写在前面
用python实现快速从身份证中explore尽量多的的信息，找了很多资料，发现并不全。参考已有的分享和其他信息自己写了。
能提取的信息：
出生日期、年龄、生肖、星座、省份、城市、区县、归属地地址、城市等级（划分标准）
id_card_area.xlsx 含省份、城市、区县、归属地地址
city_level.xlsx 含城市等级
两个文件可根据时间更新
代码
import pandas as pdimport numpy as nparea_info = pd.read_excel('id_card_area.xlsx', header = 0)area_info = area_info.set_index('district_code')city_level_ = pd.read_excel('city_level.xlsx', header = 0)city_level_ = city_level_.set_index('city')class GetIdInformation(object):def __init__(self,id):self.id = idself.birth_year = int(self.id[6:10])self.birth_month = int(self.id[10:12])self.birth_day = int(self.id[12:14])self.address_code = int(self.id[0:6])def get_birthday(self):"""通过身份证号获取出生日期"""birthday = "{0}-{1}-{2}".format(self.birth_year, self.birth_month, self.birth_day)return birthdaydef get_sex(self):"""男生：1 女生：0"""num = int(self.id[16:17])if num % 2 == 0:return 0else:return 1def get_age(self):"""通过身份证号获取年龄"""now = (datetime.datetime.now() + datetime.timedelta(days=1))year = now.yearmonth = now.monthday = now.dayif year == self.birth_year:return 0else:if self.birth_month > month or (self.birth_month == month and self.birth_day > day):return year - self.birth_year - 1else:return year - self.birth_yeardef get_zodiac(self): """通过身份证号获取生肖""" start_year = 1901zodiac_interval = (int(self.birth_year) - start_year) % 12if zodiac_interval == 1 or zodiac_interval == -11:return '鼠'if zodiac_interval == 0:return '牛'if zodiac_interval == 11 or zodiac_interval == -1:return '虎'if zodiac_interval == 10 or zodiac_interval == -2:return '兔'if zodiac_interval == 9 or zodiac_interval == -3:return '龙'if zodiac_interval == 8 or zodiac_interval == -4:return '蛇'if zodiac_interval == 7 or zodiac_interval == -5:return '马'if zodiac_interval == 6 or zodiac_interval == -6:return '羊'if zodiac_interval == 5 or zodiac_interval == -7:return '猴'if zodiac_interval == 4 or zodiac_interval == -8:return '鸡'if zodiac_interval == 3 or zodiac_interval == -9:return '狗'if zodiac_interval == 2 or zodiac_interval == -10:return '猪'else:return np.nandef get_starsign(self): """通过身份证号获取星座""" if((self.birth_month== 1 and self.birth_day > 19) or (self.birth_month== 2 and self.birth_day <= 18)):return "水瓶座"if ((self.birth_month== 2 and self.birth_day > 18) or (self.birth_month== 3 and self.birth_day <= 20)):return "双鱼座"if ((self.birth_month== 3 and self.birth_day > 20) or (self.birth_month== 4 and self.birth_day <= 19)):return "白羊座"if ((self.birth_month== 4 and self.birth_day > 19) or (self.birth_month== 5 and self.birth_day <= 20)):return "金牛座"if ((self.birth_month== 5 and self.birth_day > 20) or (self.birth_month== 6 and self.birth_day <= 21)):return "双子座"if ((self.birth_month== 6 and self.birth_day > 21) or (self.birth_month== 7 and self.birth_day <= 22)):return "巨蟹座"if ((self.birth_month== 7 and self.birth_day > 22) or (self.birth_month== 8 and self.birth_day <= 22)):return "狮子座"if ((self.birth_month== 8 and self.birth_day > 22) or (self.birth_month== 9 and self.birth_day <= 22)):return "处女座"if ((self.birth_month== 9 and self.birth_day > 22) or (self.birth_month== 10 and self.birth_day <= 23)):return "天秤座"if ((self.birth_month== 10 and self.birth_day > 23) or (self.birth_month== 11 and self.birth_day <= 22)):return "天蝎座"if ((self.birth_month== 11 and self.birth_day > 22) or (self.birth_month== 12 and self.birth_day <= 21)):return "射手座"if ((self.birth_month== 12 and self.birth_day > 21) or (self.birth_month== 1 and self.birth_day <= 19)):return "魔羯座"else:return np.nan def get_province_only(self): """通过身份证号获取省份""" province_code = int(self.id[0:2])province_dict = {11 : "北京",12 : "天津",13 : "河北",14 : "山西",15 : "内蒙古",21 : "辽宁",22 : "吉林",23 : "黑龙江",31 : "上海",32 : "江苏",33 : "浙江",34 : "安徽",35 : "福建",36 : "江西",37 : "山东",41 : "河南",42 : "湖北",43 : "湖南",44 : "广东",45 : "广西",46 : "海南",50 : "重庆",51 : "四川",52 : "贵州",53 : "云南",54 : "西藏",61 : "陕西",62 : "甘肃",63 : "青海",64 : "宁夏",65 : "新疆",71 : "台湾",81 : "香港",82 : "澳门",91 : "国外"}if province_dict[province_code] is not None:return province_dict[province_code]else:return np.nandef get_province(self): """通过身份证号获取省份""" province_dict = area_info.to_dict()['province']if self.address_code in list(province_dict.keys()):return province_dict[self.address_code]else:return np.nandef get_city(self): """通过身份证号获取城市""" city_dict = area_info.to_dict()['city']if self.address_code in list(city_dict.keys()):return city_dict[self.address_code]else:return np.nandef get_district(self): """通过身份证号获取区/县""" district_dict = area_info.to_dict()['district']if self.address_code in list(district_dict.keys()):return district_dict[self.address_code]else:return np.nandef get_address(self): """通过身份证号获取完整归属地""" address_dict = area_info.to_dict()['all']if self.address_code in list(address_dict.keys()):return address_dict[self.address_code]else:return np.nandef get_city_level(self):"""通过身份证号获取城市等级"""city_dict = area_info.to_dict()['city']city_level_dict = city_level_.to_dict()['city_level']if self.address_code in list(city_dict.keys()):city_name = city_dict[self.address_code]if city_name in list(city_level_dict.keys()):return city_level_dict[city_name]else:return '其他'else:return np.nanGetIdInformation('111111111111111111').get_city_level()#df['province'] = df.id_number.apply(lambda x:GetIdInformation(x).get_province)
Python 从身份证中提取出生日期/性别/年龄/生肖/星座/省份/城市/城市等级/区县（划分标准）
