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
沛沛老爹6 分钟前
Web转AI架构篇 Agent Skills vs MCP:工具箱与标准接口的本质区别
java·开发语言·前端·人工智能·架构·企业开发
码农小卡拉11 分钟前
Maven与Gradle选型指南:如何匹配项目的依赖管理需求
java·gradle·maven
avi911114 分钟前
Unity 天命6源码- 商业游戏说明分析
开发语言·unity·c#·游戏开发·游戏源码
黎雁·泠崖14 分钟前
吃透Java操作符进阶:算术+移位操作符 全解析(Java&C区别+完整案例+避坑指南)
java·c语言·python
低频电磁之道40 分钟前
编译C++的几种方式(MSVC编译器)
开发语言·c++
Zsy_0510031 小时前
【C++】类和对象(一)
开发语言·c++
Yu_iChan1 小时前
Day10 用户端订单模块
java
菜鸟233号1 小时前
力扣377 组合总和 Ⅳ java实现
java·数据结构·算法·leetcode
星火开发设计2 小时前
Java面向对象三大特性:封装、继承与多态的深度解析及实战
java·开发语言·microsoft·多态·继承·面向对象·封装