Java网络爬虫 HttpClient

简介 : HttpClient是Apache Jakarta Common下的子项目,用于提供高效的,功能丰富的支持HTTP协议的客户编程工具包,其主要功能如下:

1. 实现了所有HTTP的方法 : GET,POST,PUT,HEAD ..
2. 支持自动重定向
3. 支持HTTPS协议
4. 支持代理服务器

关于Http请求的方法说明，参考大佬整理的博客：

https://www.cnblogs.com/williamjie/p/9099940.html

一、环境准备

1 JDK1.8

2 IntelliJ IDEA

3 IDEA自带的Maven

创建Maven工程itcast-crawler-first并给pom.xml加入依赖

关于xml语言的介绍

<dependencies>
    <!-- HttpClient -->
    <dependency>
        <groupId>org.apache.httpcomponents</groupId>
        <artifactId>httpclient</artifactId>
        <version>4.5.3</version>
    </dependency>

    <!-- 日志 -->
    <dependency>
        <groupId>org.slf4j</groupId>
        <artifactId>slf4j-log4j12</artifactId>
        <version>1.7.25</version>
    </dependency>
</dependencies>

关于日志的配置文件

log4j.rootLogger=DEBUG,A1
log4j.logger.cn.itcast = DEBUG

log4j.appender.A1=org.apache.log4j.ConsoleAppender
log4j.appender.A1.layout=org.apache.log4j.PatternLayout
log4j.appender.A1.layout.ConversionPattern=%-d{yyyy-MM-dd HH:mm:ss,SSS} [%t] [%c]-[%p] %m%n

log4j可以将日志以文件的形式输出，也可以输出打印在控制台上，同时可以设置输出的日志内容显示格式、日志文件的生成方式（追加、覆盖、设置日志文件大小等等）。我这里就是直接将日志打印到控制台上。org.apache.log4j.ConsoleAppender

二、编写代码

编写最简单的爬虫，抓取传智播客首页：http://www.itcast.cn/

public class CrawlerFirst {

    public static void main(String[] args) throws Exception {
        //1. 打开浏览器,创建HttpClient对象
        CloseableHttpClient httpClient = HttpClients.createDefault();

        //2. 输入网址,发起get请求创建HttpGet对象
        HttpGet httpGet = new HttpGet("http://www.itcast.cn");

        //3.按回车，发起请求，返回响应，使用HttpClient对象发起请求
        CloseableHttpResponse response = httpClient.execute(httpGet);

        //4. 解析响应，获取数据
        //判断状态码是否是200
        if (response.getStatusLine().getStatusCode() == 200) {
            HttpEntity httpEntity = response.getEntity();
            String content = EntityUtils.toString(httpEntity, "utf8");

            System.out.println(content);
        }
    }
}

三、Get请求

package cn.itcast.crawler.test;

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;

import java.io.IOException;

public class HttpGetTest {

    public static void main(String[] args)  {
        //创建HttpClient对象
        CloseableHttpClient httpClient = HttpClients.createDefault();

        //创建HttpGet对象，设置url访问地址
        HttpGet httpGet = new HttpGet("http://www.itcast.cn");

        CloseableHttpResponse response = null;
        try {
            //使用HttpClient发起请求，获取response
             response = httpClient.execute(httpGet);

            //解析响应
            if (response.getStatusLine().getStatusCode() == 200) {
                String content = EntityUtils.toString(response.getEntity(), "utf8");
                System.out.println(content.length());
            }

        } catch (IOException e) {
            e.printStackTrace();
        }finally {
            //关闭response
            try {
                response.close();
            } catch (IOException e) {
                e.printStackTrace();
            }
            try {
                httpClient.close();
            } catch (IOException e) {
                e.printStackTrace();
            }
        }
    }
}

四、带参数的GET请求

public class HttpGetParamTest {

    public static void main(String[] args) throws Exception {
        //创建HttpClient对象
        CloseableHttpClient httpClient = HttpClients.createDefault();

        //设置请求地址是：http://yun.itheima.com/search?keys=Java
        //创建URIBuilder
        URIBuilder uriBuilder = new URIBuilder("http://yun.itheima.com/search");
        //设置参数
        uriBuilder.setParameter("keys","Java");

        //创建HttpGet对象，设置url访问地址
        HttpGet httpGet = new HttpGet(uriBuilder.build());

        System.out.println("发起请求的信息："+httpGet);

        CloseableHttpResponse response = null;
        try {
            //使用HttpClient发起请求，获取response
             response = httpClient.execute(httpGet);

            //解析响应
            if (response.getStatusLine().getStatusCode() == 200) {
                String content = EntityUtils.toString(response.getEntity(), "utf8");
                System.out.println(content.length());
            }

        } catch (IOException e) {
            e.printStackTrace();
        }finally {
            //关闭response
            try {
                response.close();
            } catch (IOException e) {
                e.printStackTrace();
            }
            try {
                httpClient.close();
            } catch (IOException e) {
                e.printStackTrace();
            }
        }
    }
}

五、POST请求

public class HttpPostTest {

    public static void main(String[] args)  {
        //创建HttpClient对象
        CloseableHttpClient httpClient = HttpClients.createDefault();

        //创建HttpPost对象，设置url访问地址
        HttpPost httpPost = new HttpPost("http://www.itcast.cn");

        CloseableHttpResponse response = null;
        try {
            //使用HttpClient发起请求，获取response
             response = httpClient.execute(httpPost);

            //解析响应
            if (response.getStatusLine().getStatusCode() == 200) {
                String content = EntityUtils.toString(response.getEntity(), "utf8");
                System.out.println(content.length());
            }

        } catch (IOException e) {
            e.printStackTrace();
        }finally {
            //关闭response
            try {
                response.close();
            } catch (IOException e) {
                e.printStackTrace();
            }
            try {
                httpClient.close();
            } catch (IOException e) {
                e.printStackTrace();
            }
        }
    }
}

六、带参数的POST请求

public class HttpPostParamTest {

    public static void main(String[] args) throws Exception {
        //创建HttpClient对象
        CloseableHttpClient httpClient = HttpClients.createDefault();

        //创建HttpPost对象，设置url访问地址
        HttpPost httpPost = new HttpPost("http://yun.itheima.com/search");

        //声明List集合，封装表单中的参数
        List<NameValuePair> params = new ArrayList<NameValuePair>();
        //设置请求地址是：http://yun.itheima.com/search?keys=Java
        params.add(new BasicNameValuePair("keys","Java"));

        //创建表单的Entity对象,第一个参数就是封装好的表单数据，第二个参数就是编码
        UrlEncodedFormEntity formEntity = new UrlEncodedFormEntity(params,"utf8");

        //设置表单的Entity对象到Post请求中
        httpPost.setEntity(formEntity);

        CloseableHttpResponse response = null;
        try {
            //使用HttpClient发起请求，获取response
             response = httpClient.execute(httpPost);

            //解析响应
            if (response.getStatusLine().getStatusCode() == 200) {
                String content = EntityUtils.toString(response.getEntity(), "utf8");
                System.out.println(content.length());
            }

        } catch (IOException e) {
            e.printStackTrace();
        }finally {
            //关闭response
            try {
                response.close();
            } catch (IOException e) {
                e.printStackTrace();
            }
            try {
                httpClient.close();
            } catch (IOException e) {
                e.printStackTrace();
            }
        }
    }
}

七、HTTP连接池

如果每次请求都要创建HttpClient，会有频繁创建和销毁的问题，可以使用连接池来解决这个问题。

测试以下代码，并断点查看每次获取的HttpClient都是不一样的。

public class HttpClientPoolTest {

    public static void main(String[] args) {
        //创建连接池管理器
        PoolingHttpClientConnectionManager cm = new PoolingHttpClientConnectionManager();

        //设置最大连接数
        cm.setMaxTotal(100);

        //设置每个主机的最大连接数
        cm.setDefaultMaxPerRoute(10);

        //使用连接池管理器发起请求
        doGet(cm);
        doGet(cm);
    }

    private static void doGet(PoolingHttpClientConnectionManager cm) {
        //不是每次创建新的HttpClient，而是从连接池中获取HttpClient对象
        CloseableHttpClient httpClient = HttpClients.custom().setConnectionManager(cm).build();

        HttpGet httpGet = new HttpGet("http://www.itcast.cn");

        CloseableHttpResponse response = null;
        try {
            response = httpClient.execute(httpGet);

            if (response.getStatusLine().getStatusCode() == 200) {
                String content = EntityUtils.toString(response.getEntity(), "utf8");

                System.out.println(content.length());
            }

        } catch (IOException e) {
            e.printStackTrace();
        }finally {
            if (response != null) {
                try {
                    response.close();
                } catch (IOException e) {
                    e.printStackTrace();
                }
                //不能关闭HttpClient，由连接池管理HttpClient
                //httpClient.close();
            }
        }

    }
}