JAVA爬虫系列

准备工作

导入依赖

XML 复制代码
 <dependency>
            <groupId>org.apache.httpcomponents</groupId>
            <artifactId>httpclient</artifactId>
            <version>4.5.2</version>
        </dependency>

yml

XML 复制代码
logging:
  level:
    root: info
    com.lrm: debug

1.入门程序(获取到静态页面)

java 复制代码
package com.itheima.reggie.utils;


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;

/**
 * @Author lpc
 **/
public class CrawlerFirst {
    public static void main(String[] args) throws Exception {

        //1.打开浏览器,创建Httpclient对象
        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对象发起请求
        CloseableHttpResponse response = httpClient.execute(httpGet);
        //4.解析响应,获取数据
        //判斯状态码是否是200
        if (response.getStatusLine().getStatusCode()==200){
            HttpEntity httpEntity = response.getEntity();
            //获取前端静态页面
            String content = EntityUtils.toString(httpEntity,"utf8");
            System.out.println(content);
        }


    }
}

2.HttpClient---Get

java 复制代码
package com.itheima.reggie.utils;


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;

/**
 * @Author lpc
 * @Date 2024 03 12 00 23
 **/
public class CrawlerFirst {
    public static void main(String[] args){

        //1.打开浏览器,创建Httpclient对象
        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对象发起请求
        CloseableHttpResponse response = null;

        try {
            response = httpClient.execute(httpGet);
            //4.解析响应,获取数据
            //判斯状态码是否是200
            if (response.getStatusLine().getStatusCode()==200){
                HttpEntity httpEntity = response.getEntity();
                //获取前端静态页面
                String content = EntityUtils.toString(httpEntity,"utf8");
                System.out.println(content.length());
            }
        } catch (IOException e) {
            throw new RuntimeException(e);
        }finally {
            try {
                //关闭response
                response.close();
            } catch (IOException e) {
                throw new RuntimeException(e);
            }
            try {
                //关闭浏览器
                httpClient.close();
            } catch (IOException e) {
                throw new RuntimeException(e);
            }
        }


    }
}
相关推荐
007php0072 分钟前
某游戏互联网大厂Java面试深度解析:Java基础与性能优化(一)
java·数据库·面试·职场和发展·性能优化·golang·php
lly20240611 分钟前
Kotlin 类和对象
开发语言
是苏浙16 分钟前
零基础入门C语言之C语言内存函数
c语言·开发语言
qianbailiulimeng17 分钟前
2019阿里java面试题(一)
java·后端
zhmhbest17 分钟前
Qt 全球峰会 2025:中国站速递 —— 技术中立,拥抱更大生态
开发语言·qt·系统架构
程序员大雄学编程17 分钟前
用Python来学微积分30-微分方程初步
开发语言·python·线性代数·数学·微积分
关于不上作者榜就原神启动那件事22 分钟前
模拟算法乒乓球
开发语言·c++·算法
Bug退退退12330 分钟前
ArrayList 与 LinkedList 的区别
java·数据结构·算法
LBuffer39 分钟前
破解入门学习笔记题三十四
java·笔记·学习
缺点内向43 分钟前
Java: 如何在Excel中添加或删除分页符?
java·excel