JAVA爬取网页邮箱

import java.io.BufferedReader;

import java.io.IOException;

import java.io.InputStream;

import java.io.InputStreamReader;

import java.net.HttpURLConnection;

import java.net.MalformedURLException;

import java.net.URL;

import java.net.URLConnection;

import java.util.regex.Matcher;

import java.util.regex.Pattern;

/**
 * 抓取邮箱
 * @author lsh
 *
 */
public class GetEmail {

    public static void main(String[] args) throws IOException {

         URL url = new URL("https://book.douban.com/subject/24753651/discussion/58975313/");

         HttpURLConnection conn = (HttpURLConnection) url.openConnection();

         InputStream is = conn.getInputStream();

         BufferedReader br = new BufferedReader(new InputStreamReader(is, "utf-8"));

         // 书写正则规则

         String regex = "\\w+@[0-9a-z]{2,8}\\.com";

         // 获得正则对象

         Pattern compile = Pattern.compile(regex);

         // line 始终代表网页中一行数据

         String line = br.readLine();

         while(line != null){

             // 正则对象和 要操作字符串关联  得到匹配引擎

             Matcher matcher = compile.matcher(line);

             while(matcher.find()){

                 System.out.println("邮箱 : "+matcher.group());

             }

             line = br.readLine();

         }

        }

}

 

转载于:https://www.cnblogs.com/itBulls/articles/9052773.html