HttpClient使用笔记干货满满-阿里云开发者社区

1. HttpClient 概述

HttpClient 是 apache 组织下面的一个用于处理 HTTP 请求和响应的开源工具。它不是一个浏览器，也不处理客户端缓存等浏览器的功能。它只是一个类库！它在 JDK 的基本类库基础上做了更好的封装！

HttpClient 项目依赖于 HttpCore（处理核心的 HTTP 协议）、commons-codec（处理与编码有关的问题的项目）和 commons-logging（处理与日志记录有关问题的项目）。

如果你希望能够通过 HttpClient 向服务器上传文件等与 multipart 编码类型有关的请求，以及其它复杂的

MIME 类型，那么，你需要另外一个依赖包：HttpMime（它是专门处理与 MIME 类型有关问题的项目），

开始使用 HttpClient，我们加入了下列依赖包：

httpclient-4.0.1.jar

httpcore-4.0.1.jar

httpmime-4.0.1.jar

又依赖于 mime4j（apache-mime4j-0.6.jar）
commons-codec-1.4.jar
commons-logging-1.1.1.jar
commons-io-1.4.jar – 为了更方便处理与 IO 有关的需求
【如果你下载的是包含依赖包的压缩包，那么上述依赖包（除 commons-io-1.4.jar 外）都已经在其中
了！】

2. 了解 JDK 中有关 HTTP URL 处理的 API

因为 HttpClient 是对 JDK 中 java.net.*包下面的有关基础类库的封装，所以，我们有必要了解一下，这

些基础类库的简单用法和概念。

最简单的获取网页内容的示例

@Test
  public void testURLConnection() {
    try {
      String urlString = "http://16.10.113.8:8080/hiapi/paas/asset/db";
      URL url = new URL(urlString); //代表了一个网址
      URLConnection conn = url.openConnection();
      InputStream is = conn.getInputStream(); //获得网页的内容
      //将InputStream转换为Reader，并使用缓冲读取，提高效率，同时可以按行
      BufferedReader br = new BufferedReader(new
          InputStreamReader(is, "UTF-8"));
      String line = null;
      while ((line = br.readLine()) != null) {
        System.out.println(line);
      }
      is.close();
    } catch (Exception e) {
      e.printStackTrace();
    }
  }

运行结果

[{"sign":"paas","deptId":103,"hostName":"66.3.125.80,66.3.125.81,66.3.125.82","port":"1521","dbId":88,"dbType":"ORACLE","dbName":"nnsptf","isCapture":null,"dbaUser":"system","dbaPwd":"oracle","dbAlias":"压测1"},{"sign":"paas","deptId":103,"hostName":"66.3.125.80,66.3.125.81,66.3.125.82","port":"1521","dbId":96,"dbType":"ORACLE","dbName":"cjecgc","isCapture":null,"dbaUser":"system","dbaPwd":"oracle","dbAlias":"测试ora"},{"sign":"paas","deptId":105,"hostName":"66.3.125.80,66.3.125.81,66.3.125.82","port":"1521","dbId":157,"dbType":"ORACLE","dbName":"uujarl","isCapture":null,"dbaUser":"system","dbaPwd":"oracle","dbAlias":"溧水库"},{"sign":"paas","deptId":105,"hostName":"66.3.125.80,66.3.125.81,66.3.125.82","port":"1521","dbId":164,"dbType":"ORACLE","dbName":"qwxutc","isCapture":null,"dbaUser":"system","dbaPwd":"oracle","dbAlias":"溧水数据库2"},{"sign":"paas","deptId":103,"hostName":"66.3.125.80,66.3.125.81,66.3.125.82","port":"1521","dbId":298,"dbType":"ORACLE","dbName":"vosrtz","isCapture":null,"dbaUser":"system","dbaPwd":"oracle","dbAlias":"zijin001"},{"sign":"paas","deptId":103,"hostName":"66.3.125.80,66.3.125.81,66.3.125.82","port":"1521","dbId":299,"dbType":"ORACLE","dbName":"pffklf","isCapture":null,"dbaUser":"system","dbaPwd":"oracle","dbAlias":"zijin002"}]
Process finished with exit code 0

3.使用 HttpClient 获取网页内容

3.1 使用 GET 方式向后台递交请求

// org.apache.http.client.HttpClient
  @Test
  public void testHttpClient(){
    try {
      //HttpClient主要负责执行请求
      HttpClient httpclient = new DefaultHttpClient();
      //利用HTTP GET向服务器发起请求
      HttpGet get = new HttpGet("http://11.10.113.8:8080/hiapi/paas/asset/db");
      //获得服务器响应的的所有信息
      HttpResponse response = httpclient.execute(get);
      //获得服务器响应回来的消息体（不包括HTTP HEAD）
      HttpEntity entity = response.getEntity();
      if(entity != null){
        InputStream is = entity.getContent();
        //将InputStream转换为Reader，并使用缓冲读取，提高效率，同时
        BufferedReader br = new BufferedReader(new InputStreamReader(is,"UTF-8"));
        String line = null;
        while((line = br.readLine()) != null){
          System.out.println(line);
        }
        is.close();
      }
      //释放所有的链接资源，一般在所有的请求处理完成之后，才需要释放
      httpclient.getConnectionManager().shutdown();
    } catch (ClientProtocolException e) {
      e.printStackTrace();
    } catch (IOException e) {
      e.printStackTrace();
    }
  }

3.2 自动获得响应的编码信息

我们希望程序能够自动分辨响应的内容的编码

@Test
    public void testHttpClient2() {
        try {
            //HttpClient主要负责执行请求
            HttpClient httpclient = new DefaultHttpClient();
            //利用HTTP GET向服务器发起请求
            HttpGet get = new HttpGet("http://66.10.113.8:8080/hiapi/paas/asset/db");
            //获得服务器响应的的所有信息
            HttpResponse response = httpclient.execute(get);
            //获得服务器响应回来的消息体（不包括HTTP HEAD）
            HttpEntity entity = response.getEntity();
            if (entity != null) {
                //获得响应的字符集编码信息
                //即获取HTTP HEAD的：ContentType:text/html;charset=UTF-8中的字符集信息
                String charset = EntityUtils.getContentCharSet(entity);
                System.out.println("响应的字符集是：" + charset);
                InputStream is = entity.getContent();
                //使用响应中的编码来解释响应的内容
                BufferedReader br = new BufferedReader(new
                        InputStreamReader(is, charset));
                String line = null;
                while ((line = br.readLine()) != null) {
                    System.out.println(line);
                }
                is.close();
            }
            //释放所有的链接资源，一般在所有的请求处理完成之后，才需要释放
            httpclient.getConnectionManager().shutdown();
        } catch (ClientProtocolException e) {
            e.printStackTrace();
        } catch (IOException e) {
            e.printStackTrace();
        }
    }

3.3 设置代理服务器，访问网站

@Test
    public void testFetch03() {
        try {
            //HttpClient主要负责执行请求
            HttpClient httpclient = new DefaultHttpClient();
            //设置代理服务器
            httpclient.getParams().setParameter(ConnRoutePNames.DEFAULT_PROXY, new HttpHost("121.12.249.207", 3128));
            //利用HTTP GET向服务器发起请求
            HttpGet get = new HttpGet("http://www.baidu.com/");//new HttpGet("http://localhost:8080/cms");
            //获得服务器响应的的所有信息
            HttpResponse response = httpclient.execute(get);
            //获得服务器响应回来的消息体（不包括HTTP HEAD）
            HttpEntity entity = response.getEntity();
            if (entity != null) {
                //获得响应的字符集编码信息
                //即获取HTTP HEAD的：ContentType:text/html;charset=UTF-8中的字符集信息
                String charset =
                        EntityUtils.getContentCharSet(entity);
                System.out.println("响应的字符集是：" + charset);
                InputStream is = entity.getContent();
                //使用响应中的编码来解释响应的内容
                BufferedReader br = new BufferedReader(new
                        InputStreamReader(is, charset));
                String line = null;
                while ((line = br.readLine()) != null) {
                    System.out.println(line);
                }
                is.close();
            }
            //释放所有的链接资源，一般在所有的请求处理完成之后，才需要释放
            httpclient.getConnectionManager().shutdown();
        } catch (ClientProtocolException e) {
            e.printStackTrace();
        } catch (IOException e) {
            e.printStackTrace();
        }
    }

3.4 获得重定向之后的网址信息

HttpClient 缺省情况下自动处理客户端重定向，即当你访问网页（比如 A 网页）之后，假设被重定向到了
B 网页，那么，HttpClient 将自动返回 B 网页的内容，无需再编程处理它！有时候我们可能想要知道 A 网
页被重定向到了哪里，也就是取得 B 网页的网址，那么可以通过下述例子获得：

@Test
    public void testFetch04(){
        try {
            //HttpClient主要负责执行请求
            HttpClient httpclient = new DefaultHttpClient();
            HttpContext context = new BasicHttpContext();
            //利用HTTP GET向服务器发起请求
            HttpGet get = new
                    HttpGet("http://localhost:8080/cms/backend/main.jsp");
            //获得服务器响应的的所有信息
            HttpResponse response = httpclient.execute(get,context);
            //获得重定向之后的主机地址信息
            HttpHost targetHost =
                    (HttpHost)context.getAttribute(ExecutionContext.HTTP_TARGET_HOST);
            System.out.println(targetHost); // http://localhost:8080
            //获得实际的请求对象的URI（即重定向之后的"/cms/backend/login.jsp"）
            HttpUriRequest actualRequest = (HttpUriRequest)
                    context.getAttribute(ExecutionContext.HTTP_REQUEST);
            System.out.println(actualRequest.getURI());
            //获得服务器响应回来的消息体（不包括HTTP HEAD）
            HttpEntity entity = response.getEntity();
            if(entity != null){
                //获得响应的字符集编码信息
                //即获取HTTP HEAD的：ContentType:text/html;charset=UTF-8中的字符集信息
                String charset =
                        EntityUtils.getContentCharSet(entity);
                System.out.println("响应的字符集是："+charset);
                InputStream is = entity.getContent();
                //使用响应中的编码来解释响应的内容
                BufferedReader br = new BufferedReader(new
                        InputStreamReader(is,charset));
                String line = null;
                while((line = br.readLine()) != null){
                    System.out.println(line);
                }
                is.close();
            }
            //释放所有的链接资源，一般在所有的请求处理完成之后，才需要释放
            httpclient.getConnectionManager().shutdown();
        } catch (Exception e) {
            e.printStackTrace();
        }
    }

3.5 自动 Cookie 处理

HttpClient 能够支持自动 Cookie 处理。设想一个典型的场景：首先打开登录页面，然后输入用户名和密
码登录，然后访问那些只有登录之后才能访问的网页…… 
如果我们用浏览器，因为浏览器可以将登录之后的会话信息用 Cookie 存储在本地，所以，登录之后的每次
请求，都会自动向服务器发送 Cookie 的信息，我们利用 HttpClient，这些过程都全部可以自动化处理
了。

@Test
    public void testFetch05() {
        try {
            //HttpClient主要负责执行请求
            HttpClient httpclient = new DefaultHttpClient();
            HttpContext context = new BasicHttpContext();
            //利用HTTP GET向服务器发起请求，
            HttpGet get = new
                    HttpGet("http://localhost:8080/cms/backend/login.jsp");
            //获得服务器响应的的所有信息
            HttpResponse response = httpclient.execute(get, context);
            //获得服务器响应回来的消息体（不包括HTTP HEAD）
            HttpEntity entity = response.getEntity();
            String charset = null;
            if (entity != null) {
                //获得响应的字符集编码信息
                //即获取HTTP HEAD的：ContentType:text/html;charset=UTF-8中的字符集信息
                charset = EntityUtils.getContentCharSet(entity);
                System.out.println("响应的字符集是：" + charset);
                InputStream is = entity.getContent();
                //使用响应中的编码来解释响应的内容
                BufferedReader br = new BufferedReader(new
                        InputStreamReader(is, charset));
                String line = null;
                while ((line = br.readLine()) != null) {
                    System.out.println(line);
                }
                is.close();
            }
            //************* 执行登录请求 ********************//
            HttpPost post = new
                    HttpPost("http://localhost:8080/cms/backend/LoginServlet");
            //添加POST参数
            List<NameValuePair> nvps = new ArrayList<NameValuePair>();
            nvps.add(new BasicNameValuePair("username", "admin"));
            nvps.add(new BasicNameValuePair("password", "admin"));
            post.setEntity(new UrlEncodedFormEntity(nvps, charset));
            response = httpclient.execute(post);
            entity = response.getEntity();
            if (entity != null) {
                InputStream is = entity.getContent();
                //使用响应中的编码来解释响应的内容
                BufferedReader br = new BufferedReader(new
                        InputStreamReader(is, charset));
                String line = null;
                while ((line = br.readLine()) != null) {
                    System.out.println(line);
                }
                is.close();
            }
            //******************* 请求文章查询 ********************//
            get = new HttpGet("http://localhost:8080/cms/backend/ArticleServlet");
            response = httpclient.execute(get);
            entity = response.getEntity();
            if (entity != null) {
                InputStream is = entity.getContent();
                //使用响应中的编码来解释响应的内容
                BufferedReader br = new BufferedReader(new
                        InputStreamReader(is, charset));
                String line = null;
                while ((line = br.readLine()) != null) {
                    System.out.println(line);
                }
                is.close();
            }
            //释放所有的链接资源，一般在所有的请求处理完成之后，才需要释放
            httpclient.getConnectionManager().shutdown();
        } catch (Exception e) {
            e.printStackTrace();
        }
    }

HttpClient使用笔记干货满满