使用brower use AI 代理自动控制浏览器完成任务

longze_72025-03-23 16:45

第一步：终端运行命令下载 brower use

bash 复制代码

pip install browser-use

第二步：终端运行命令下载playwright

bash 复制代码

playwright install

第三步：新建test.py代码，粘贴复制以下代码

python 复制代码

import asyncio
import os

from dotenv import load_dotenv
from langchain_openai import ChatOpenAI
from pydantic import SecretStr

from 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

bash 复制代码

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