java爬取网页上qq号，邮箱号等

标签：爬取   except   mail   main   htm   puts   汉字   cep   .com   

import java.io.BufferedReader;
import java.io.FileReader;
import java.io.InputStreamReader;
import java.net.URL;
import java.net.URLConnection;
import java.util.regex.Matcher;
import java.util.regex.Pattern;

public class GetMail {
public static void main(String[] args) throws Exception {
//getMails();
getMails_url();
}

public static void getMails_url() throws Exception {
URL url = new URL("https://wenku.baidu.com/view/ce81b0a1ddccda38366baf61.html");//这里就是要爬取的网页
URLConnection conn = url.openConnection();
BufferedReader bufr = new BufferedReader(new InputStreamReader(conn.getInputStream()));
String line = null;
String maileRes = "[\u4E00-\u9FA5]+";//这里存放需要设定的规则

//匹配邮箱："\\w+@\\w+(\\.\\w+)+"
//匹配汉字："[\u4E00-\u9FA5]+";
//匹配QQ号："[1-9][0-9]{4,14}"
//qq邮箱："(.)+@(.)+(\\.[a-z]+){1,}";
Pattern p = Pattern.compile(maileRes);


while((line=bufr.readLine())!=null) {
Matcher m = p.matcher(line);
while(m.find()) {
System.out.println(m.group());
}

}
}

java爬取网页上qq号，邮箱号等

标签：爬取   except   mail   main   htm   puts   汉字   cep   .com   

原文地址：https://www.cnblogs.com/zxwm/p/9235960.html