通过URL对象获取指定网页的内容

Code:

import java.net.URL;

import java.net.URLConnection;

import java.io.*;

import java.util.Date;

import java.util.Scanner;



public class Test {

public static void main(String[] args) {

ReadHtml rh = new ReadHtml();

rh.getWebPage();

rh.displayAll();

}

}



class ReadHtml {

private URL u;

private URLConnection uc;

String addr = new String(); //用来存放网址

Scanner sc = new Scanner(System.in); //用来输入网址

File f = new File("webpage.html"); //创建一个存放网页的文件

InputStreamReader in; //创建一个文件输入流

OutputStreamWriter out; //创建一个文件输出流

char[] buf = new char[1024]; //每次读写1k内容

public ReadHtml() {

try {

System.out.println("请输入文件的URL地址：");

addr = sc.nextLine();

u = new URL(addr); //定义URL对象

uc = u.openConnection(); //获得一个URLConnection对象

uc.connect(); //连接

in = new InputStreamReader(uc.getInputStream());

out = new OutputStreamWriter(new FileOutputStream(f));

} catch(IOException e) {

e.printStackTrace();

}

}

public void getWebPage() {

try {

while(in.read(buf, 0, buf.length) > 0) {

out.write(buf, 0, buf.length);

}

in.close();

out.close(); //关闭流

} catch(IOException e) {

e.printStackTrace();

}

}

//打印所有信息

public void displayAll() {

System.out.println("内容类型: "+uc.getContentType());

System.out.println("内容编码: "+uc.getContentEncoding());

System.out.println("内容长度: "+uc.getContentLength());

System.out.println("创建日期: "+new Date(uc.getDate()));

System.out.println("最后修改日期: "+new Date(uc.getLastModified()));

System.out.println("终止日期: "+new Date(uc.getExpiration()));

}

}

studying