jsoup爬取网站图片

Posted 2020-10-29 Stay Hungry, Stay Foolish

package com.ij34.JsoupTest;
import java.io.File;  
import java.io.FileOutputStream;  
import java.io.InputStream;  
import java.net.HttpURLConnection;
import java.net.URL;  
import java.net.URLEncoder;
import java.text.SimpleDateFormat;
import java.util.Date;
import java.util.Random;

import org.jsoup.Jsoup;  
import org.jsoup.nodes.Document;  
import org.jsoup.nodes.Element;  
import org.jsoup.select.Elements;  
 
public class JsoupTest {  
  

  
    public static void downImages(String filePath,String imgUrl) throws Exception {  
          
        //获取网址
        String beforeUrl = imgUrl.substring(0,imgUrl.lastIndexOf("/")+1);  
        //图片url后面的图片名字
        String fileName = imgUrl.substring(imgUrl.lastIndexOf("/")+1);  
        String newFileName = URLEncoder.encode(fileName, "UTF-8");  
        //"+"替换为UTF-8中的空格  
        newFileName = newFileName.replaceAll("\\\\+", "\\\\%20");  
        //编码之后的url  
        imgUrl = beforeUrl + newFileName;  
         //创建文件目录  
            File files = new File(filePath);  
            if (!files.exists()) {  
                files.mkdirs();  
            }  
            URL url = new URL(imgUrl);  
            HttpURLConnection connection = (HttpURLConnection)url.openConnection();  
            InputStream is = connection.getInputStream();  
            Date day=new Date();    
            SimpleDateFormat df = new SimpleDateFormat("yyyyMMddHHmmss"); 
            Random ra=new Random();
            int Num=ra.nextInt(11)+100;
            String fn=df.format(day)+Num; 
            //去图片的格式例如.jpg .jpeg
            int lastIndex=fileName.lastIndexOf(".");
            String result=fileName.substring(lastIndex);
            File file = new File(filePath +fn+ result);  
            FileOutputStream out = new FileOutputStream(file);  
            int i = 0;  
            while((i = is.read()) != -1){  
                out.write(i);  
            }  
      
       
    }  
      
    public static void main(String[] args) throws Exception {  
        //int[] a=new int[]{};
          //for(int i=a.length-1;i>=0;i--){
          //爬取的网址
              String url = "http://www.ivsky.com/tupian/laohu_v45527";//+a[i];
            String savePath = "D://webmagic//";  
            Document document = Jsoup.connect(url).get();  
            Elements elements = document.getElementsByTag("img");  
            for(Element element : elements){  
                //图片的绝对路径  
                String imgSrc = element.attr("abs:src");  
                //取jpg格式
                if(imgSrc.contains(".jpg")){
                downImages(savePath, imgSrc);  
                System.out.println(url+":"+imgSrc);  
                } 
            }  
      //    }
    }  
}