pip install python-Levenshtein
from openpyxl import Workbook
import xlrd
import time
import Levenshtein as Le target_city_list = []
file_name = 'DB任务_csv_py_wholeCSV-加百度170825095914'
FEXCEL = '%s%s' % (file_name, '.xlsx')
data = xlrd.open_workbook(FEXCEL)
table = data.sheets()[0]
nrows, ncols = table.nrows, table.ncols
wb = Workbook()
worksheet = wb.active
file_title_str = 'dbid, area_code, ref_area_type_code, city, district, address, city_street, name_, BDpoi_list, BD_name, BD_addr, seqratio_res'
file_title_l = file_title_str.replace(' ', '').split(',')
worksheet.append(file_title_l)
BDpoi_list_tag, BDpoi_list_tagb = '|-|', '|--|'
for i in range(0, nrows):
l = table.row_values(i)
dbid, area_code, ref_area_type_code, city, district, address, city_street, name_, BDpoi_list = l
if dbid == 'dbid':
continue
addr_ = '%s%s%s%s' % (city, district, address, city_street)
chk_name_lsit,cmp_list,sorted_seqratio_res_dic = [name_,addr_],BDpoi_list.split(BDpoi_list_tag),{}
for ii in cmp_list:
cmp_, BD_name, BD_addr = ['', ''], '', ''
cmp_one = ii.split(BDpoi_list_tagb)
if len(cmp_one) == 2:
BD_name, BD_addr = cmp_[0], cmp_[1] = cmp_one
else:
BD_name = cmp_[0] = cmp_one[0]
seqratio_res = Le.seqratio(chk_name_lsit, cmp_)
ll = dbid, area_code, ref_area_type_code, city, district, address, city_street, name_, BDpoi_list, BD_name, BD_addr, seqratio_res
if seqratio_res not in sorted_seqratio_res_dic:
sorted_seqratio_res_dic[seqratio_res] = []
sorted_seqratio_res_dic[seqratio_res].append(ll) sorted_seqratio_res_list = sorted(sorted_seqratio_res_dic) for seqratio_res in sorted_seqratio_res_list:
lll = sorted_seqratio_res_dic[seqratio_res]
for vl in lll:
worksheet.append(vl) localtime_ = time.strftime("%y%m%d%H%M%S", time.localtime())
file_name = '%s%s%s' % (file_name,'-Levenshtein',localtime_)
file_name_save = '%s%s' % (file_name, '.xlsx')
wb.save(file_name_save)