原数据为: http://www.mca.gov.cn/article/sj/xzqh/2018/201804-12/201804-06041553.html

手动替换了一下格式,注意有些省直属县(第三位为9的)需要手动处理一下,并使用下面的代码处理.

# 输入格式
s = """
110000:北京市
110101:东城区
110102:西城区
110105:朝阳区
110106:丰台区
110107:石景山区
110108:海淀区
110109:门头沟区
110111:房山区
110112:通州区
110113:顺义区
110114:昌平区
110115:大兴区
110116:怀柔区
110117:平谷区
110118:密云区
110119:延庆区
"""
slist = s.split("\n")province_code = ""  # 省级单位的代码
city_code = ""  # 市级单位的代码
province_name = ""  # 省级单位的名字
city_name = ""  # 市级单位的名字
res = {}  # 要数出的结果for index, i in enumerate(slist):if not i:continuei = i.split(":")code = i[0]name = i[1]_province_code = code[0:2]if _province_code != province_code and code.endswith("0000"):  # 省级代码以 0000 结尾province_code = _province_codeprovince_name = namecity_code = ""  # 清空市的信息city_name = ""  # 清空市的信息res[name] = {'code': code}  # 添加省的字典else:  # 遍历市_city_code = code[2:4]if _city_code != city_code and code.endswith("00"):  # 省级代码以 0000 结尾city_code = _city_codecity_name = nameres[province_name][city_name] = {'code': code}  # 添加市的字典else: # 遍历县print(province_name, city_name, name)if city_name:res[province_name][city_name][name] = {'code': code}  # 添加县的字典elif name:res[province_name][name] = {'code': code}  # 添加县的字典,直辖市的

处理结果为:

{"北京市": {"code": "110000","东城区": {"code": "110101"},"西城区": {"code": "110102"},"朝阳区": {"code": "110105"},"丰台区": {"code": "110106"},"石景山区": {"code": "110107"},"海淀区": {"code": "110108"},"门头沟区": {"code": "110109"},"房山区": {"code": "110111"},"通州区": {"code": "110112"},"顺义区": {"code": "110113"},"昌平区": {"code": "110114"},"大兴区": {"code": "110115"},"怀柔区": {"code": "110116"},"平谷区": {"code": "110117"},"密云区": {"code": "110118"},"延庆区": {"code": "110119"}},
}