2 Commits

Author SHA1 Message Date
98ef180878 增强 Playwright 反爬虫检测能力
添加:
- 禁用自动化控制特征
- 真实浏览器参数配置
- 反检测脚本注入
- 地理位置等真实特征
- 更强的 User-Agent 模拟

Playwright 后端可以更好地绕过反爬虫检测
2026-07-05 00:55:09 +08:00
6b7e856e38 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
2026-07-05 00:19:18 +08:00
2 changed files with 91 additions and 4 deletions

43
PROJECT_SUMMARY.md Normal file
View File

@@ -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

52
app.py
View File

@@ -59,12 +59,17 @@ class AgentBrowserSession:
def run(self, cmd, timeout=60000): def run(self, cmd, timeout=60000):
"""执行 agent-browser 命令""" """执行 agent-browser 命令"""
full_cmd = self.base_cmd + cmd 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: try:
result = subprocess.run( result = subprocess.run(
full_cmd, full_cmd,
capture_output=True, capture_output=True,
text=True, text=True,
timeout=timeout / 1000 timeout=timeout / 1000,
env=env
) )
return result.returncode == 0, result.stdout, result.stderr return result.returncode == 0, result.stdout, result.stderr
except subprocess.TimeoutExpired: except subprocess.TimeoutExpired:
@@ -74,6 +79,9 @@ class AgentBrowserSession:
def open(self, url): def open(self, url):
"""打开网页""" """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) return self.run(["open", url], timeout=30000)
def set_viewport(self, width, height): def set_viewport(self, width, height):
@@ -134,6 +142,9 @@ def capture_with_agent_browser(
# 打开网页 # 打开网页
success, stdout, stderr = session.open(url) success, stdout, stderr = session.open(url)
if not success: 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}"} return {"success": False, "error": f"Failed to open URL: {stderr}"}
# 等待页面加载 # 等待页面加载
@@ -183,26 +194,59 @@ async def capture_with_playwright(
): ):
""" """
使用 Playwright 捕获网页 使用 Playwright 捕获网页
Playwright 有更强的反爬虫能力
""" """
if not PLAYWRIGHT_AVAILABLE: 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] session_id = str(uuid.uuid4())[:8]
try: try:
async with async_playwright() as p: 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
browser = await p.chromium.launch(
headless=True,
args=[
'--disable-blink-features=AutomationControlled', # 反自动化检测
'--disable-dev-shm-usage',
'--no-sandbox',
'--disable-setuid-sandbox',
'--disable-web-security',
]
)
viewport_settings = viewport or {"width": 1920, "height": 1080} 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( context = await browser.new_context(
viewport={ viewport={
"width": viewport_settings.get("width", 1920), "width": viewport_settings.get("width", 1920),
"height": viewport_settings.get("height", 1080) "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/120.0.0.0 Safari/537.36',
# 添加更多浏览器特征
locale='zh-CN',
timezone_id='Asia/Shanghai',
geolocation={'latitude': 31.2304, 'longitude': 121.4737}, # 上海坐标
permissions=['geolocation'],
) )
# 注入反检测脚本
await context.add_init_script("""
Object.defineProperty(navigator, 'webdriver', {
get: () => undefined
});
Object.defineProperty(navigator, 'plugins', {
get: () => [1, 2, 3, 4, 5]
});
Object.defineProperty(navigator, 'languages', {
get: () => ['zh-CN', 'zh', 'en', 'en-US']
});
window.chrome = {
runtime: {}
};
""")
page = await context.new_page() page = await context.new_page()
try: try: