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;
/** *//**
*
* @抓取页面文章标题及内容（测试） 手动输入网址抓取，可进一步自动抓取整个页面的全部内容
*
*/
public class webcontent ...{
  /** *//**
   * 读取一个网页全部内容
   */
  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();
  }
  /** *//**
   *
   * @param s
   * @return 获得网页标题
   */
  public string gettitle(string s) ...{
    string regex;
    string title = "";
    list<string> list = new arraylist<string>();
    regex = "<title>.*?</title>";
    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);
  }
  /** *//**
   *
   * @param s
   * @return 获得链接
   */
  public list<string> getlink(string s) ...{
    string regex;
    list<string> list = new arraylist<string>();
    regex = "<a[^>]*href=("([^"]*)"|'([^']*)'|([^s>]*))[^>]*>(.*?)</a>";
    pattern pa = pattern.compile(regex, pattern.dotall);
    matcher ma = pa.matcher(s);
    while (ma.find()) ...{
      list.add(ma.group());
    }
    return list;
  }
  /** *//**
   *
   * @param s
   * @return 获得脚本代码
   */
  public list<string> getscript(string s) ...{
    string regex;
    list<string> list = new arraylist<string>();
    regex = "<script.*?</script>";
    pattern pa = pattern.compile(regex, pattern.dotall);
    matcher ma = pa.matcher(s);
    while (ma.find()) ...{
      list.add(ma.group());
    }
    return list;
  }
  /** *//**
   *
   * @param s
   * @return 获得css
   */
  public list<string> getcss(string s) ...{
    string regex;
    list<string> list = new arraylist<string>();
    regex = "<style.*?</style>";
    pattern pa = pattern.compile(regex, pattern.dotall);
    matcher ma = pa.matcher(s);
    while (ma.find()) ...{
      list.add(ma.group());
    }
    return list;
  }
  /** *//**
   *
   * @param s
   * @return 去掉标记
   */
  public string outtag(string s) ...{
    return s.replaceall("<.*?>", "");
  }