jsoup 爬取案例 jsoup

package jousp;

import java.io.ByteArrayOutputStream;
import java.io.File;
import java.io.FileOutputStream;
import java.io.InputStream;
import java.net.HttpURLConnection;
import java.net.URL;

import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import org.jsoup.select.Elements;

public class JSoupP {

    public static void main(String[] args) throws Exception {
        Document document = Jsoup.connect("https://book.douban.com").get();
        Elements elements = document.getElementsByTag("img");
        Element element = elements.get(0);
        String url  = element.attr("src");
        URL url1 = new URL(url);
        HttpURLConnection connection = (HttpURLConnection)url1.openConnection();
        connection.setRequestMethod("GET");
        connection.setConnectTimeout(5*1000);
        //获得图片的输入流
        InputStream inputStream = connection.getInputStream();
        byte data[] = readInputStream(inputStream);
        //定义图片位置
        File imageFile = new File("D://BeautyGirl.jpg");  
        //定义输出流
        FileOutputStream outStream = new FileOutputStream(imageFile);
        outStream.write(data);
        outStream.flush();
        outStream.close();  
    }
    public static byte[] readInputStream(InputStream inStream) throws Exception{  
        ByteArrayOutputStream outStream = new ByteArrayOutputStream();  
        //创建一个Buffer字符串  
        byte[] buffer = new byte[1024];  
        //每次读取的字符串长度，如果为-1，代表全部读取完毕  
        int len = 0;  
        //使用一个输入流从buffer里把数据读取出来  
        while( (len=inStream.read(buffer)) != -1 ){  
            //用输出流往buffer里写入数据，中间参数代表从哪个位置开始读，len代表读取的长度  
            outStream.write(buffer, 0, len);  
        }  
        //关闭输入流  
        inStream.close();  
        //把outStream里的数据写入内存  
        return outStream.toByteArray();  
    }  


}