# -*- coding: utf-8 -*-
import xlrd
import xlwt
from datetime import date,datetime
def read_excel():
# 打开文件
workbook = xlrd.open_workbook(r'F:\demo.xlsx')
# 获取所有sheet
print workbook.sheet_names() # [u'sheet1', u'sheet2']
sheet2_name = workbook.sheet_names()[1]
# 根据sheet索引或者名称获取sheet内容
sheet2 = workbook.sheet_by_index(1) # sheet索引从0开始
sheet2 = workbook.sheet_by_name('sheet2')
# sheet的名称,行数,列数
print sheet2.name,sheet2.nrows,sheet2.ncols
# 获取整行和整列的值(数组)
rows = sheet2.row_values(3) # 获取第四行内容
cols = sheet2.col_values(2) # 获取第三列内容
print rows
print cols
# 获取单元格内容
print sheet2.cell(1,0).value.encode('utf-8')
print sheet2.cell_value(1,0).encode('utf-8')
print sheet2.row(1)[0].value.encode('utf-8')
# 获取单元格内容的数据类型
print sheet2.cell(1,0).ctype
if __name__ == '__main__':
read_excel()
1、python读取excel中单元格内容为日期的方式
python读取excel中单元格的内容返回的有5种类型,即上面例子中的ctype:
ctype : 0 empty,1 string, 2 number, 3 date, 4 boolean, 5 error
即date的ctype=3,这时需要使用xlrd的xldate_as_tuple来处理为date格式,先判断表格的ctype=3时xldate才能开始操作。现在命令行看下:
>>> sheet2.cell(2,2).ctype #1990/2/22
>>> sheet2.cell(2,1).ctype #24
>>> sheet2.cell(2,0).ctype #小胖
>>> sheet2.cell(2,4).ctype #空值(这里是合并单元格的原因)
>>> sheet2.cell(2,2).value #1990/2/22
33656.0
>>> xlrd.xldate_as_tuple(sheet2.cell_value(2,2),workbook.datemode)
(1992, 2, 22, 0, 0, 0)
>>> date_value = xlrd.xldate_as_tuple(sheet2.cell_value(2,2),workbook.datemode)
>>> date_value
(1992, 2, 22, 0, 0, 0)
>>> date(*date_value[:3])
datetime.date(1992, 2, 22)
>>> date(*date_value[:3]).strftime('%Y/%m/%d')
'1992/02/22'
即可以做下简单处理,判断ctype是否等于3,如果等于3,则用时间格式处理:
if (sheet.cell(row,col).ctype == 3):
date_value = xlrd.xldate_as_tuple(sheet.cell_value(rows,3),book.datemode)
date_tmp = date(*date_value[:3]).strftime('%Y/%m/%d')
读取整行整列的内容
>>> sheet2.col_values(4)
[u'\u5173\u7cfb', u'\u597d\u670b\u53cb', '', u'\u540c\u5b66', '', '', u'\u4e00\u4e2a\u4eba', '']
>>> for i in range(sheet2.nrows):
print sheet2.col_values(4)[i]
关系
好朋友
同学
一个人
>>> sheet2.row_values(7)
[u'\u65e0\u540d', 20.0, u'\u6682\u65e0', '', '']
>>> for i in range(sheet2.ncols):
print sheet2.row_values(7)[i]
无名
20.0
暂无
>>>
3、获取合并的单元格
读取文件的时候需要将formatting_info参数设置为True,默认是False,所以上面获取合并的单元格数组为空,
>>> workbook = xlrd.open_workbook(r'F:\demo.xlsx',formatting_info=True)
>>> sheet2 = workbook.sheet_by_name('sheet2')
>>> sheet2.merged_cells
[(7, 8, 2, 5), (1, 3, 4, 5), (3, 6, 4, 5)]
merged_cells返回的这四个参数的含义是:(row,row_range,col,col_range),其中[row,row_range)包括row,不包括row_range,col也是一样,即(1, 3, 4, 5)的含义是:第1到2行(不包括3)合并,(7, 8, 2, 5)的含义是:第2到4列合并。
利用这个,可以分别获取合并的三个单元格的内容:
>>> print sheet2.cell_value(1,4) #(1, 3, 4, 5)
好朋友
>>> print sheet2.cell_value(3,4) #(3, 6, 4, 5)
同学
>>> print sheet2.cell_value(7,2) #(7, 8, 2, 5)
暂无
发现规律了没?是的,获取merge_cells返回的row和col低位的索引即可! 于是可以这样一劳永逸:
>>> merge = []
>>> for (rlow,rhigh,clow,chigh) in sheet2.merged_cells:
merge.append([rlow,clow])
>>> merge
[[7, 2], [1, 4], [3, 4]]
>>> for index in merge:
print sheet2.cell_value(index[0],index[1])
暂无
好朋友
同学
>>>
写xlsxwrite
from xlsxwriter.workbook import Workbook
list1 = []
list2 = []
with open('a.txt', 'r') as f:
while True:
i = f.readline()
if i=='':
break
data = i.split(' ')
list1.append(data)
for i in list1:
if len(i)==1:
path = i
path = i[0].replace('\n','')
if i[0].startswith('-r'):
list2.append([path, i[0]])
workbook = Workbook('a.xlsx')
worksheet = workbook.add_worksheet('sheet1')
workformat = workbook.add_format({'bold':12})
worksheet.write_row('A1', ['num', 'dir'], workformat)
for num, dir in enumerate(list2):
worksheet.write_row(num+1, 0, dir, workformat)
workbook.close()
OPENPYXL
import datetime
from random import choice
from time import time
from openpyxl import load_workbook
from openpyxl.utils import get_column_letter
# 设置文件 mingc
addr = "openpyxl.xlsx"
# 打开文件
wb = load_workbook(addr)
# 创建一张新表
ws = wb.create_sheet()
# 第一行输入
ws.append(['TIME', 'TITLE', 'A-Z'])
# 输入内容(500行数据)
for i in range(500):
TIME = datetime.datetime.now().strftime("%H:%M:%S")
TITLE = str(time())
A_Z = get_column_letter(choice(range(1, 50)))
ws.append([TIME, TITLE, A_Z])
# 获取最大行
row_max = ws.max_row
# 获取最大列
con_max = ws.max_column
# 把上面写入内容打印在控制台
for j in ws.rows: # we.rows 获取每一行数据
for n in j:
print(n.value, end="\t") # n.value 获取单元格的值
print()
# 保存,save(必须要写文件名(绝对地址)默认 py 同级目录下,只支持 xlsx 格式)
wb.save(addr)