chrome headless截图

Headless Chrome

Headless Chrome 是 Chrome 浏览器的无界面形态，可以在不打开浏览器的前提下，使用所有 Chrome 支持的特性运行你的程序。相比于现代浏览器，Headless Chrome 更加方便测试 web 应用，获得网站的截图，做爬虫抓取信息等。相比于出道较早的 PhantomJS，SlimerJS 等，Headless Chrome 则更加贴近浏览器环境。

容器部署

https://github.com/Zenika/alpine-chrome

docker search alpine-chrome

docker pull zenika/alpine-chrome

docker container run -d -p 9222:9222 zenika/alpine-chrome --no-sandbox   --remote-debugging-address=0.0.0.0 --remote-debugging-port=9222 https://www.chromestatus.com/

示例代码

curl http://127.0.0.1:9222/json/version //获取版本等信息

// Command screenshot is a chromedp example demonstrating how to take a
// screenshot of a specific element and of the entire browser viewport.
package main

import (
	"context"
	"encoding/json"
	"fmt"
	"io/ioutil"
	"net"
	"net/http"
	"net/url"
	"sync"
	"time"

	"github.com/chromedp/chromedp"
	"github.com/panjf2000/ants/v2"
)

type chromeVersion struct {
	Browser              string `json:"Browser"`
	ProtocalVersion      string `json:"Protocol-Version"`
	UserAgent            string `json:"User-Agent"`
	V8Version            string `json:"V8-Version"`
	WebKitVersion        string `json:"WebKit-Version"`
	WebSocketDebuggerURL string `json:"webSocketDebuggerUrl"`
}

// fullScreenshot takes a screenshot of the entire browser viewport.
//
// Note: chromedp.FullScreenshot overrides the device's emulation settings. Use
// device.Reset to reset the emulation and viewport settings.
func fullScreenshot(urlstr string, quality int, res *[]byte) chromedp.Tasks {
	return chromedp.Tasks{
		chromedp.Navigate(urlstr),
		chromedp.FullScreenshot(res, quality),
	}
}

func getChromeVersion(address string) (string, error) {
	u, _ := url.Parse("http://" + address)

	ip, err := net.ResolveIPAddr("ip", u.Hostname())
	if err != nil {
		return "", err
	}

	link := "http://" + ip.String() + ":" + u.Port() + `/json/version`
	resp, err := http.Get(link)
	if err != nil {
		return "", err
	}
	defer resp.Body.Close()

	body, err := ioutil.ReadAll(resp.Body)
	if err != nil {
		return "", err
	}

	chromeVer := &chromeVersion{}
	json.Unmarshal(body, chromeVer)
	return chromeVer.WebSocketDebuggerURL, nil
}

func myFunc(i interface{}) {
	// create context
	ctx, cancel2 := chromedp.NewContext(allocatorContext)
	defer cancel2()

	ctx, cancel3 := context.WithTimeout(ctx, 300*time.Second)
	defer cancel3()

	ctx, cancel4 := context.WithDeadline(ctx, time.Now().Add(300*time.Second))
	defer cancel4()

	var buf []byte
	if err := chromedp.Run(ctx, fullScreenshot(`https://brank.as/`, 90, &buf)); err != nil {
		fmt.Println("idx:", i, "failed run")
		fmt.Println(err)

		err := chromedp.Cancel(ctx)
		if err != nil {
			fmt.Println("Cancel", err)
		}
		return
	}
	if err := ioutil.WriteFile(fmt.Sprintf("./tmp/%v_fullScreenshot.png", i), buf, 0o644); err != nil {
		fmt.Println(err)
	}

	err := chromedp.Cancel(ctx)
	if err != nil {
		fmt.Println("Cancel", err)
	}
}

var allocatorContext context.Context

func main() {
	ws, err := getChromeVersion("127.0.0.1:9222")
	if err != nil {
		fmt.Println(err)
		return
	}
	allocatorContexttmp, cancel1 := chromedp.NewRemoteAllocator(context.Background(), ws)
	defer cancel1()
	allocatorContext = allocatorContexttmp
	var wg sync.WaitGroup

	defer ants.Release()

	runTimes := 100
	p, _ := ants.NewPoolWithFunc(10, func(i interface{}) {
		myFunc(i)
		wg.Done()
	})
	defer p.Release()
	for i := 0; i < runTimes; i++ {
		wg.Add(1)
		_ = p.Invoke(int32(i))
	}
	wg.Wait()
	fmt.Printf("running goroutines: %d\n", p.Running())
}

运行结果

在tmp目录生成png截图文件