python 字符分割预处理_[Python]替换指定字符，Excel数据预处理,python,excel

当我们所需要替换的数据量比较大的时候，使用excel中自带的替换功能会发现非常耗时，这时可以使用python，快准狠！

#coding=utf-8

import xlrd

import codecs

import re

def open_xlsx():

# 加载Excel数据，处理数据

data = xlrd.open_workbook('测试.xlsx') # 读取工作表

table = data.sheet_by_name('Sheet1') # 读取当前sheet表对象

rows = table.nrows # 获取行数

print('一共有{}行数据，开始清洗数据'.format(rows))

for i in range(1,rows):

company = table.row_values(i)[0]

job = table.row_values(i)[1]

degree = table.row_values(i)[2]

fuli = table.row_values(i)[3]

salary = table.row_values(i)[4]

experience = table.row_values(i)[5]

area = table.row_values(i)[6]

zhize = table.row_values(i)[7]

yaoqiu = table.row_values(i)[8]

degree = degree.replace("?"," ")

experience = experience.replace("?"," ")

area = area.replace("?"," ")

zhize =zhize.replace("?"," ").replace("["," ").replace("]"," ")

yaoqiu = yaoqiu.replace("?"," ").replace("["," ").replace("]"," ")

output = ('{}\t{}\t{}\t{}\t{}\t{}\t{}\t{}\t{}\n').format(company, job, degree, fuli, salary, experience, area, zhize, yaoqiu)

f = codecs.open('清洗后的数据.xls', 'a+')

f.write(output)

f.close()

if __name__ == '__main__':

open_xlsx()