JSP远程采集原理

<%@ page language="java" pageEncoding="UTF-8"%>
<%@ page import="java.io.*,java.net.URL"%>
<%
URL url = new URL("http://www.itpub.net");//建立URL对象，并实例化为url，获得要抓取的网页地址
BufferedReader reader = new BufferedReader(new InputStreamReader(url.openStream(),"GB2312"));//建立BufferedReader对象，并实例化为reader，这里的GB2312是要抓取的网页编码格式
while(reader.ready())
{
  out.println(reader.readLine());
}
reader.close();
%>

  public static String matcherStr(String str, String cp, String s){
        if(str==null || str.equals("")){
            return "";
        }
        String txt = new String();
        txt = str;
        if(str!=null && !str.equals("")){
            txt = str;
            Pattern p = Pattern.compile(cp,2); //参数2表示大小写不区分
            Matcher m = p.matcher(txt);
            StringBuffer sb = new StringBuffer();
            int i=0;
            boolean result = m.find();
            //使用循环将句子里所有匹配的内容找出并替换再将内容加到sb里
            while(result) {
                i++;
                sb.append(m.group());
                sb.append(s);
                //继续查找下一个匹配对象
                result = m.find();
            }
            txt = String.valueOf(sb);
        }else{
            txt = "";
        }
        return txt;      
    }