<!--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
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.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 pacohngde {
public static void main(String[] args) throws IOException, URISyntaxException {
//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();
// 组合示例https://search.bilibili.com/all?keyword=药水哥&search_source=1
//创建URTBuilder 说白就是把网站组合起来使用搜索功能
URIBuilder uriBuilder = new URIBuilder("https://search.bilibili.com/all");
//设置参数
uriBuilder.setParameter("keyword","药水哥").setParameter("search_source","1");
//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(uriBuilder.build());
System.out.println("要爬取的网址"+httpGet);
//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,"utf8");
//打印
System.out.println(content);
}
//释放资源
response.close();
//关闭网页
aDefault.close();
}
}