【Java爬虫】006-URLConnection与HttpURLConnection（网页内容获取）

訾博ZiBo

发布于 2025-01-06 15:12:55

32000

代码可运行

文章被收录于专栏：全栈开发工程师全栈开发工程师

运行总次数：0

代码可运行

最后更新：2020年8月31日11:42:00

一、概述

URLConnection是java.net包中的一个抽象类，其主要用于实现应用程序与URL之间的通信；

HttpURLConnection继承自URLConnection，也是抽象类；

在网络爬虫中，可以使用URLConnection或HttpURLConnection请求URL获取流数据，通过对流数据的操作，获取具体的实体内容；

二、实例化

1、说明

URLConnection与HttpURLConnection都是抽象类，无法直接创建实例化对象，但可以通过java.net包URL类中的openConnection()方法创建URLConnection与HttpURLConnection实例；

2、代码示例

package com.zb.book.connection;

import java.io.IOException;
import java.net.HttpURLConnection;
import java.net.URL;
import java.net.URLConnection;

public class Main {
    public static void main(String[] args) throws IOException {
        URL url = new URL("http://www.baidu.com/");
        URLConnection urlConnection = url.openConnection();
        HttpURLConnection httpURLConnection = (HttpURLConnection) url.openConnection();
    }
}

三、通过GET请求获取响应体html

package com.zb.book.connection;

import java.io.BufferedReader;
import java.io.IOException;
import java.io.InputStreamReader;
import java.net.HttpURLConnection;
import java.net.URL;
import java.nio.charset.StandardCharsets;

public class Main {
    public static void main(String[] args) throws IOException {
        //创建URL
        URL url = new URL("http://www.baidu.com/");
        //创建连接
        HttpURLConnection connection = (HttpURLConnection)url.openConnection();
        //允许input
        connection.setDoInput(true);
        //设置请求方法是GET
        connection.setRequestMethod("GET");
        //进行连接操作
        connection.connect();
        //如果响应码等于200
        if(HttpURLConnection.HTTP_OK == connection.getResponseCode()){
            //创建BufferedReader输入流来读取URL的响应，并设置编码
            BufferedReader bufferedReader = new BufferedReader(new InputStreamReader(connection.getInputStream(), StandardCharsets.UTF_8));
            //读取内容
            String readLine;
            StringBuilder response = new StringBuilder();
            while (null != (readLine = bufferedReader.readLine())){
                response.append(readLine);
            }
            bufferedReader.close();
            System.out.println(response.toString());
        }
    }
}

四、模拟提交表单（POST请求）

package com.zb.book.connection;

import java.io.BufferedReader;
import java.io.IOException;
import java.io.InputStreamReader;
import java.net.HttpURLConnection;
import java.net.URL;
import java.nio.charset.StandardCharsets;

//模拟提交表单（POST请求）
public class PostSubmitForm {
    public static void main(String[] args) throws IOException {
        //初始化提交表单的参数
        String wen = "EH629625211CS";
        String action = "ajax";
        //初始化URL
        URL url = new URL("http:www.***.com/ems.php");
        //创建连接
        HttpURLConnection connection = (HttpURLConnection)url.openConnection();
        //允许Output
        connection.setDoOutput(true);
        connection.setRequestMethod("POST");
        //拼接请求参数
        byte[] bytes = ("wen" + "=" + wen + "&" + "action" + "=" + action).getBytes();
        //在连接中添加参数
        connection.getOutputStream().write(bytes);
        //定义BufferedReader输入流来读取URL的响应，这里设置编码
        BufferedReader bufferedReader = new BufferedReader(new InputStreamReader(connection.getInputStream(), StandardCharsets.UTF_8));
        String line;
        StringBuilder html= new StringBuilder();
        while ((line = bufferedReader.readLine()) != null){
            html.append(line);
        }
        System.out.println(html.toString());
        bufferedReader.close();
    }
}

五、设置头消息

package com.zb.book.connection;

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

//设置头信息
public class SetHeader {
    public static void main(String[] args) throws IOException {
        //初始化URL
        URL url = new URL("http://www.***.com.cn/b.asp");
        URLConnection connection = url.openConnection();
        //HttpURLConnection urlConnection = (HttpURLConnection) url.openConnection();
        //添加请求头信息
        connection.setRequestProperty("Accept", "text/html");
        connection.setRequestProperty("Accept-Language","zh-CN,zh;q=0.5");
        connection.setRequestProperty("Host","www.***.com.cn");
        connection.setRequestProperty("Cache-Control","max-age=0");
        connection.setRequestProperty("User-Agent","Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.108 Safari/537.36");
        connection.connect();
        //其后进行其他操作即可
    }
}

六、连接超时设置

1、概述

使用URLConnection或HttpURLConnection时，可以设置两种超时时间，分别是连接超时时间（ConnectTimeout）和读取超时时间（ReadTimeout）；

2、代码演示

package com.zb.book.connection;

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

//设置超时时间
public class SetTimeout {
    public static void main(String[] args) throws IOException {
        //初始化URL
        URL url = new URL("http://www.***.com.cn/b.asp");
        URLConnection connection = url.openConnection();
        //HttpURLConnection urlConnection = (HttpURLConnection) url.openConnection();
        //设置超时时间
        connection.setConnectTimeout(10000);//连接超时
        connection.setReadTimeout(10000);//读取超时
        //后续可进行其他操作
    }
}

七、代理服务器的使用

package com.zb.book.connection;

import java.io.IOException;
import java.net.InetSocketAddress;
import java.net.Proxy;
import java.net.URL;
import java.net.URLConnection;

//代理服务器的设置
public class SetProxy {
    public static void main(String[] args) throws IOException {
        //创建代理对象
        Proxy proxy = new Proxy(Proxy.Type.HTTP, new InetSocketAddress("171.97.67.160", 3128));
        //初始化URL
        URL url = new URL("http://www.***.com.cn/b.asp");
        //创建连接对象并设置代理
        URLConnection connection = url.openConnection(proxy);
        //建立连接
        connection.connect();
    }
}

八、HTTPS请求认证

package com.crawler;

import java.io.BufferedReader;
import java.io.IOException;
import java.io.InputStreamReader;
import java.net.HttpURLConnection;
import java.net.URL;
import java.security.cert.X509Certificate;
import javax.net.ssl.HttpsURLConnection;
import javax.net.ssl.SSLContext;
import javax.net.ssl.SSLSocketFactory;
import javax.net.ssl.TrustManager;
import javax.net.ssl.X509TrustManager;
public class URLConnectionSSL {
	public static void main(String[] args) throws IOException {
		initUnSecureTSL();
		//使用URLConnection请求数据
		URL url = new URL("https://cn.kompass.com/a/hospitality-tourism-hotel-and-catering-industries/78/");
		HttpURLConnection conn = (HttpURLConnection) url.openConnection();
				int statusCode = conn.getResponseCode(); //获取响应状态码
		String responseBody = null;
		//如果响应状态码为200
		if (HttpURLConnection.HTTP_OK == statusCode) {  
			// 定义BufferedReader输入流来读取URL的响应 ,这里设置编码
			BufferedReader bufferedReader = new BufferedReader(
					new InputStreamReader(conn.getInputStream(), "utf-8"));  
			//读取内容
			String readLine = null;
			StringBuffer response = new StringBuffer();
			while (null != (readLine = bufferedReader.readLine())) {
				response.append(readLine);
			}

			bufferedReader.close();
			responseBody = response.toString();
		}
		System.out.println(responseBody);
	}
	private static void initUnSecureTSL()  {
		// 创建信任管理器(不验证证书)
		final TrustManager[] trustAllCerts = new TrustManager[]{new X509TrustManager() {
			//检查客户端证书
			public void checkClientTrusted(final X509Certificate[] chain, final String authType) {
				//do nothing 接受任意客户端证书
			}
			//检查服务器端证书
			public void checkServerTrusted(final X509Certificate[] chain, final String authType) {
				//do nothing  接受任意服务器端证书
			}
			//返回受信任的X509证书
			public X509Certificate[] getAcceptedIssuers() {
				return null; //或者return new X509Certificate[0];
			}
		}};
		try {
			// 创建SSLContext对象,并使用指定的信任管理器初始化
			SSLContext sslContext = SSLContext.getInstance("SSL");
			sslContext.init(null, trustAllCerts, new java.security.SecureRandom());
			// 基于信任管理器创建套接字工厂 (ssl socket factory)
			SSLSocketFactory sslSocketFactory = sslContext.getSocketFactory();
			//为HttpsURLConnection配置套接字工厂SSLSocketFactory
			HttpsURLConnection.setDefaultSSLSocketFactory(sslSocketFactory);
			//正常访问Https协议网站
		} catch (Exception e) {
			e.printStackTrace();
		}
	}
}

本文参与腾讯云自媒体同步曝光计划，分享自作者个人站点/博客。

原始发表：2025-01-06，如有侵权请联系 cloudcommunity@tencent.com 删除

爬虫