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
冷雨夜中漫步20 分钟前
Python快速入门(6)——for/if/while语句
开发语言·经验分享·笔记·python
JH30731 小时前
SpringBoot 优雅处理金额格式化:拦截器+自定义注解方案
java·spring boot·spring
m0_736919102 小时前
C++代码风格检查工具
开发语言·c++·算法
喵手2 小时前
Python爬虫实战:旅游数据采集实战 - 携程&去哪儿酒店机票价格监控完整方案(附CSV导出 + SQLite持久化存储)!
爬虫·python·爬虫实战·零基础python爬虫教学·采集结果csv导出·旅游数据采集·携程/去哪儿酒店机票价格监控
Coder_Boy_2 小时前
技术让开发更轻松的底层矛盾
java·大数据·数据库·人工智能·深度学习
2501_944934732 小时前
高职大数据技术专业,CDA和Python认证优先考哪个?
大数据·开发语言·python
invicinble3 小时前
对tomcat的提供的功能与底层拓扑结构与实现机制的理解
java·tomcat
较真的菜鸟3 小时前
使用ASM和agent监控属性变化
java
黎雁·泠崖3 小时前
【魔法森林冒险】5/14 Allen类(三):任务进度与状态管理
java·开发语言
2301_763472464 小时前
C++20概念(Concepts)入门指南
开发语言·c++·算法