线程池的方式爬虫

复制代码

<!--爬虫仅支持1.8版本的jdk-->
<!-- 爬虫需要的依赖-->
<dependency>
    <groupId>org.apache.httpcomponents</groupId>
    <artifactId>httpclient</artifactId>
    <version>4.5.2</version>
</dependency>

<!-- 爬虫需要的日志依赖-->
<dependency>
    <groupId>org.slf4j</groupId>
    <artifactId>slf4j-log4j12</artifactId>
    <version>1.7.25</version>
</dependency>

爬虫配置文件位置及存放位置

复制代码

#爬虫日志配置文件 不写就报错
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

实例代码

复制代码

package day02;
import org.apache.http.HttpEntity;
import org.apache.http.ParseException;
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.impl.conn.PoolingHttpClientConnectionManager;
import org.apache.http.util.EntityUtils;

import java.io.IOException;

public class pacohngde2 {
    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);
        //设置每个主机的最大连接数  就是说每个网页地址最多分配10个线程
        cm.setDefaultMaxPerRoute(10);
        
        lianjie(cm);

    }

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

        //输入需要爬取的网址地址
        HttpGet httpGet = new HttpGet("https://www.gushicimingju.com/gushi/tangshisanbaishou/");
//          把地址交给CloseableHttpResponse 去爬取数据
        CloseableHttpResponse execute = build.execute(httpGet);

        //4.解析响应，获取数据//判断状态码是否是200     200为正常型号  其他为异常
        if (execute.getStatusLine().getStatusCode() == 200) {
            try {
                //获取爬取数据
                HttpEntity httpEntity = execute.getEntity();
                //将爬取数据解析为utf-8格式
                String content = EntityUtils.toString(httpEntity, "utf8");
                //打印
                System.out.println(content);
            } catch (IOException e) {
                e.printStackTrace();
            } catch (ParseException e) {
                e.printStackTrace();
            } finally {
                if (execute != null) {
                    execute.close();
                }
            }

        }
        
    }
}