python 身份证归属地解析

浏览器抓包114身份证查询网站得知身份证归属地查询实际地址为：http://tool.114la.com/static/js/area.js

复制到txt后将整个文本改成一个大list，用python读取

import pandas as pd
import numpy as np
from datetime import datetime

id_no=eval(open(r'C:\Users\admin\Desktop\身份证\身份证归属区.txt').read())

id_text=pd.DataFrame(id_no,columns={'id':0,'area':1})

id_text['id']=id_text.id.apply(lambda x:eval('['+str(x).replace('_',',')+']'))

id_part1=id_text[id_text.id.apply(lambda x:len(x)==1)].reset_index(drop=True)
id_part2=id_text[id_text.id.apply(lambda x:len(x)==2)].reset_index(drop=True)
id_part3=id_text[id_text.id.apply(lambda x:len(x)==3)].reset_index(drop=True)

out_put1=pd.DataFrame()#输出位为与part2链接键
title1=list()
title2=list()
for i in id_part1.index:
    for ii,city1 in enumerate(id_part1.loc[i,'area']):
        #print(str(ii)+'|'+str(id_part1.loc[i,'area'][ii]))
        title1.append(ii)
        title2.append(id_part1.loc[i,'area'][ii])
out_put1=pd.DataFrame({'id_key1':title1,'city1':title2})

out_put2=pd.DataFrame()#id第二位与part1链接id_key1，第二位与输出位合并为与part3链接键id_key2
title1=list()
title2=list()
title3=list()
for i in id_part2.index:
    for ii,city2 in enumerate(id_part2.loc[i,'area']):#ii为输出位
        #print(str(ii)+'|'+str(id_part2.loc[i,'area'][ii])+"|"+str(id_part2.loc[i,'id'][1]))
        if (len(str(id_part2.loc[i,'id'][1]))<=1)&(len(str(ii))<=1):
            title1.append('0'+str(id_part2.loc[i,'id'][1])+'0'+str(ii))
        elif len(str(id_part2.loc[i,'id'][1]))<=1:
            title1.append('0'+str(id_part2.loc[i,'id'][1])+str(ii))
        elif len(str(ii))<=1:
            title1.append(str(id_part2.loc[i,'id'][1])+'0'+str(ii))
        else:
            title1.append(str(id_part2.loc[i,'id'][1])+str(ii))
        title2.append(id_part2.loc[i,'area'][ii])
        title3.append(id_part2.loc[i,'id'][1])
out_put2=pd.DataFrame({'id_key1':title3,'id_key2':title1,'city2':title2})

out_put3=pd.DataFrame()#id第二位与id第三位合并为与part3链接键
title1=list()
title2=list()
for i in id_part3.index:
    for ii,city3 in enumerate(id_part3.loc[i,'area']):
        #print(str(ii)+'|'+str(id_part3.loc[i,'area'][ii])+"|"+str(id_part3.loc[i,'id'][1])+"|"+str(id_part3.loc[i,'id'][2]))
        #title1.append(str(id_part3.loc[i,'id'][1])+str(id_part3.loc[i,'id'][2]))
        if (len(str(id_part3.loc[i,'id'][1]))<=1)&(len(str(id_part3.loc[i,'id'][2]))<=1):
            title1.append('0'+str(id_part3.loc[i,'id'][1])+'0'+str(id_part3.loc[i,'id'][2]))
        elif len(str(id_part3.loc[i,'id'][1]))<=1:
            title1.append('0'+str(id_part3.loc[i,'id'][1])+str(id_part3.loc[i,'id'][2]))
        elif len(str(id_part3.loc[i,'id'][2]))<=1:
            title1.append(str(id_part3.loc[i,'id'][1])+'0'+str(id_part3.loc[i,'id'][2]))
        else:
            title1.append(str(id_part3.loc[i,'id'][1])+str(id_part3.loc[i,'id'][2]))
        title2.append(id_part3.loc[i,'area'][ii])
out_put3=pd.DataFrame({'id_key2':title1,'city3':title2})

#连接并输出
pd.merge(pd.merge(out_put1,out_put2,on='id_key1',how='left'),out_put3,on='id_key2',how='left').to_excel('身份证归属地解析.xlsx',index=False)