OpenClaw浏览器自动化配置
配置OpenClaw连接远程Chrome/CDP浏览器,实现无头浏览器自动化操作与管理。
HappyFee
@happyfee
What This Skill Does
Configures OpenClaw to connect to a remote Chrome browser via CDP (Chrome DevTools Protocol) for headless browser automation. Supports local Docker containers, remote servers, and cloud services like browserless.io.
Replaces manually managing browser instances and Selenium setups by providing a single configuration to attach OpenClaw to any CDP-enabled browser.
When to Use It
- Connect OpenClaw to a headless Chrome container for automated web scraping
- Attach OpenClaw to a remote server's Chrome browser for remote control
- Integrate browserless.io cloud service with OpenClaw for scalable automation
- Verify CDP endpoint is reachable before configuring OpenClaw profiles
- Switch OpenClaw between multiple remote browser profiles for different tasks
Install
$ openclaw skills install @happyfee/openclaw-browser-autoOpenClaw 浏览器自动化配置
配置OpenClaw连接远程Chrome/CDP浏览器进行自动化操作。
适用场景
- 连接远程服务器的Chrome浏览器
- 使用Docker容器运行的无头浏览器
- 连接browserless.io云服务
配置步骤
1. 启动CDP浏览器容器
推荐使用 chromedp/headless-shell(轻量且保持会话):
docker run -d --name browser-auto -p 9222:9222 --shm-size=512m chromedp/headless-shell:latest
验证CDP可用:
curl http://127.0.0.1:9222/json/version
2. 配置OpenClaw
在 ~/.openclaw/openclaw.json 中添加browser配置:
{
"browser": {
"enabled": true,
"defaultProfile": "remote-chrome",
"attachOnly": true,
"profiles": {
"remote-chrome": {
"cdpUrl": "http://127.0.0.1:9222",
"color": "#00AA00"
}
}
}
}
3. 重启Gateway
systemctl --user restart openclaw-gateway
4. 验证
openclaw browser status
关键配置项
| 配置项 | 说明 |
|---|---|
browser.enabled | 启用浏览器 |
browser.defaultProfile | 默认使用的浏览器配置名 |
browser.attachOnly | true=不尝试启动本地浏览器,只连接远程 |
profiles.<name>.cdpUrl | 远程CDP地址 |
云服务方案
Browserless.io(付费)
{
"browser": {
"defaultProfile": "browserless",
"profiles": {
"browserless": {
"cdpUrl": "https://production-sfo.browserless.io?token=<API_KEY>"
}
}
}
}
常见问题
- 端口被占用 - 设置
attachOnly: true - 标签页丢失 - 使用 chromedp/headless-shell 而非 browserless/chrome
- 环境变量不生效 - 需要修改systemd服务配置
Top skills in this category
Multi Search Engine
@gpyangyoujunMulti search engine integration with 16 engines (7 CN + 9 Global). Supports advanced search operators, time filters, site search, privacy engines, and Wolfra...
Agent Browser
@matrixyHeadless browser automation CLI optimized for AI agents with accessibility tree snapshots and ref-based element selection
Openai Whisper
@steipeteLocal speech-to-text with the Whisper CLI (no API key).
Tavily 搜索
@jacky1n7Web search via Tavily API (alternative to Brave). Use when the user asks to search the web / look up sources / find links and Brave web_search is unavailable...
Baidu web search
@ide-reaSearch the web using Baidu AI Search Engine (BDSE). Use for live information, documentation, or research topics.