HttpClient简介与实现

1. HttpClient简介

HttpClient官网：http://hc.apache.org/

HttpClient4.5：http://hc.apache.org/httpcomponents-client-4.5.x/

HttpClient官方文档：http://hc.apache.org/httpcomponents-client-4.5.x/tutorial/html/index.html

HttpClient是Apache Jakarta Common下的子项目，可以用来提供高效的、最新的、功能丰富的支持HTTP协议的客户端编程工具包，并且它支持HTTP协议最新的版本和建议。

HTTP协议可能是现在Internet上使用得最多、最重要的协议了，越来越多的Java应用程序需要直接通过HTTP协议来访问网络资源。虽然在JDK的javanet包中已经提供了访问HTTP协议的基本功能，但是对于大部分应用程序来说，JDK库本身提供的功能还不够丰富和灵活。HttpClient是Apache Jakarta Common下的子项目，用来提供高效的、最新的、功能丰富的支持HTTP协议的客户端编程工具包，并且它支持HTTP协议最新的版本和建议。HttpClient已经应用在很多的项目中，比如Apache Jakarta上很著名的另外两个开源项目Cactus和HTMLUnit都使用了HttpClient。爬虫主要是用HttpClient模拟浏览器请求第三方站点url，然后响应，获取网页数据，然后用Jsoup来提取我们需要的信息。

2. HttpClient实现HelloWorld

New -> Project -> Maven Project -> Next ->
Create a simple project -> Next ->
    Group Id: com.andrew
    Artifact Id: HttpClientDemo
    Version: 0.0.1-SNAPSHOT
    Packaging: jar
    
pom.xml

<project xmlns="http://maven.apache.org/POM/4.0.0" 
    xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
    xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
  <modelVersion>4.0.0</modelVersion>
  <groupId>com.andrew</groupId>
  <artifactId>HttpClientDemo</artifactId>
  <version>0.0.1-SNAPSHOT</version>
  <dependencies>
      <dependency>
        <groupId>org.apache.httpcomponents</groupId>
        <artifactId>httpclient</artifactId>
        <version>4.5.2</version>
    </dependency>
  </dependencies>
</project>

HelloWorld01.java

package com.andrew.httpClient;

import java.io.IOException;

import org.apache.http.HttpEntity;
import org.apache.http.ParseException;
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 HelloWorld01 {
    public static void main(String[] args) {
        CloseableHttpClient httpClient = HttpClients.createDefault(); // 创建httpClient实例
        HttpGet httpGet = new HttpGet("http://www.csdn.net/"); // 创建httpget实例
        CloseableHttpResponse response = null;
        try {
            response = httpClient.execute(httpGet); // 执行http get请求
        } catch (ClientProtocolException e) { // http协议异常
            e.printStackTrace();
        } catch (IOException e) { // io异常
            e.printStackTrace();
        }
        HttpEntity entity = response.getEntity(); // 获取返回实体
        try {
            System.out.println("网页内容：" + EntityUtils.toString(entity, "utf-8")); // 获取网页内容
        } catch (ParseException e) { // 解析异常
            e.printStackTrace();
        } catch (IOException e) { // io异常
            e.printStackTrace();
        }
        try {
            response.close(); // response关闭
        } catch (IOException e) { // io异常
            e.printStackTrace();
        }
        try {
            httpClient.close(); // httpClient关闭
        } catch (IOException e) {
            e.printStackTrace();
        }
    }
}

HelloWorld02.java

package com.andrew.httpClient;

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 HelloWorld02 {
    public static void main(String[] args) throws ClientProtocolException, IOException {
        CloseableHttpClient httpClient = HttpClients.createDefault(); // 创建httpClient实例
        HttpGet httpGet = new HttpGet("http://www.csdn.net/"); // 创建httpget实例
        CloseableHttpResponse response = httpClient.execute(httpGet); // 执行http get请求
        HttpEntity entity = response.getEntity(); // 获取返回实体
        System.out.println("网页内容：" + EntityUtils.toString(entity, "utf-8")); // 获取网页内容
        response.close(); // response关闭
        httpClient.close(); // httpClient关闭
    }
}