java正则表达式匹配网页所有网址和链接文字的示例

import java.io.bufferedreader;
import java.io.ioexception;
import java.io.inputstreamreader;
import java.net.malformedurlexception;
import java.net.url;
import java.util.arraylist;
import java.util.hashmap;
import java.util.list;
import java.util.regex.matcher;
import java.util.regex.pattern;

import java.net.*;
import java.io.*;
import java.util.regex.*;

/*
根据指定的规则，通过构造正则表达式获取网址
*/

public class urls
{
    private string starturl;                                         //开始采集网址
    string  urlcontent;
    string contentarea;
    private string strareabegin ,strareaend ;            //采集区域开始采集字符串和结束采集字符串
    private string stringinurl,stringnotinurl;       
    string strcontent;//获得的采集内容
    string[] allurls;                                                            //采集到的所有网址
    private string  regex;                                                 //采集规则

    urlandtitle   urlandtitle=new urlandtitle();    //存储网址和标题                   

   
    public static void main(string[] args)
    {
         urls myurl=new urls("<body","/body>");
         myurl.getstarturl("http://www.zuzwn.com/");
         myurl.geturlcontent();
         myurl.getcontentarea();
         myurl.getstarturl("http://www.zuzwn.com/");
         myurl.getstringnotinurl("google");
         myurl.urls();

        //system.out.println("starturl:"+myurl.starturl);
        //system.out.println("urlcontent:"+myurl.urlcontent);
        //system.out.println("contentarea:"+myurl.contentarea);

    }

   
    //初始化构造函数 strareabegin 和strareaend

    public urls (string strareabegin,string strareaend)
    {
        this.strareabegin=strareabegin;
        this.strareaend=strareaend;
  }

  //
    public void urls()
    {
        int i=0;
        //string regex ="<a href="?'?http://[a-za-z0-9]+/.[a-za-z0-9]+/.[a-za-z]+/?[/.?[/s|/s]]+[a>]$";
        string regex ="<a.*?/a>";
         //string regex ="http://.*?>";
        pattern pt=pattern.compile(regex);
        matcher mt=pt.matcher(contentarea);
        while(mt.find())
         {
                 system.out.println(mt.group());
                 i++;

                 //获取标题
                 matcher title=pattern.compile(">.*?</a>").matcher(mt.group());
                 while(title.find())
                 {
                      system.out.println("标题:"+title.group().replaceall(">|</a>",""));
                 }

                 //获取网址
                 matcher myurl=pattern.compile("href=.*?>").matcher(mt.group());
                 while(myurl.find())
                 {
                      system.out.println("网址:"+myurl.group().replaceall("href=|>",""));
                 }

                 system.out.println();

                
         }

        system.out.println("共有"+i+"个符合结果");

    }   

    //获得开始采集网址
    public void getstarturl(string starturl)
    {
        this.starturl=starturl;
    }

    //获得网址所在内容;
    public void geturlcontent()
    {

        stringbuffer is=new stringbuffer();
        try
        {
            url myurl=new url(starturl);
            bufferedreader br= new bufferedreader(
                                                        new inputstreamreader(myurl.openstream()));

            string s;                                               
            while((s=br.readline())!=null)
            {
                is.append(s);
            }                                           
            urlcontent=is.tostring();
        }
    catch(exception e)

    {
        system.out.println("网址文件未能输出");
        e.printstacktrace();
    }

       
    }

   
    //获得网址所在的匹配区域部分
    public void getcontentarea()
    {
         int pos1=0,pos2=0;
         pos1= urlcontent.indexof(strareabegin)+strareabegin.length();
         pos2=urlcontent.indexof(strareaend,pos1);
         contentarea=urlcontent.substring(pos1,pos2);
    }

    //以下两个函数获得网址应该要包含的关键字及不能包含的关键字
    //这里只做初步的实验。后期，保护的关键字及不能包含的关键字应该是不只一个的。
    public void getstringinurl(string stringinurl)
    {
         this.stringinurl=stringinurl;       

    }

    public void getstringnotinurl(string stringnotinurl)
    {
        this.stringnotinurl=stringnotinurl;
    }

    //获取采集规则

    //获取url网址
    public void geturl()
    {

    }

    public string getregex()
    {
        return regex;

    }

    class urlandtitle
    {
        string myurl;
        string title;
    }
}