Python中openpyxl处理Excel文件详解

前言：openpyxl是一个用于读/写excel 2010 xlsx/xlsm/xltx/xltm文件的python库，所有对phpexcel团队的赞誉都是因为openpyxl最初是基于phpexcel的。以下从Excel格式处理，单元格数值修改等方面详解openpyxl的操作功能。

---

一、Excel单元格设置

1.处理表格

from openpyxl import load_workbook
import datetime 
wb = load_workbook(r'D:\Pyfiles\xx公司指标体系.xlsx')

2.sheet设置

#创建sheet
ws1=wb.create_sheet("mysheet")

#设定sheet的名字
ws1.title='newtitle'

#设定sheet的标签的背景颜色
ws1.sheet_properties.tabColor='1072BA'

#获取某个sheet对象
print(wb.get_sheet_by_name("newtitle"))
print(wb["newtitle"])

#遍历sheet名字
print(wb.sheetnames)
for sheetname in wb.sheetnames:
    print(sheetname)
for sheet in wb:
    print(sheet.title)

#复制一个sheet
wb['newtitle']['A1']='123'
source=wb["newtitle"]
target=wb.copy_worksheet(source)

#操作单元格
ws = wb.active

#调整列宽
ws.column_dimensions['A'].width = 10

#调整行高
ws.row_dimensions[1].height = 13.5
d=ws.cell(row=4,column=2)
#d=ws.cell(row=4,column=2,value=10)//更改该单元格的值
print(d.value)

#操作单列
print(ws['B'])
for cell in ws['B']:
    print(cell.value)

#操作多列
print(ws["A:C"])
for column in ws["A:C"]:
    for cell in column:
        print(cell.value)

#操作多行
row_range = ws1[1:3]
print row_range
for row in row_range:
    for cell in row:
        print cell.value
for row in ws1.iter_rows(min_row=1, min_col=1, max_col=3, max_row=3):
    for cell in row:
        print cell.value

#获取所有行
print ws1.rows
for row in ws1.rows:
    print row
#获取所有列
print ws1.columns
for col in ws1.columns:
    print col

#获取所有的行对象
rows1=[]
for row in ws.iter_rows():
    rows1.append(row)
print(rows1[2][3].value)

#获取所有的列对象
col1=[]
for col in ws.iter_cols():
    col1.append(col)
print(col1[2][2].value)

#单元格格式
ws['B2']=datetime.datetime(2021,7,21)
print(ws['B2'].number_format)#yyyy-mm-dd h:mm:ss
ws['B3']='12%'
print(ws['B3'].number_format)#General

#使用公式
ws["A1"]=1
ws["A2"]=2
ws["A3"]=3
ws["A4"] = "=SUM(1, 1)"
ws["A5"] = "=SUM(A1:A3)"
print (ws["A4"].value ) #打印的是公式内容，不是公式计算后的值,程序无法取到计算后的值
print (ws["A5"].value) #=SUM(A1:A3)

#合并单元格
ws.merge_cells('B2:B4')
ws.merge_cells(start_row=2,start_column=1,end_row=2,end_column=4)

#拆分单元格
ws.unmerge_cells('B2:B4')
ws.unmerge_cells(start_row=2,start_column=1,end_row=2,end_column=4)

#隐藏单元格
ws.column_dimensions.group('A','D',hidden=False)
ws.row_dimensions.group(5,7,hidden=False)

#设定字体格式Font()
ws=wb.active
import openpyxl
from openpyxl.styles import fills,colors,NamedStyle,Font,Side,Border,PatternFill,Alignment,Protection
for irow,row in enumerate(ws.rows,start=1): #           加粗        斜体        下划线
        font=Font('微软雅黑',size=11,color=colors.BLACK,bold=False,italic=True,underline='double')
    for cell in row:
        cell.font=font
        if irow%3==0:
            cell.fill=fills.GradientFill(stop=['FF0000', '0000FF'])#填充渐变

from openpyxl.styles import fills,colors,NamedStyle,Font,Side,Border,PatternFill,Alignment,Protection

3.格式处理示例 

#字体
    ft = Font(name=u'微软雅黑',
        size=11,
        bold=True,
        italic=True,#斜体
        vertAlign='baseline',#上下标'subscript','baseline'='none,'superscript'
        underline='single',#下划线'singleAccounting', 'double', 'single', 'doubleAccounting'
        strike=False ,#删除线
        color='00FF00')
    
    fill = PatternFill(fill_type="solid",
        start_color='FFFFFF',#单元格填充色
        end_color='FFFFFF')
    
#边框   可以选择的值为：'hair', 'medium', 'dashDot', 'dotted', 'mediumDashDot', 'dashed', 'mediumDashed', 'mediumDashDotDot', 'dashDotDot', 'slantDashDot', 'double', 'thick', 'thin']
    bd = Border(left=Side(border_style="thin",
                  color='0000FF'),
        right=Side(border_style="double",
                   color='5C3317'),
        top=Side(border_style="thin",
                 color='FF110000'),
        bottom=Side(border_style="hair",
                    color='238E23'),
        diagonal=Side(border_style='dashed',#对角线
                      color='3299CC'),
        diagonal_direction=1,
        outline=Side(border_style='slantDashDot',#外边框
                     color='BC1717'),
        vertical=Side(border_style='medium',#竖直线
                      color=colors.BLACK),
        horizontal=Side(border_style='dotted',#水平线
                       color=colors.WHITE)
                    )
 #对齐方式
    alignment=Alignment(horizontal='center',#水平'center', 'centerContinuous', 'justify', 'fill', 'general', 'distributed', 'left', 'right'
            vertical='top',#垂直'distributed', 'bottom', 'top', 'center', 'justify'
            text_rotation=0,#旋转角度0~180
            wrap_text=False,#文字换行
            shrink_to_fit=True,#自适应宽度，改变文字大小,上一项false
            indent=0)
    
    number_format = 'General'
    
    protection = Protection(locked=True,
                hidden=False)
    
    ws["B5"].font = ft
    ws["B5"].fill =fill
    ws["B5"].border = bd
    ws["B5"].alignment = alignment
    ws["B5"].number_format = number_format
    
    ws["B5"].value ="123"
    wb.save(r'D:\Pythontest\reptile\豆瓣排名250.xlsx')

颜色编码参考表：https://www.sioe.cn/yingyong/yanse-rgb-16/

 4.填充、边框、根据首行内容自动调整列宽

import openpyxl
from openpyxl.styles import Font,PatternFill,Side,Alignment,Border

def reset_color(filename):
    wb=openpyxl.load_workbook(filename)
    fill=PatternFill(  #设置填充样式
        fill_type='solid',
        start_color='99ccff')
    border=Border(top=Side(border_style='thin',color='000000'), #设置边框样式
            bottom=Side(border_style='thin',color='000000'),
            left=Side(border_style='thin',color='000000'),
            right=Side(border_style='thin',color='000000'))
    for i in wb.sheetnames:
        ws=wb[i]
        ws.sheet_view.showGridLines=False  #隐藏默认网线
        for c in range(1,ws.max_column+1):
            for r in range(1,ws.max_row+1): #添加边框
                bordercell=ws.cell(r,c)
                bordercell.border=border
        for end in range(1,ws.max_column+1):
            fillcell=ws.cell(1,end)
            fillcell.fill=fill #填充首行
    wb.save(filename)
def reset_col(filename):
    wb=load_workbook(filename)
    for sheet in wb.sheetnames:
        ws=wb[sheet]
        df=pd.read_excel(filename,sheet)
        for col in df.columns:
            index=list(df.columns).index(col)
            letter=get_column_letter(index+1)
            collen=len(str(col).encode())  #读取首行（标题行）宽度
            print(collen)
            ws.column_dimensions[letter].width=collen+4  #设置列宽为当前列标题宽度+4
    wb.save(filename)
            
filename=r'{}\2.xlsx'.format(path)


reset_color(filename)            
reset_col(filename)

5.设置行高列宽

import openpyxl
wb=openpyxl.Workbook()
sheet=wb.active

# 设置行高
sheet['A1']='行高被设置为 100'
sheet.row_dimensions[1].height=100

# 设置列宽
sheet['B2']='列宽被设置为 50'
sheet.column_dimensions['B'].width=50

wb.save('dimensions.xlsx')

#Excel默认行高为13.5，列宽为8.38

二、修改Excel表格中的内容

注意：通过脚本对表格进行操作的时候，不要用其他软件打开表格，否则可能会造成脚本运行失败

1、向某个格子中写入内容并保存

方式一：相当于直接修改源文件中的单元格

from openpyxl import load_workbook


workbook = load_workbook(filename='../excelDemo/testCase.xlsx')

sheet = workbook.active
print(sheet)

# 方式一：相当于直接修改源文件

sheet["C2"] = "无效"
workbook.save(filename='../excelDemo/testCase.xlsx')

方式二：修改单元格内容后另存文件

from openpyxl import load_workbook

workbook = load_workbook(filename='../excelDemo/testCase.xlsx')

sheet = workbook.active
print(sheet)


# 方式二：将“C4”单元格的数据改为了“失效”，并另存为了“test.xlsx”文件（路径为当前py程序下）
cell = sheet["C4"]
cell.value = "失效"
workbook.save(filename = "test.xlsx")

2、向表格中插入行数据 .append()

.append()方式：会在表格已有的数据后面，增添这些数(按行插入)；
这个操作很有用，爬虫得到的数据，可以使用该方式保存成 Excel 文件

from openpyxl import load_workbook



workbook = load_workbook(filename='./test1.xlsx')

sheet = workbook.active
# print(sheet)



data = [
["机审规则","不同用户类型跑不同publine","主"],
["机审规则","不同用户类型跑不同publine","低"],
["机审规则","不同用户类型跑不同publine","中"],
["机审规则","不同用户类型跑不同publine","中"],
]
for row in data:
	sheet.append(row)
	# print(row)

workbook.save(filename='./test2.xlsx')

3、在 python 中使用 excel 函数公式

python 究竟支持写哪些“excel 函数公式”呢？我们可以使用如下操作查看一下

from openpyxl import load_workbook

from openpyxl.utils import FORMULAE

print(FORMULAE)

 计算平均值

from openpyxl import load_workbook


workbook = load_workbook(filename='./cash.xlsx')

sheet = workbook.active
# print(sheet)


sheet["k1"] = "平均消费"
for i in range(2,5):
	sheet[f"k{i}"] = f'=AVERAGE(B{i}:J{i})'


workbook.save(filename='./cash.xlsx')

 4、插入空行和空列 .insert_cols()和.insert_rows()

 .insert_cols(idx=数字编号, amount=要插入的列数)，插入的位置是在 idx 列数的左
侧插入；
 .insert_rows(idx=数字编号, amount=要插入的行数)，插入的行数是在 idx 行数的下
方插入；

from openpyxl import load_workbook



workbook = load_workbook(filename='./cash.xlsx')

sheet = workbook.active
# print(sheet)


sheet.insert_cols(idx=2,amount=1)
# 在第二列插入一列空列

sheet.insert_rows(idx=3,amount=2)
# 在第三行插入两行空行

workbook.save(filename='./cash.xlsx')

效果如下，在第二列插入一列空列，在第三行插入两行空行。

注意：

通过函数对表格进行操作时，表格不能用其他软件进行打开，否则该脚本会运行失败
插入空行和空列，会对之前的使用 excel 函数公式产生影响，例如饮料喝肉类两行的平均消费的值就发生了改变，因为计算平均值的时候，是根据所限定范围内的单元格进行操作的，插入空行和空列后，指定的单元格的内容已经发生了改变

5、删除行和列 .delete_rows()和.delete_cols()

 .delete_rows(idx=数字编号, amount=要删除的行数)
 .delete_cols(idx=数字编号, amount=要删除的列数)

from openpyxl import load_workbook



workbook = load_workbook(filename='./cash.xlsx')

sheet = workbook.active
# print(sheet)


sheet.delete_cols(idx=2,amount=1)
# 删除第二列

sheet.delete_rows(idx=3,amount=2)
# 从第三行开始删除两行

workbook.save(filename='./cash.xlsx')

效果如下，删除第二列，从第三行开始删除两行，表格又回复原样了

6、移动格子 .move_range()

 .move_range("数据区域",rows=,cols=)：正整数为向下或向右、负整数为向左或向上

from openpyxl import load_workbook



workbook = load_workbook(filename='./cash.xlsx')

sheet = workbook.active
# print(sheet)


sheet.move_range("D2:G5",rows=2,cols=1)
# 将"D2:G5"这块区域向下平移2行，向右平移一列

workbook.save(filename='./cash.xlsx')

效果如下

7、创建新的 sheet 表格 .create_sheet()

 .create_sheet("新的 sheet 名")：创建一个新的 sheet 表

from openpyxl import load_workbook



workbook = load_workbook(filename='./cash.xlsx')

sheet = workbook.active
# print(sheet)


workbook.create_sheet("newSheet")
print(workbook.sheetnames)
# ['Sheet1', 'newSheet'] 现在存在两个sheet表，其中newSheet是新建的

workbook.save(filename='./cash.xlsx')

效果如下

8、删除某个 sheet 表 .remove()

from openpyxl import load_workbook



workbook = load_workbook(filename='./cash.xlsx')

sheet = workbook.active
print(workbook.sheetnames)
# ['Sheet1', 'newSheet'] 目前有两个sheet表


# 这个操作相当于激活的这个要删除的 sheet 表，激活状态下，才可以操作；
remove_sheet = workbook['newSheet']

workbook.remove(remove_sheet)


print(workbook.sheetnames)
# ['Sheet1'] newSheet表已被删除，现在只有一张表

workbook.save(filename='./cash.xlsx')

 9、复制一个 sheet 表 .copy_worksheet()

from openpyxl import load_workbook



workbook = load_workbook(filename='./cash.xlsx')

sheet = workbook.active
print(workbook.sheetnames)
# ['Sheet1']


# 这个操作相当于激活的这个要操作的 sheet 表，激活状态下，才可以操作；
copy_sheet = workbook['Sheet1']

workbook.copy_worksheet(copy_sheet)

print(workbook.sheetnames)
# ['Sheet1', 'Sheet1 Copy']

workbook.save(filename='./cash.xlsx')

效果如下

 当然，你还可以再对这个复制出来的表再进行一次复制操作

from openpyxl import load_workbook



workbook = load_workbook(filename='./cash.xlsx')

sheet = workbook.active
print(workbook.sheetnames)
# ['Sheet1', 'Sheet1 Copy']


# 这个操作相当于激活的这个要操作的 sheet 表，激活状态下，才可以操作；
copy_sheet = workbook['Sheet1 Copy']

workbook.copy_worksheet(copy_sheet)

print(workbook.sheetnames)
# ['Sheet1', 'Sheet1 Copy', 'Sheet1 Copy Copy']

workbook.save(filename='./cash.xlsx')

10、修改 sheet 表的名称 sheet.title

 .title = "新的 sheet 表名"

from openpyxl import load_workbook



workbook = load_workbook(filename='./cash.xlsx')

sheet = workbook.active
print(workbook.sheetnames)
# ['Sheet1', 'Sheet1 Copy', 'Sheet1 Copy Copy']

sheet.title = "sheetUpdate"
print(workbook.sheetnames)

# ['sheetUpdate', 'Sheet1 Copy', 'Sheet1 Copy Copy']，第一张 sheet 表的表名已改变
# 若excel表中存在多个 sheet 表，默认修改第一张 sheet 表

# 也可以指定 sheet 表更改表名
updateSheet = workbook['Sheet1 Copy Copy']

updateSheet.title = "sheetUpdate2"
print(workbook.sheetnames)
# ['sheetUpdate', 'Sheet1 Copy', 'sheetUpdate2']

workbook.save(filename='./cash.xlsx')

11、创建新的 excel 表格文件

from openpyxl import Workbook



workbook = Workbook()
sheet = workbook.active

# sheet 表名为"表格 1"
sheet.title = "表格 1"


# excel 表名为 “新建的 excel 表格”
workbook.save(filename = "新建的 excel 表格")

12、冻结窗口 sheet.freeze_panes

 .freeze_panes = "单元格"

from openpyxl import load_workbook



workbook = load_workbook(filename='./cash.xlsx')

sheet = workbook.active
print(sheet)

# 冻结  "C3"单元格
sheet.freeze_panes = "C3"


workbook.save(filename='./cash.xlsx')

效果如下：第一二行固定在表格顶部，第一二列固定在左边，其余可拖动滚动条进行滑动查看

13、给表格添加“筛选器” sheet.auto_filter.ref

 .auto_filter.ref = sheet.dimension 给所有字段添加筛选器；
 .auto_filter.ref = "A1" 给 A1 这个格子添加“筛选器”，就是给第一列添加“筛选器”

from openpyxl import load_workbook



workbook = load_workbook(filename='./test2.xlsx')

sheet = workbook.active
# print(sheet)
sheet.auto_filter.ref = "C1"

workbook.save(filename='./test2.xlsx')

效果如下

---

资料参考：

https://blog.csdn.net/qq_44614026/article/details/108213906

https://blog.csdn.net/weixin_47536499/article/details/115417784

https://blog.csdn.net/qq_42819930/article/details/89463202

感谢各位博主的知识分享，本文在此基础上进行了进一步详细的归纳。

---

让我们一起，为梦想窒息。