Jsoup 解析网页内容获取年月日假期等

1 引入依赖

<dependency>
    <groupId>org.jsoup</groupId>
    <artifactId>jsoup</artifactId>
    <version>1.14.3</version>
</dependency>

2 工具代码

import lombok.extern.slf4j.Slf4j;
import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import org.jsoup.select.Elements;

import java.io.BufferedReader;
import java.io.IOException;
import java.io.InputStream;
import java.io.InputStreamReader;
import java.net.HttpURLConnection;
import java.net.MalformedURLException;
import java.net.URL;

/**
 * @author : wangcen
 * @description :
 * @date : 2023/3/10 16:51
 */
@Slf4j
public class HolidayUtil {
    public static void main(String[] args) {
        getDateFromPage("https://wannianrili.bmcx.com/");
    }

    public static void getDateFromPage(String url) {
        String pageContent = getPageContent(url);
        //获取Document对象
        Document parse  = Jsoup.parse(pageContent);

        //Element head = parse.head();
        Element body = parse.body();
        //通过class 获取元素列表
        Elements monthDay = body.getElementsByClass("wnrl_k_you");
        for (Element day : monthDay) {
            String style = day.attr("style");
            if( "display: block;".equals(style)) {
                Elements dayAttr = day.children();
                String dayTitle = dayAttr.get(0).html();
                String dateNum = dayAttr.get(1).html();
                String dateStr = dayAttr.get(2).html();
                log.info("dayTitle:"+dayTitle+", dateNum:"+ dateNum+", dateStr"+dateStr);
            }
        }
    }


    public static String getPageContent(String urlStr) {
        StringBuilder sb = new StringBuilder();
        HttpURLConnection httpUrlConn = null;
        InputStream input = null;;
        InputStreamReader read = null;
        BufferedReader br = null;
        try {
            //建立连接
            URL url = new URL(urlStr);
            httpUrlConn = (HttpURLConnection) url.openConnection();
            httpUrlConn.setDoInput(true);
            httpUrlConn.setRequestMethod("GET");
            httpUrlConn.setRequestProperty("User-Agent", "Mozilla/4.0 (compatible; MSIE 5.0; Windows NT; DigExt)");
            //获取输入流
            input = httpUrlConn.getInputStream();
            //将字节输入流转换为字符输入流
            read = new InputStreamReader(input, "utf-8");
            //为字符输入流添加缓冲
            br = new BufferedReader(read);
            // 读取返回结果
            String data = br.readLine();
            while(data!=null)  {
                sb.append(data);
                data=br.readLine();
            }
        } catch (MalformedURLException e) {
            e.printStackTrace();
        } catch (IOException e) {
            e.printStackTrace();
        } finally {
            try {
                if(br != null) br.close();
            } catch (IOException e) {
                e.printStackTrace();
            }
            try {
                if(read !=null) read.close();
            } catch (IOException e) {
                e.printStackTrace();
            }
            try {
                if(input != null)input.close();
            } catch (IOException e) {
                e.printStackTrace();
            }
            if(httpUrlConn != null)httpUrlConn.disconnect();
        }

        return sb.toString();
    }

}