Java正则表达式匹配获取链接地址 Java使用正则表达式匹配获取链接地址的方法示例

String content = "<a href="URL" rel="external nofollow" >";
String pattern= "href="([^" rel="external nofollow" ]*)"";
Pattern p = Pattern.compile(pattern, 2 | Pattern.DOTALL);
Matcher m = p.matcher(content);
if(m.find()) {
   System.out.println("url="+m.group(1));
}

package com.gong.example;
import Java.util.regex.Matcher;
import java.util.regex.Pattern;
public class Simple {
 public static void main(String[] args){
 String input="<a style=" " href = "//www.qb5200.com" target="_blank" >www.qb5200.com</a>" +
 "<a href = 'http://www.163.com' target='_blank' >www.163.com</a> " +
 "<a href=http://www.yahoo.com target=_blank >www.yahoo.com</a>";
 String patternString = "\s*(?i)href\s*=\s*("([^"]*")|'[^']*'|([^'">\s]+))"; //href
 Pattern pattern = Pattern.compile(patternString,
  Pattern.CASE_INSENSITIVE);
 Matcher matcher = pattern.matcher(input);
 while (matcher.find()) {
  String link=matcher.group();
  System.out.println(link);
  link=link.replaceAll("href\s*=\s*(['|"]*)", "");
  System.out.println("--"+link);
  link=link.replaceAll("['|"]", "");
  System.out.println("---"+link);
 }
 }
}

/*
   功能说明：分析字符串s，提取s里面的超链接和链接文字
*/
import java.util.regex.Matcher;
import java.util.regex.Pattern;
public class RegTest
{
  public static void main(String[] args)
  {
    //String s="<p id=km> <a href=http://down.yourweb.com>空间</a> | <a ";
    String s="</p><p style=height:14px><a href=http://mb.yourweb.com>企业推广</a> | <a href=http://code.yourweb.com>搜索风云榜</a> | <a href=/home.html>关于百度</a> | <a href=http://www.yourweb.com>About Baidu</a></p><p id=b>©2008 Baidu <a href=http://www.yourweb.com>使用百度前必读</a> <a href=http://www.miibeian.gov.cn target=_blank>京ICP证03xxxx号</a> <a href=//www.qb5200.com><img src=/get_pic/2013/11/22/20131122031447947.gif></a></p></center></body></html><!--543ff95f18f36b11-->";
     String regex="<a.*?/a>";
    //String regex = "<a.*>(.*)</a>";
    Pattern pt=Pattern.compile(regex);
    Matcher mt=pt.matcher(s);
    while(mt.find())
    {
       System.out.println(mt.group());
       System.out.println();
       String s2=">.*?</a>";//标题部分
       String s3="href=.*?>";
       Pattern pt2=Pattern.compile(s2);
       Matcher mt2=pt2.matcher(mt.group());
       while(mt2.find())
       {
        System.out.println("标题："+mt2.group().replaceAll(">|</a>",""));
       }
       Pattern pt3=Pattern.compile(s3);
       Matcher mt3=pt3.matcher(mt.group());
       while(mt3.find())
       {
        System.out.println("网址："+mt3.group().replaceAll("href=|>",""));
       }
    }
  }
}