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:
    传递闭包+求概率——列项相消法lightoj1321好题
    TSP+期望——lightoj1287记忆化搜索,好题!
    高斯消元+期望dp——light1151
    异或前缀和,组合数学——cf1054D
    数论GCD——cf1055C
    字符串哈希——1056E
    区间dp——cf1025D二叉搜索树的中序遍历好题!
    集合划分——cf1028D思维题
    线性dp——求01串最大连续个数不超过k的方案数,cf1027E 好题!
    java_and_tomcat_set_environment
  • 原文地址:https://www.cnblogs.com/php-linux/p/13096577.html
Copyright © 2011-2022 走看看