python 行政区域地址标准化：业务经理填报的地址乱起八糟，高德接口有点厉害!

file_name = 'data/address2test.xls'
df = pd.read_excel(file_name,dtype=object)
city_bk = '惠州市'
# 构造请求
req_geo_url = ''
req_geo_s = 'https://restapi.amap.com/v3/geocode/geo?address='
req_geo_e = '&output=XML&key=2a8d3af7ce489cb7e219d7df54d92678'
req_regeo_url = ''
req_regeo_s = 'https://restapi.amap.com/v3/geocode/regeo?output=xml&location='
req_regeo_e = '&key=2a8d3af7ce489cb7e219d7df54d92678&radius=1000&extensions=all'
headers = {
            'User-Agent':'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.1; WOW64; Trident/7.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; .NET4.0C; .NET4.0E; Media Center PC 6.0)',
}
list_err_url = []  # 存储错误的url

#　对标题进行重新排序，默认取第一个列为地址，并追加后续列，如果已经有，则会保存。reIndex需要通过返回赋值，没有inplace参数。
new_columns =  [df.columns[0]] + ['执行结果','标准地址','国家','省份','城市','县区代码','县区','乡镇代码','乡镇','街道',"乡村地址""]
df = df.reindex(columns=new_columns)  

df_sel = df['执行结果'] != 1
df.loc[df_sel,"执行结果"],df.loc[df_sel,"标准地址"],df.loc[df_sel,"国家"],df.loc[df_sel,"省份"],df.loc[df_sel,"城市"],df.loc[df_sel,"县区代码"],df.loc[df_sel,"县区"],df.loc[df_sel,"乡镇代码"],df.loc[df_sel,"乡镇"],df.loc[df_sel,"街道"] =  zip(*df[df_sel].apply(append_address, axis=1))

# 请求函数
def append_address(x):
    result = 1
    url = req_geo_s + str(x[0]) + req_geo_e
    print('执行序号:',str(x.name),'地址：',str(x[0]),'url:',url)
    # 初始化结果
    location = formatted_address = country = province = city = citycode = district = ''
    adcode = township = towncode = streetNumber_street = streetNumber_number = ''
    try:
        resp = requests.get(url,timeout=5,headers = headers)  # 设置访问超时，以及http头
        xml = etree.XML(resp.content)
        count = xml.xpath('/response/count/text()')[0]
        if int(count) == 0:
            # 如果为空，说明他的地址很不规范，但是这种一般是本地的业务
            resp = requests.get(req_geo_s + city_bk + str(x[0]) + req_geo_e,timeout=5,headers = headers)  # 设置访问超时，以及http头
            xml = etree.XML(resp.content)
        city = xml.xpath('/response/geocodes/geocode/city/text()')  # 如果有多个，则选择为惠州市的
        locations = xml.xpath('/response/geocodes/geocode/location/text()')
        # 判断找到了多少个，如果有多个的话，则返回默认城市
        if len(city) == 1:
            location = locations[0]
        else:
            location = locations[0]
            for i in range(len(city)):
                if city[i] == city_bk:
                    location = locations[i]
    except Exception as e:
        print('req_geo_e error message:',str(e),'error url:',url)
        list_err_url.append(url)
        result = 0
        location = ''
    # 如果正常，则继续访问
    if location != '' and result != 0:
        url = req_regeo_s + location + req_regeo_e
        try:
            resp = requests.get(url,timeout=5,headers = headers)  # 设置访问超时，以及http头
            xml = etree.XML(resp.content)
            # 逆编码内容
            formatted_address = xml.xpath('/response/regeocode/formatted_address/text()')
            if len(formatted_address)>0: formatted_address = formatted_address[0]
            
            country = xml.xpath('/response/regeocode/addressComponent/country/text()')
            if len(country)>0: country = country[0]
            
            province = xml.xpath('/response/regeocode/addressComponent/province/text()')
            if len(province)>0: province = province[0]
            
            city = xml.xpath('/response/regeocode/addressComponent/city/text()')
            if len(city)>0: city = city[0]
            
            citycode = xml.xpath('/response/regeocode/addressComponent/citycode/text()')
            if len(citycode)>0: citycode = citycode[0]
            
            district = xml.xpath('/response/regeocode/addressComponent/district/text()')
            if len(district)>0: district = district[0]
            
            adcode = xml.xpath('/response/regeocode/addressComponent/adcode/text()')
            if len(adcode)>0: adcode = adcode[0]
            
            township = xml.xpath('/response/regeocode/addressComponent/township/text()')
            if len(township)>0: township = township[0]
            
            towncode = xml.xpath('/response/regeocode/addressComponent/towncode/text()')
            if len(towncode)>0: towncode = towncode[0]
            
            streetNumber_street = xml.xpath('/response/regeocode/addressComponent/streetNumber/street/text()')
            if len(streetNumber_street)>0: streetNumber_street = streetNumber_street[0]
            
            streetNumber_number = xml.xpath('/response/regeocode/addressComponent/streetNumber/number/text()')
            if len(streetNumber_number)>0: streetNumber_number = streetNumber_number[0]
        except Exception as e:
            print('location error message:',str(e),'error url:',url)
            result = 0
            list_err_url.append(url)
    # 返回元祖执行结果
    return(result,formatted_address,country,province,city,adcode,district,towncode,township,streetNumber_street + streetNumber_number)

# 读取行政区划，village解析为5级字典
sdf  = pd.read_csv('data/stats.csv',dtype=object)) 
sdf.drop(sdf[sdf['statType'] != 'village'].index, inplace=True)
sdf.drop(columns=['statName', 'statProvince','statCity','statCounty','statTown','statVillageType'],inplace=True)

# 构造行政区域字典，
d_state = {}
for i in range(len(sdf)):
    #if i > 3:
    #    break
    # 分割
    statCode = str(sdf.iloc[i]['statCode']).strip().replace("'","")
    city = statCode[:6]
    town = statCode[6:9]
    # 形成(乡全程，乡简称（用于匹配），标识符）
    village_deal = deal_village(str(sdf.iloc[i]['statVillage']))  #处理过户
    #print('city:',city,'town:',town)
    if not city in d_state:
        d_state[city] = {}
    d_t = d_state[city]
    if not town in d_t:
        d_t[town] = []
    d_t[town].append(village_deal)