java爬虫，无限下一页无限下载图片jsoup实现

java爬虫，无限下一页无限下载图片jsoup实现

package com.test;

import java.io.ByteArrayOutputStream;
import java.io.File;
import java.io.FileOutputStream;
import java.io.IOException;
import java.io.InputStream;
import java.net.HttpURLConnection;
import java.net.URL;
import java.util.ArrayList;
import java.util.List;
import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.select.Elements;


//爬瑟瑟
public class ReptileTest {
    //定义路径
    static String baseurl = "https://www.4kbizhi.com/";
    static String geturl = "https://www.4kbizhi.com/";
    static String filepath = "C:\\Users\\Administrator\\Desktop\\新建文件\\";

    public static void main(String[] args) {
        System.out.println("初始下载页面："+baseurl);
        String html = getHtml(baseurl); //html页面内容
        List<String> srclists = getImgSrcListFromHtml(html); //图片地址集合
        downloadImg(srclists, filepath); //下载图片
        do{
            String htmlnext = getHtml(geturl);//下一页的网页内容
            //获取下一个页面进行下载
            String next = nextpage(htmlnext);
            if (next==null){
                break;
            }
            System.out.println("下一个下载页面："+next);
            String html2 = getHtml(next); //html页面内容
            List<String> srclists2 = getImgSrcListFromHtml(html2); //图片地址集合
            downloadImg(srclists2, filepath); //下载图片
        }while (true);
        System.out.println("下载完毕");
    }
    
    //动态下一页
    public static String nextpage(String html){
        String next=null;
        //解析成html页面
        Document document = Jsoup.parse(html);
        //获取目标
        Elements elements = document.select(".next");
        //System.out.println("测试elements："+elements);
        if (elements.get(elements.size()-1).attr("href")!=null) {
            next = baseurl + elements.get(elements.size() - 1).attr("href");
            System.out.println("测试next:"+next);
        }
        geturl=next;
        System.out.println("测试geturl："+geturl);
        return next;
    }

    /**
     *
     * @Title: getImgSrcListFromHtml
     * @Description: 获取页面内容图片路径
     * @param @param html  页面内容
     * @param @return    图片路径数组
     * @return ArrayList<String>    返回类型
     * @throws
     */
    public static List<String> getImgSrcListFromHtml(String html){
        List<String> list = new ArrayList<>();
        //解析成html页面
        Document document = Jsoup.parse(html);
        //获取目标
        Elements elements = document.select("ul[class=item] > li > a").select("img");
        //System.out.println("测试elements："+elements);
        int len = elements.size();
        for (int i = 0; i < len; i++) {
            list.add(baseurl+elements.get(i).attr("src"));
            //System.out.println("测试list："+list);
        }
        return list;
    }

    /**
     *
     * @Title: getHtml
     * @Description: 获取页面内容
     * @param @param url
     * @param @return  页面内容
     * @return String  返回类型
     * @throws
     */
    public static String getHtml(String url){
        String html = "";
        try {
            html = Jsoup.connect(url).execute().body();
        } catch (IOException e) {
            e.printStackTrace();
        }
        return html;
    }

    /**
     *
     * @Title: downloadImg
     * @Description: 下载图片 -- 通过获取的流转成byte[]数组，再通过FileOutputStream写出
     * @param @param list 图片路径数组
     * @param @param filepath  保存文件夹位置
     * @return void    返回类型
     * @throws
     */
    public static void downloadImg(List<String> list, String filepath){
        String myfilepath;
        URL newUrl = null;
        HttpURLConnection hconnection = null;
        InputStream inputStream = null;
        FileOutputStream fileOutputStream = null;
        byte[] bs = null;
        try {
            int len = list.size();
            for (int i = 0; i < len; i++) {
                newUrl = new URL(list.get(i));
                hconnection = (HttpURLConnection) newUrl.openConnection(); //打开连接
                inputStream = hconnection.getInputStream();  //获取流
                bs = getBytesFromInputStream(inputStream); //流转btye[]
                myfilepath = filepath + list.get(i).substring(list.get(i).lastIndexOf("/")+1); //获取图片名称
                System.out.println("生成图片路径:"+myfilepath);
                fileOutputStream = new FileOutputStream(new File(myfilepath));
                fileOutputStream.write(bs); //写出
            }
        } catch (Exception e) {
            e.printStackTrace();
        } finally {
            try {
                inputStream.close();
                fileOutputStream.close();
            } catch (IOException e) {
                e.printStackTrace();
            }
        }
    }

    /**
     *
     * @Title: getBytesFromInputStream
     * @Description: InputStream流转换byte[]
     * @param @param inputStream
     * @param @return    byte[]
     * @return byte[]    返回类型
     * @throws
     */
    public static byte[] getBytesFromInputStream(InputStream inputStream){
        byte[] bs = null;
        try {
            byte[] buffer = new byte[1024];
            int len = 0;
            ByteArrayOutputStream arrayOutputStream = new ByteArrayOutputStream();
            while((len = inputStream.read(buffer)) != -1){
                arrayOutputStream.write(buffer, 0 ,len);
            }
            bs = arrayOutputStream.toByteArray();
        } catch (IOException e) {
            e.printStackTrace();
        }
        return bs;
    }
}