Browser-use：基於 Python 的智能瀏覽器自動化 AI 工具調研與實戰

一、概述

Browser-use 是一個旨在將 AI “智能體”（Agents）與真實瀏覽器進行交互的 Python 庫，可以輕鬆實現瀏覽器自動化。在配合 LLM（如 GPT 系列）使用時，瀏覽器-use 能夠讓你的智能體發起對網頁的訪問、操作頁面元素、收集信息、執行腳本等，從而擴展 AI 應用的落地場景。

• GitHub: browser-use/browser-use
• 官網: browser-use.com
• 文檔: docs.browser-use.com

<font style="color:#0e0e0e;">目前 Browser-use 最低需要 </font><font style="color:#0e0e0e;">Python 3.11</font><font style="color:#0e0e0e;"> 及以上，才能正常使用其封裝的 Playwright 功能。</font>

<font style="color:rgb(64, 64, 64);">1. 技術棧:</font>

• <font style="color:rgb(64, 64, 64);">LangChain（AI Agent框架）</font>
• <font style="color:rgb(64, 64, 64);">Playwright（瀏覽器自動化）</font>
• dotenv（環境變量 key）
• <font style="color:rgb(64, 64, 64);">異步I/O架構</font>

2. 流程圖

browser-use：語言模型 -> 決策/控制 -> 瀏覽器執行 -> 數據回傳 -> 模型後處理

二、核心特性

1. 簡單的 Agent 接口

通過 Agent 類即可快速創建帶瀏覽器交互能力的智能體，賦能 LLM 與網頁之間的複雜操作。

agent = Agent(
        task="打開 https://cn.vuejs.org/guide/essentials/computed，獲取頁面裏所有的 h2 標籤文本及所有的 a 標籤文本（以及它的 href）",
        llm=llm,
    )
result = await agent.run()

2. 多語言模型支持

可輕鬆集成 LangChain 提供的各類 LLM（如 OpenAI、Anthropic、Cohere 等）進行高級任務管理。

3. 基於 Playwright

默認使用 Playwright 進行瀏覽器的無頭啓動、頁面操作和渲染控制；對常見網頁交互場景提供友好的抽象。

4. 雲端版 & 本地版

除了本地安裝運行外，Browser-use 也提供託管版本，可以直接在雲端執行，無需配置本地環境。

三、安裝與環境配置

1. Python 版本

• 需要 Python 3.11 或更高版本。
• 推薦在獨立虛擬環境(venv)或管理工具（如 uv）中配置環境。

1.1. 推薦使用 pyenv 管理 python

Github：https://github.com/pyenv/pyenv

brew install pyenv
pyenv install 3.11.9

# pyenv 根目錄
export PYENV_ROOT="$HOME/.pyenv"
export PATH="$PYENV_ROOT/bin:$PATH"

# 初始化
eval "$(pyenv init -)"

2. 安裝方法

2.1. 安裝 browser-use

pip3 install browser-use

2.2. 安裝 Playwright

playwright install

• 此操作會自動下載 Chromium 無頭瀏覽器，用於後續的瀏覽器自動化。

2.3. 配置 LLM API Keys（可選）

• 在 .env 文件中填寫相應的 OPENAI_API_KEY=、ANTHROPIC_API_KEY= 等 Key。

OPENAI_API_KEY=sk-xxxxxxx

• 如果使用其他 LLM，需要參考 LangChain 文檔或對應服務提供的説明進行配置。

四、基礎配置

1. Agent

1.1. Agent 參數

1.2. Agent 執行流程圖

2. Browser 配置

Browser-use 提供兩個主要配置類：

• BrowserConfig：控制瀏覽器整體行為
• BrowserContextConfig：控制單個上下文（瀏覽器標籤頁/會話）的行為

官方推薦：「1 個 Agent 對應 1 個 Browser 和 1 個 Context」，以增強穩定性和開發體驗。

2.1. BrowserConfig

from browser_use import BrowserConfig

config = BrowserConfig(
    headless=False,
    disable_security=True
)
browser = Browser(config=config)

2.2. BrowserContextConfig 配置

from browser_use.browser.context import BrowserContextConfig

config = BrowserContextConfig(
    cookies_file="path/to/cookies.json",
    wait_for_network_idle_page_load_time=3.0,
    browser_window_size={'width': 1280, 'height': 1100},
    locale='en-US',
    user_agent='Mozilla/5.0...',
    highlight_elements=True,
    viewport_expansion=500,
    allowed_domains=['google.com', 'wikipedia.org'],
)

3. 輸出內容

3.1. History 方法

3.2. 示例

from pydantic import BaseModel
from typing import List
from dotenv import load_dotenv
from browser_use import Agent, Controller
from langchain_openai import ChatOpenAI
import asyncio

# Define the output format as a Pydantic model
class Post(BaseModel):
    post_title: str
    post_url: str


class Posts(BaseModel):
    posts: List[Post]


load_dotenv()
controller = Controller(output_model=Posts)


async def main():
    task = '從掘金獲取 Vue / React / AI 相關文章'
    model = ChatOpenAI(model='gpt-4o')
    agent = Agent(task=task, llm=model, controller=controller)
    history = await agent.run()
    result = history.final_result()
    print('result--->', result)
    print('history.urls()--->', history.urls())
    # print('history.screenshots()--->', history.screenshots())
    print('history.action_names()--->', history.action_names())
    print('history.extracted_content()--->', history.extracted_content())
    print('history.errors()--->', history.errors())
    print('history.model_actions()--->', history.model_actions())
    print('history.is_done()--->', history.is_done())
    print('history.has_errors()--->', history.has_errors())
    print('history.model_thoughts()--->', history.model_thoughts())
    print('history.action_results()--->', history.action_results())
    if result:
        parsed: Posts = Posts.model_validate_json(result)

        for post in parsed.posts:
            print('\n--------------------------------')
            print(f'Title:            {post.post_title}')
            print(f'URL:              {post.post_url}')
    else:
        print('No result')


if __name__ == '__main__':
    asyncio.run(main())

result---> {"posts": [{"post_title": "vue3.5+deepseek+arco+markdown\u642d\u5efaweb\u7248\u6d41\u5f0f\u8f93\u51faAI\u6a21\u677f", "post_url": "https://juejin.cn/post/7486369696738017321"}, {"post_title": "\ud83d\ude80\ud83d\ude80\ud83d\ude80\u5c24\u96e8\u6eaa\u8fde\u53d1\u4e24\u6761\u63a8\u7279\u5899\u88c2\u63a8\u8350\u7684\u8fd9\u4e9b\u5e93\u4f60\u4e00\u5b9a\u8981\u77e5\u9053\uff01", "post_url": "https://juejin.cn/post/7484131071569772595"}, {"post_title": "\u524d\u7aef\u4f6c\u4eec\uff01\u584c\u623f\u4e86\uff01\u7528\u8fc7Element-Plus\u7684\u8fdb\u6765~", "post_url": "https://juejin.cn/post/7485966905418760227"}, {"post_title": "\u548c\u540e\u7aef\u5927\u6218\u4e09\u767e\u56de\u5408\u540e\uff0c\u5351\u5fae\u524d\u7aef\u8fd8\u662f\u9009\u62e9\u4e86\u81ea\u5df1\u5199excel\u5bfc\u51fa", "post_url": "https://juejin.cn/post/7447368539936587776"}, {"post_title": "\u4ece DeepSeek \u770b25\u5e74\u524d\u7aef\u7684\u4e00\u4e2a\u5c0f\u8d8b\u52bf", "post_url": "https://juejin.cn/post/7468323178931879972"}, {"post_title": "\ud83d\ude80\ud83d\ude80\ud83d\ude80\u5c24\u96e8\u6eaa\u8fde\u53d1\u4e24\u6761\u63a8\u7279\u5899\u88c2\u63a8\u8350\u7684\u8fd9\u4e9b\u5e93\u4f60\u4e00\u5b9a\u8981\u77e5\u9053\uff01", "post_url": "https://juejin.cn/post/7484131071569772595"}, {"post_title": "\u524d\u7aef\u4f6c\u4eec\uff01\u584c\u623f\u4e86\uff01\u7528\u8fc7Element-Plus\u7684\u8fdb\u6765~", "post_url": "https://juejin.cn/post/7485966905418760227"}, {"post_title": "\u548c\u540e\u7aef\u5927\u6218\u4e09\u767e\u56de\u5408\u540e\uff0c\u5351\u5fae\u524d\u7aef\u8fd8\u662f\u9009\u62e9\u4e86\u81ea\u5df1\u5199excel\u5bfc\u51fa", "post_url": "https://juejin.cn/post/7447368539936587776"}, {"post_title": "vue3.5+deepseek+arco+markdown\u642d\u5efaweb\u7248\u6d41\u5f0f\u8f93\u51faAI\u6a21\u677f", "post_url": "https://juejin.cn/post/7486369696738017321"}, {"post_title": "\u4ece DeepSeek \u770b25\u5e74\u524d\u7aef\u7684\u4e00\u4e2a\u5c0f\u8d8b\u52bf", "post_url": "https://juejin.cn/post/7468323178931879972"}, {"post_title": "\u6709\u4e86Trae\uff0c\u4eba\u4eba\u90fd\u662f\u7a0b\u5e8f\u5458\u7684\u65f6\u4ee3\u6765\u4e86", "post_url": "https://juejin.cn/post/7463397212120973375"}, {"post_title": "\u6b63\u5f0f\u5ba3\u6218\uff0cDeepSeek \u9876\u5f97\u4f4f\u5417\uff1f", "post_url": "https://juejin.cn/post/7464848482987704329"}, {"post_title": "\u7528 DeepSeek \u6253\u9020\u4f60\u7684\u8d85\u5f3a\u4ee3\u7801\u52a9\u624b", "post_url": "https://juejin.cn/post/7454888708588945443"}, {"post_title": "\u521a\u521a\uff0cDeepSeek \u89e3\u7b54\u4e86\u56f0\u6270\u6211\u4e94\u5e74\u7684\u6280\u672f\u95ee\u9898\u3002\u65f6\u4ee3\u786e\u5b9e\u53d8\u4e86\uff01", "post_url": "https://juejin.cn/post/7472248441454018575"}, {"post_title": "\u653e\u5f03\u6ca1\u7528\u7684\u672c\u5730\u90e8\u7f72\u6b8b\u8840\u7248DeepSeek\u5427\uff0c\u6559\u4f60\u5982\u4f55\u767d\u5ad6\u6ee1\u8840\u7248DeepSeek", "post_url": "https://juejin.cn/post/7466832084486914083"}]}
history.urls()---> ['about:blank', 'https://juejin.cn/', 'https://juejin.cn/', 'https://juejin.cn/', 'https://juejin.cn/', 'https://juejin.cn/', 'https://juejin.cn/', 'https://juejin.cn/']
history.action_names()---> ['go_to_url', 'input_text', 'click_element', 'extract_content', 'input_text', 'click_element', 'extract_content', 'input_text', 'click_element', 'extract_content', 'done']
history.extracted_content()---> ['🔗  Navigated to https://juejin.cn', '⌨️  Input Vue into index 11', '🖱️  Clicked button with index 11: ', '📄  Extracted from page\n: ```json\n{\n  "top_5_vue_articles": [\n    {\n      "post_title": "vue3.5+deepseek+arco+markdown搭建web版流式輸出AI模板",\n      "post_url": "https://juejin.cn/post/7486369696738017321"\n    },\n    {\n      "post_title": "🚀🚀🚀尤雨溪連發兩條推特牆裂推薦的這些庫你一定要知道！",\n      "post_url": "https://juejin.cn/post/7484131071569772595"\n    },\n    {\n      "post_title": "前端佬們！塌房了！用過Element-Plus的進來~",\n      "post_url": "https://juejin.cn/post/7485966905418760227"\n    },\n    {\n      "post_title": "和後端大戰三百回合後，卑微前端還是選擇了自己寫excel導出",\n      "post_url": "https://juejin.cn/post/7447368539936587776"\n    },\n    {\n      "post_title": "從 DeepSeek 看25年前端的一個小趨勢",\n      "post_url": "https://juejin.cn/post/7468323178931879972"\n    }\n  ]\n}\n```\n', '⌨️  Input React into index 11', '🖱️  Clicked button with index 11: ', '📄  Extracted from page\n: ```json\n{\n  "top_5_react_articles": [\n    {\n      "post_title": "🚀🚀🚀尤雨溪連發兩條推特牆裂推薦的這些庫你一定要知道！",\n      "post_url": "/post/7484131071569772595"\n    },\n    {\n      "post_title": "前端佬們！塌房了！用過Element-Plus的進來~",\n      "post_url": "/post/7485966905418760227"\n    },\n    {\n      "post_title": "和後端大戰三百回合後，卑微前端還是選擇了自己寫excel導出",\n      "post_url": "/post/7447368539936587776"\n    },\n    {\n      "post_title": "vue3.5+deepseek+arco+markdown搭建web版流式輸出AI模板",\n      "post_url": "/post/7486369696738017321"\n    },\n    {\n      "post_title": "從 DeepSeek 看25年前端的一個小趨勢",\n      "post_url": "/post/7468323178931879972"\n    }\n  ]\n}\n```\n', '⌨️  Input AI into index 11', '🖱️  Clicked button with index 11: ', '📄  Extracted from page\n: ```json\n{\n  "top_5_ai_articles": [\n    {\n      "post_title": "有了Trae，人人都是程序員的時代來了",\n      "post_url": "/post/7463397212120973375"\n    },\n    {\n      "post_title": "正式宣戰，DeepSeek 頂得住嗎？",\n      "post_url": "/post/7464848482987704329"\n    },\n    {\n      "post_title": "用 DeepSeek 打造你的超強代碼助手",\n      "post_url": "/post/7454888708588945443"\n    },\n    {\n      "post_title": "剛剛，DeepSeek 解答了困擾我五年的技術問題。時代確實變了！",\n      "post_url": "/post/7472248441454018575"\n    },\n    {\n      "post_title": "放棄沒用的本地部署殘血版DeepSeek吧，教你如何白嫖滿血版DeepSeek",\n      "post_url": "/post/7466832084486914083"\n    }\n  ]\n}\n```\n', '{"posts": [{"post_title": "vue3.5+deepseek+arco+markdown\\u642d\\u5efaweb\\u7248\\u6d41\\u5f0f\\u8f93\\u51faAI\\u6a21\\u677f", "post_url": "https://juejin.cn/post/7486369696738017321"}, {"post_title": "\\ud83d\\ude80\\ud83d\\ude80\\ud83d\\ude80\\u5c24\\u96e8\\u6eaa\\u8fde\\u53d1\\u4e24\\u6761\\u63a8\\u7279\\u5899\\u88c2\\u63a8\\u8350\\u7684\\u8fd9\\u4e9b\\u5e93\\u4f60\\u4e00\\u5b9a\\u8981\\u77e5\\u9053\\uff01", "post_url": "https://juejin.cn/post/7484131071569772595"}, {"post_title": "\\u524d\\u7aef\\u4f6c\\u4eec\\uff01\\u584c\\u623f\\u4e86\\uff01\\u7528\\u8fc7Element-Plus\\u7684\\u8fdb\\u6765~", "post_url": "https://juejin.cn/post/7485966905418760227"}, {"post_title": "\\u548c\\u540e\\u7aef\\u5927\\u6218\\u4e09\\u767e\\u56de\\u5408\\u540e\\uff0c\\u5351\\u5fae\\u524d\\u7aef\\u8fd8\\u662f\\u9009\\u62e9\\u4e86\\u81ea\\u5df1\\u5199excel\\u5bfc\\u51fa", "post_url": "https://juejin.cn/post/7447368539936587776"}, {"post_title": "\\u4ece DeepSeek \\u770b25\\u5e74\\u524d\\u7aef\\u7684\\u4e00\\u4e2a\\u5c0f\\u8d8b\\u52bf", "post_url": "https://juejin.cn/post/7468323178931879972"}, {"post_title": "\\ud83d\\ude80\\ud83d\\ude80\\ud83d\\ude80\\u5c24\\u96e8\\u6eaa\\u8fde\\u53d1\\u4e24\\u6761\\u63a8\\u7279\\u5899\\u88c2\\u63a8\\u8350\\u7684\\u8fd9\\u4e9b\\u5e93\\u4f60\\u4e00\\u5b9a\\u8981\\u77e5\\u9053\\uff01", "post_url": "https://juejin.cn/post/7484131071569772595"}, {"post_title": "\\u524d\\u7aef\\u4f6c\\u4eec\\uff01\\u584c\\u623f\\u4e86\\uff01\\u7528\\u8fc7Element-Plus\\u7684\\u8fdb\\u6765~", "post_url": "https://juejin.cn/post/7485966905418760227"}, {"post_title": "\\u548c\\u540e\\u7aef\\u5927\\u6218\\u4e09\\u767e\\u56de\\u5408\\u540e\\uff0c\\u5351\\u5fae\\u524d\\u7aef\\u8fd8\\u662f\\u9009\\u62e9\\u4e86\\u81ea\\u5df1\\u5199excel\\u5bfc\\u51fa", "post_url": "https://juejin.cn/post/7447368539936587776"}, {"post_title": "vue3.5+deepseek+arco+markdown\\u642d\\u5efaweb\\u7248\\u6d41\\u5f0f\\u8f93\\u51faAI\\u6a21\\u677f", "post_url": "https://juejin.cn/post/7486369696738017321"}, {"post_title": "\\u4ece DeepSeek \\u770b25\\u5e74\\u524d\\u7aef\\u7684\\u4e00\\u4e2a\\u5c0f\\u8d8b\\u52bf", "post_url": "https://juejin.cn/post/7468323178931879972"}, {"post_title": "\\u6709\\u4e86Trae\\uff0c\\u4eba\\u4eba\\u90fd\\u662f\\u7a0b\\u5e8f\\u5458\\u7684\\u65f6\\u4ee3\\u6765\\u4e86", "post_url": "https://juejin.cn/post/7463397212120973375"}, {"post_title": "\\u6b63\\u5f0f\\u5ba3\\u6218\\uff0cDeepSeek \\u9876\\u5f97\\u4f4f\\u5417\\uff1f", "post_url": "https://juejin.cn/post/7464848482987704329"}, {"post_title": "\\u7528 DeepSeek \\u6253\\u9020\\u4f60\\u7684\\u8d85\\u5f3a\\u4ee3\\u7801\\u52a9\\u624b", "post_url": "https://juejin.cn/post/7454888708588945443"}, {"post_title": "\\u521a\\u521a\\uff0cDeepSeek \\u89e3\\u7b54\\u4e86\\u56f0\\u6270\\u6211\\u4e94\\u5e74\\u7684\\u6280\\u672f\\u95ee\\u9898\\u3002\\u65f6\\u4ee3\\u786e\\u5b9e\\u53d8\\u4e86\\uff01", "post_url": "https://juejin.cn/post/7472248441454018575"}, {"post_title": "\\u653e\\u5f03\\u6ca1\\u7528\\u7684\\u672c\\u5730\\u90e8\\u7f72\\u6b8b\\u8840\\u7248DeepSeek\\u5427\\uff0c\\u6559\\u4f60\\u5982\\u4f55\\u767d\\u5ad6\\u6ee1\\u8840\\u7248DeepSeek", "post_url": "https://juejin.cn/post/7466832084486914083"}]}']
history.errors()---> [None, None, None, None, None, None, None, None]
history.model_actions()---> [{'go_to_url': {'url': 'https://juejin.cn'}, 'interacted_element': None}, {'input_text': {'index': 11, 'text': 'Vue'}, 'interacted_element': DOMHistoryElement(tag_name='input', xpath='html/body/div/div/div/div/div/div/header/div/nav/ul/ul/li/ul/li/form/input', highlight_index=11, entire_parent_branch_path=['div', 'div', 'div', 'div', 'div', 'div', 'header', 'div', 'nav', 'ul', 'ul', 'li', 'ul', 'li', 'form', 'input'], attributes={'type': 'search', 'maxlength': '64', 'placeholder': '探索稀土掘金', 'value': '', 'class': 'search-input', 'data-v-fdf9839c': ''}, shadow_root=False, css_selector='html > body > div > div > div > div > div > div > header > div > nav > ul > ul > li > ul > li > form > input.search-input[type="search"][placeholder="探索稀土掘金"]', page_coordinates=None, viewport_coordinates=None, viewport_info=None)}, {'click_element': {'index': 11}, 'interacted_element': DOMHistoryElement(tag_name='input', xpath='html/body/div/div/div/div/div/div/header/div/nav/ul/ul/li/ul/li/form/input', highlight_index=11, entire_parent_branch_path=['div', 'div', 'div', 'div', 'div', 'div', 'header', 'div', 'nav', 'ul', 'ul', 'li', 'ul', 'li', 'form', 'input'], attributes={'type': 'search', 'maxlength': '64', 'placeholder': '探索稀土掘金', 'value': '', 'class': 'search-input', 'data-v-fdf9839c': ''}, shadow_root=False, css_selector='html > body > div > div > div > div > div > div > header > div > nav > ul > ul > li > ul > li > form > input.search-input[type="search"][placeholder="探索稀土掘金"]', page_coordinates=None, viewport_coordinates=None, viewport_info=None)}, {'extract_content': {'goal': "Extract the top 5 articles for 'Vue' including post_title and post_url."}, 'interacted_element': None}, {'input_text': {'index': 11, 'text': 'React'}, 'interacted_element': DOMHistoryElement(tag_name='input', xpath='html/body/div/div/div/div/div/div/header/div/nav/ul/ul/li/ul/li/form/input', highlight_index=11, entire_parent_branch_path=['div', 'div', 'div', 'div', 'div', 'div', 'header', 'div', 'nav', 'ul', 'ul', 'li', 'ul', 'li', 'form', 'input'], attributes={'type': 'search', 'maxlength': '64', 'placeholder': '搜索文章/小冊/標籤/用户', 'value': '', 'class': 'search-input active', 'data-v-fdf9839c': '', 'style': ''}, shadow_root=False, css_selector='html > body > div > div > div > div > div > div > header > div > nav > ul > ul > li > ul > li > form > input.search-input.active[type="search"][placeholder="搜索文章/小冊/標籤/用户"]', page_coordinates=None, viewport_coordinates=None, viewport_info=None)}, {'click_element': {'index': 11}, 'interacted_element': DOMHistoryElement(tag_name='input', xpath='html/body/div/div/div/div/div/div/header/div/nav/ul/ul/li/ul/li/form/input', highlight_index=11, entire_parent_branch_path=['div', 'div', 'div', 'div', 'div', 'div', 'header', 'div', 'nav', 'ul', 'ul', 'li', 'ul', 'li', 'form', 'input'], attributes={'type': 'search', 'maxlength': '64', 'placeholder': '搜索文章/小冊/標籤/用户', 'value': '', 'class': 'search-input active', 'data-v-fdf9839c': '', 'style': ''}, shadow_root=False, css_selector='html > body > div > div > div > div > div > div > header > div > nav > ul > ul > li > ul > li > form > input.search-input.active[type="search"][placeholder="搜索文章/小冊/標籤/用户"]', page_coordinates=None, viewport_coordinates=None, viewport_info=None)}, {'extract_content': {'goal': "Extract the top 5 articles for 'React' including post_title and post_url."}, 'interacted_element': None}, {'input_text': {'index': 11, 'text': 'AI'}, 'interacted_element': DOMHistoryElement(tag_name='input', xpath='html/body/div/div/div/div/div/div/header/div/nav/ul/ul/li/ul/li/form/input', highlight_index=11, entire_parent_branch_path=['div', 'div', 'div', 'div', 'div', 'div', 'header', 'div', 'nav', 'ul', 'ul', 'li', 'ul', 'li', 'form', 'input'], attributes={'type': 'search', 'maxlength': '64', 'placeholder': '搜索文章/小冊/標籤/用户', 'value': '', 'class': 'search-input active', 'data-v-fdf9839c': '', 'style': ''}, shadow_root=False, css_selector='html > body > div > div > div > div > div > div > header > div > nav > ul > ul > li > ul > li > form > input.search-input.active[type="search"][placeholder="搜索文章/小冊/標籤/用户"]', page_coordinates=None, viewport_coordinates=None, viewport_info=None)}, {'click_element': {'index': 11}, 'interacted_element': DOMHistoryElement(tag_name='input', xpath='html/body/div/div/div/div/div/div/header/div/nav/ul/ul/li/ul/li/form/input', highlight_index=11, entire_parent_branch_path=['div', 'div', 'div', 'div', 'div', 'div', 'header', 'div', 'nav', 'ul', 'ul', 'li', 'ul', 'li', 'form', 'input'], attributes={'type': 'search', 'maxlength': '64', 'placeholder': '搜索文章/小冊/標籤/用户', 'value': '', 'class': 'search-input active', 'data-v-fdf9839c': '', 'style': ''}, shadow_root=False, css_selector='html > body > div > div > div > div > div > div > header > div > nav > ul > ul > li > ul > li > form > input.search-input.active[type="search"][placeholder="搜索文章/小冊/標籤/用户"]', page_coordinates=None, viewport_coordinates=None, viewport_info=None)}, {'extract_content': {'goal': "Extract the top 5 articles for 'AI' including post_title and post_url."}, 'interacted_element': None}, {'done': {'posts': [{'post_title': 'vue3.5+deepseek+arco+markdown搭建web版流式輸出AI模板', 'post_url': 'https://juejin.cn/post/7486369696738017321'}, {'post_title': '🚀🚀🚀尤雨溪連發兩條推特牆裂推薦的這些庫你一定要知道！', 'post_url': 'https://juejin.cn/post/7484131071569772595'}, {'post_title': '前端佬們！塌房了！用過Element-Plus的進來~', 'post_url': 'https://juejin.cn/post/7485966905418760227'}, {'post_title': '和後端大戰三百回合後，卑微前端還是選擇了自己寫excel導出', 'post_url': 'https://juejin.cn/post/7447368539936587776'}, {'post_title': '從 DeepSeek 看25年前端的一個小趨勢', 'post_url': 'https://juejin.cn/post/7468323178931879972'}, {'post_title': '🚀🚀🚀尤雨溪連發兩條推特牆裂推薦的這些庫你一定要知道！', 'post_url': 'https://juejin.cn/post/7484131071569772595'}, {'post_title': '前端佬們！塌房了！用過Element-Plus的進來~', 'post_url': 'https://juejin.cn/post/7485966905418760227'}, {'post_title': '和後端大戰三百回合後，卑微前端還是選擇了自己寫excel導出', 'post_url': 'https://juejin.cn/post/7447368539936587776'}, {'post_title': 'vue3.5+deepseek+arco+markdown搭建web版流式輸出AI模板', 'post_url': 'https://juejin.cn/post/7486369696738017321'}, {'post_title': '從 DeepSeek 看25年前端的一個小趨勢', 'post_url': 'https://juejin.cn/post/7468323178931879972'}, {'post_title': '有了Trae，人人都是程序員的時代來了', 'post_url': 'https://juejin.cn/post/7463397212120973375'}, {'post_title': '正式宣戰，DeepSeek 頂得住嗎？', 'post_url': 'https://juejin.cn/post/7464848482987704329'}, {'post_title': '用 DeepSeek 打造你的超強代碼助手', 'post_url': 'https://juejin.cn/post/7454888708588945443'}, {'post_title': '剛剛，DeepSeek 解答了困擾我五年的技術問題。時代確實變了！', 'post_url': 'https://juejin.cn/post/7472248441454018575'}, {'post_title': '放棄沒用的本地部署殘血版DeepSeek吧，教你如何白嫖滿血版DeepSeek', 'post_url': 'https://juejin.cn/post/7466832084486914083'}], 'success': True}, 'interacted_element': None}]
history.is_done()---> True
history.has_errors()---> False
history.model_thoughts()---> [AgentBrain(evaluation_previous_goal='Unknown - No previous actions to evaluate.', memory="Starting the task. Need to open the Juejin website and search for 'Vue', 'React', and 'AI' keywords. Each search should yield at least 5 articles. Currently, 0 out of 3 keywords searched.", next_goal='Open the Juejin website.'), AgentBrain(evaluation_previous_goal='Success - Successfully navigated to the Juejin website.', memory="Task started. Currently, 0 out of 3 keywords searched ('Vue', 'React', 'AI'). Next, search for 'Vue' and extract the top 5 articles.", next_goal="Search for the keyword 'Vue' on Juejin."), AgentBrain(evaluation_previous_goal="Success - Successfully searched for the keyword 'Vue'.", memory="Task in progress. Searched for 'Vue' (1/3 keywords completed). Next, extract the top 5 articles for 'Vue'.", next_goal="Extract the top 5 articles for 'Vue'."), AgentBrain(evaluation_previous_goal="Success - Extracted the top 5 articles for 'Vue'.", memory="Task in progress. Searched for 'Vue' (1/3 keywords completed). Next, search for 'React' and extract the top 5 articles.", next_goal="Search for the keyword 'React' on Juejin."), AgentBrain(evaluation_previous_goal="Success - Successfully searched for the keyword 'React'.", memory="Task in progress. Searched for 'React' (2/3 keywords completed). Next, extract the top 5 articles for 'React'.", next_goal="Extract the top 5 articles for 'React'."), AgentBrain(evaluation_previous_goal="Success - Extracted the top 5 articles for 'React'.", memory="Task in progress. Searched for 'React' (2/3 keywords completed). Next, search for 'AI' and extract the top 5 articles.", next_goal="Search for the keyword 'AI' on Juejin."), AgentBrain(evaluation_previous_goal="Success - Successfully searched for the keyword 'AI'.", memory="Task in progress. Searched for 'AI' (3/3 keywords completed). Next, extract the top 5 articles for 'AI'.", next_goal="Extract the top 5 articles for 'AI'."), AgentBrain(evaluation_previous_goal="Success - Extracted the top 5 articles for 'AI'.", memory="Task completed. Searched for all 3 keywords ('Vue', 'React', 'AI') and extracted the top 5 articles for each. Total of 15 articles collected.", next_goal='Compile and return the final results.')]
history.action_results()---> [ActionResult(is_done=False, success=None, extracted_content='🔗  Navigated to https://juejin.cn', error=None, include_in_memory=True), ActionResult(is_done=False, success=None, extracted_content='⌨️  Input Vue into index 11', error=None, include_in_memory=True), ActionResult(is_done=False, success=None, extracted_content='🖱️  Clicked button with index 11: ', error=None, include_in_memory=True), ActionResult(is_done=False, success=None, extracted_content='📄  Extracted from page\n: ```json\n{\n  "top_5_vue_articles": [\n    {\n      "post_title": "vue3.5+deepseek+arco+markdown搭建web版流式輸出AI模板",\n      "post_url": "https://juejin.cn/post/7486369696738017321"\n    },\n    {\n      "post_title": "🚀🚀🚀尤雨溪連發兩條推特牆裂推薦的這些庫你一定要知道！",\n      "post_url": "https://juejin.cn/post/7484131071569772595"\n    },\n    {\n      "post_title": "前端佬們！塌房了！用過Element-Plus的進來~",\n      "post_url": "https://juejin.cn/post/7485966905418760227"\n    },\n    {\n      "post_title": "和後端大戰三百回合後，卑微前端還是選擇了自己寫excel導出",\n      "post_url": "https://juejin.cn/post/7447368539936587776"\n    },\n    {\n      "post_title": "從 DeepSeek 看25年前端的一個小趨勢",\n      "post_url": "https://juejin.cn/post/7468323178931879972"\n    }\n  ]\n}\n```\n', error=None, include_in_memory=True), ActionResult(is_done=False, success=None, extracted_content='⌨️  Input React into index 11', error=None, include_in_memory=True), ActionResult(is_done=False, success=None, extracted_content='🖱️  Clicked button with index 11: ', error=None, include_in_memory=True), ActionResult(is_done=False, success=None, extracted_content='📄  Extracted from page\n: ```json\n{\n  "top_5_react_articles": [\n    {\n      "post_title": "🚀🚀🚀尤雨溪連發兩條推特牆裂推薦的這些庫你一定要知道！",\n      "post_url": "/post/7484131071569772595"\n    },\n    {\n      "post_title": "前端佬們！塌房了！用過Element-Plus的進來~",\n      "post_url": "/post/7485966905418760227"\n    },\n    {\n      "post_title": "和後端大戰三百回合後，卑微前端還是選擇了自己寫excel導出",\n      "post_url": "/post/7447368539936587776"\n    },\n    {\n      "post_title": "vue3.5+deepseek+arco+markdown搭建web版流式輸出AI模板",\n      "post_url": "/post/7486369696738017321"\n    },\n    {\n      "post_title": "從 DeepSeek 看25年前端的一個小趨勢",\n      "post_url": "/post/7468323178931879972"\n    }\n  ]\n}\n```\n', error=None, include_in_memory=True), ActionResult(is_done=False, success=None, extracted_content='⌨️  Input AI into index 11', error=None, include_in_memory=True), ActionResult(is_done=False, success=None, extracted_content='🖱️  Clicked button with index 11: ', error=None, include_in_memory=True), ActionResult(is_done=False, success=None, extracted_content='📄  Extracted from page\n: ```json\n{\n  "top_5_ai_articles": [\n    {\n      "post_title": "有了Trae，人人都是程序員的時代來了",\n      "post_url": "/post/7463397212120973375"\n    },\n    {\n      "post_title": "正式宣戰，DeepSeek 頂得住嗎？",\n      "post_url": "/post/7464848482987704329"\n    },\n    {\n      "post_title": "用 DeepSeek 打造你的超強代碼助手",\n      "post_url": "/post/7454888708588945443"\n    },\n    {\n      "post_title": "剛剛，DeepSeek 解答了困擾我五年的技術問題。時代確實變了！",\n      "post_url": "/post/7472248441454018575"\n    },\n    {\n      "post_title": "放棄沒用的本地部署殘血版DeepSeek吧，教你如何白嫖滿血版DeepSeek",\n      "post_url": "/post/7466832084486914083"\n    }\n  ]\n}\n```\n', error=None, include_in_memory=True), ActionResult(is_done=True, success=True, extracted_content='{"posts": [{"post_title": "vue3.5+deepseek+arco+markdown\\u642d\\u5efaweb\\u7248\\u6d41\\u5f0f\\u8f93\\u51faAI\\u6a21\\u677f", "post_url": "https://juejin.cn/post/7486369696738017321"}, {"post_title": "\\ud83d\\ude80\\ud83d\\ude80\\ud83d\\ude80\\u5c24\\u96e8\\u6eaa\\u8fde\\u53d1\\u4e24\\u6761\\u63a8\\u7279\\u5899\\u88c2\\u63a8\\u8350\\u7684\\u8fd9\\u4e9b\\u5e93\\u4f60\\u4e00\\u5b9a\\u8981\\u77e5\\u9053\\uff01", "post_url": "https://juejin.cn/post/7484131071569772595"}, {"post_title": "\\u524d\\u7aef\\u4f6c\\u4eec\\uff01\\u584c\\u623f\\u4e86\\uff01\\u7528\\u8fc7Element-Plus\\u7684\\u8fdb\\u6765~", "post_url": "https://juejin.cn/post/7485966905418760227"}, {"post_title": "\\u548c\\u540e\\u7aef\\u5927\\u6218\\u4e09\\u767e\\u56de\\u5408\\u540e\\uff0c\\u5351\\u5fae\\u524d\\u7aef\\u8fd8\\u662f\\u9009\\u62e9\\u4e86\\u81ea\\u5df1\\u5199excel\\u5bfc\\u51fa", "post_url": "https://juejin.cn/post/7447368539936587776"}, {"post_title": "\\u4ece DeepSeek \\u770b25\\u5e74\\u524d\\u7aef\\u7684\\u4e00\\u4e2a\\u5c0f\\u8d8b\\u52bf", "post_url": "https://juejin.cn/post/7468323178931879972"}, {"post_title": "\\ud83d\\ude80\\ud83d\\ude80\\ud83d\\ude80\\u5c24\\u96e8\\u6eaa\\u8fde\\u53d1\\u4e24\\u6761\\u63a8\\u7279\\u5899\\u88c2\\u63a8\\u8350\\u7684\\u8fd9\\u4e9b\\u5e93\\u4f60\\u4e00\\u5b9a\\u8981\\u77e5\\u9053\\uff01", "post_url": "https://juejin.cn/post/7484131071569772595"}, {"post_title": "\\u524d\\u7aef\\u4f6c\\u4eec\\uff01\\u584c\\u623f\\u4e86\\uff01\\u7528\\u8fc7Element-Plus\\u7684\\u8fdb\\u6765~", "post_url": "https://juejin.cn/post/7485966905418760227"}, {"post_title": "\\u548c\\u540e\\u7aef\\u5927\\u6218\\u4e09\\u767e\\u56de\\u5408\\u540e\\uff0c\\u5351\\u5fae\\u524d\\u7aef\\u8fd8\\u662f\\u9009\\u62e9\\u4e86\\u81ea\\u5df1\\u5199excel\\u5bfc\\u51fa", "post_url": "https://juejin.cn/post/7447368539936587776"}, {"post_title": "vue3.5+deepseek+arco+markdown\\u642d\\u5efaweb\\u7248\\u6d41\\u5f0f\\u8f93\\u51faAI\\u6a21\\u677f", "post_url": "https://juejin.cn/post/7486369696738017321"}, {"post_title": "\\u4ece DeepSeek \\u770b25\\u5e74\\u524d\\u7aef\\u7684\\u4e00\\u4e2a\\u5c0f\\u8d8b\\u52bf", "post_url": "https://juejin.cn/post/7468323178931879972"}, {"post_title": "\\u6709\\u4e86Trae\\uff0c\\u4eba\\u4eba\\u90fd\\u662f\\u7a0b\\u5e8f\\u5458\\u7684\\u65f6\\u4ee3\\u6765\\u4e86", "post_url": "https://juejin.cn/post/7463397212120973375"}, {"post_title": "\\u6b63\\u5f0f\\u5ba3\\u6218\\uff0cDeepSeek \\u9876\\u5f97\\u4f4f\\u5417\\uff1f", "post_url": "https://juejin.cn/post/7464848482987704329"}, {"post_title": "\\u7528 DeepSeek \\u6253\\u9020\\u4f60\\u7684\\u8d85\\u5f3a\\u4ee3\\u7801\\u52a9\\u624b", "post_url": "https://juejin.cn/post/7454888708588945443"}, {"post_title": "\\u521a\\u521a\\uff0cDeepSeek \\u89e3\\u7b54\\u4e86\\u56f0\\u6270\\u6211\\u4e94\\u5e74\\u7684\\u6280\\u672f\\u95ee\\u9898\\u3002\\u65f6\\u4ee3\\u786e\\u5b9e\\u53d8\\u4e86\\uff01", "post_url": "https://juejin.cn/post/7472248441454018575"}, {"post_title": "\\u653e\\u5f03\\u6ca1\\u7528\\u7684\\u672c\\u5730\\u90e8\\u7f72\\u6b8b\\u8840\\u7248DeepSeek\\u5427\\uff0c\\u6559\\u4f60\\u5982\\u4f55\\u767d\\u5ad6\\u6ee1\\u8840\\u7248DeepSeek", "post_url": "https://juejin.cn/post/7466832084486914083"}]}', error=None, include_in_memory=False)]

4. Prompt

用於 控制 Agent 的行為與能力，對其整體邏輯有深層影響。

自定義提示會顯著影響性能、穩定性和輸出風格。

message_context 字段

5. 持久化會話

增加 Cookie

context_config = BrowserContextConfig(cookies_file="cookies.json")

五、Demo 示例

1. 簡單示例

#!/usr/bin/env python3
# -*- coding: utf-8 -*-

import asyncio
from dotenv import load_dotenv
from langchain_openai import ChatOpenAI
from browser_use import Agent

load_dotenv()

llm = ChatOpenAI(model="gpt-4o")

async def main():
    agent = Agent(
        task="打開 https://cn.vuejs.org/guide/essentials/computed，獲取頁面裏所有的 h2 標籤文本及所有的 a 標籤文本（以及它的 href）",
        llm=llm,
    )
    result = await agent.run()
    print('result:',result)

if __name__ == "__main__":
    asyncio.run(main())

1.1. 核心流程:

1. 從 .env 中讀取 OPENAI_API_KEY 等信息，初始化 ChatOpenAI。
2. 創建一個 Agent，指定 task 即描述智能體要完成的任務。
3. 調用 agent.run() 發起執行，包括瀏覽器自動化與 LLM 結合的流程。

2. 使用本地的 Chrome 瀏覽器

#!/usr/bin/env python3
# -*- coding: utf-8 -*-

from browser_use import Agent, Browser, BrowserConfig
from langchain_openai import ChatOpenAI
from dotenv import load_dotenv
import asyncio

load_dotenv()
browser = Browser(
    config=BrowserConfig(
        chrome_instance_path='/Applications/Google Chrome.app/Contents/MacOS/Google Chrome',
    )
)

llm = ChatOpenAI(model="gpt-4o")

agent = Agent(
    task="打開 https://cn.vuejs.org/guide/essentials/computed，獲取頁面裏所有的 h2 標籤文本及所有的 a 標籤文本（以及它的 href）",
    llm=llm,
    browser=browser,
)

async def main():
    await agent.run()
    await browser.close()

if __name__ == '__main__':
    asyncio.run(main())

3. Prompt

from pydantic import BaseModel
from typing import List
from dotenv import load_dotenv
from browser_use import Agent, Controller, Browser, BrowserConfig
from langchain_openai import ChatOpenAI
import asyncio

class WikiResult(BaseModel):
    post_title: str
    post_url: str

class WikiResults(BaseModel):
    posts: List[WikiResult]


load_dotenv()

browser = Browser(
    config=BrowserConfig(
        chrome_instance_path='/Applications/Google Chrome.app/Contents/MacOS/Google Chrome',
    )
)

instruction_message = """
你正在訪問一個公司內部 Wiki 系統：http://wiki.xxx.com/pages/

你的目標是：
1. 打開該頁面並使用搜索功能，輸入關鍵詞：RAP
2. 等待頁面加載完畢，提取所有與搜索結果相關的條目，包括標題、簡要描述和對應鏈接。
3. 優先提取條目中出現 "接口管理"、"Mock"、"權限" 等關鍵詞的內容。
4. 將所有結果以列表形式返回。

請確保你的返回格式如下：
{
  "posts": [
    {
      "post_title": "xxx",
      "post_url": "http://..."
    },
    ...
  ]
}
"""

controller = Controller(output_model=WikiResults)

async def main():
    task = "搜索 Wiki 中有關 RAP 的內容"
    model = ChatOpenAI(model='gpt-4o')

    agent = Agent(
        task=task,
        llm=model,
        controller=controller,
        browser=browser,
        message_context=instruction_message
    )

    history = await agent.run()
    result = history.final_result()

    if result:
        parsed: WikiResults = WikiResults.model_validate_json(result)

        for post in parsed.posts:
            print('\n--------------------------------')
            print(f'Title:  {post.post_title}')
            print(f'URL:    {post.post_url}')
    else:
        print('No result')


if __name__ == '__main__':
    asyncio.run(main())

4. 多個 Agent 執行

agent1 = Agent(
    task="打開 https://cn.vuejs.org/guide/essentials/computed，獲取頁面裏所有的 h2 標籤文本及所有的 a 標籤文本（以及它的 href）",
    llm=llm,
    use_vision=False
)
result1 = await agent1.run()
agent2 = Agent(
    task="打開 https://docs.browser-use.com/customize/custom-functions，獲取頁面裏所有的 h2 標籤文本及所有的 a 標籤文本（以及它的 href）",
    llm=llm,
    use_vision=False
)
result2 = await agent2.run()

六、常見操作

1. 修改 LLM 模型

llm = ChatOpenAI(model="gpt-3.5-turbo")

或

llm = ChatOpenAI(model="gpt-4o")

2. 在 .env 中設置 API Key

OPENAI_API_KEY=sk-xxxx
ANTHROPIC_API_KEY=xxxxxx

如果你還需使用其他模型（如 Cohere、HuggingFace Hub），可一併配置對應的 Key，並在 Python 腳本中初始化相應的 LLM 對象。

3. 官方文檔示例

在 docs.browser-use.com/introduction 可以找到更多場景示例，比如如何定製 browser-use 的 Tools、配合 PythonREPLTool 擴展執行 Python 腳本等。

七、UI 測試方式

1. 安裝 Gradio

pip3 install gradio

2. 運行示例

import asyncio

import gradio as gr
from dotenv import load_dotenv
from langchain_openai import ChatOpenAI

from browser_use import Agent

load_dotenv()


llm=ChatOpenAI(base_url='https://api.deepseek.com/v1', model='deepseek-chat', api_key="sk-XXX")

async def run_browser_task(
    task: str,
) -> str:
    try:
        print('task', task)
        agent = Agent(
            task=task,
            llm=llm,
            use_vision=False
        )
        result = await agent.run()
        print('final_result()', result.final_result())
        return result
    except Exception as e:
        return f'Error: {str(e)}'


def create_ui():
    with gr.Blocks(title='Browser Use GUI') as interface:
        gr.Markdown('# Browser Use Task Automation')

        with gr.Row():
            with gr.Column():
                task = gr.Textbox(
                    label='Task Description',
                    placeholder='Task 描述',
                    lines=3,
                )
                model = gr.Dropdown(
                    choices=['gpt-4', 'gpt-3.5-turbo'], label='Model', value='gpt-4'
                )
                headless = gr.Checkbox(label='Run Headless', value=True)
                submit_btn = gr.Button('Run Task')

            with gr.Column():
                output = gr.Textbox(label='Output', lines=10, interactive=False)

        submit_btn.click(
            fn=lambda *args: asyncio.run(run_browser_task(task.value)),
            inputs=[task, model, headless],
            outputs=output,
        )

    return interface


if __name__ == '__main__':
    demo = create_ui()
    demo.launch()

打開終端提示的地址，就能看到一個簡易的 web 界面，在界面中輸入 task 等信息測試智能體。

八、常見問題 & 解決思路

• 報錯：playwright not installed 或 executable path not found

  • 請確認已執行 playwright install chromium，且安裝成功。

• Python 版本過低

  • Browser-use 要求 Python >= 3.11，如果你使用的是 3.10 或更低版本，需要升級環境。

• LLM 調用失敗

  • 檢查是否在 .env 中填寫了正確的 API key，或你的 Key 是否仍在有效期內。

• 一直執行 Step1

  • Key 沒錢了...

• UI Demo 啓動後無法訪問

  • 可能是端口占用，或者 Gradio 版本過舊。嘗試更新 gradio 或換一個端口。

• 長時間卡住/超時

  • 檢查網絡環境，LLM 請求或瀏覽器加載是否耗時過長。

• DeepSeek

  • 需要添加 use_vision=False 字段

九、總結

Browser-use 讓 AI 與瀏覽器的結合變得更便捷，能夠快速構建出“會瀏覽網頁、抓取信息、進行動態交互”的智能體。只需簡單的配置與幾行代碼，就能讓 LLM 自動處理網頁操作，為項目帶來更多可能性。

• 使用 Python >= 3.11；
• 安裝並配置好 Playwright；
• 在主代碼中初始化 Agent 並提供 LLM；
• 在 .env 中存放 API Keys；

十、參考

• GitHub: browser-use/browser-use
• 官網: browser-use.com
• 官方文檔: docs.browser-use.com/introduction