httpclient是Java的http协议客户端,用于抓取网页
首先pom.xml文件导入依赖
<!--HttpClient-->
<dependency>
<groupId>org.apache.httpcomponents</groupId>
<artifactId>httpclient</artifactId>
<version>4.5.10</version>
</dependency>
<!--日志-->
<dependency>
<groupId>org.slf4j</groupId>
<artifactId>slf4j-log4j12</artifactId>
<version>1.7.25</version>
<scope>test</scope>
</dependency>
添加log4j.properties日志配置文件
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
接下来给出httpclient的get/post请求方式即带参不带参的例子,使用起来不难,可作为参考
GET请求
package com.spride.demo.testHttp;
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;
import java.io.IOException;
public class HttpGetTest {
public static void main(String[] args) throws IOException {
//打开浏览器
CloseableHttpClient httpClient = HttpClients.createDefault();
//目标网址,发起get请求创建httpGET对象
HttpGet httpGet = new HttpGet("https://www.baidu.com/");
//发起请求,返回响应
CloseableHttpResponse response = httpClient.execute(httpGet);
//解析响应
if (response.getStatusLine().getStatusCode() == 200) {
HttpEntity httpEntity = response.getEntity();
String content = EntityUtils.toString(httpEntity, "utf-8");
System.out.println(content);
}
//关闭资源
response.close();
httpClient.close();
}
}
GET带参请求
package com.spride.demo.testHttp;
import org.apache.http.HttpEntity;
import org.apache.http.client.methods.CloseableHttpResponse;
import org.apache.http.client.methods.HttpGet;
import org.apache.http.client.utils.URIBuilder;
import org.apache.http.impl.client.CloseableHttpClient;
import org.apache.http.impl.client.HttpClients;
import org.apache.http.util.EntityUtils;
import java.io.IOException;
import java.net.URISyntaxException;
public class HttpGetParamTest {
public static void main(String[] args) throws IOException, URISyntaxException {
//打开浏览器
CloseableHttpClient httpClient = HttpClients.createDefault();
//创建URLBuilder
URIBuilder urlBuilder = new URIBuilder("http://yun.itheima.com/search");
//设置参数
urlBuilder.setParameter("keys","java");
//目标网址,发起get请求创建httpGET对象
HttpGet httpGet = new HttpGet(urlBuilder.build());
//发起请求,返回响应
CloseableHttpResponse response = httpClient.execute(httpGet);
//解析响应
if (response.getStatusLine().getStatusCode() == 200) {
HttpEntity httpEntity = response.getEntity();
String content = EntityUtils.toString(httpEntity, "utf-8");
System.out.println(content);
}
//关闭资源
response.close();
httpClient.close();
}
}
POST请求
post不带参请求其实和get不带参请求差不多,只是将HttpGet换为HttpPost
package com.spride.demo.testHttp;
import org.apache.http.HttpEntity;
import org.apache.http.client.methods.CloseableHttpResponse;
import org.apache.http.client.methods.HttpPost;
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 HttpPostTest {
public static void main(String[] args) throws IOException {
//打开浏览器
CloseableHttpClient httpClient = HttpClients.createDefault();
//目标网址,发起get请求创建httpGET对象
HttpPost httpPost = new HttpPost("https://www.baidu.com");
//发起请求,返回响应
CloseableHttpResponse response = httpClient.execute(httpPost);
//解析响应
if(response.getStatusLine().getStatusCode()==200){
HttpEntity httpEntity = response.getEntity();
String content = EntityUtils.toString(httpEntity,"utf-8");
System.out.println(content);
}
//关闭资源
response.close();
httpClient.close();
}
}
POST带参请求
post带参请求需要将参数进行封装
package com.spride.demo.testHttp;
import org.apache.http.HttpEntity;
import org.apache.http.NameValuePair;
import org.apache.http.client.entity.UrlEncodedFormEntity;
import org.apache.http.client.methods.CloseableHttpResponse;
import org.apache.http.client.methods.HttpPost;
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;
import java.io.IOException;
import java.util.ArrayList;
import java.util.List;
public class HttpPostParamTest {
public static void main(String[] args) throws IOException {
//创建HttpClient对象
CloseableHttpClient httpClient = HttpClients.createDefault();
//创建HttpPost对象,设置访问地址
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<>();
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);
//发起请求,返回响应
CloseableHttpResponse response = httpClient.execute(httpPost);
//解析响应
if (response.getStatusLine().getStatusCode() == 200) {
HttpEntity httpEntity = response.getEntity();
String content = EntityUtils.toString(httpEntity, "utf8");
System.out.println(content.length());
}
//关闭资源
response.close();
httpClient.close();
}
}
Httpclien连接池
package com.spride.demo.testHttp;
import org.apache.http.NameValuePair;
import org.apache.http.client.entity.UrlEncodedFormEntity;
import org.apache.http.client.methods.CloseableHttpResponse;
import org.apache.http.client.methods.HttpPost;
import org.apache.http.impl.client.CloseableHttpClient;
import org.apache.http.impl.client.HttpClients;
import org.apache.http.impl.conn.PoolingHttpClientConnectionManager;
import org.apache.http.message.BasicNameValuePair;
import org.apache.http.util.EntityUtils;
import java.io.IOException;
import java.util.ArrayList;
import java.util.List;
public class HttpClientPoolTest {
public static void main(String[] args) throws IOException {
//创建连接池管理器
PoolingHttpClientConnectionManager cm = new PoolingHttpClientConnectionManager();
//设置最大连接数
cm.setMaxTotal(100);
//设置每个主机最大连接数
cm.setDefaultMaxPerRoute(10);
//使用连接池管理器发起请求
doGet(cm);
}
private static void doGet(PoolingHttpClientConnectionManager cm) throws IOException {
//不是每次创建新的httpclient,而是从连接池中获取
CloseableHttpClient httpClient = HttpClients.custom().setConnectionManager(cm).build();
HttpPost httpPost = new HttpPost("http://yun.itheima.com/search");
List<NameValuePair> parameters = new ArrayList<>();
parameters.add(new BasicNameValuePair("keys","java"));
UrlEncodedFormEntity formEntity = new UrlEncodedFormEntity(parameters, "utf8");
httpPost.setEntity(formEntity);
CloseableHttpResponse response = httpClient.execute(httpPost);
if(response.getStatusLine().getStatusCode()==200){
System.out.println(EntityUtils.toString(response.getEntity()));
}
response.close();
}
}
Httpclient请求参数配置
package com.spride.demo.testHttp;
import org.apache.http.HttpEntity;
import org.apache.http.client.config.RequestConfig;
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 HttpConfigTest {
public static void main(String[] args) throws IOException {
//打开浏览器
CloseableHttpClient httpClient = HttpClients.createDefault();
//目标网址,发起get请求创建httpGET对象
HttpGet httpGet = new HttpGet("https://www.baidu.com/");
//配置请求信息
RequestConfig config = RequestConfig.custom().setConnectTimeout(1000)
.setConnectionRequestTimeout(500)
.setSocketTimeout(10*1000)
.build();
//设置请求信息
httpGet.setConfig(config);
//发起请求,返回响应
CloseableHttpResponse response = httpClient.execute(httpGet);
//解析响应
if (response.getStatusLine().getStatusCode() == 200) {
HttpEntity httpEntity = response.getEntity();
String content = EntityUtils.toString(httpEntity, "utf-8");
System.out.println(content);
}
//关闭资源
response.close();
httpClient.close();
}
}
HttpClient的简单使用,通过上面的例子,很容易就可以上手