HttpClient基本使用

1.在pom.xml加入对httpclient的必需的jar包的依赖

        <!--//httpclient的接口基本都在这儿-->
        <dependency>
            <groupId>org.apache.httpcomponents</groupId>
            <artifactId>httpclient</artifactId>
            <version>4.5.2</version>
        </dependency>
        <dependency>
            <groupId>org.apache.httpcomponents</groupId>
            <artifactId>httpclient-cache</artifactId>
            <version>4.5</version>
        </dependency>
        <dependency>
            <groupId>org.apache.httpcomponents</groupId>
            <artifactId>httpmime</artifactId>
            <version>4.3.2</version>
        </dependency>

注意：常见的MIME类型(通用型)：

超文本标记语言文本 .html text/html

xml文档 .xml text/xml

XHTML文档 .xhtml application/xhtml+xml

普通文本 .txt text/plain

RTF文本 .rtf application/rtf

PDF文档 .pdf application/pdf

Microsoft Word文件 .word application/msword

PNG图像 .png image/png

GIF图形 .gif image/gif

JPEG图形 .jpeg,.jpg image/jpeg

au声音文件 .au audio/basic

MIDI音乐文件 mid,.midi audio/midi,audio/x-midi

RealAudio音乐文件 .ra, .ram audio/x-pn-realaudio

MPEG文件 .mpg,.mpeg video/mpeg

AVI文件 .avi video/x-msvideo

GZIP文件 .gz application/x-gzip

TAR文件 .tar application/x-tar

任意的二进制数据 application/octet-stream

2.抓取网页的内容并打印到控制台的demo

package com.zhouhe.modules.api.test;

import java.io.IOException;
import java.io.InputStream;

import org.apache.http.HttpEntity;
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;

/**
 * Created by zhouhe on 2019/3/14 8:52
 */
public class Test {

    public static void main(String[] args) {
        // TODO Auto-generated method stub
        String url="http://www.baidu.com";

        //1.使用默认的配置的httpclient
        CloseableHttpClient client = HttpClients.createDefault();
        //2.使用get方法
        HttpGet httpGet = new HttpGet(url);
        InputStream inputStream = null;
        CloseableHttpResponse response = null;

        try {
            //3.执行请求，获取响应
            response = client.execute(httpGet);

            //看请求是否成功，这儿打印的是http状态码
            System.out.println(response.getStatusLine().getStatusCode());
            //4.获取响应的实体内容，就是我们所要抓取得网页内容
            HttpEntity entity = response.getEntity();

            //5.将其打印到控制台上面
            //方法一：使用EntityUtils
            if (entity != null) {
                System.out.println(EntityUtils.toString(entity, "utf-8"));
            }
            EntityUtils.consume(entity);

            //方法二  :使用inputStream
           /* if (entity != null) {
                inputStream = entity.getContent();

                BufferedReader bufferedReader = new BufferedReader(new InputStreamReader(inputStream));
                String line = "";
                while ((line = bufferedReader.readLine()) != null) {
                    System.out.println(line);

                }
            }*/

        } catch (Exception e) {
            // TODO Auto-generated catch block
            e.printStackTrace();
        } finally {
            if (inputStream != null) {
                try {
                    inputStream.close();
                } catch (IOException e) {
                    // TODO Auto-generated catch block
                    e.printStackTrace();
                }
            }
            if (response != null) {
                try {
                    response.close();
                } catch (IOException e) {
                    // TODO Auto-generated catch block
                    e.printStackTrace();
                }
            }

        }

    }
}

原文网址：

https://www.cnblogs.com/LuckyBao/p/6096145.html