HttpClient4.5简单使用

一、HttpClient简介

    HttpClient是一个客户端的HTTP通信实现库，它不是一个浏览器。关于HTTP协议，可以搜索相关的资料。它设计的目的是发送与接收HTTP报文。它不会执行嵌入在页面中JavaScript代码，所以当需要抓取通过AJAX技术获取实际内容的页面时需要使用WebClient等其他开源库。HttpClient最新版已经到第5版，但已经稳定的应该是4.5.2版本，官方网址：http://hc.apache.org/。

二、HttpClient简单使用

    HttpClient的主要用途是接收HTTP响应的内容，下面介绍HttpClient的简单使用，抓取博客园的首页。至于HttpClient4.5的常用API可以参考这篇文章：http://liangbizhi.github.io/httpclient-4-3-x-chapter-1/。

package com.httpclient.demo;

import java.io.IOException;
import java.nio.charset.Charset;
import java.util.regex.Matcher;
import java.util.regex.Pattern;

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

public class SimpleHttpClient {
  // 使用HttpClient获取博客园首页
  public static void main(String[] args) throws ClientProtocolException, IOException {
    String targetUrl = "http://www.cnblogs.com/";
    
    // 1.建立HttpClient对象
    CloseableHttpClient client = HttpClients.createDefault();

    // 2.建立Get请求
    HttpGet get = new HttpGet(targetUrl);

    // 3.发送Get请求
    CloseableHttpResponse res = client.execute(get);

    // 4.处理请求结果
    if (res.getStatusLine().getStatusCode() == HttpStatus.SC_OK) {
      HttpEntity entity = res.getEntity();
      ContentType contentType = ContentType.getOrDefault(entity);
      Charset charset = contentType.getCharset();
      String mimeType = contentType.getMimeType();
      // 获取字节数组
      byte[] content = EntityUtils.toByteArray(entity);
      if (charset == null) {
        // 默认编码转成字符串
        String temp = new String(content);
        String regEx = "(?=<meta).*?(?<=charset=[\\'|\\\"]?)([[a-z]|[A-Z]|[0-9]|-]*)";
        Pattern p = Pattern.compile(regEx, Pattern.CASE_INSENSITIVE);
        Matcher m = p.matcher(temp);
        if (m.find() && m.groupCount() == 1) {
          charset = Charset.forName(m.group(1));
        } else {
          charset = Charset.forName("ISO-8859-1");
        }
      }
      System.out.println(new String(content, charset));
    }

  }

}

　　

三、HttpClient模拟登陆

     HTTP协议本来是无状态的，但为了保持会话的状态，使用Cookie保存Session信息，当向服务器发送请求时会附加一些会话信息，从而能区分不同会话的状态。用户登陆过程，其实简单而言，就是首先验证用户名与密码，然后服务器生成会话信息保存到本地，最后用户凭借会话信息能够访问类似用户信息等需登陆的网页。

    HttpClient4.5通过CookieStore保存用户的会话信息，还提供HttpClientContext保存用户连接的信息。下面是一个使用HttpClient模拟知乎登陆的简单案例。

package com.httpclient.demo;

import java.io.IOException;
import java.util.LinkedList;
import java.util.List;

import org.apache.http.Consts;
import org.apache.http.NameValuePair;
import org.apache.http.client.CookieStore;
import org.apache.http.client.config.CookieSpecs;
import org.apache.http.client.config.RequestConfig;
import org.apache.http.client.entity.UrlEncodedFormEntity;
import org.apache.http.client.methods.CloseableHttpResponse;
import org.apache.http.client.methods.HttpGet;
import org.apache.http.client.methods.HttpPost;
import org.apache.http.client.protocol.HttpClientContext;
import org.apache.http.cookie.Cookie;
import org.apache.http.impl.client.BasicCookieStore;
import org.apache.http.impl.client.CloseableHttpClient;
import org.apache.http.impl.client.HttpClients;
import org.apache.http.message.BasicNameValuePair;
import org.apache.http.util.EntityUtils;

/**
 * 模拟登陆知乎
 */
public class ZhiHuTest {

  public static void main(String[] args) throws java.text.ParseException {
    String name = "username";
    String password = "password"
    
    // 全局请求设置
    RequestConfig globalConfig = RequestConfig.custom().setCookieSpec(CookieSpecs.STANDARD).build();
    // 创建cookie store的本地实例
    CookieStore cookieStore = new BasicCookieStore();
    // 创建HttpClient上下文
    HttpClientContext context = HttpClientContext.create();
    context.setCookieStore(cookieStore);

    // 创建一个HttpClient
    CloseableHttpClient httpClient = HttpClients.custom().setDefaultRequestConfig(globalConfig)
        .setDefaultCookieStore(cookieStore).build();

    CloseableHttpResponse res = null;

    // 创建本地的HTTP内容
    try {
      try {
        // 创建一个get请求用来获取必要的Cookie，如_xsrf信息
        HttpGet get = new HttpGet("http://www.zhihu.com/");

        res = httpClient.execute(get, context);
        // 获取常用Cookie,包括_xsrf信息
        System.out.println("访问知乎首页后的获取的常规Cookie:===============");
        for (Cookie c : cookieStore.getCookies()) {
          System.out.println(c.getName() + ": " + c.getValue());
        }
        res.close();

        // 构造post数据
        List<NameValuePair> valuePairs = new LinkedList<NameValuePair>();
        valuePairs.add(new BasicNameValuePair("email", name));
        valuePairs.add(new BasicNameValuePair("password", password));
        valuePairs.add(new BasicNameValuePair("remember_me", "true"));
        UrlEncodedFormEntity entity = new UrlEncodedFormEntity(valuePairs, Consts.UTF_8);
        entity.setContentType("application/x-www-form-urlencoded");

        // 创建一个post请求
        HttpPost post = new HttpPost("https://www.zhihu.com/login/email");
        // 注入post数据
        post.setEntity(entity);
        res = httpClient.execute(post, context);

        // 打印响应信息，查看是否登陆是否成功
        System.out.println("打印响应信息===========");
        HttpClientUtils.printResponse(res);
        res.close();

        System.out.println("登陆成功后,新的Cookie:===============");
        for (Cookie c : context.getCookieStore().getCookies()) {
          System.out.println(c.getName() + ": " + c.getValue());
        }

        // 构造一个新的get请求，用来测试登录是否成功
        HttpGet newGet = new HttpGet("http://www.zhihu.com/question/following");
        res = httpClient.execute(newGet, context);
        String content = EntityUtils.toString(res.getEntity());
        System.out.println("登陆成功后访问的页面===============");
        System.out.println(content);
        res.close();

      } finally {
        httpClient.close();
      }
    } catch (IOException e) {
      e.printStackTrace();
    }
  }
}