copy网站上内容

package com.softeem.basic;

import java.io.*;
import java.net.URL;
import java.net.URLConnection;
import java.util.regex.Matcher;
import java.util.regex.Pattern;

public class Demo_02 {
    public static void saveImg(String imgPath) throws IOException {
        String dirPath = "d:\\img";
        String fileName = imgPath.substring(imgPath.lastIndexOf("/"));

        URL url = new URL(imgPath);
        URLConnection urlConnection = url.openConnection();

        InputStream is = urlConnection.getInputStream();
        String filePath = dirPath + fileName;
        FileOutputStream fos = new FileOutputStream(new File(filePath));
        //缓冲区
        byte[] arr = new byte[1024];
        int len = -1;
        //用来比较读取到的信息数是否为-1
        while ((len = is.read(arr)) != -1){
            //上面读取信息,下面写信息
            fos.write(arr,0,len);
        }
    }

    public static void main(String[] args) throws IOException {
        //加载要寻找元素的网址地址
        URL url = new URL(" ");//要copy的网站
        URLConnection urlConnection = url.openConnection();
        //输入流用来读取数据
        InputStream is = urlConnection.getInputStream();
        //把这个输入流伪装成一个高级
        BufferedReader br = new BufferedReader(new InputStreamReader(is,"gbk"));
        StringBuffer sb = new StringBuffer("");

        String msg = null;
        while ((msg = br.readLine()) != null){
            sb.append(msg);
        }

        Pattern p = Pattern.compile("[a-zA-z]+://[^\\s]*jpg");//模式，jpg格式的文件
        Matcher m = p.matcher(sb.toString());
        while (m.find()){
            String imgPath = m.group();
            saveImg(imgPath);
        }
        br.close();
        is.close();
    }


}