正则表达式提取URL

package com.url;

import java.io.IOException;
import java.io.InputStream;
import java.net.URL;
import java.net.URLConnection;
import java.util.regex.Matcher;
import java.util.regex.Pattern;

public class Urlconnection {

private static Pattern pattern = null;
private static Matcher matcher = null;
private static Pattern pattern1 = null;
private static Matcher matcher1 = null;
private static String regulation = "<\\s*a\\s*.*\\s*>.*<\\s*/\\s*a\\s*>|<\\s*a\\s*.*/\\s*>" ;
private static String regulation1="\\bhref\\s*=\\s*(['\"])(.*?)\\1(\\s+|>)";
//\\bhref\\s*=\\s*(['])(.*?)\\1\\b

public static void main(String[] args) throws IOException {
URL url = new URL("http://www.baidu.com/");
URLConnection conn = url.openConnection() ;
InputStream input = conn.getInputStream();
String charater = conn.getContentEncoding();
if(null == charater){
charater = "GBK";
}
byte[] bytes = new byte[4096];
int leng=-1 ;
StringBuffer sb = new StringBuffer("");
pattern = Pattern.compile(regulation,Pattern.CASE_INSENSITIVE|Pattern.MULTILINE|Pattern.DOTALL);
pattern1 = Pattern.compile(regulation1,Pattern.CASE_INSENSITIVE|Pattern.MULTILINE|Pattern.DOTALL);
while((leng=input.read(bytes))!=-1){
sb.append(new String(bytes,charater)) ;
matcher = pattern.matcher(sb.toString());
while(matcher.find()){
// System.out.println(matcher.group());
String str = matcher.group() ;
// str = str.replaceAll("\"", "'");
matcher1 = pattern1.matcher(str);
while(matcher1.find()){
System.out.println(matcher1.group(2));
}
}
sb.delete(0, sb.length());
}



}
}

转载于:https://www.cnblogs.com/xinzhuangzi/archive/2012/05/01/4100397.html

评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值