爬取中国信用黑名单网站图片和数据到本地

import java.io.File;
import java.io.IOException;
import java.io.InputStream;
import java.net.URL;
import java.net.URLConnection;

import org.apache.commons.io.FileUtils;



public class SpiderDemo {
    public static void main(String[] args) throws IOException {
//        URL url = new URL("http://www.zhongguoxinyongheimingdan.com");
//        URLConnection connection = url.openConnection();
//        InputStream in = connection.getInputStream();
//        File file = new File("F://a.txt");
//        FileUtils.copyInputStreamToFile(in, file);
        File srcDir = new File("F://a.txt");
        String str = FileUtils.readFileToString(srcDir, "UTF-8");
        String[] str1 = str.split("href=");
        for (int i = 3; i < str1.length-1; i++) {
            URL url = new URL("http://www.zhongguoxinyongheimingdan.com"+str1[i].substring(1, 27));
            File f = new File("F://abc//"+str1[i].substring(2, 22));
            if(!f.exists()){
            f.mkdir();    
            File desc1 = new File(f,str1[i].substring(1, 22)+".txt");
            URLConnection connection = url.openConnection();
            InputStream in = connection.getInputStream();
            FileUtils.copyInputStreamToFile(in, desc1);
            String str2 = FileUtils.readFileToString(desc1, "UTF-8");
            String[] str3 = str2.split("" src="");
            for(int j = 1;j<str3.length-2;j++){
                URL url1 = new URL(str3[j].substring(0, 81));
                URLConnection connection1 = url1.openConnection();
                connection1.setDoInput(true);
                InputStream in1 = connection1.getInputStream();
                File desc2 = new File(f,str3[j].substring(44,76)+".jpg");
                FileUtils.copyInputStreamToFile(in1, desc2);
            }
            }
            }
        }
    
}