Java使用Jsoup实现将浏览器书签HTML转换为JSON

<DL>
  <DT><H3>文件夹</H3>
  <DL>
    <DT><A href="https://www.baidu.com/" rel="external nofollow" >百度</A>
    <DT><H3>子文件夹</H3>
    <DL>
      <DT><A href="https://map.baidu.com/" rel="external nofollow" >百度地图</A>
    </DL>
  </DL>
</DL>

package com.nav.test;

import com.alibaba.fastjson2.JSONArray;
import com.alibaba.fastjson2.JSONObject;
import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import org.jsoup.select.Elements;
import org.junit.Test;
import org.junit.runner.RunWith;
import org.springframework.boot.test.context.SpringBootTest;
import org.springframework.test.context.junit4.SpringRunner;

@SpringBootTest
@RunWith(SpringRunner.class)
public class Bookmark {

    @Test
    public void main() {
        // 模拟浏览器导出的书签 HTML 内容
        String bookmarkContent = "<!DOCTYPE NETSCAPE-Bookmark-file-1>\n" +
                "<!-- This is an automatically generated file. -->\n" +
                "<META HTTP-EQUIV=\"Content-Type\" CONTENT=\"text/html; charset=UTF-8\">\n" +
                "<TITLE>Bookmarks</TITLE>\n" +
                "<H1>Bookmarks</H1>\n" +
                "<DL><p>\n" +
                "    <DT><H3 ADD_DATE=\"1632971641\" LAST_MODIFIED=\"1689686797\" PERSONAL_TOOLBAR_FOLDER=\"true\">书签栏</H3>\n" +
                "    <DL><p>\n" +
                "        <DT><A HREF=\"https://www.baidu.com/\" ADD_DATE=\"1689686710\">百度一下，你就知道</A>\n" +
                "        <DT><H3 ADD_DATE=\"1689686747\" LAST_MODIFIED=\"1689686798\">子书签</H3>\n" +
                "        <DL><p>\n" +
                "            <DT><A HREF=\"https://map.baidu.com/\" ADD_DATE=\"1689686769\">百度地图</A>\n" +
                "        </DL><p>\n" +
                "    </DL><p>\n" +
                "</DL><p>";

        // 使用 Jsoup 解析 HTML
        Document doc = Jsoup.parse(bookmarkContent);

        // 找到书签栏（Chrome 的 PERSONAL_TOOLBAR_FOLDER）
        Element mainFolder = doc.select("h3[personal_toolbar_folder]").first();

        // 递归处理
        JSONObject result = processFolder(mainFolder);

        // 输出 JSON
        System.out.println(result.toJSONString());
    }

    /**
     * 递归处理文件夹
     *
     * @param folderElement 文件夹对应的 H3 元素
     * @return JSONObject 结构 {name, links, subFolders}
     */
    private static JSONObject processFolder(Element folderElement) {
        JSONObject folderJson = new JSONObject();

        // 文件夹名称
        folderJson.put("name", folderElement.text());

        // 当前文件夹对应的 <DL>
        Element dl = folderElement.nextElementSibling();

        // 当前目录下的链接
        JSONArray links = new JSONArray();
        for (Element a : dl.select("> dt > a")) {
            JSONObject linkJson = new JSONObject();
            linkJson.put("name", a.text());
            linkJson.put("url", a.attr("href"));
            links.add(linkJson);
        }
        folderJson.put("links", links);

        // 子文件夹
        JSONArray subFolders = new JSONArray();
        for (Element h3 : dl.select("> dt > h3")) {
            subFolders.add(processFolder(h3));
        }
        folderJson.put("subFolders", subFolders);

        return folderJson;
    }
}

{
  "name": "书签栏",
  "links": [
    {
      "name": "百度一下，你就知道",
      "url": "https://www.baidu.com/"
    }
  ],
  "subFolders": [
    {
      "name": "子书签",
      "links": [
        {
          "name": "百度地图",
          "url": "https://map.baidu.com/"
        }
      ],
      "subFolders": []
    }
  ]
}