爬虫爬取网站图片

依赖：

		
            commons-io
            commons-io
            2.11.0
        
        
        
            org.jsoup
            jsoup
            1.14.3
        

源码：

import org.jsoup.Connection;
import org.jsoup.nodes.Document;
import org.jsoup.select.Elements;

import java.io.File;
import java.io.FileOutputStream;
import java.io.IOException;
import java.util.ArrayList;
import java.util.Date;
import java.util.List;

import static org.jsoup.Jsoup.connect;


public class Picture {
    public static void main(String[] args) throws IOException {
        int max = 10;//网站页码
        String url; //观察网站页码规律编辑
        for (int j = 1; j < max ;j++){
            if(j==1){
                url = "http://www.******.com/tupian/"; //我用的网址不能发可以找我要
            }else{
                url = "http://www.******.com/tupian/index_"+j+".html";
            }
            //获取连接
            Connection connect = connect(url);
            //网页内容
            Document document = connect.get();
            //通过class属性获取页面元素
            Elements titles = document.getElementsByClass("lazy");
            System.out.println("ElementsCount:"+titles.size());
            List urls = new ArrayList();
            for (int i = 0; i < titles.size(); i++) {
                System.out.println("src=="+titles.get(i).attr("src"));
                //获取src属性内容
                urls.add(titles.get(i).attr("src"));
            }
            int a = 1;
            //文件存储位置
            File file = new File("F:\pic\"+new Date().getTime());
            if(!file.exists()){
                file.mkdirs();
            }
            for (String prcUrl: urls) {
                String geshi = prcUrl.substring(prcUrl.lastIndexOf("."));//获取图片格式
                Connection.Response execute = connect(prcUrl).ignoreContentType(true).execute();//获取图片
                FileOutputStream out = (new FileOutputStream(new java.io.File(file,a+geshi)));//设置输出流
                out.write(execute.bodyAsBytes());
                out.close();
                a++;
            }
        }
    }
}