使用brower use AI 代理自动控制浏览器完成任务

第一步：终端运行命令下载 brower use

pip install browser-use

第二步： 终端运行命令下载playwright

playwright install

第三步：新建test.py代码，粘贴复制以下代码 

import asyncio
import osfrom dotenv import load_dotenv
from langchain_openai import ChatOpenAI
from pydantic import SecretStrfrom browser_use import Agent# dotenv
load_dotenv()api_key = os.getenv('DEEPSEEK_API_KEY', '')
if not api_key:raise ValueError('DEEPSEEK_API_KEY is not set')async def run_search():agent = Agent(task=('go to bing.com and type test click search and give me the first url'),llm=ChatOpenAI(base_url='https://api.deepseek.com/v1',model='deepseek-chat',api_key=SecretStr(api_key),),use_vision=False,)await agent.run()if __name__ == '__main__':asyncio.run(run_search())

第四步：新建.env文件并输入自己的key 

DEEPSEEK_API_KEY=

第五步：运行python代码 

参考仓库：GitHub - browser-use/browser-use: Make websites accessible for AI agents