Golang爬虫框架 colly的使用

go get -u github.com/gocolly/colly

package main

import (
	"fmt"
	"github.com/gocolly/colly"
)

func main() {
	c := colly.NewCollector()

	// goquery selector class
	c.OnHTML(".sidebar_link", func(e *colly.HTMLElement) {
		e.Request.Visit(e.Attr("href"))
/*		link := e.Attr("href")
		// Print link
		fmt.Printf("Link found: %q -> %s\n", e.Text, link)
		// Visit link found on page
		// Only those links are visited which are in AllowedDomains
		c.Visit(e.Request.AbsoluteURL(link))*/
	})

	c.OnRequest(func(r *colly.Request) {
		fmt.Println("url：",r.URL)
	})
	c.Visit("https://gorm.io/zh_CN/docs/")

}

func collback()  {  // 添加回调 收集器
	c:= colly.NewCollector()
	c.OnRequest(func(r *colly.Request) {
		fmt.Println("请求前调用:OnRequest")
		// fmt.Println("Visiting", r.URL)
	})

	c.OnError(func(_ *colly.Response, err error) {
		fmt.Println("发生错误调用:OnReOnError")
		//log.Println("Something went wrong:", err)
	})

/*	c.OnResponseHeaders(func(r *colly.Response) {  //高版本已经不用了
		fmt.Println("Visited", r.Request.URL)
	})
*/
	c.OnResponse(func(r *colly.Response) {
		fmt.Println("获得响应后调用:OnResponse")
		//fmt.Println("Visited", r.Request.URL)
	})

	c.OnHTML("a[href]", func(e *colly.HTMLElement) {
		fmt.Println("OnResponse收到html内容后调用:OnHTML")
		//e.Request.Visit(e.Attr("href"))
	})

/*	c.OnHTML("tr td:nth-of-type(1)", func(e *colly.HTMLElement) {
		fmt.Println("First column of a table row:", e.Text)
	})*/

	c.OnXML("//h1", func(e *colly.XMLElement) {
		fmt.Println("OnResponse收到xml内容后调用:OnXML")
		//fmt.Println(e.Text)
	})

	c.OnScraped(func(r *colly.Response) {
		fmt.Println("结束", r.Request.URL)
	})
	c.Visit("https://gorm.io/zh_CN/docs/")

}

//设置UserAgent的两种方式：

/*	//方式一 :
    c2 := colly.NewCollector()
	c2.UserAgent = "xy"
	c2.AllowURLRevisit = true*/

/*  //方式二 :
	c2 := colly.NewCollector(
		colly.UserAgent("xy"),
		colly.AllowURLRevisit(),
	)*/

	//设置cookie的两种方式
	//方式一：通过手动网页添加cookies
	c.OnRequest(func(r *colly.Request) {
		r.Headers.Add("cookie","_ga=GA1.2.1611472128.1650815524; _gid=GA1.2.2080811677.1652022429; __atuvc=2|17,0|18,5|19")
	})
	// 方式二 :通过url 添加cookies
	siteCookie := c.Cookies("url")
	c.SetCookies("",siteCookie)

c := colly.NewCollector()
c.WithTransport(&http.Transport{
	Proxy: http.ProxyFromEnvironment,
	DialContext: (&net.Dialer{
		Timeout:   30 * time.Second,
		KeepAlive: 30 * time.Second,
		DualStack: true,
	}).DialContext,
	MaxIdleConns:          100,
	IdleConnTimeout:       90 * time.Second,
	TLSHandshakeTimeout:   10 * time.Second,
	ExpectContinueTimeout: 1 * time.Second,
}

	c.OnHTML("a[href]", func(e *colly.HTMLElement) {
        fmt.Printf("e.Name:%v\n",e.Name)
		e.Request.Visit(e.Attr("href"))
	})




func html()  {
	c:= colly.NewCollector()
	c.OnHTML("#sidebar", func(e *colly.HTMLElement) {
		//fmt.Printf("e.Name:%v\n",e.Name) //名字
		//fmt.Printf("e.Text:%v\n",e.Text) //文本

		ret, _ := e.DOM.Html() // selector 选择器
		fmt.Printf("ret:%v\n",ret)
	})
	c.OnRequest(func(r *colly.Request) {
		fmt.Println("url：",r.URL)
	})
	c.Visit("https://gorm.io/zh_CN/docs/")
}

package main

import (
	"fmt"
	"github.com/gocolly/colly"
)

func main()  {
	c:= colly.NewCollector()
	c.OnHTML(".sidebar_link", func(e *colly.HTMLElement) {  // 左侧链接

		href := e.Attr("href")
		if href != "index.html"{
			c.Visit(e.Request.AbsoluteURL(href))
		}
	})
	c.OnHTML(".article-title", func(h *colly.HTMLElement) {  // 选择链接之后的标题
		title := h.Text
		fmt.Printf("title: %v\n",title)
	})
	c.OnHTML(".article", func(h *colly.HTMLElement) {  //内容
		content, _ := h.DOM.Html()
		fmt.Printf("content: %v\n",content)
	})
	c.OnRequest(func(r *colly.Request) {
		fmt.Println("url：",r.URL.String())
	})
	c.Visit("https://gorm.io/zh_CN/docs/")
}