java正则表达式解析html示例分享

package work;

import java.io.bufferedreader;
import java.io.ioexception;
import java.io.inputstream;
import java.io.inputstreamreader;
import java.util.regex.matcher;
import java.util.regex.pattern;

import org.apache.commons.httpclient.defaulthttpmethodretryhandler;
import org.apache.commons.httpclient.httpclient;
import org.apache.commons.httpclient.httpexception;
import org.apache.commons.httpclient.httpstatus;
import org.apache.commons.httpclient.methods.getmethod;
import org.apache.commons.httpclient.params.httpmethodparams;

public class chuanboyi {

 public static void main(string[] args){
  // todo auto-generated method stub
  stringbuffer html = new stringbuffer();
  httpclient httpclient = new httpclient();
  //创建get方法实例
  getmethod getmethod = new getmethod("//www.jb51.net");
  //使用系统提供的默认恢复策略
  getmethod.getparams().setparameter(httpmethodparams.retry_handler, new defaulthttpmethodretryhandler());
  try{
   //执行get方法
   int statuscode = httpclient.executemethod(getmethod);
   if(statuscode != httpstatus.sc_ok){
    system.out.println("method is wrong " + getmethod.getstatusline());
   }
   inputstream responsebody = getmethod.getresponsebodyasstream();
   bufferedreader reader = new bufferedreader(new inputstreamreader(responsebody,"utf-8"));
   string line = reader.readline();
   while(line != null){
    html.append(line).append("\n");
    line = reader.readline();
   }
   reader.close();
   //正则表达式
   string regex = "<form name=\"compareform\"[\\s\\s]+>[\\s\\s]+</form>.*<script.*>";
   string regexa ="(?<=<li>)[\\s\\s]+?(?=</li>)";
   pattern pattern = pattern.compile(regex);
         matcher m = pattern.matcher(html);
         stringbuffer str = new stringbuffer();
         int i = 0;
         while(m.find()){
          str.append(m.group());
         }
         pattern = pattern.compile(regexa);
         m = pattern.matcher(str);
         while(m.find()){
          attrs(m.group());
          i++;
         }
         system.out.println("共有"+i+"条数据！");
  }catch (httpexception e) {
   // todo: handle exception
   system.out.println("please check your provided http address!");
   e.printstacktrace();
  }catch (ioexception e) {
   // todo: handle exception
   system.out.println("the line is wrong!");
   e.printstacktrace();
  }finally{
   getmethod.releaseconnection();//释放链接
  }
 }
 public static void attrs(string str){

  //获取url的正则表达式
  string regexurl = "[a-z]+-[0-9]+\\.html";
  //获取name的正则表达式
  string regexname = "(?<=title=\")[[\\w-\\s][^x00-xff]]+(?=\")";
  //获取图片的正则表达式
  string regexpicture = "images.*\\.jpg";

  pattern patternurl = pattern.compile(regexurl);
  pattern patternname = pattern.compile(regexname);
  pattern patternpicture = pattern.compile(regexpicture);
  matcher murl = patternurl.matcher(str);
  matcher mname = patternname.matcher(str);
  matcher mpicture = patternpicture.matcher(str);
  if(mname.find()){
   system.out.println("名字:"+mname.group());
  }
  if(murl.find()){
   system.out.println("链接:"+murl.group());
  }
  if(mpicture.find()){
   system.out.println("图片:"+mpicture.group());
  }
 } 
}