只听说过用python做爬虫，java程序员笑了！

<table>
	<!-- 定义表格头部 -->
	<tr>
		<td>编号</td>
		<td>姓名</td>
	</tr>
	<!-- 定义表格内容 -->
	<tr>
		<td>100</td>
		<td>张三</td>
	</tr>
	<tr>
		<td>101</td>
		<td>李四</td>
	</tr>
</table>

<!--解析HTML-->
<dependency>
    <groupId>org.jsoup</groupId>
    <artifactId>jsoup</artifactId>
    <version>1.11.2</version>
</dependency>

public class ChinaRegionsInfo {

    /**
     * 行政区域编码
     */
    private String code;

    /**
     * 行政区域名称
     */
    private String name;

    /**
     * 行政区域类型，1:省份，2：城市，3：区或者县城
     */
    private Integer type;

    /**
     * 上一级行政区域编码
     */
    private String parentCode;

    //省略get、set
}

//需要抓取的网页地址
private static final String URL = "http://www.mca.gov.cn//article/sj/xzqh/2020/202006/202008310601.shtml";

public static void main(String[] args) throws IOException {
    List<ChinaRegionsInfo> regionsInfoList = new ArrayList<>();
	//抓取网页信息
    Document document = Jsoup.connect(URL).get();
	//获取真实的数据体
    Element element = document.getElementsByTag("tbody").get(0);
    String provinceCode = "";//省级编码
    String cityCode = "";//市级编码
    if(Objects.nonNull(element)){
        Elements trs = element.getElementsByTag("tr");
        for (int i = 3; i < trs.size(); i++) {
            Elements tds = trs.get(i).getElementsByTag("td");
            if(tds.size() < 3){
                continue;
            }
            Element td1 = tds.get(1);//行政区域编码
            Element td2 = tds.get(2);//行政区域名称
            if(StringUtils.isNotEmpty(td1.text())){
                if(td1.classNames().contains("xl7030796")){
                    if(td2.toString().contains("span")){
                        //市级
                        ChinaRegionsInfo chinaRegions = new ChinaRegionsInfo();
                        chinaRegions.setCode(td1.text());
                        chinaRegions.setName(td2.text());
                        chinaRegions.setType(2);
                        chinaRegions.setParentCode(provinceCode);
                        regionsInfoList.add(chinaRegions);
                        cityCode = td1.text();
                    } else {
                        //省级
                        ChinaRegionsInfo chinaRegions = new ChinaRegionsInfo();
                        chinaRegions.setCode(td1.text());
                        chinaRegions.setName(td2.text());
                        chinaRegions.setType(1);
                        chinaRegions.setParentCode("");
                        regionsInfoList.add(chinaRegions);
                        provinceCode = td1.text();
                    }

                } else {
                    //区或者县级
                    ChinaRegionsInfo chinaRegions = new ChinaRegionsInfo();
                    chinaRegions.setCode(td1.text());
                    chinaRegions.setName(td2.text());
                    chinaRegions.setType(3);
                    chinaRegions.setParentCode(StringUtils.isNotEmpty(cityCode) ? cityCode : provinceCode);
                    regionsInfoList.add(chinaRegions);
                }
            }
        }
    }
    //打印结果
    System.out.println(JSONArray.toJSONString(regionsInfoList));
}

CREATE TABLE `china_regions` (
  `id` bigint(20) unsigned NOT NULL COMMENT '主键ID',
  `code` varchar(32) COLLATE utf8mb4_unicode_ci NOT NULL DEFAULT '' COMMENT '行政地域编码',
  `name` varchar(50) COLLATE utf8mb4_unicode_ci NOT NULL DEFAULT '' COMMENT '行政地域名称',
  `type` tinyint(4) NOT NULL DEFAULT '1' COMMENT '行政地域类型，1:省份，2：城市，3：区域',
  `parent_code` varchar(32) COLLATE utf8mb4_unicode_ci NOT NULL DEFAULT '' COMMENT '上一级行政编码',
  `is_delete` tinyint(4) NOT NULL DEFAULT '0' COMMENT '是否删除 1：已删除；0：未删除',
  `create_time` datetime NOT NULL DEFAULT CURRENT_TIMESTAMP COMMENT '创建时间',
  `update_time` datetime NOT NULL DEFAULT CURRENT_TIMESTAMP ON UPDATE CURRENT_TIMESTAMP COMMENT '更新时间',
  PRIMARY KEY (`id`),
  KEY `idx_code` (`code`) USING BTREE,
  KEY `idx_name` (`name`) USING BTREE,
  KEY `idx_type` (`type`) USING BTREE,
  KEY `idx_parent_code` (`parent_code`) USING BTREE
) ENGINE=InnoDB DEFAULT CHARSET=utf8mb4 COLLATE=utf8mb4_unicode_ci COMMENT='国家行政地域信息表';

chinaRegionsService.saveBatch(regionsInfoList);