zoukankan      html  css  js  c++  java
  • go 正则 爬取邮箱代码

    package main
    
    import (
    	"net/http"
    	"fmt"
    	"io/ioutil"
    	"regexp"
    )
    
    var url string = "https://tieba.baidu.com/p/5518324938?red_tag=1795043739"
    var reEmail = `(d+)@qq.com`
    func main()  {
    
    	resp, err := http.Get(url)
    	handError(err)
    
    	defer resp.Body.Close()
    
    	bytesContent, err := ioutil.ReadAll(resp.Body)
    
    	handError(err)
    
    	getEmail(string(bytesContent))
    
    }
    
    // 处理错误
    func handError(err error)  {
    	//fmt.Println(err)
    	if err != nil{
    		fmt.Println(err)
    	}
    
    }
    
    // 获取邮箱 qq邮箱 使用正则
    func getEmail(content string)  {
    	re := regexp.MustCompile(reEmail)
    	list := re.FindAllStringSubmatch(content, -1)
    
    	var result []string
    
    	for _,v := range list {
    		if v != nil{
    			result = append(result,v[0])
    		}
    
    	}
    	fmt.Println(result)
    
    }
    

      

    结果

    GOROOT=/usr/local/go #gosetup
    GOPATH=/www/gopath #gosetup
    /usr/local/go/bin/go build -i -o /private/var/folders/fc/4txmmczj6q92p6058h3w7t_80000gn/T/___go_build_main_go /www/gopath/src/wang/main.go #gosetup
    /private/var/folders/fc/4txmmczj6q92p6058h3w7t_80000gn/T/___go_build_main_go #gosetup
    [3304778804@qq.com 742948861@qq.com 1261766424@qq.com 2903927557@qq.com 973327005@qq.com 973327005@qq.com 51061804@qq.com 3154089413@qq.com 2501667505@qq.com 1733510262@qq.com 289207537@qq.com 11886843@qq.com 1069016912@qq.com 765730856@qq.com 643074575@qq.com 330256148@qq.com 2025643306@qq.com 1903987556@qq.com 136772698@qq.com 990242520@qq.com 876958445@qq.com 776283765@qq.com 184756372@qq.com 2580145919@qq.com 710830708@qq.com 459618331@qq.com 964974049@qq.com 1499820286@qq.com 1822036045@qq.com 29522755@qq.com 1903987556@qq.com 2444694413@qq.com]

    Process finished with exit code 0

    package main
    
    import (
    	"net/http"
    	"fmt"
    	"io/ioutil"
    	"regexp"
    )
    
    var url string = "https://tieba.baidu.com/p/5934645800"
    var reQQEmail = `(d+)@qq.com`
    var reEmail = `w+@w+.w+`
    func main()  {
    
    	content := getPageString(url)
    	res1 := getEmail(content,reEmail)
    	res2 := getEmail(content,reQQEmail)
    
    	fmt.Println("一共找到邮箱",len(res1))
    	fmt.Println("一共找到邮箱",len(res2))
    
    }
    
    // 处理错误
    func handError(err error)  {
    	//fmt.Println(err)
    	if err != nil{
    		fmt.Println(err)
    	}
    
    }
    
    // 获取邮箱 qq邮箱 使用正则
    func getEmail(content string,reg string) []string {
    	re := regexp.MustCompile(reg)
    	list := re.FindAllStringSubmatch(content, -1)
    
    	var result []string
    
    	for _,v := range list {
    		if v != nil{
    			result = append(result,v[0])
    		}
    
    	}
    	return result
    
    }
    
    func getPageString(url string)  string {
    	resp, err := http.Get(url)
    	handError(err)
    
    	defer resp.Body.Close()
    
    	bytesContent, err := ioutil.ReadAll(resp.Body)
    
    	handError(err)
    	return string(bytesContent)
    }
    

      

  • 相关阅读:
    关于地址添加 子窗体向父窗体传值 树的使用详细
    C# 常见面试题2
    微软2014实习生及秋令营技术类职位在线测试
    【面试题004】c/c++字符串,替换空格
    【面试题003】c数组做为参数退化的问题,二维数组中的查找
    【面试题001】类型转换关键字,空类对象模型,拷贝构造函数,赋值运算符函数
    【面试题002】java实现的单例模式,c++实现单例模式,实现禁止拷贝
    【设计模式6原则总结】
    【设计模式六大原则6】开闭原则(Open Close Principle)
    【设计模式六大原则5】迪米特法则(Law Of Demeter)
  • 原文地址:https://www.cnblogs.com/php-linux/p/13096577.html
Copyright © 2011-2022 走看看