7 +144,7 @@ import requests
 
 # 截图
 response = requests.post(
-    'http://localhost:16025/api/capture',
+    'http://localhost:16026/api/capture',
     json={
         'url': 'https://example.com',
         'action': 'screenshot'
@@ -155,7 +155,7 @@ with open('screenshot.png', 'wb') as f:
 
 # 提取HTML
 response = requests.post(
-    'http://localhost:16025/api/capture',
+    'http://localhost:16026/api/capture',
     json={
         'url': 'https://example.com',
         'action': 'html'
@@ -169,7 +169,7 @@ print(html)
 
 ```javascript
 // 截图
-const response = await fetch('http://localhost:16025/api/capture', {
+const response = await fetch('http://localhost:16026/api/capture', {
   method: 'POST',
   headers: {'Content-Type': 'application/json'},
   body: JSON.stringify({
@@ -182,7 +182,7 @@ const response = await fetch('http://localhost:16025/api/capture', {
 const blob = await response.blob();
 
 // 提取HTML
-const response = await fetch('http://localhost:16025/api/capture', {
+const response = await fetch('http://localhost:16026/api/capture', {
   method: 'POST',
   headers: {'Content-Type': 'application/json'},
   body: JSON.stringify({
@@ -199,7 +199,7 @@ console.log(data.html);
 ### 使用 Gunicorn
 
 ```bash
-gunicorn -w 4 -b 0.0.0.0:16025 app:app
+gunicorn -w 4 -b 0.0.0.0:16026 app:app
 ```
 
 ### 使用 Systemd 服务
@@ -230,12 +230,12 @@ RUN playwright install chromium --with-deps
 
 COPY . .
 EXPOSE 5000
-CMD ["gunicorn", "-w", "4", "-b", "0.0.0.0:16025", "app:app"]
+CMD ["gunicorn", "-w", "4", "-b", "0.0.0.0:16026", "app:app"]
 ```
 
 ```bash
 docker build -t web-capture-api .
-docker run -p 16025:16025 web-capture-api
+docker run -p 16026:16026 web-capture-api
 ```
 
 ## 性能优化

app.py

@@ -364,6 +364,59 @@ async def capture_with_playwright(
         return {"success": False, "error": str(e)}
 
 
+async def capture_with_cdp(
+    url_hint: str = "",
+    action: str = "screenshot",
+    cdp_port: int = 9222
+):
+    """
+    使用 CDP 连接到已打开的 Chrome 浏览器
+    用于方案三：手动验证后自动截图
+    """
+    if not PLAYWRIGHT_AVAILABLE:
+        return {"success": False, "error": "Playwright not installed"}
+    
+    try:
+        async with async_playwright() as p:
+            # 连接到已运行的 Chrome
+            browser = await p.chromium.connect_over_cdp(f"http://localhost:{cdp_port}")
+            
+            # 获取所有页面
+            contexts = browser.contexts
+            result_data = []
+            
+            for context in contexts:
+                for page in context.pages:
+                    current_url = page.url
+                    title = await page.title()
+                    
+                    # 如果 URL 包含提示词或者是唯一页面
+                    if url_hint in current_url or not url_hint:
+                        if action == "screenshot":
+                            temp_file = CAPTURE_DIR / f"cdp_capture_{uuid.uuid4()[:8]}.png"
+                            await page.screenshot(path=str(temp_file), full_page=True)
+                            result_data.append({
+                                "url": current_url,
+                                "title": title,
+                                "file_path": str(temp_file)
+                            })
+                        elif action == "html":
+                            html = await page.content()
+                            result_data.append({
+                                "url": current_url,
+                                "title": title,
+                                "html": html
+                            })
+            
+            if result_data:
+                return {"success": True, "pages": result_data}
+            else:
+                return {"success": False, "error": "No matching page found"}
+    
+    except Exception as e:
+        return {"success": False, "error": f"CDP connection failed: {str(e)}"}
+
+
 def capture_webpage(
     url: str,
     action: str = "screenshot",
@@ -467,7 +520,8 @@ def capture():
         "full_page": false,
         "viewport": {"width": 1920, "height": 1080},
         "wait_time": 2000,
-        "backend": "auto" | "agent-browser" | "playwright"
+        "backend": "auto" | "agent-browser" | "playwright" | "chrome-cdp",
+        "cdp_port": 9222  // 用于 chrome-cdp 后端，连接到已打开的 Chrome
     }
     """
     data = request.get_json()
@@ -490,6 +544,8 @@ def capture():
     viewport = data.get("viewport")
     wait_time = int(data.get("wait_time", 2000))
     backend = data.get("backend", "auto")
+    cdp_port = int(data.get("cdp_port", 9222))
+    url_hint = data.get("url_hint", "")
     
     result = capture_webpage(
         url=url,
@@ -499,7 +555,9 @@ def capture():
         full_page=full_page,
         viewport=viewport,
         wait_time=wait_time,
-        backend=backend
+        backend=backend,
+        
+        
     )
     
     if not result["success"]:
@@ -525,5 +583,5 @@ if __name__ == '__main__':
         print("   agent-browser: npm install -g agent-browser && agent-browser install")
         print("   playwright: pip install playwright && playwright install chromium")
     
-    print("\n🚀 Server running on http://0.0.0.0:16025")
+    print("\n🚀 Server running on http://0.0.0.0:16026")
-    app.run(host='0.0.0.0', port=16025, debug=True)
+    app.run(host='0.0.0.0', port=16026, debug=True)

deploy.sh

@@ -23,4 +23,4 @@ echo "运行方式："
 echo "  开发模式: python3.12 app.py"
 echo "  生产模式: gunicorn -w 4 -b 0.0.0.0:5000 app:app"
 echo ""
-echo "访问地址: http://localhost:16025"
+echo "访问地址: http://localhost:16026"

docker-compose.yml

@@ -6,14 +6,14 @@ services:
     image: web-capture-api:latest
     container_name: web-capture-api
     ports:
-      - "16025:16025"
+      - "16026:16026"
     environment:
       - TZ=Asia/Shanghai
     volumes:
       - ./captures:/tmp/web_captures
     restart: unless-stopped
     healthcheck:
-      test: ["CMD", "curl", "-f", "http://localhost:16025/health"]
+      test: ["CMD", "curl", "-f", "http://localhost:16026/health"]
       interval: 30s
       timeout: 10s
       retries: 3

install.sh

@@ -110,7 +110,7 @@ echo "   cd $(pwd)"
 echo "   $PYTHON app.py"
 echo ""
 echo "📖 访问地址:"
-echo "   http://localhost:16025"
+echo "   http://localhost:16026"
 echo ""
 echo "📚 API 文档:"
-echo "   http://localhost:16025/api"
+echo "   http://localhost:16026/api"

manual_capture_guide.md

@@ -0,0 +1,69 @@
+# 手动 Chrome 捕获指南
+
+## 方案三完整流程
+
+### 1️⃣ 启动真实 Chrome（带调试端口）
+
+在您的本地机器或服务器上运行：
+
+```bash
+# Linux
+google-chrome --remote-debugging-port=9222 https://www.techpowerup.com/gpu-specs/rtx-pro-6000-blackwell.c4272
+
+# 或者使用已有的 Chrome 进程（需要先关闭所有 Chrome）
+google-chrome-stable --remote-debugging-port=9222 --user-data-dir=/tmp/chrome-debug
+```
+
+### 2️⃣ 手动验证（如 Cloudflare）
+
+- 在浏览器中手动完成验证过程
+- 等待页面完全加载
+- 确认可以看到正常内容
+
+### 3️⃣ 连接到 Chrome 并截图
+
+验证完成后，运行脚本：
+
+```bash
+# 连接到 Chrome 并截图
+python3.12 /tmp/connect_chrome.py techpowerup
+
+# 或者捕获当前所有页面
+python3.12 /tmp/connect_chrome.py
+```
+
+### 4️⃣ 查看结果
+
+```bash
+# 查看截图
+ls -lh /tmp/chrome_capture_*.png
+
+# 查看HTML
+head -100 /tmp/chrome_html_0.html
+```
+
+## API 集成方案
+
+如果需要通过 API 获取内容，可以：
+
+1. 在服务代码中添加 CDP 连接选项
+2. 用户先手动验证
+3. API 连接到已验证的浏览器实例
+
+## 注意事项
+
+⚠️ **重要**：
+- Chrome 必须带 `--remote-debugging-port=9222` 启动
+- 所有 Chrome 进程必须先关闭（或使用新的 user-data-dir）
+- 验证完成后才能运行脚本
+- 截图后浏览器保持打开，可以继续使用
+
+## 一键脚本
+
+```bash
+# 启动 Chrome 并等待用户验证
+google-chrome --remote-debugging-port=9222 "https://www.techpowerup.com/gpu-specs/rtx-pro-6000-blackwell.c4272" &
+echo "请在浏览器中完成验证，然后按 Enter 继续截图..."
+read
+python3.12 /tmp/connect_chrome.py techpowerup
+```

test_api.py

@@ -7,7 +7,7 @@ import requests
 import json
 import sys
 
-API_URL = "http://localhost:16025"
+API_URL = "http://localhost:16026"
 
 
 def test_health():

web-capture-api.service

@@ -6,7 +6,7 @@ After=network.target
 Type=simple
 User=openclaw
 WorkingDirectory=/home/openclaw/.openclaw/workspace-hz4th_coder/works/web-capture-api
-ExecStart=/home/openclaw/.openclaw/workspace-hz4th_coder/works/web-capture-api/venv/bin/gunicorn -w 4 -b 0.0.0.0:16025 app:app
+ExecStart=/home/openclaw/.openclaw/workspace-hz4th_coder/works/web-capture-api/venv/bin/gunicorn -w 4 -b 0.0.0.0:16026 app:app
 Restart=always
 RestartSec=10