今天刚开始看爬虫内容,跟着网上做了个Demo
先贴配置信息吧
log4j.properties
log4j.rootLogger=DEBUG,A1
log4j.logger.cn.itcast = DEBUG
###org.apache.log4j.ConsoleAppender(控制台)
log4j.appender.A1=org.apache.1og4j.ConsoleAppender
###2.3 配置日志信息的输出格式(Layout)
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
pom.xml
<?xml version="1.0" encoding="UTF-8"?>
<project xmlns="http://maven.apache.org/POM/4.0.0"
xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
<modelVersion>4.0.0</modelVersion>
<groupId>cn.itcast</groupId>
<artifactId>itcast-crawler-first</artifactId>
<version>1.0-SNAPSHOT</version>
<dependencies>
<!-- https://mvnrepository.com/artifact/org.apache.httpcomponents/httpclient -->
<dependency>
<groupId>org.apache.httpcomponents</groupId>
<artifactId>httpclient</artifactId>
<version>4.5.2</version>
</dependency>
<!-- https://mvnrepository.com/artifact/org.slf4j/slf4j-log4j12 -->
<dependency>
<groupId>org.slf4j</groupId>
<artifactId>slf4j-log4j12</artifactId>
<version>1.7.25</version>
<scope>test</scope>
</dependency>
</dependencies>
</project>
java
package cn.a.aa.test;
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;
public class Demo{
public static void main(String[] args) throws Exception {
//1.打开浏览器。创建一个httpclient对象
//HttpClient(用CloseableHttpClient发送get/post请求)
// HttpClient httpClient = new HttpClient();
CloseableHttpClient httpClient = HttpClients.createDefault();
//2.输入网址,发起get请求,创建httpget对象
HttpGet httpGet = new HttpGet("http://www.itcast.cn");
//3.按回车,发起请求,返回响应,使用httpClient对象发送请求,相当于回车
CloseableHttpResponse response = httpClient.execute(httpGet);
//4.解析响应,获取数据
//判断响应状态码是否是200,200就代表响应成功
if (response.getStatusLine().getStatusCode()==200) {
//得到响应体,比如请求网页的时候,返回的是网页的HTML代码
HttpEntity httpEntity = response.getEntity();
//对其进行解析,获得其里面的数据
String content = EntityUtils.toString(httpEntity,"utf8");
System.out.println(content);
}
}
}