public Boolean checkHttpStatusCode(String code) {
        if (code.equals("404") || code.equals("503")) {
            return true;
        }
        return false;
    }

public static String getHtmlTitle(String html){
        try {
            // 使用 Jsoup 解析 HTML
            Document doc = Jsoup.parse(html);

            // 获取 <title> 标签
            Element titleElement = doc.select("title").first();

            // 检查是否存在 <title> 标签并获取其内容
            if (titleElement != null) {
                String title = titleElement.text();
                return title;
            } else {
                return "";
            }
        } catch (Exception e) {
            e.printStackTrace();
        }
        return "";
    }

import org.apache.commons.lang3.StringEscapeUtils;

import java.io.IOException;
import java.nio.charset.StandardCharsets;
import java.util.regex.Matcher;
import java.util.regex.Pattern;

public class HtmlUtil {



    public static String delHTMLTag(String htmlStr) {
        String regEx_script = "<script[^>]*?>[\\s\\S]*?<\\/script>"; //定义script的正则表达式
        String regEx_style = "<style[^>]*?>[\\s\\S]*?<\\/style>"; //定义style的正则表达式
        String regEx_html = "<[^>]+>"; //定义HTML标签的正则表达式

        Pattern p_script = Pattern.compile(regEx_script, Pattern.CASE_INSENSITIVE);
        Matcher m_script = p_script.matcher(htmlStr);
        htmlStr = m_script.replaceAll(""); //过滤script标签

        Pattern p_style = Pattern.compile(regEx_style, Pattern.CASE_INSENSITIVE);
        Matcher m_style = p_style.matcher(htmlStr);
        htmlStr = m_style.replaceAll(""); //过滤style标签

        Pattern p_html = Pattern.compile(regEx_html, Pattern.CASE_INSENSITIVE);
        Matcher m_html = p_html.matcher(htmlStr);
        htmlStr = m_html.replaceAll(""); //过滤html标签

        return htmlStr.trim();
    }

    public static String htmlTextFormat(String htmlText) {
        htmlText = htmlText
                .replaceAll("(\\\\n)+", " ")
                .replaceAll("(\\\\t)+"," ")
                .replaceAll("(\t)+"," ")
                .replaceAll("(\n)+"," ");
        htmlText = htmlText.replaceAll(" +"," ");
        htmlText = htmlText.replaceAll(" +"," ");
        return htmlText;
    }

    public static String getContent(String html) {
        String ans = "";
        try {
            html = StringEscapeUtils.unescapeHtml4(html);
            html = delHTMLTag(html);
            html = htmlTextFormat(html);

            return html;
        } catch (Exception e) {
            e.printStackTrace();
        }
        return ans;
    }
}

public class UrlPattern {
    private String pattern; // 正则
    private String description; // 描述
    private String location; // 位置
}

private Boolean checkOneUrlPattern(UrlPattern urlPattern, String url) {
        URL url1 = null;
        try {
            url1 = new URL(url);
        } catch (MalformedURLException e) {
            e.printStackTrace();
        }
        if (Objects.isNull(url1)) return false;
        Pattern pattern = Pattern.compile(urlPattern.getPattern());
        String val = "";
        if (urlPattern.getLocation().equalsIgnoreCase("path")) {
            val = url1.getPath();
        } else if (urlPattern.getLocation().equalsIgnoreCase("query")) {
            val = url1.getQuery();
        } else if (urlPattern.getLocation().equalsIgnoreCase("host")) {
            val = url1.getHost();
        }
        if (!StringUtils.hasText(val))return false;
        Matcher matcher = pattern.matcher(val);
        if (matcher.find()) {
            return true;
        }
        return false;
    }

public class PageStructUtil {

    public static List<String> getAllLabelsFromHtml(String html) {
        Document document = Jsoup.parse(html);
        Elements elements = document.getAllElements();
        List<String> elementList = new ArrayList<>();
        for (Element element : elements) {
            elementList.add(element.nodeName());
        }
        return elementList;
    }


    /**
     * a 基于 base的相似性
     *
     * @param a
     * @param base
     * @return
     */
    public static Double pageStructScore(List<String> a, List<String> base) {
        SequenceUtils<String> stringSequenceUtils = new SequenceUtils<>();
        Integer length = stringSequenceUtils.getLongestCommonSequence(a, base);
        int n = base.size();
        int m = a.size();
        // TODO: 2020/5/25 定义：页面结构的相似度为 (2.0*公共序列的长度）/(旧的公共序列的长度+新的公共序列的长度)
        Double score = (2 * length) / ((n + m) * 1.0);
        return score;
    }


    public static void main(String[] args) {

    }

}

/**
     * 自出404页面的页面结构分析
     *
     * @param user404Html
     * @param html
     * @param score
     * @return
     */
    public Boolean checkUserPage404Struct(String user404Html, String html, Double score) {
        try {
            return PageStructUtil.pageStructScore(PageStructUtil.getAllLabelsFromHtml(user404Html), PageStructUtil.getAllLabelsFromHtml(html)) >= score;
        } catch (Exception e) {
        }
        return false;
    }