#常用属性练习

    workbook_path= os.path.join(CONFIG_PATH,'testdata.xlsx')

    wb = openpyxl.load_workbook(workbook_path)

    ws = wb.active

    print(ws)#<Worksheet "Sheet1">

    ws_list=wb.worksheets

    print(ws_list)#[<Worksheet "Sheet1">, <Worksheet "Sheet2">, <Worksheet "Sheet3">]

    print(wb.read_only) #False

    print(wb.encoding)#utf-8

    print(wb.write_only)#False

    print(wb.sheetnames)#['Sheet1', 'Sheet2', 'Sheet3']

    print(wb.properties)

    #<openpyxl.packaging.core.DocumentProperties object>

    #Parameters:

    #creator='openpyxl', title=None, description=None, subject=None, identifier=None, language=None, created=datetime.datetime(2018, 8, 18, 2, 14, 50),

    # modified=datetime.datetime(2018, 8, 18, 5, 12, 7), lastModifiedBy='wuxiaoli', category=None, contentStatus=None, version=None, revision=None,

    #  keywords=None, lastPrinted=None

 #workbook常用方法练习

    workbook_path= os.path.join(CONFIG_PATH,'testdata.xlsx')

    wb = openpyxl.load_workbook(workbook_path)

    sheet_names_list=wb.get_sheet_names()#['Sheet1', 'Sheet2', 'Sheet3']

    ws1 = wb.get_sheet_by_name('Sheet2')#<Worksheet "Sheet2">

    ws2 = wb.get_active_sheet()#<Worksheet "Sheet1">

    ws3 = wb.create_sheet('text')#<Worksheet "text">

    print(wb.sheetnames)

    #wb.remove_sheet(ws3)

    wb.copy_worksheet(from_worksheet=ws1)

<1>openpyxl的三种最重要的数据结构

NULL空值：对应于python中的None，表示这个cell里面没有数据。

numberic： 数字型，统一按照浮点数来进行处理。对应于python中的float。

string： 字符串型，对应于python中的unicode。

<2>Excel 文件的三个对象

workbook： 工作簿，一个excel工作簿包含多个sheet。

sheet：工作表，一个workbook有多个，表名识别，如“sheet1”,“sheet2”等。

cell： 单元格，存储数据对象

<3>导入

from openpyxl import Workbook

from openpyxl import load_workbook

from openpyxl.styles import PatternFill, Border, Side, Alignment, Protection, Font, Color, Fill

from openpyxl.styles import colors

from openpyxl.styles import Fill,fills

from openpyxl.formatting.rule import ColorScaleRule

<4>加载workbook

加载workbook时注意openpyxl只支持xlsx格式，老版的xls格式需要其他方法去加载。

wb = load_workbook('file_name.xlsx')或wb = load_workbook(filename = r'file_namexlsx')

<5>新建worksheet

新建工作表用函数create_sheet()

create_sheet(title=None, index=None):

        """Create a worksheet (at an optional index).

        :param title: optional title of the sheet

        :type title: unicode

        :param index: optional position at which the sheet will be inserted

        :type index: int

        """

ws1 = wb.create_sheet() #默认插在最后

ws2 = wb.create_sheet(0) #插在开头建表后默认名按顺序，如sheet1，sheet2...

ws.title = "New Title" #修改表名称

简化 ws2 = wb.create_sheet(title="sheet_name")

<6>打开 worksheet

1)通过名字

    ws = wb["sheet_name"]

    等同于 ws2 = wb.get_sheet_by_name('sheet_name')

2)不知道名字用index

    sheet_names = wb.get_sheet_names()

    ws = wb.get_sheet_by_name(sheet_names[index])# index为0为第一张表 

或者

    ws =wb.active

    等同于  ws = wb.get_active_sheet() #通过_active_sheet_index设定读取的表，默认0读第一个表

3) 获取活动表表名wb.get_active_sheet().title

<7>编辑单元格

1)读写单个单元格

c = ws['A4'] #read 等同于 c = ws.cell('A4')

ws['A4'] = 4 #write

#ws.cell有两种方式，行号列号从1开始

d = ws.cell(row = 4, column = 2) #行列读写

d = ws.cell('A4')

写入cell值

    ws.cell(row = 4, column = 2).value = 'test')

    ws.cell(row = 4, column = 2, value = 'test')

2)读写多个单元格

cell_range = ws['A1':'C2']#读取A1到C1单元格数据

get_cell_collection()#读所有单元格数据

<8>获取最大行和最大列

print(sheet.max_row)

print(sheet.max_column)

<9>获取行和列的值

sheet.rows为生成器, 里面是每一行的数据，每一行又由一个tuple包裹。

sheet.columns类似，不过里面是每个tuple是每一列的单元格。

# 按行获取值，返回值为A1, B1, C1这样的顺序

for row in sheet.rows:

    for cell in row:

        print(cell.value)

# 按列获取值，返回值为A1, A2, A3这样的顺序

for column in sheet.columns:

    for cell in column:

        print(cell.value)

上面的代码就可以获得所有单元格的数据。如果要获得某行的数据呢？因sheet.rows是生成器类型，不能使用索引，但是转换成list之后便可使用索引，如list(sheet.rows)[2]这样就获取到第三行的tuple对象。

for cell in list(sheet.rows)[2]:

    print(cell.value)

也可以通过iter_rows的参数min_row, max_row指定并获取指定行内容，如下所示，获取第二行表格的内容:

for row in ws.iter_rows(min_row=2, max_row=2,):

    line = [cell.value for cell in row]

    print(line)

此外可使用方法ws.iter_rows()逐行读取数据

ws.iter_rows(range_string=None, row_offset=0, column_offset=0): range-string(string)-单元格的范围：例如('A1:C4') row_offset-添加行 column_offset-添加列

   # 返回一个生成器, 注意取值时要用value,例如：

from openpyxl import load_workbook

from constant.constant import CONFIG_PATH

import os.path

test_data = os.path.join(CONFIG_PATH,'testdata.xlsx')

wb = load_workbook(test_data)

ws = wb.active

ws.title = 'testdata.xlsx'

for row in ws.iter_rows('A1:C2'):

    for cell in row:

        print(cell.value)

<10>获取任意区间的值

法1.使用range函数

可以使用range函数，下面的写法，获得了以A1为左上角，B3为右下角矩形区域的所有单元格。注意range从1开始的，因为在openpyxl中为了和Excel中的表达方式一致，并不和编程语言的习惯以0表示第一个值。

workbook_path= os.path.join(CONFIG_PATH,'testdata.xlsx')

wb = openpyxl.load_workbook(workbook_path)

ws = wb.get_sheet_by_name(name='Sheet1')

for i in range(1, 4):

    for j in range(1, 3):

        print(ws.cell(row=i, column=j))

#out

#<Cell 'Sheet1'.A1>

#<Cell 'Sheet1'.B1>

#<Cell 'Sheet1'.A2>

#<Cell 'Sheet1'.B2>

#<Cell 'Sheet1'.A3>

#<Cell 'Sheet1'.B3>

法2.使用切片，如sheet['A1':'B3']，返回一个tuple，该元组内部还是元组，由每行的单元格构成一个元组。

workbook_path= os.path.join(CONFIG_PATH,'testdata.xlsx')

wb = openpyxl.load_workbook(workbook_path)

ws = wb.get_sheet_by_name(name='Sheet1')

for row_cell in ws['A1':'B3']:

     for cell in row_cell:

           print(cell)

#out

#<Cell 'Sheet1'.A1>

#<Cell 'Sheet1'.B1>

#<Cell 'Sheet1'.A2>

#<Cell 'Sheet1'.B2>

#<Cell 'Sheet1'.A3>

#<Cell 'Sheet1'.B3>

for cell in sheet['A1':'B3']:

    print(cell)

#out

#(<Cell 'Sheet1'.A1>, <Cell 'Sheet1'.B1>)

#(<Cell 'Sheet1'.A2>, <Cell 'Sheet1'.B2>)

#(<Cell 'Sheet1'.A3>, <Cell 'Sheet1'.B3>)

<11>根据字母获得列号，根据列号返回字母

from openpyxl.utils import get_column_letter, column_index_from_string

# 根据列的数字返回字母

print(get_column_letter(2))  # B

# 根据字母返回列的数字

print(column_index_from_string('D'))  #

<12>写单元格

# 直接给单元格赋值就行

sheet['A1'] = 'good'

# 利用公式在B9处写入平均值

sheet['B9'] = '=AVERAGE(B2:B8)'

#注意：如果是读取，需要加上data_only=True，这样读到B9返回的才是数字，如果不加这个参数，返回的将是公式本身'=AVERAGE(B2:B8)'

<13>使用append函数写数据

append函数可以一次添加多行数据，从第一行空白行开始（下面都是空白行）写入。

ws.append(iterable)

 #添加一行到当前sheet的最底部（即逐行追加从第一行开始） iterable必须是list,tuple,dict,range,generator类型的。 1,如果是list,将list从头到尾顺序添加。 2，如果是dict,按照相应的键添加相应的键值。

 ws.append([‘This is A1’, ‘This is B1’, ‘This is C1’])

 ws.append({‘A’ : ‘This is A1’, ‘C’ : ‘This is C1’})

 ws.append({1 : ‘This is A1’, 3 : ‘This is C1’})

# 添加一行如下：

row = [1 ,2, 3, 4, 5]

sheet.append(row)

import openpyxl

if __name__=='__main__':

    wb = openpyxl.load_workbook(r'D:\pythonstudy\2018-08-18.xlsx')

    # 取第一张表

    sheetnames = wb.sheetnames

    ws = wb[sheetnames[0]]

    # 显示表名，表行数，表列数

    print("Work Sheet Title:", ws.title)

    print("Work Sheet Rows:", ws.max_row)

    print("Work Sheet Cols:",ws.max_column)

   #获取指定行的值，如第三行

    row3_values = []

    row3_cell_list = list(ws.rows)[2]

    for cell in row3_cell_list:

        row3_values.append(cell.value)

    print(row3_values)#output:['A3', 'B3', 'C3', 'D3']

    #获取所有行的数据

    # 建立存储数据的字典

    data = {}

    # 获取表格所有值

    #法1:

    for i in range(0,ws.max_row):

        every_row_values = []

        every_row_cell_list = list(ws.rows)[i]

        for cell in every_row_cell_list:

            every_row_values.append(cell.value)

        data[i+1]= every_row_values

    print(data)

    #{1: ['A1', 'B1', 'C1', 'D1'], 2: ['A2', 'B2', 'C2', 'D2'], 3: ['A3', 'B3', 'C3', 'D3'], 4: ['A4', 'B4', 'C4', 'D4'], 5: ['A5', 'B5', 'C5', 'D5'],

    #  6: ['A6', 'B6', 'C6', 'D6'], 7: ['A7', 'B7', 'C7', 'D7'], 8: ['A8', 'B8', 'C8', 'D8'], 9: ['A9', 'B9', 'C9', 'D9'], 10: ['A10', 'B10', 'C10', 'D10'],

    # 11: ['A11', 'B11', 'C11', 'D11']}

    #法2

    for row in ws.rows:

    line = [cell.value for cell in row]

    print (line)#output:['A1', 'B1', 'C1', 'D1'],['A2', 'B2', 'C2', 'D2'], ['A3', 'B3', 'C3', 'D3'],['A4', 'B4', 'C4', 'D4'], ['A5', 'B5', 'C5', 'D5'],['A6', 'B6', 'C6', 'D6'],['A7', 'B7', 'C7', 'D7'],['A8', 'B8', 'C8', 'D8'],['A9', 'B9', 'C9', 'D9'],['A10', 'B10', 'C10', 'D10'],['A11', 'B11', 'C11', 'D11']

    #获取某个区间的值，例：获得了以A3为左上角，C6为右下角矩形区域的所有单元格

    #法1：使用range

    data1={}

    for i in range(2,6):

        every_row_values = []

        every_row_cell_list = list(ws.rows)[i]

        for cell in every_row_cell_list:

            every_row_values.append(cell.value)

        data1[i+1]=every_row_values

    print(data1)

#output{3: ['A3', 'B3', 'C3', 'D3'], 4: ['A4', 'B4', 'C4', 'D4'], 5: ['A5', 'B5', 'C5', 'D5'], 6: ['A6', 'B6', 'C6', 'D6']}

    #法2:使用切片

    data_list = []

    for row_cell in ws['A3':'C6']:

        every_row_value = []

        for cell in row_cell:

            every_row_value.append(cell.value)

        data_list.append(every_row_value)

    print(data_list)#output:[['A3', 'B3', 'C3'], ['A4', 'B4', 'C4'], ['A5', 'B5', 'C5'], ['A6', 'B6', 'C6']]

#-*- coing=utf-8 -*-

from openpyxl import load_workbook

from constant.constant import CONFIG_PATH

import os.path

class ExcelReader(object):

    """

        Read the contents of the excel file, Return list.

        example:

        The contents of the excel file：

        | A  | B  | C  |

        | A1 | B1 | C1 |

        | A2 | B2 | C2 |

        print(ExcelReader(excel, title_line=True).data)，output：

        [{A: A1, B: B1, C:C1}, {A:A2, B:B2, C:C2}]

        print(ExcelReader(excel, title_line=False).data)，output：

        [[A,B,C], [A1,B1,C1], [A2,B2,C2]]

        You can specify sheet through index or name:

        example:

        ExcelReader(excel, sheet=2)

        ExcelReader(excel, sheet='testdata')

    """

    def __init__(self, excel, sheet=0, title_line=True):

        if os.path.exists(excel):

           self.excel = excel

        else:

            raise FileNotFoundError('Excel file does not exist ！')

        self.sheet = sheet

        self.title_line = title_line

        self._data = list()

    @property

    def data(self):

        if not self._data:

            workbook = load_workbook(self.excel)

            if type(self.sheet) not in [int, str]:

                raise TypeError('Please pass in <type int> or <type str>, not {0}'.format(type(self.sheet)))

            elif type(self.sheet) == int:

                sheetnames = workbook.sheetnames

                ws = workbook[sheetnames[self.sheet]]

            else:

                ws = workbook[self.sheet]

            if self.title_line:

                for row in ws.iter_rows(min_row=1, max_row=1, ):

                    title = [cell.value for cell in row]# 首行为title

                for i in range(1, ws.max_row):

                    every_row_cell_list = list(ws.rows)[i]

                    every_row_value = []

                    for cell in every_row_cell_list:

                        every_row_value.append(cell.value)

                    self._data.append(dict(zip(title, every_row_value)))

            else:

                for row in ws.rows:

                    self._data.append([cell.value for cell in row])

        return self._data

if __name__ == '__main__':

    test_data = os.path.join(CONFIG_PATH,'testdata.xlsx')

    reader = ExcelReader(test_data,sheet= 0,title_line=False)

    print(reader.data)

#-*- coing=utf-8 -*-

from openpyxl import load_workbook

from openpyxl.utils import get_column_letter, column_index_from_string

from config.globalconfig import TEST_DATA_PATH

import os.path

class ExcelReader(object):

    def __init__(self, excel, sheet=0, title_line=True,column=None,row=None):

        """

        :param excel: excel path,type=str

        :param sheet: sheet name or sheet sequence number,type = str or int

        :param title_line: title_line = True,return dic,title_line = False,return list

        :param column: Non essential parameter,type = int or str,int express column number，str express column field name of first line

        :param row: Non essential parameter,type = int,express row number

        """

        if os.path.exists(excel):

           self.excel = excel

        else:

            raise FileNotFoundError('Excel file does not exist ！')

        self.sheet = sheet

        self.title_line = title_line

        self.column = column

        self.row = row

        self._data = []

        self._cell_data = str()

        self.workbook = load_workbook(self.excel)

        if type(self.sheet) not in [int, str]:

            raise TypeError('Please pass in <type int> or <type str>, not {0}'.format(type(self.sheet)))

        elif type(self.sheet) == int:

            sheetnames = self.workbook.sheetnames

            self.ws = self.workbook[sheetnames[self.sheet]]

        else:

            self.ws = self.workbook[self.sheet]

    @property

    def sheet_data(self):

        """

            Read the contents of the excel file, Return list.

            example:

            The contents of the excel file：

            | A  | B  | C  |

            | A1 | B1 | C1 |

            | A2 | B2 | C2 |

            print(ExcelReader(excel, title_line=True).data)，output：

            [{A: A1, B: B1, C:C1}, {A:A2, B:B2, C:C2}]

            print(ExcelReader(excel, title_line=False).data)，output：

            [[A,B,C], [A1,B1,C1], [A2,B2,C2]]

            You can specify sheet through index or name:

            example:

            ExcelReader(excel, sheet=2)

            ExcelReader(excel, sheet='testdata')

        """

        if not self._data:

            if self.title_line:

                for row in self.ws.iter_rows(min_row=1, max_row=1, ):

                    title = [cell.value for cell in row]# 首行为title

                for i in range(1, self.ws.max_row):

                    every_row_cell_list = list(self.ws.rows)[i]

                    every_row_value = []

                    for cell in every_row_cell_list:

                        every_row_value.append(cell.value)

                    self._data.append(dict(zip(title, every_row_value)))

            else:

                for row in self.ws.rows:

                    self._data.append([cell.value for cell in row])

        return self._data

    def column_letter(self):

        """Column number converted to letter form."""

        if isinstance(self.column, (int)):

            return get_column_letter(self.column)  # 数字转换为字母

        elif isinstance(self.column, (str)):

            for row in self.ws.iter_rows(min_row=1, max_row=1, ):

                columnFieldName = [cell.value for cell in row]

            if columnFieldName.count(self.column) == 1:  # 相同字段名存在的个数

                for index, cell in enumerate(columnFieldName):

                    if cell == self.column:

                        return get_column_letter(index + 1)

            elif columnFieldName.count(self.column) == 0:

                raise ValueError("Current sheet page '%s' no field name '%s' exists!" % (self.ws.title, self.column))

            else:

                raise ValueError("Current sheet page'%s'include duplicate field name '%s'" % (self.ws.title, self.column))

        else:

            raise TypeError("The column parameter type should be int or str, not '%s'" % (self.column.__class__))

    @property

    def cell_data(self):

        if not self._cell_data:

            if not isinstance(self.row, (int)):

                raise TypeError("The row parameter type should be int instead of '%s'!" % (self.row.__class__))

            column = self.column_letter()

            return self.ws[column + str(self.row)].value

class ExcelWritter(ExcelReader):

    def __init__(self, excel, sheet=0, column=None,row=None,value=''):

        ExcelReader.__init__(self,excel,sheet=0)

        self.value = value

        self.column =column

        self.row = row

    def write_cell(self):

        if not isinstance(self.row, (int)):

            raise TypeError("The row parameter type should be int instead of '%s'!" % (self.row.__class__))

        if not isinstance(self.value, (str)):

            raise TypeError("The value parameter type should be str instead of '%s'!" % (self.value.__class__))

        column = self.column_letter()

        self.ws[column + str(self.row)].value = self.value

        self.workbook.save(self.excel)