Golang跨平台GUI自动化控制鼠标键盘插件库robotgo的使用

简介

Robotgo是一个Golang桌面自动化库，可以控制鼠标、键盘，读取屏幕内容，处理窗口句柄、图像和位图，以及全局事件监听。它支持Mac、Windows和Linux(X11)平台，同时支持arm64和x86-amd64架构。

安装要求

在安装Robotgo之前，请确保已正确安装Golang和GCC。

所有平台

Golang
GCC

MacOS

brew install go
xcode-select --install

Windows

winget install Golang.go
winget install MartinStorsjo.LLVM-MinGW.UCRT

Ubuntu

sudo snap install go --classic
sudo apt install gcc libc6-dev
sudo apt install libx11-dev xorg-dev libxtst-dev
sudo apt install xsel xclip
sudo apt install libpng++-dev
sudo apt install xcb libxcb-xkb-dev x11-xkb-utils libx11-xcb-dev libxkbcommon-x11-dev libxkbcommon-dev

安装

使用Go模块支持(Go 1.11+)时，只需导入：

import "github.com/go-vgo/robotgo"

否则，运行以下命令安装robotgo包：

go get github.com/go-vgo/robotgo

更新

go get -u github.com/go-vgo/robotgo

示例代码

鼠标控制示例

package main

import (
  "fmt"
  "github.com/go-vgo/robotgo"
)

func main() {
  robotgo.MouseSleep = 300

  robotgo.Move(100, 100)
  fmt.Println(robotgo.Location())
  robotgo.Move(100, -200) // 支持多屏幕
  robotgo.MoveSmooth(120, -150)
  fmt.Println(robotgo.Location())

  robotgo.ScrollDir(10, "up")
  robotgo.ScrollDir(20, "right")

  robotgo.Scroll(0, -10)
  robotgo.Scroll(100, 0)

  robotgo.MilliSleep(100)
  robotgo.ScrollSmooth(-10, 6)

  robotgo.Move(10, 20)
  robotgo.MoveRelative(0, -10)
  robotgo.DragSmooth(10, 10)

  robotgo.Click("wheelRight")
  robotgo.Click("left", true)
  robotgo.MoveSmooth(100, 200, 1.0, 10.0)

  robotgo.Toggle("left")
  robotgo.Toggle("left", "up")
}

键盘控制示例

package main

import (
  "fmt"
  "github.com/go-vgo/robotgo"
)

func main() {
  robotgo.TypeStr("Hello World")
  robotgo.TypeStr("だんしゃり", 0, 1)

  robotgo.TypeStr("Hi, Seattle space needle, Golden gate bridge, One world trade center.")
  robotgo.TypeStr("Hi galaxy, hi stars, hi MT.Rainier, hi sea. こんにちは世界.")
  robotgo.Sleep(1)

  robotgo.KeySleep = 100
  robotgo.KeyTap("enter")
  robotgo.KeyTap("i", "alt", "cmd")

  arr := []string{"alt", "cmd"}
  robotgo.KeyTap("i", arr)

  robotgo.MilliSleep(100)
  robotgo.KeyToggle("a")
  robotgo.KeyToggle("a", "up")

  robotgo.WriteAll("Test")
  text, err := robotgo.ReadAll()
  if err == nil {
    fmt.Println(text)
  }
}

屏幕操作示例

package main

import (
  "fmt"
  "strconv"
  "github.com/go-vgo/robotgo"
  "github.com/vcaesar/imgo"
)

func main() {
  x, y := robotgo.Location()
  fmt.Println("pos: ", x, y)

  color := robotgo.GetPixelColor(100, 200)
  fmt.Println("color---- ", color)

  sx, sy := robotgo.GetScreenSize()
  fmt.Println("get screen size: ", sx, sy)

  bit := robotgo.CaptureScreen(10, 10, 30, 30)
  defer robotgo.FreeBitmap(bit)

  img := robotgo.ToImage(bit)
  imgo.Save("test.png", img)

  num := robotgo.DisplaysNum()
  for i := 0; i < num; i++ {
    robotgo.DisplayID = i
    img1, _ := robotgo.CaptureImg()
    path1 := "save_" + strconv.Itoa(i)
    robotgo.Save(img1, path1+".png")
    robotgo.SaveJpeg(img1, path1+".jpeg", 50)

    img2, _ := robotgo.CaptureImg(10, 10, 20, 20)
    robotgo.Save(img2, "test_"+strconv.Itoa(i)+".png")

    x, y, w, h := robotgo.GetDisplayBounds(i)
    img3, err := robotgo.CaptureImg(x, y, w, h)
    fmt.Println("Capture error: ", err)
    robotgo.Save(img3, path1+"_1.png")
  }
}

窗口操作示例

package main

import (
  "fmt"
  "github.com/go-vgo/robotgo"
)

func main() {
  fpid, err := robotgo.FindIds("Google")
  if err == nil {
    fmt.Println("pids... ", fpid)

    if len(fpid) > 0 {
      robotgo.TypeStr("Hi galaxy!", fpid[0])
      robotgo.KeyTap("a", fpid[0], "cmd")

      robotgo.KeyToggle("a", fpid[0])
      robotgo.KeyToggle("a", fpid[0], "up")

      robotgo.ActivePid(fpid[0])
      robotgo.Kill(fpid[0])
    }
  }

  robotgo.ActiveName("chrome")

  isExist, err := robotgo.PidExists(100)
  if err == nil && isExist {
    fmt.Println("pid exists is", isExist)
    robotgo.Kill(100)
  }

  abool := robotgo.Alert("test", "robotgo")
  if abool {
    fmt.Println("ok@@@ ", "ok")
  }

  title := robotgo.GetTitle()
  fmt.Println("title@@@ ", title)
}

未来计划

1. 将部分C代码重构为Go代码(如x11、windows相关代码)
2. 改进多屏幕支持
3. 支持Wayland
4. 更新窗口句柄处理
5. 尝试支持Android和IOS平台

Robotgo是一个功能强大的跨平台自动化库，可以用于各种GUI自动化任务，如测试自动化、屏幕截图、鼠标键盘模拟等。