HttpClient实现HelloWorld

HttpClient 这个框架主要用来请求第三方服务器，然后获取到网页，得到我们需要的数据

搞个简单实例，让大家体验一把

创建一个Maven项目 在pom.xml贴上依赖

<dependency>
	    <groupId>org.apache.httpcomponents</groupId>
	    <artifactId>httpclient</artifactId>
	    <version>4.5.3</version>
	</dependency>

第一种：

package com.gcx.demo.HelloWorld2;

import java.io.IOException;

import org.apache.http.HttpEntity;
import org.apache.http.client.ClientProtocolException;
import org.apache.http.client.methods.CloseableHttpResponse;
import org.apache.http.client.methods.HttpGet;
import org.apache.http.impl.client.CloseableHttpClient;
import org.apache.http.impl.client.HttpClients;
import org.apache.http.util.EntityUtils;

public class App2 {
	public static void main(String[] args) {
		//创建一个httpclient 实例
		CloseableHttpClient httpClient=HttpClients.createDefault();
		//创见HttpGet实例
		HttpGet httpGet=new HttpGet("https://www.baidu.com");
		CloseableHttpResponse execute=null;
		//执行这个实例
		try {
			 execute = httpClient.execute(httpGet);
			 //获取返回的实体
			 HttpEntity entity = execute.getEntity();
			 System.out.println("网页内容:"+EntityUtils.toString(entity,"utf-8"));
		} catch (ClientProtocolException e) {
			// TODO Auto-generated catch block
			e.printStackTrace();
		} catch (IOException e) {
			// TODO Auto-generated catch block
			e.printStackTrace();
		}finally{
			try {
				execute.close();
			} catch (IOException e) {
				// TODO Auto-generated catch block
				e.printStackTrace();
			}
		}
				
	}
}

输出：

这里得到了百度首页源码，当然要获得具体数据的话，要用到Jsoup，后面文章在做详述

第二种(简化下)：

package com.gcx.demo.HelloWorld2;

import java.io.IOException;

import org.apache.http.HttpEntity;
import org.apache.http.client.ClientProtocolException;
import org.apache.http.client.methods.CloseableHttpResponse;
import org.apache.http.client.methods.HttpGet;
import org.apache.http.impl.client.CloseableHttpClient;
import org.apache.http.impl.client.HttpClients;
import org.apache.http.util.EntityUtils;

/**
 * Hello world!
 *
 */
public class App 
{
    public static void main( String[] args ) throws ClientProtocolException, IOException{
    	//创建HttpClient实例
    	CloseableHttpClient httpClient=HttpClients.createDefault();
    	//创建httpget实例
    	HttpGet httpGet=new HttpGet("http://www.baidu.com");
    	//执行这个实例
    	CloseableHttpResponse response = httpClient.execute(httpGet);
    	//获取返回实体
    	HttpEntity entity = response.getEntity();
    	System.out.println("网页内容:"+EntityUtils.toString(entity,"utf-8"));
    	
    	response.close();
    
    
    }
}

但是实际开发的话，我们对于每一种异常的抛出，catch里都需要做一些业务上的操作，所以以后用的话，还是第一种，假如爬虫任务很简单，容易爬取，并且量小，那就第二种。还是要根据具体情况而定