package com.free.html.util;
import java.io.*;
import java.net.*;
public class ReadHtml {
/**
* @param args
*/
public static void main(String[] args) {
// TODO Auto-generated method stub
// readJSP("http://www.yz91.net/zpxx.asp");
readHtml("http://www.yz91.net/zpxx.asp","gb2312");
// getStaticPage("http://www.yz91.net/zpxx.asp","gb2312");
}
public static void readHtml(String utl,String bm ){
try {
URL url=new URL(utl);
HttpURLConnection con=(java.net.HttpURLConnection)url.openConnection();
con.connect();
BufferedReader br=new BufferedReader(new InputStreamReader(con.getInputStream(),bm));
FileOutputStream fos =new FileOutputStream("D:\\My Documents\\word.txt");
OutputStreamWriter osw =new OutputStreamWriter(fos,"utf-8");
BufferedWriter bw=new BufferedWriter(osw);
int a;
StringBuilder temp = new StringBuilder();
while((a=br.read())!=-1){
System.out.println(br.readLine()); //这里后台输出。。。信息后面再代码后面给出 有点问题
bw.write(br.readLine());
bw.flush(); //这里写到txt里 总是少第一个<html>
// temp.append((char)a);
// bw.write(temp);
// System.out.println(temp.toString()); 这里后台输出正常
}
br.close();
bw.close();
con.disconnect();
} catch (IOException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
}
}
[color=red]问题1.[/color]使用System.out.println(br.readLine()); 后台输出的问题:
html>
head>
meta http-equiv="Content-Type" content="text/html; charset=gb2312" />
title>详见扬州人力资源网(www.yz91.net) ,扬州数字电视“扬州就业”栏目</title>
/head>
body>
table width="100%" border="1" align="center" cellpadding="0" cellspacing="0">
<tr >
<td >单位名称</td>
<td >岗位</td>
<td align="center">年龄</td>
<td align="center">男</td>
<td align="center">女</td>
<td align="center">不限</td>
<td align="center">文化程度</td>
<td >待遇</td>
<td >联系人</td>
<td >联系电话</td>
</tr>
tr>
td width="30%">扬州统一机械有限公司</td>
<td >技术员</td>
<td >18-50</td>
<td >1</td>
<td >0</td>
<td >0</td>
<td >大专</td>
<td >930+</td>
<td >桑耿娟</td>
<td >0514-85550686 13064889698</td>
/tr>
//.....类似
tr>
td width="30%">扬州青青环保成套设备有限公司</td>
<td >文员</td>
<td >18-50</td>
<td >0</td>
<td >5</td>
<td >0</td>
<td >大专</td>
<td >930+</td>
<td ></td>
<td ></td>
/tr>
/table>
/body>
/html>
大概问题就是 少左尖括号。
[color=red]问题2.[/color]把流写入txt后总少头上<html>这一个标签,不管是用bw.write(br.readLine());还是用 bw.write((char)a);
求教大大们了 :cry: :cry: :cry: