java href=的正则表达式_java正则表达式获取qq首页里所有超链接的href属性值

import java.io.BufferedReader;

import java.io.IOException;

import java.io.InputStreamReader;

import java.net.URL;

import java.nio.charset.Charset;

import java.util.regex.Matcher;

import java.util.regex.Pattern;

public class WebSpiderTest {

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

/*

* 获取单网页里所有超链接里的href属性值并打印到控制台

*/

URL url = new URL("http://www.qq.com");

StringBuilder sb = new StringBuilder();

BufferedReader  br = new BufferedReader(new InputStreamReader(url.openStream(),Charset.forName("gbk")));

String temp = "";

//    BufferedWriter bw = new BufferedWriter(new OutputStreamWriter(new FileOutputStream("E:/163.txt"),Charset.forName("gbk")));

while((temp=br.readLine() )!= null){

sb.append(temp);

sb.append("\n");

}

//[\\s\\s] 匹配所有字符

String regStr ="?";

Pattern p = Pattern.compile(regStr);

Matcher m = p.matcher(sb.toString());

while(m.find()){

System.out.println(m.group().replaceAll("\\s+", " "));//打印出匹配子序列[把多空格或者换号或者多tab替换成一个空格，便于查看]

System.out.println(m.group(1));//打印出匹配到的子序列里的捕获组，即是 (http[\\s\\S]+?) 这个捕获组匹配到的值，其实就是href属性的值

}

}

}