Java用正则表达式如何读取网页内容

学习java的正则表达式，抓取网页并解析HTML部分内容  

package com.xiaofeng.picup;
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;

public class WebContent ...{
  
  public String getoneHtml(String htmlurl) throws IOException...{
    URL url;
    String temp;
    StringBuffer sb = new StringBuffer();
    try ...{
      url = new URL(htmlurl);
      BufferedReader in = new BufferedReader(new InputStreamReader(url
   .openStream(), "utf-8"));// 读取网页全部内容
      while ((temp = in.readLine()) != null) ...{
 sb.append(temp);
      }
      in.close();
    }catch(MalformedURLException me)...{
      System.out.println("你输入的URL格式有问题！请仔细输入");
      me.getMessage();
      throw me;
    }catch (IOException e) ...{
      e.printStackTrace();
      throw e;
    }
    return sb.toString();
  }
  
  public String getTitle(String s) ...{
    String regex;
    String title = "";
    List list = new ArrayList();
    regex = "";
    Pattern pa = Pattern.compile(regex, Pattern.CANON_EQ);
    Matcher ma = pa.matcher(s);
    while (ma.find()) ...{
      list.add(ma.group());
    }
    for (int i = 0; i < list.size(); i++) ...{
      title = title + list.get(i);
    }
    return outTag(title);
  }
  
  public List getlink(String s) ...{
    String regex;
    List list = new ArrayList();
    regex = "]*href=("([^"]*)"|'([^']*)'|([^s>]*))[^>]*>(.*?)";
    Pattern pa = Pattern.compile(regex, Pattern.DOTALL);
    Matcher ma = pa.matcher(s);
    while (ma.find()) ...{
      list.add(ma.group());
    }
    return list;
  }
  
  public List getscript(String s) ...{
    String regex;
    List list = new ArrayList();
    regex = "";
    Pattern pa = Pattern.compile(regex, Pattern.DOTALL);
    Matcher ma = pa.matcher(s);
    while (ma.find()) ...{
      list.add(ma.group());
    }
    return list;
  }
  
  public List getCSS(String s) ...{
    String regex;
    List list = new ArrayList();
    regex = "";
    Pattern pa = Pattern.compile(regex, Pattern.DOTALL);
    Matcher ma = pa.matcher(s);
    while (ma.find()) ...{
      list.add(ma.group());
    }
    return list;
  }
  
  public String outTag(String s) ...{
    return s.replaceAll("<.*?>", "");
  }