java爬虫(jsoup)爬取斗图吧网站表情包

java爬虫(jsoup)爬取斗图吧网站表情包

import java.util.*;
import org.jsoup.*;
import org.jsoup.nodes.*;
import java.io.*;
import org.jsoup.select.*;
public class EmotionPackage{
	public static void main(String[] args)throws Exception{ 
		downLoad(1);
	}
	static void downLoad(int page)throws Exception{
		Document doc=Jsoup.connect("https://m.doutub.com/img_lists/miao/" + page + "").get();
		Elements Elements= doc.select("div.expression-list.clearfix a img");
		int i=1;
		for (Element element : Elements){
			String imgUrl=element.attr("src");
			String end= imgUrl.substring(imgUrl.length() - 4, imgUrl.length());
			String name=element.attr("alt");
			System.out.println(name);
			byte[] bytes= Jsoup.connect(imgUrl).ignoreContentType(true).execute().bodyAsBytes();		
			File file=new File("/storage/emulated/0/0-0表情包/猫/第" + page + "页");
			if (!file.exists())
				file.mkdirs(); 
			FileOutputStream fos=new FileOutputStream("" + file + "/" + i + "-" + name + "" + end + "");
		   	fos.write(bytes);
			i++;
		}
		System.out.println("第" + page + "页下载完成");	
		downLoad(page + 1);	
	}
}