多级省市区嵌套实现

multilevel-nest.go

package main

func main() {

}

multilevel-nest.php

<?php
$data = file_get_contents("http://preview.www.mca.gov.cn/article/sj/xzqh/2020/2020/202101041104.html");
preg_match_all('#<td class=xl\d+?>(<span.*?)?(\d+|[\x{4e00}-\x{9fa5}]+).*?</td>#u', $data, $matches);

$administratives = [];
$node = array(
    'id' => '',
    'name' => ''
);
$fixNode = array(
    'id' => '',
    'name' => '市辖区'
);
foreach ($matches[2] as $idx => $v) {
    if ($idx % 2 == 0) {
        $node = array(
            'id' => $v,
            'name' => ''
        );
        if (in_array($v, ['110000', '120000', '310000', '500000'])) {
            $v[3] = '1';
            $fixNode['id'] = $v;
        }
    } else if ($idx % 2 == 1) {
        $node['name'] = $v;
        $administratives[] = $node;
        
        if (in_array($v, ['北京市', '天津市', '上海市', '重庆市'])) {
            $administratives[] = $fixNode;
        }
    }
}
unset($node);

$root = array();
$nodeMap = array();

foreach ($administratives as $item) {
    $rawId = (string)$item['id'];
    $id = (int)$rawId;
    $provinceId = (int)($id / 10000);
    $cityId = ((int)($id / 100)) % 100;
    $districtId = $id % 100;

    if ($cityId === 0 && $districtId === 0) {
        // 省份信息
        $node = array(
            'Id' => $rawId,
            'Name' => $item['name'],
            'Cities' => []
        );
        $nodeMap[$id] = &$node;

        $root[] = &$node;
    } else if ($districtId === 0) {
        // 市信息
        $fullCityId = $provinceId * 10000 + $cityId * 100;
        $node = array(
            'Id' => $rawId,
            'Name' => $item['name'],
            'Districts' => []
        );
        $nodeMap[$fullCityId] = &$node;

        $provinceNode = &$nodeMap[$provinceId * 10000];
        $provinceNode['Cities'][] = &$node;
    } else {
        // 区信息
        $fullCityId = $provinceId * 10000 + $cityId * 100;
        $node = array(
            'Id' => $rawId,
            'Name' => $item['name'],
        );
        $cityNode = &$nodeMap[$fullCityId];

        $cityNode['Districts'][] = $node;
    }
    unset($node);
}

print_r($root);

multilevel-nest.py

import requests