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
迪康Defender4 分钟前
PHP 高危漏洞应急分析:从风险原理到端点侧纵深防护
运维·开发语言·安全·自动化·php·运维开发·远程工作
卓豪终端管理5 分钟前
【无标题】
java·服务器·前端
2601_9669496510 分钟前
为什么不应该把 QuantDash API Key 直接写进公开代码仓库?从 Git 提交历史理解凭证泄露风险
开发语言·python·数据分析·pandas·量化交易·股票数据·quantdash
智_永无止境12 分钟前
又找到一个纯Java的OCR项目,识别的格式还挺多
java·开发语言·ocr
小灰灰搞电子13 分钟前
Rust+Slint 实现动态流光边框源码分享
开发语言·前端·rust·流光边框
学编程就要猛17 分钟前
MCP(Model Context Protocol)
java·springai
用户0723670666027 分钟前
Apollo 配置热更新落地:让 Spring Boot @ConfigurationProperties Bean 不重启即时生效
java
包小黑29 分钟前
Python 转 EXE (实用工具)
开发语言·python
2601_9707038333 分钟前
中国除湿机与湿度控制行业研究报告
java·大数据·人工智能
我命由我1234543 分钟前
6-3.Python 异常处理 - 异常处理进阶(else 块与 finally 块、异常传递、自定义异常)
开发语言·前端·数据库·后端·python·学习·java-ee