1.建一个maven项目
2.添加依赖
<!-- https://mvnrepository.com/artifact/org.apache.httpcomponents/httpclient -->
<dependency>
<groupId>org.apache.httpcomponents</groupId>
<artifactId>httpclient</artifactId>
<version>4.5.6</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>
3.配置日志,resources下建 log4j.properties
log4j.rootLogger=DEBUG,A1
log4j.logger.域名后缀.域名.项目名 = DEBUG
log4j.append.A1 = org.apache.log4j.ConsoleAppender
log4j.append.A1.layout = org.apache.log4j.PatternLayout
log4j.append.A1.layout.ConversionPattern=%-d{yyyy-MM-dd HH:mm:ss,SSS} [%t] [%c]-[%p] %m%n
4.开始撸代java码
public class CrawlerDemo {
public static void main(String[] args) throws Exception {
//打开浏览器,创建httpclient
CloseableHttpClient httpClient = HttpClients.createDefault();
//输入网址
HttpGet httpGet = new HttpGet("http://www.xxxx.cn/");
//按回车发起请求返回响应
CloseableHttpResponse response = httpClient.execute(httpGet);
//解析响应,获取数据,判断状态码
if(response.getStatusLine().getStatusCode() == 200){
HttpEntity httpEntity = response.getEntity();
//字符集
String content = EntityUtils.toString(httpEntity,"utf-8");
System.out.println(content);
}
}
}