python 将地址按照省市区三级切分

以下是用Python将地址按照省市区三级切分的示例代码：

import pypinyin

def split_address(address):
    # 获取省份和直辖市的列表
    provinces = ['北京市', '天津市', '上海市', '重庆市']
    # 加载城市名称和编码的映射表
    city_codes = {
        '北京市': '110000',
        '天津市': '120000',
        '上海市': '310000',
        '重庆市': '500000',
        # 其他省市的映射表可自行添加
    }
    # 加载区县名称和编码的映射表
    district_codes = {
        # 省市区县的映射表可自行添加
    }

    # 将地址转换为拼音，并去除空格和特殊字符
    address_pinyin = pypinyin.lazy_pinyin(address, style=pypinyin.NORMAL, errors='ignore')
    address_pinyin = ''.join(filter(str.isalnum, address_pinyin))

    # 判断地址是否包含省份或直辖市名称
    province = ''
    for p in provinces:
        if p in address:
            province = p
            break

    # 判断地址是否包含城市名称
    if province:
        address_pinyin = address_pinyin.replace(province, '')
        city = ''
        for c in city_codes:
            if c in address_pinyin:
                city = c
                break
        if city:
            address_pinyin = address_pinyin.replace(city, '')
    else:
        city = ''
        for c in city_codes:
            if c in address_pinyin:
                city = c
                break
        if city:
            address_pinyin = address_pinyin.replace(city, '')
            province = city[:-1]

    # 判断地址是否包含区县名称
    district = ''
    for d in district_codes:
        if d in address_pinyin:
            district = d
            break
    if district:
        address_pinyin = address_pinyin.replace(district, '')

    # 根据省份、城市和区县名称获取对应的编码
    province_code = city_codes.get(province, '')
    city_code = city_codes.get(city, '')
    district_code = district_codes.get(district, '')

    # 返回省份、城市和区县的名称和编码
    return {
        'province': province,
        'province_code': province_code,
        'city': city,
        'city_code': city_code,
        'district': district,
        'district_code': district_code
    }

需要注意的是，这只是一个基本的地址切分方法，实际情况中还需要根据具体的地址库和需求进行修改和调整。代码中使用了pypinyin库将中文地址转换为拼音，需要先安装该库。