Java之下载相关网页到本地

最新推荐文章于 2024-08-18 03:08:17 发布

find_czk

最新推荐文章于 2024-08-18 03:08:17 发布

阅读量239

点赞数 1

分类专栏： Java相关文章标签： java java入门爬虫下载网页

本文链接：https://blog.csdn.net/findzk/article/details/98251212

版权

Java相关专栏收录该内容

11 篇文章 0 订阅

订阅专栏

                        
                     
 
题目：通过URL/UrlConnetion编程，将百度首页下载到本地，存储文件baidu.txt中
代码实现
package com.czk.test.io;
import  java.io.BufferedInputStream;
import java.io.IOException;
import java.io.InputStream;
import  java.net.HttpURLConnection;
import  java.net.MalformedURLException;
import  java.net.ProtocolException;
import java.net.URL;
import  com.sun.xml.internal.messaging.saaj.util.ByteOutputStream;
/**
* 下载任意URL对应的网页html代码
*
* @author czk
*
* @time：2019年8月2日
*/
public class  DownloadWebPage4UrlConnection  {
   public static String  download(String httpUrl)  throws IOException {
     URL url = new  URL(httpUrl);
     HttpURLConnection  connection =  (HttpURLConnection)  url.openConnection();
     connection.setRequestMethod("GET");
     connection.setRequestProperty("Connection", "Keep-Alive");
     connection.connect();
     BufferedInputStream bis =  null;
     ByteOutputStream bos =  null;
     try {
        InputStream is =  connection.getInputStream();
        bis = new  BufferedInputStream(is);
        bos = new  ByteOutputStream();
        int b = 0;
        byte[] byArr = new  byte[1024];
        while ((b =  bis.read(byArr)) != -1) {
          bos.write(byArr, 0,  b);
        }
        return new  String(bos.toByteArray(),  "utf-8");
     } catch (Exception e) {
        e.printStackTrace();
     } finally {
        try {
          if (bis != null) {
             bis.close();
          }
          if (bos != null) {
             bos.close();
          }
        } catch (IOException  e) {
          e.printStackTrace();
        }
     }
     return null;
   }
   public static void  main(String[] args) throws  IOException {
     String httpUrl =  "http://www.baidu.com";
     String  content=download(httpUrl);
     System.out.println(content);
   }
}