Java爬虫（httpClient+Jsoup）爬取彼岸桌面壁纸简单实例

java爬虫（httpClient+Jsoup）爬取高清大图简单实例

爬取的网站：
http://www.netbian.com/

import org.apache.commons.io.FileUtils;
import org.apache.http.HttpEntity;
import org.apache.http.client.ClientProtocolException;
import org.apache.http.client.methods.CloseableHttpResponse;
import org.apache.http.client.methods.HttpGet;
import org.apache.http.impl.client.CloseableHttpClient;
import org.apache.http.impl.client.HttpClients;
import org.apache.http.util.EntityUtils;
import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import org.jsoup.select.Elements;



import java.util.Scanner;
import java.io.File;
import java.io.IOException;
import java.io.InputStream;

public class Main {
    static int sum = 0;

    public static void main(String[] args) throws ClientProtocolException, IOException, InterruptedException {
    	int ch = 0;//初始化
    	int page=1;
    	boolean selectAll=false;//判断用下载全部的真假情况
        String flage = null;
   while(true){
	  
    	String[] arry= {"rili","dongman","fengjing","meinv","youxi","yingshi","dongtai","weimei","sheji","keai","qiche","huahui","dongwu"
    			
    	    ,"jieri","renwu","meishi","shuiguo","jianzhu","tiyou","junshi","feizhuliu","qita","s/wangzherongyao" ,"s/huyan" ,"s/lol" };
    	
    	System.out.println("彼岸桌面壁纸\n壁纸预览请打开网址http://www.netbian.com/\n壁纸的大小为1920*1080\n请选择你要下载的壁纸类型\t\n1.日历壁纸  2.动漫壁纸  3.风景壁纸  4.美女壁纸  5.游戏"
    			+ "\n6.影视        7.动态  8.唯美壁纸  9.设计  10.可爱壁纸 "
    			+ "\n11.汽车壁纸   12.花卉  13.动物  14.节日  15.人物 \n16.美食     17.水果  18.建筑  19.体育  20.军事 \n21.非主流    22.其它  23.王者荣耀  24.护眼  25.LOL"
    			+ "\n26.下载以上全部类型\n0.退出");
    Scanner in = new Scanner(System.in);
        if(selectAll==false) //如果选择下载全部类型为 假
            ch=in.nextInt();//让用户自己选择下载什么类型
        if(ch==26) {//如果选择26.下载全部类型
        	selectAll=true;//选择全部为 真
        	ch=0;//并赋值为0；
        }
        if(selectAll==true)//选择下载全部类型为 真
        	ch++;//ch自动加1，达到自动下载全部,
    	switch(ch) {//执行选择
    	case 1:flage = arry[ch-1];break;
    	case 2:flage = arry[ch-1];break;
    	case 3:flage = arry[ch-1];break;
    	case 4:flage = arry[ch-1];break;
    	case 5:flage = arry[ch-1];break;
    	case 6:flage = arry[ch-1];break;
    	case 7:flage = arry[ch-1];break;
    	case 8:flage = arry[ch-1];break;
    	case 9:flage = arry[ch-1];break;
    	case 10:flage = arry[ch-1];break;
    	case 11:flage = arry[ch-1];break;
    	case 12:flage = arry[ch-1];break;
    	case 13:flage = arry[ch-1];break;
    	case 14:flage = arry[ch-1];break;
    	case 15:flage = arry[ch-1];break;
    	case 16:flage = arry[ch-1];break;
    	case 17:flage = arry[ch-1];break;
    	case 18:flage = arry[ch-1];break;
    	case 19:flage = arry[ch-1];break;
    	case 20:flage = arry[ch-1];break;
    	case 21:flage = arry[ch-1];break;
    	case 22:flage = arry[ch-1];break;
    	case 23:flage = arry[ch-1];break;
    	case 24:flage = arry[ch-1];break;
    	case 25:flage = arry[ch-1];break;
    	default: System.exit(0);
    	
    	}
    	try {
    		downLoadPicture(page, flage);
    		
		} catch (Exception e) {
			// TODO: handle exception
			 System.out.println("感谢你的使用！总共为你下载了" + sum + "张图;目录在C:/爬虫图片/"+flage+"/");
	          System.out.println("下载完毕,返回主菜单！");          
	          in=new Scanner(System.in);
		}
    	}
        
    }

    

	public static void downLoadPicture(int page, String flage) throws ClientProtocolException, IOException, InterruptedException {
        // 创建一个链接
        CloseableHttpClient httpClient = HttpClients.createDefault();
        // 利用链接发送请求index_2.htm
        String adress;
        
        
        if (page == 1)
            adress = "http://www.netbian.com/"+flage+"/index.htm";
        else
            adress = "http://www.netbian.com/"+flage+"/index_" + page + ".htm";
        HttpGet httpGet = new HttpGet(adress);
        // 接收回应
        CloseableHttpResponse httpResponse = httpClient.execute(httpGet);
        // 获取响应解析工具httpEntity
        HttpEntity httpEntity = httpResponse.getEntity();
        // content响应内容（网页源代码），并解决中文乱码用UTF-8
        String content = EntityUtils.toString(httpEntity, "UTF-8");
        // 现在得到了网页源代码，而图片就在源代码中
        // 拿到了脏数据----要清洗--像洗菜一样---
        // Jsoup解析器
        Document document = Jsoup.parse(content);
        // elements标签下的内容                                             //直接从浏览器复制过来
        Elements elements = document.select("div.wrap.clearfix #main div.list  ul  li  a ");// 选择，元素，标签
        int i = 0;                     //如果类名有空格继续用.链接
      
            // 进一步清洗
            for (i = 0; i < 21; i++) {// 观察到一个有略缩图的网页一共有30张
                Element element = elements.get(i);
                // 拿到高清图的链接，这个链接在 href 标签里面，attr接收到高清图链接
                String attr = element.attr("href");
                if (attr.equals("https://pic.netbian.com/"))
                    continue;
                // 重复上面的步骤 //创建一个链接
                CloseableHttpClient httpClient2 = HttpClients.createDefault();
                // 利用高清图链接发送请求
                HttpGet httpGet2 = new HttpGet("http://www.netbian.com" + attr + "");
                // 接收回应
                CloseableHttpResponse httpResponse2 = httpClient2.execute(httpGet2);
                // 获取响应解析工具httpEntity
                HttpEntity httpEntity2 = httpResponse2.getEntity();
                // content响应内容（网页源代码），并解决中文乱码用UTF-8
                String content2 = EntityUtils.toString(httpEntity2, "UTF-8");
                // Jsoup解析器                    再进一步的清洗
                Document document2 = Jsoup.parse(content2);//直接从浏览器复制过来
                Elements elements2 = document2.select("div.endpage div.pic p a img");// 选择，元素，标签
                // System.out.println( elements2);
                Element element2 = elements2.get(0);
                // src有图片的地址，得到了高清图片的地址src.....
                String attr3 = element2.attr("src");
                // 利用高清图地址发送请求
                HttpGet httpGet3 = new HttpGet(attr3);
                // 执行下载该高清原图
                CloseableHttpResponse httpResponse3 = httpClient.execute(httpGet3);
                HttpEntity httpEntity3 = httpResponse3.getEntity();
                //流入本地文件夹
                InputStream stream = httpEntity3.getContent();
                FileUtils.copyInputStreamToFile(stream, new File("C://爬虫图片//"+flage+"//" + page + "-" + i + ".png"));
                sum++;
                //Thread.sleep(1000);
                System.out.println("恭喜第" + page + " 页的图片正在下载......总共下载了" + sum + "张图;目录在C:/爬虫图片/"+flage+"/");
            }
      

        page++;//下一页
        downLoadPicture(page,flage);
    }
}

运行效果如下

仅供学习和研究使用。

[添加链接描述]
我是一个java初学者：
由于对爬虫非常感兴趣，但又不是主学python的，那我就换一个姿势爬虫吧，这个我是在B站看视频学会的，大家也想学学的可以去看看
(https://www.bilibili.com/video/BV1wJ411J7dm)