爬虫原理

最新推荐文章于 2024-05-25 21:08:58 发布

vhujbvf

最新推荐文章于 2024-05-25 21:08:58 发布

阅读量72

点赞数

分类专栏：笔记

本文链接：https://blog.csdn.net/qq_51592187/article/details/114481121

版权

Java 网络爬虫 HttpURLConnection GET请求 User-Agent

关键词由CSDN通过智能技术生成

笔记专栏收录该内容

129 篇文章 0 订阅

订阅专栏

java网络简单连接爬虫原理

package Net;

import java.io.BufferedReader;
import java.io.InputStream;
import java.io.InputStreamReader;
import java.net.HttpURLConnection;
import java.net.MalformedURLException;
import java.net.URL;

public class TestSpider {
public static void main(String[] args) throws Exception {
// //获取URL(有权访问)
// URL u = new URL(“https://www.jd.com”);
// //openStream()打开与这个URL的连接并返回InputStream从该链接中读取
// InputStream i = u.openStream();
// BufferedReader b = new BufferedReader(new InputStreamReader(i,“UTF-8”));
// String msg = null;
// while(null!=(msg = b.readLine())) {
// System.out.println(msg);
// }
// b.close();
//获取URL
URL u = new URL(“https://www.123.com”);
//下载资源
HttpURLConnection h = (HttpURLConnection)u.openConnection();
h.setRequestMethod(“GET”);//两种方法get(相对不安全)与post(相对安全)
//再网站上点击f12 然后点开User-Agent获取
h.setRequestProperty(“User-Agent”,"");
BufferedReader b = new BufferedReader(new InputStreamReader(h.getInputStream(),“UTF-8”));
String msg = null;
while(null!=(msg = b.readLine())) {
System.out.println(msg);
}
b.close();
}
}