golang爬虫登录

www.changtu.com

实现登录页面的抓取，http请求登录，下面直接贴代码：

package main

import (
	"fmt"
	"io/ioutil"
	"net/http"
	"regexp"

)

type MySpider struct {
	indexUrl string
}

//实现GET请求函数
func (this MySpider) readUrlBody() (string, error) {
	resp, err := http.Get(this.indexUrl)
	if err != nil {
		return "err", err
	}
	defer resp.Body.Close()
	body, err := ioutil.ReadAll(resp.Body)
	if err != nil {
		return "err", err
	}
	return string(body), err
}

//抓取登录的域名地址
func (this MySpider) catchCategoryUrl() []string {
	body, _ := this.readUrlBody()
	rcg := regexp.MustCompile(`class="catalog_sec_btn clearfix mgt15">(?sU:.*)(?sU:.*)(.*?)(?sU:.*)
`)
		result1 := rcg1.FindAllStringSubmatch(body1, -1)
		for i := range result1 {
			line1 := result1[i]
			fmt.Println("<<======>>", line1[1])
		}
		//		fmt.Println(result1)
		return ""
	}
	//	fmt.Println(string(body))
	fmt.Println("<<======>>登录失败")
	return ""
}

//验证目前是否处于未登录状态
func (this MySpider) catchLoginInfo() string {
	body, _ := this.readUrlBody()
	rcg := regexp.MustCompile(`
(?sU:.*)
(.*?)
(?sU:.*)
`)
	result := rcg.FindAllStringSubmatch(body, -1)
	//	fmt.Println("body=", body)
	for i := range result {
		line := result[i]
		fmt.Println("<<======>>", line[1])
	}
	return ""
}

func (this MySpider) run() string {
	cateUrls := this.catchCategoryUrl()
	for _, u := range cateUrls {
		this.indexUrl = u
		this.catchLoginInfo()
		this.getData()
		break
	}
	return ""
}
func main() {
	ms := new(MySpider)
	ms.indexUrl = "https://www.changtu.com"
	ms.run()
}