java 爬虫入门

依赖

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

package ai.wincloud.dapp.common.util;

import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;

/**
 * @author cy
 */
public class HtmlUtil {
    public static String getHtml(String html) {
//        HtmlUtil.
        return ";";
    }

    public static void main(String[] args) {
        try {
            // 连接到网页
            Document document = Jsoup.connect("https://bscscan.com/tx/0x604eefe23e37e6d57c38360c6a23a34be574bb1d37eb2f100c411015b4650d24").get();

            // 获取指定的HTML标签内容
            Element element = document.select("span#spanTxHash").first();
            if (element != null) {
                String hash = element.text();
                System.out.println("hash: " + hash);
            }
            Element elementTime = document.select("span#showUtcLocalDate").first();
            String time = elementTime.attr("data-timestamp");

            Element elementStatus = document.select("div.col.col-md-9 span.badge.bg-success").first();
            String status = elementStatus.text();

            Element elementFrom = document.select("div.row.mb-4 div.col-md-9 div span.me-1 a").last();
            String from = elementFrom.text();

            Element elementTo = document.select("span.d-flex.align-items-center span.d-inline").first();
            String to = elementTo.text();

            Element elementMoney = document.select(".d-flex.flex-wrap.align-items-center span.me-1").first();
            String money = elementMoney.getElementsByAttribute("2").text();
            System.out.println("content: " + money);
        } catch (Exception e) {
            e.printStackTrace();
        }
    }
}