HttpClient

HttpClient

1.pom.xml依赖

<!-- 自动爬取 -->
<dependency>
    <groupId>org.apache.httpcomponents</groupId>
    <artifactId>httpclient</artifactId>
    <version>4.5.12</version>
</dependency>
<!-- 日志 -->
<dependency>
    <groupId>org.slf4j</groupId>
    <artifactId>slf4j-log4j12</artifactId>
    <version>2.0.0-alpha1</version>
    <scope>test</scope>
</dependency>

2.日志

#log4j.properties
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} [%c]-[%p] %m%n

3.入门程序-Get

3.1无参

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
        String uri = "http://www.itcast.cn";
        HttpGet httpGet = new HttpGet(uri);
        //3.按回车，发起请求，返回响应，使用HttpClient对象发起请求
        CloseableHttpResponse execute = httpClient.execute(httpGet);
        //4.解析响应，获取数据
        //判断状态码是否是200
        if (execute.getStatusLine().getStatusCode() == 200){
            //拿到响应体
            HttpEntity httpEntity = execute.getEntity();
            //拿到响应体的String对象
            String content = EntityUtils.toString(httpEntity, "utf8");
            System.out.println(content);
        }
    }
}

3.2带参数

public class HttpGetParamTest {
    public static void main(String[] args){
        //创建HttpClient对象
        CloseableHttpClient httpClient = HttpClients.createDefault();
        //设置请求地址是：http://yun.itheima.com/search
        String uri = "http://yun.itheima.com/search";
        URIBuilder builder = null;
        try {
            builder = new URIBuilder(uri);
            //设置参数
            builder.setParameter("keys", "java");
        } catch (URISyntaxException e) {
            e.printStackTrace();
        }
        String url = "http://www.itcast.cn";
        //创建HttpGet对象，设置url访问地址
        HttpGet httpGet = null;
        try {
            httpGet = new HttpGet(builder.build());
        } catch (URISyntaxException e) {
            e.printStackTrace();
        }
        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);
                System.out.println(content.length());
            }
        } catch (IOException e) {
            e.printStackTrace();
        }finally {
            //关闭连接
            try {
                response.close();
                httpClient.close();
            } catch (IOException e) {
                e.printStackTrace();
            }
        }
    }
}

4.入门程序-Post

4.1无参

public class HttpPostTest {
    public static void main(String[] args){
        //创建HttpClient对象
        CloseableHttpClient httpClient = HttpClients.createDefault();
        String url = "http://www.itcast.cn";
        //创建HttpGet对象，设置url访问地址
        HttpPost httpPost = new HttpPost(url);
        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);
                System.out.println(content.length());
            }
        } catch (IOException e) {
            e.printStackTrace();
        }finally {
            //关闭连接
            try {
                response.close();
                httpClient.close();
            } catch (IOException e) {
                e.printStackTrace();
            }
        }
    }
}

4.2带参数

public class HttpPostParamTest {
    public static void main(String[] args) throws UnsupportedEncodingException {
        //创建HttpClient对象
        CloseableHttpClient httpClient = HttpClients.createDefault();
        String url = "http://yun.itheima.com/search";
        //创建HttpGet对象，设置url访问地址
        HttpPost httpPost = new HttpPost(url);
        //声明List集合，封装表单中的参数
        ArrayList<NameValuePair> params = new ArrayList<NameValuePair>();
        params.add(new BasicNameValuePair("keys", "java"));
        //创建表单的Entity对象
        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);
                System.out.println(content.length());
            }
        } catch (IOException e) {
            e.printStackTrace();
        }finally {
            //关闭连接
            try {
                response.close();
                httpClient.close();
            } catch (IOException e) {
                e.printStackTrace();
            }
        }
    }
}

5.结果

6.连接池

​ 每次请求都要创建HttpClient，会有频繁创建和销毁的问题，这里可以参照数据库连接池，使用连接池来解决这个问题。

代码

public class HttpClientPoolTest {
    public static void main(String[] args){
        //创建连接池管理器
        PoolingHttpClientConnectionManager poolingHttpClientConnectionManager = new PoolingHttpClientConnectionManager();
        //设置最大连接数
        poolingHttpClientConnectionManager.setMaxTotal(100);
        //设置每个主机的最大连接数：这个可以设置每个主机可同时连接的最大连接数，防止连接池里所有连接都去爬同一个网站，造成数据爬取不均衡
        poolingHttpClientConnectionManager.setDefaultMaxPerRoute(10);
        //使用连接池管理器发起请求
        doGet(poolingHttpClientConnectionManager);
        doGet(poolingHttpClientConnectionManager);

    }

    private static void doGet(PoolingHttpClientConnectionManager poolingHttpClientConnectionManager) {
        //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(poolingHttpClientConnectionManager).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);
                System.out.println(content.length());
            }
        } catch (IOException e) {
            e.printStackTrace();
        }finally {
            if (response != null){
                try {
                    response.close();
                } catch (IOException e) {
                    e.printStackTrace();
                }
//                这里不关闭httpClient的连接，因为是连接池管理的，不手动释放
//                httpClient.close();
            }
        }
    }
}

7.设置请求参数

设置连接的超时时间等参数

public class HttpConfigTest {
    public static void main(String[] args){
        //创建HttpClient对象
        CloseableHttpClient httpClient = HttpClients.createDefault();
        String url = "http://www.itcast.cn";
        //创建HttpGet对象，设置url访问地址
        HttpGet httpGet = new HttpGet(url);
        
        //配置请求信息
        RequestConfig requestConfig = RequestConfig.custom().setConnectTimeout(1000)  //创建连接的最长时间，单位：毫秒
                .setConnectionRequestTimeout(500)   //设置获取连接的最长时间，单位：毫秒
                .setSocketTimeout(10 * 1000)          //设置数据传输的最长时间，单位：毫秒
                .build();
        //给请求设置请求信息
        httpGet.setConfig(requestConfig);

        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);
                System.out.println(content.length());
            }
        } catch (IOException e) {
            e.printStackTrace();
        }finally {
            //关闭连接
            try {
                response.close();
                httpClient.close();
            } catch (IOException e) {
                e.printStackTrace();
            }
        }
    }
}