java网络爬虫2：HttpClient设置超时

HttpClient设置超时：

当我们不希望在某个网址上花太多的时间去等待下载完成时，要设置超时，设置方法如下

package java爬虫;

import java.io.BufferedReader;
import java.io.IOException;
import java.io.InputStreamReader;
import java.net.MalformedURLException;
import java.net.URL;

import org.apache.http.HttpEntity;
import org.apache.http.HttpResponse;
import org.apache.http.client.config.RequestConfig;
import org.apache.http.client.methods.HttpGet;
import org.apache.http.impl.client.CloseableHttpClient;
import org.apache.http.impl.client.HttpClientBuilder;
import org.apache.http.util.EntityUtils;
import org.omg.CORBA.portable.InputStream;

public class first {

	public static void main(String[] args) throws IOException {
		// TODO Auto-generated method stub
		//配置参数
		int socketTimeout=9000;//读数据超时
		int connectionTimeout=9000;//连接超时
		//请求配置
		RequestConfig requestConfig=RequestConfig.custom()
				.setConnectTimeout(connectionTimeout)
				.setConnectionRequestTimeout(connectionTimeout)
				.setSocketTimeout(socketTimeout).build();
		//创建一个客户端。类似于打开一个浏览器
		CloseableHttpClient httpclient=HttpClientBuilder.create()
										.setDefaultRequestConfig(requestConfig).build();
		//创建一个get方法，类似于在浏览器地址栏中输入一个地址
		HttpGet httpget=new HttpGet("http://www.sdu.edu.cn/");
		//类似于在浏览器中输入回车，获得网页内容
		HttpResponse response=httpclient.execute(httpget);
		//查看返回的内容。类似于在浏览器中查看网页源代码
		HttpEntity entity=response.getEntity();
		//如果返回的内容不是空的话
		if(entity!=null) {
			//读入内容流。并以字符串的形式返回，在这里指定网页的编码是gbk
			String content=EntityUtils.toString(entity,"gbk");
			//输出内容
			System.out.println(content);
			//关闭内容流
			EntityUtils.consume(entity);
		}
		//释放连接
		httpclient.close();
	}

}