python 表格处理 下载_Python处理excel表格

工作遇见统计流量，只能把网页里的复制到excel表格里，看到表格里的数据无比的头疼，只能用万能的Python来解决(写的很简单又错误或者有更好方法可以指点指点)：

下载安装xlrd：

tar zxvf xlrd-0.9.4.tar.gz

cd xlrd-0.9.4

python setup.py install

>>> import xlrd#不报错说明安装成功

>>>

Python来操作excel文件：

#!/usr/local/python2.7

import string

import xlrd

import os

def read_excel(arg):

data=xlrd.open_workbook(arg)#打开文件

sheet1_name=data.sheet_names()[0]

sheet1 = data.sheet_by_name("Sheet1")#获取sheet

cols = sheet1.col_values(1)#获取第三列

sum=0

for str in cols:

if "GB" in str:#获取符合的数据，再求和

data=str.split(" ")[0].replace(",","")

sum += string.atof(data)

return sum

if __name__ == "__main__":

while True:

file_name=raw_input("Please Input you FileName:")

if os.path.exists(file_name):

print read_excel(file_name)

else:

print "The File Is Inexistence,Please Input FileName !!"

稍微改进了一下，只需要把excel文件放到已知的目录里，输入目录名，就可以格式化输出了：

#!/usr/local/python2.7

import string

import xlrd

import os

def read_excel(dir):

file_list=os.listdir(dir)

for file in file_list:

file_path=os.path.join(dir,file)

data=xlrd.open_workbook(file_path)

sheet1_name=data.sheet_names()[0]

sheet1 = data.sheet_by_name("Sheet1")

cols = sheet1.col_values(1)

sum=0

for str in cols:

if "GB" in str:

data=str.split(" ")[0].replace(",","")

sum += string.atof(data)

print  file,sum

if __name__ == "__main__":

Catalog_name=raw_input("Please Input you CatalogName:")

if os.path.exists(Catalog_name):

read_excel(Catalog_name)

else:

print "The File Is Inexistence,Please Input !!"