browser-navigation

使用 agent-browser 进行浏览器自动化

全面的浏览器自动化，用于测试、数据提取和网页交互。

快速开始

agent-browser open <url>        # Navigate to page
agent-browser snapshot -i       # Get interactive elements with refs
agent-browser click @e1         # Click element by ref
agent-browser fill @e2 "text"   # Fill input by ref
agent-browser close             # Close browser

核心工作流

1. 导航：agent-browser open <url>
2. 快照：agent-browser snapshot -i（返回带有 @e1、@e2 等引用的元素）
3. 使用快照中的引用进行交互
4. 导航或 DOM 发生重大变化后，重新获取快照

安装

# Install globally
npm install -g agent-browser

# Or use via npx
npx agent-browser open https://example.com

命令参考

导航

agent-browser open <url>      # Navigate to URL
agent-browser back            # Go back
agent-browser forward         # Go forward
agent-browser reload          # Reload page
agent-browser close           # Close browser

页面分析（快照）

agent-browser snapshot            # Full accessibility tree
agent-browser snapshot -i         # Interactive elements only (RECOMMENDED)
agent-browser snapshot -c         # Compact output
agent-browser snapshot -d 3       # Limit depth to 3
agent-browser snapshot -s "#main" # Scope to CSS selector

交互（使用快照中的 @refs）

# Clicking
agent-browser click @e1           # Click
agent-browser dblclick @e1        # Double-click
agent-browser hover @e1           # Hover

# Focus
agent-browser focus @e1           # Focus element

# Text Input
agent-browser fill @e2 "text"     # Clear and type
agent-browser type @e2 "text"     # Type without clearing

# Keyboard
agent-browser press Enter         # Press key
agent-browser press Control+a     # Key combination
agent-browser keydown Shift       # Hold key down
agent-browser keyup Shift         # Release key

# Forms
agent-browser check @e1           # Check checkbox
agent-browser uncheck @e1         # Uncheck checkbox
agent-browser select @e1 "value"  # Select dropdown option

# Scrolling
agent-browser scroll down 500     # Scroll page
agent-browser scrollintoview @e1  # Scroll element into view

# Other
agent-browser drag @e1 @e2        # Drag and drop
agent-browser upload @e1 file.pdf # Upload files

获取信息

agent-browser get text @e1        # Get element text
agent-browser get html @e1        # Get innerHTML
agent-browser get value @e1       # Get input value
agent-browser get attr @e1 href   # Get attribute
agent-browser get title           # Get page title
agent-browser get url             # Get current URL
agent-browser get count ".item"   # Count matching elements
agent-browser get box @e1         # Get bounding box

检查状态

agent-browser is visible @e1      # Check if visible
agent-browser is enabled @e1      # Check if enabled
agent-browser is checked @e1      # Check if checked

截图和 PDF

agent-browser screenshot          # Screenshot to stdout
agent-browser screenshot path.png # Save to file
agent-browser screenshot --full   # Full page
agent-browser pdf output.pdf      # Save as PDF

视频录制

agent-browser record start ./demo.webm    # Start recording
agent-browser click @e1                   # Perform actions
agent-browser record stop                 # Stop and save video
agent-browser record restart ./take2.webm # Stop current + start new

等待

agent-browser wait @e1                     # Wait for element
agent-browser wait 2000                    # Wait milliseconds
agent-browser wait --text "Success"        # Wait for text
agent-browser wait --url "**/dashboard"    # Wait for URL pattern
agent-browser wait --load networkidle      # Wait for network idle
agent-browser wait --fn "window.ready"     # Wait for JS condition

Cookie 和存储

agent-browser cookies                     # Get all cookies
agent-browser cookies set name value      # Set cookie
agent-browser cookies clear               # Clear cookies
agent-browser storage local               # Get all localStorage
agent-browser storage local key           # Get specific key
agent-browser storage local set k v       # Set value
agent-browser storage local clear         # Clear all

网络

agent-browser network route <url>              # Intercept requests
agent-browser network route <url> --abort      # Block requests
agent-browser network route <url> --body '{}'  # Mock response
agent-browser network unroute [url]            # Remove routes
agent-browser network requests                 # View tracked requests
agent-browser network requests --filter api    # Filter requests

浏览器设置

agent-browser set viewport 1920 1080      # Set viewport size
agent-browser set device "iPhone 14"      # Emulate device
agent-browser set geo 37.7749 -122.4194   # Set geolocation
agent-browser set offline on              # Toggle offline mode
agent-browser set headers '{"X-Key":"v"}' # Extra HTTP headers
agent-browser set credentials user pass   # HTTP basic auth
agent-browser set media dark              # Emulate color scheme

标签页和窗口

agent-browser tab                 # List tabs
agent-browser tab new [url]       # New tab
agent-browser tab 2               # Switch to tab
agent-browser tab close           # Close tab
agent-browser window new          # New window

框架

agent-browser frame "#iframe"     # Switch to iframe
agent-browser frame main          # Back to main frame

对话框

agent-browser dialog accept [text]  # Accept dialog
agent-browser dialog dismiss        # Dismiss dialog

JavaScript 执行

agent-browser eval "document.title"   # Run JavaScript

工作流示例

提交表单

agent-browser open https://example.com/form
agent-browser snapshot -i
# Output shows: textbox "Email" [ref=e1], textbox "Password" [ref=e2], button "Submit" [ref=e3]

agent-browser fill @e1 "[email protected]"
agent-browser fill @e2 "password123"
agent-browser click @e3
agent-browser wait --load networkidle
agent-browser snapshot -i  # Check result

使用已保存状态进行身份验证

# Login once
agent-browser open https://app.example.com/login
agent-browser snapshot -i
agent-browser fill @e1 "username"
agent-browser fill @e2 "password"
agent-browser click @e3
agent-browser wait --url "**/dashboard"
agent-browser state save auth.json

# Later sessions: load saved state
agent-browser state load auth.json
agent-browser open https://app.example.com/dashboard

抓取数据

agent-browser open https://example.com/products
agent-browser snapshot -i --json > page_structure.json

# Get specific data
agent-browser get text @e5  # Product title
agent-browser get attr @e6 href  # Product link

获取整页截图

agent-browser open https://example.com
agent-browser wait --load networkidle
agent-browser screenshot --full fullpage.png

测试登录流程

# Navigate to login
agent-browser open https://app.example.com/login

# Take initial snapshot
agent-browser snapshot -i

# Fill credentials
agent-browser fill @e1 "[email protected]"
agent-browser fill @e2 "testpassword"

# Click login
agent-browser click @e3

# Wait for redirect
agent-browser wait --url "**/dashboard"

# Verify logged in
agent-browser get text @e10  # Should show username

调试

agent-browser open example.com --headed              # Show browser window
agent-browser console                                # View console messages
agent-browser console --clear                        # Clear console
agent-browser errors                                 # View page errors
agent-browser errors --clear                         # Clear errors
agent-browser highlight @e1                          # Highlight element
agent-browser trace start                            # Start recording trace
agent-browser trace stop trace.zip                   # Stop and save trace
agent-browser --cdp 9222 snapshot                    # Connect via CDP

会话（并行浏览器）

agent-browser --session test1 open site-a.com
agent-browser --session test2 open site-b.com
agent-browser session list

JSON 输出

添加 --json 以获取机器可读的输出：

agent-browser snapshot -i --json
agent-browser get text @e1 --json

语义定位器（引用的替代方案）

agent-browser find role button click --name "Submit"
agent-browser find text "Sign In" click
agent-browser find label "Email" fill "[email protected]"
agent-browser find first ".item" click
agent-browser find nth 2 "a" text

最佳实践

1. 始终先获取快照：在交互前获取当前页面状态
2. 使用交互模式（-i）：仅显示可点击或可填写的元素
3. 适当等待：导航后使用 --load networkidle
4. 更改后重新获取快照：DOM 更新会使引用失效
5. 保存身份验证状态：避免重复登录
6. 使用 --headed 进行调试：查看浏览器所见内容
7. 检查控制台中的错误：agent-browser console 可显示问题

何时使用此技能

• 对 Web 应用进行端到端测试
• 自动执行重复性的网页任务
• 从网站抓取数据
• 调试前端问题
• 为文档截取屏幕截图
• 录制演示视频
• 验证 UI 功能
• 以编程方式填写表单

禁用冲突的 MCP

如果启用了 Chrome DevTools 或 Playwright MCP，请询问用户是否要禁用它，以节省上下文。此技能涵盖相同的功能。

请让他们运行：

/mcp

如果看到列出了 chrome-devtools 或 playwright，建议他们移除它：

/mcp remove chrome-devtools
/mcp remove playwright

不要自行运行这些命令。由用户决定是否禁用该 MCP。