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
罗超驿13 分钟前
2.算法效率的核心密码:时间复杂度和空间复杂度详解
java·数据结构·算法
栈溢出了1 小时前
Redis 分片集群与哈希槽笔记
java·redis·笔记·spring
遨游DATA1 小时前
Spring Boot 启动失败排查:如何区分多 Bean 冲突与清理阶段异常
java·spring boot·后端
从零开始的代码生活_2 小时前
C++ 内存管理:从内存分区到 new/delete 底层原理
开发语言·c++·后端
wabs6662 小时前
关于单调栈【力扣739.每日温度的思考】
java·开发语言
AOwhisky2 小时前
Python 学习笔记(第三期)——流程控制核心知识点自测与详解
开发语言·笔记·python·学习·云原生·运维开发·流程控制
雪碧聊技术2 小时前
为什么要学函数式编程?
java·函数式编程
aaPIXa6223 小时前
C++ 用 13 条规则让模型写出安全现代 C++
java·c++·安全
逆向编程3 小时前
Socket异常连接自动清理方案
开发语言
2601_949817724 小时前
C++指针与引用深度精讲:底层原理、差异对比与高阶实战陷阱
java·jvm·c++