java爬虫入门程序

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>

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

复制代码

package day02;
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 pacohngde {
    public static void main(String[] args) throws IOException {
        //注意这个方法是爬取网址所有位置

        //1.打开浏览器,创建Httpclient对象
       //        CloseableHttpclient httpclient = Httpclients.createDefault();
        CloseableHttpClient aDefault = HttpClients.createDefault();

     //2.输入网址，发起get请求创建HttpGet对象 输入你需要爬取的网址
     HttpGet httpGet = new HttpGet("https://zhuanlan.zhihu.com/p/98346518");

        //3.按回车，发起请求，返回响应，使用httpclient对象发起请求
        CloseableHttpResponse response = aDefault.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(response.getStatusLine().getStatusCode()== 200){
            //获取爬取数据
            HttpEntity httpEntity =response.getEntity();
            //将爬取数据解析为utf-8格式
          String content = EntityUtils.toString(httpEntity,"utf-8");
          //打印
                System.out.println(content);
}

复制代码

//释放资源
response.close();
//关闭网页
aDefault.close();
    }
}