"""
------------------------------------
@Time : 2019/5/13 18:00
@Auth : linux超
@File : ParseExcel.py
@IDE : PyCharm
@Motto: Real warriors,dare to face the bleak warning,dare to face the incisive error!
------------------------------------
"""
from openpyxl import load_workbook
from openpyxl.styles import Font
from openpyxl.styles.colors import BLACK
from collections import namedtuple


class ParseExcel(object):
"""解析excel文件"""

def __init__(self, filename, sheet_name=None):
try:
self.filename = filename
self.sheet_name = sheet_name
self.wb = load_workbook(self.filename)
if self.sheet_name is None:
self.work_sheet = self.wb.active
else:
self.work_sheet = self.wb[self.sheet_name]
except FileNotFoundError as e:
raise e

def get_max_row_num(self):
"""獲取最大行號"""
max_row_num = self.work_sheet.max_row
return max_row_num

def get_max_column_num(self):
"""獲取最大列號"""
max_column = self.work_sheet.max_column
return max_column

def get_cell_value(self, coordinate=None, row=None, column=None):
"""獲取指定單元格的數(shù)據(jù)"""
if coordinate is not None:
try:
return self.work_sheet[coordinate].value
except Exception as e:
raise e
elif coordinate is None and row is not None and column is not None:
if isinstance(row, int) and isinstance(column, int):
return self.work_sheet.cell(row=row, column=column).value
else:
raise TypeError('row and column must be type int')
else:
raise Exception("Insufficient Coordinate of cell!")

def get_row_value(self, row):
"""獲取某一行的數(shù)據(jù)"""
column_num = self.get_max_column_num()
row_value = []
if isinstance(row, int):
for column in range(1, column_num + 1):
values_row = self.work_sheet.cell(row, column).value
row_value.append(values_row)
return row_value
else:
raise TypeError('row must be type int')

def get_column_value(self, column):
"""獲取某一列數(shù)據(jù)"""
row_num = self.get_max_column_num()
column_value = []
if isinstance(column, int):
for row in range(1, row_num + 1):
values_column = self.work_sheet.cell(row, column).value
column_value.append(values_column)
return column_value
else:
raise TypeError('column must be type int')

def get_all_value_1(self):
"""獲取指定表單的所有數(shù)據(jù)(除去表頭)"""
max_row_num = self.get_max_row_num()
max_column = self.get_max_column_num()
values = []
for row in range(2, max_row_num + 1):
value_list = []
for column in range(1, max_column + 1):
value = self.work_sheet.cell(row, column).value
value_list.append(value)
values.append(value_list)
return values

def get_all_value_2(self):
"""獲取指定表單的所有數(shù)據(jù)(除去表頭)"""
rows_obj = self.work_sheet.iter_rows(min_row=2, max_row=self.work_sheet.max_row,
values_only=True) # 指定values_only 會(huì)直接提取數(shù)據(jù)不需要再使用cell().value
values = []
for row_tuple in rows_obj:
value_list = []
for value in row_tuple:
value_list.append(value)
values.append(value_list)
return values

def get_excel_title(self):
"""獲取sheet表頭"""
title_key = tuple(self.work_sheet.iter_rows(max_row=1, values_only=True))[0]
return title_key

def get_listdict_all_value(self):
"""獲取所有數(shù)據(jù)，返回嵌套字典的列表"""
sheet_title = self.get_excel_title()
all_values = self.get_all_value_2()
value_list = []
for value in all_values:
value_list.append(dict(zip(sheet_title, value)))
return value_list

def get_list_nametuple_all_value(self):
"""獲取所有數(shù)據(jù)，返回嵌套命名元組的列表"""
sheet_title = self.get_excel_title()
values = self.get_all_value_2()

excel = namedtuple('excel', sheet_title)
value_list = []
for value in values:
e = excel(*value)
value_list.append(e)
return value_list
def write_cell(self, row, column, value=None, bold=True, color=BLACK):
"""
指定單元格寫入數(shù)據(jù)
:param work_sheet:
:param row: 行號
:param column: 列號
:param value: 待寫入數(shù)據(jù)
:param bold: 加粗， 默認(rèn)加粗
:param color: 字體顏色，默認(rèn)黑色
:return:
"""
try:
if isinstance(row, int) and isinstance(column, int):
cell_obj = self.work_sheet.cell(row, column)
cell_obj.font = Font(color=color, bold=bold)
cell_obj.value = value
self.wb.save(self.filename)
else:
raise TypeError('row and column must be type int')
except Exception as e:
raise e
if __name__ == '__main__':
pe = ParseExcel('testdata.xlsx')
# sheet = pe.get_sheet_object('testcase')
column_row = pe.get_max_column_num()
print('最大列號:', column_row)
max_row = pe.get_max_row_num()
print('最大行號:', max_row)
#
cell_value_1 = pe.get_cell_value(row=2, column=3)
print('第%d行, 第%d列的數(shù)據(jù)為: %s' % (2, 3, cell_value_1))
cell_value_2 = pe.get_cell_value(coordinate='A5')
print('A5單元格的數(shù)據(jù)為: {}'.format(cell_value_2))
value_row = pe.get_row_value(3)
print('第{}行的數(shù)據(jù)為:{}'.format(3, value_row))
value_column = pe.get_column_value(2)
print('第{}列的數(shù)據(jù)為:{}'.format(2, value_column))
#
values_1 = pe.get_all_value_1()
print('第一種方式獲取所有數(shù)據(jù)\n', values_1)
values_2 = pe.get_all_value_2()
print('第二種方式獲取所有數(shù)據(jù)\n', values_2)
title = pe.get_excel_title()
print('表頭為\n{}'.format(title))
dict_value = pe.get_listdict_all_value()
print('所有數(shù)據(jù)組成的嵌套字典的列表:\n', dict_value)
#
namedtuple_value = pe.get_list_nametuple_all_value()
print('所有數(shù)據(jù)組成的嵌套命名元組的列表:\n', namedtuple_value)
pe.write_cell(1, 2, 'Tc_title')

"""
------------------------------------
@Time : 2019/5/22 9:11
@Auth : linux超
@File : ParseExcel.py
@IDE : PyCharm
@Motto: Real warriors,dare to face the bleak warning,dare to face the incisive error!
------------------------------------
"""
from openpyxl import load_workbook
from openpyxl.styles import Font
from openpyxl.styles.colors import BLACK
from collections import namedtuple
class ParseExcel(object):
"""解析excel文件"""
def __init__(self, filename):
try:
self.filename = filename
self.__wb = load_workbook(self.filename)
except FileNotFoundError as e:
raise e
def get_max_row_num(self, sheet_name):
"""獲取最大行號"""
max_row_num = self.__wb[sheet_name].max_row
return max_row_num
def get_max_column_num(self, sheet_name):
"""獲取最大列號"""
max_column = self.__wb[sheet_name].max_column
return max_column
def get_cell_value(self, sheet_name, coordinate=None, row=None, column=None):
"""獲取指定單元格的數(shù)據(jù)"""
if coordinate is not None:
try:
return self.__wb[sheet_name][coordinate].value
except Exception as e:
raise e
elif coordinate is None and row is not None and column is not None:
if isinstance(row, int) and isinstance(column, int):
return self.__wb[sheet_name].cell(row=row, column=column).value
else:
raise TypeError('row and column must be type int')
else:
raise Exception("Insufficient Coordinate of cell!")
def get_row_value(self, sheet_name, row):
"""獲取某一行的數(shù)據(jù)"""
column_num = self.get_max_column_num(sheet_name)
row_value = []
if isinstance(row, int):
for column in range(1, column_num + 1):
values_row = self.__wb[sheet_name].cell(row, column).value
row_value.append(values_row)
return row_value
else:
raise TypeError('row must be type int')
def get_column_value(self, sheet_name, column):
"""獲取某一列數(shù)據(jù)"""
row_num = self.get_max_column_num(sheet_name)
column_value = []
if isinstance(column, int):
for row in range(1, row_num + 1):
values_column = self.__wb[sheet_name].cell(row, column).value
column_value.append(values_column)
return column_value
else:
raise TypeError('column must be type int')
def get_all_value_1(self, sheet_name):
"""獲取指定表單的所有數(shù)據(jù)(除去表頭)"""
max_row_num = self.get_max_row_num(sheet_name)
max_column = self.get_max_column_num(sheet_name)
values = []
for row in range(2, max_row_num + 1):
value_list = []
for column in range(1, max_column + 1):
value = self.__wb[sheet_name].cell(row, column).value
value_list.append(value)
values.append(value_list)
return values
def get_all_value_2(self, sheet_name):
"""獲取指定表單的所有數(shù)據(jù)(除去表頭)"""
rows_obj = self.__wb[sheet_name].iter_rows(min_row=2, max_row=self.__wb[sheet_name].max_row, values_only=True)
values = []
for row_tuple in rows_obj:
value_list = []
for value in row_tuple:
value_list.append(value)
values.append(value_list)
return values
def get_excel_title(self, sheet_name):
"""獲取sheet表頭"""
title_key = tuple(self.__wb[sheet_name].iter_rows(max_row=1, values_only=True))[0]
return title_key
def get_listdict_all_value(self, sheet_name):
"""獲取所有數(shù)據(jù)，返回嵌套字典的列表"""
sheet_title = self.get_excel_title(sheet_name)
all_values = self.get_all_value_2(sheet_name)
value_list = []
for value in all_values:
value_list.append(dict(zip(sheet_title, value)))
return value_list
def get_list_nametuple_all_value(self, sheet_name):
"""獲取所有數(shù)據(jù)，返回嵌套命名元組的列表"""
sheet_title = self.get_excel_title(sheet_name)
values = self.get_all_value_2(sheet_name)
excel = namedtuple('excel', sheet_title)
value_list = []
for value in values:
e = excel(*value)
value_list.append(e)
return value_list
def write_cell(self, sheet_name, row, column, value=None, bold=True, color=BLACK):
if isinstance(row, int) and isinstance(column, int):
try:
cell_obj = self.__wb[sheet_name].cell(row, column)
cell_obj.font = Font(color=color, bold=bold)
cell_obj.value = value
self.__wb.save(self.filename)
except Exception as e:
raise e
else:
raise TypeError('row and column must be type int')
if __name__ == '__main__':
pe = ParseExcel('testdata.xlsx')
print(pe.get_all_value_2('division'))
print(pe.get_list_nametuple_all_value('division'))
column_row = pe.get_max_column_num('division')
print('最大列號:', column_row)
max_row = pe.get_max_row_num('division')
print('最大行號:', max_row)
cell_value_1 = pe.get_cell_value('division', row=2, column=3)
print('第%d行, 第%d列的數(shù)據(jù)為: %s' % (2, 3, cell_value_1))
cell_value_2 = pe.get_cell_value('division', coordinate='A5')
print('A5單元格的數(shù)據(jù)為: {}'.format(cell_value_2))
value_row = pe.get_row_value('division', 3)
print('第{}行的數(shù)據(jù)為:{}'.format(3, value_row))
value_column = pe.get_column_value('division', 2)
print('第{}列的數(shù)據(jù)為:{}'.format(2, value_column))
values_1 = pe.get_all_value_1('division')
print('第一種方式獲取所有數(shù)據(jù)\n', values_1)
values_2 = pe.get_all_value_2('division')
print('第二種方式獲取所有數(shù)據(jù)\n', values_2)
title = pe.get_excel_title('division')
print('表頭為\n{}'.format(title))
dict_value = pe.get_listdict_all_value('division')
print('所有數(shù)據(jù)組成的嵌套字典的列表:\n', dict_value)
namedtuple_value = pe.get_list_nametuple_all_value('division')
print('所有數(shù)據(jù)組成的嵌套命名元組的列表:\n', namedtuple_value)
pe.write_cell('division', 1, 2, 'Tc_title')

"""
------------------------------------
@Time : 2019/5/13 21:22
@Auth : linux超
@File : ParseExcel_xlrd.py
@IDE : PyCharm
@Motto: Real warriors,dare to face the bleak warning,dare to face the incisive error!
------------------------------------
"""
import xlrd
from xlutils import copy
from collections import namedtuple

class ParseExcel(object):
# xlrd 解析excel， 行號和列號都是從0開始的
def __init__(self, filename, sheet):
try:
self.filename = filename
self.sheet = sheet
self.wb = xlrd.open_workbook(self.filename, formatting_info=True)
if isinstance(sheet, str):
self.sheet = self.wb.sheet_by_name(sheet)
elif isinstance(sheet, int):
self.sheet = self.wb.sheet_by_index(sheet)
else:
raise TypeError('sheet must be int or str')
except Exception as e:
raise e

def get_max_row(self):
"""獲取表單的最大行號"""
max_row_num = self.sheet.nrows
return max_row_num

def get_max_column(self):
"""獲取表單的最大列號"""
min_row_num = self.sheet.ncols
return min_row_num

def get_cell_value(self, row, column):
"""獲取某個(gè)單元格的數(shù)據(jù)"""
if isinstance(row, int) and isinstance(column, int):
values = self.sheet.cell(row-1, column-1).value
return values
else:
raise TypeError('row and column must be type int')

def get_row_values(self, row):
"""獲取某一行的數(shù)據(jù)"""
if isinstance(row, int):
values = self.sheet.row_values(row-1)
return values
else:
raise TypeError('row must be type int')

def get_column_values(self, column):
"""獲取某一列的數(shù)據(jù)"""

if isinstance(column, int):
values = self.sheet.col_values(column-1)
return values
else:
raise TypeError('column must be type int')

def get_table_title(self):
"""獲取表頭"""
table_title = self.get_row_values(1)
return table_title

def get_all_values_dict(self):
"""獲取所有的數(shù)據(jù)，不包括表頭，返回一個(gè)嵌套字典的列表"""
max_row = self.get_max_row()
table_title = self.get_table_title()
value_list = []
for row in range(2, max_row):
values = self.get_row_values(row)
value_list.append(dict(zip(table_title, values)))
return value_list

def get_all_values_nametuple(self):
"""獲取所有的數(shù)據(jù)，不包括表頭，返回一個(gè)嵌套命名元組的列表"""
table_title = self.get_table_title()
max_row = self.get_max_row()
excel = namedtuple('excel', table_title)
value_list = []
for row in range(2, max_row):
values = self.get_row_values(row)
e = excel(*values)
value_list.append(e)
return value_list

def write_value(self, sheet_index, row, column, value):
"""寫入某個(gè)單元格數(shù)據(jù)"""
if isinstance(row, int) and isinstance(column, int):
if isinstance(sheet_index, int):
wb = copy.copy(self.wb)
worksheet = wb.get_sheet(sheet_index)
worksheet.write(row-1, column-1, value)
wb.save(self.filename)
else:
raise TypeError('{} must be int'.format(sheet_index))
else:
raise TypeError('{} and {} must be int'.format(row, column))

if __name__ == '__main__':
pe = ParseExcel('testdata.xls', 'testcase')
print('最大行號:', pe.get_max_row())
print('最大列號:', pe.get_max_column())
print('第2行第3列數(shù)據(jù):', pe.get_cell_value(2, 3))
print('第2行數(shù)據(jù)', pe.get_row_values(2))
print('第3列數(shù)據(jù)', pe.get_column_values(3))
print('表頭:', pe.get_table_title())
print('所有的數(shù)據(jù)返回嵌套字典的列表:', pe.get_all_values_dict())
print('所有的數(shù)據(jù)返回嵌套命名元組的列表:', pe.get_all_values_nametuple())
　　 pe.write_value(0, 1, 3, 'test')

"""
------------------------------------
@Time : 2019/5/13 14:00
@Auth : linux超
@File : ParseExcel_pandas.py
@IDE : PyCharm
@Motto: Real warriors,dare to face the bleak warning,dare to face the incisive error!
------------------------------------
"""
import pandas as pd


class ParseExcel(object):
def __init__(self, filename, sheet_name=None):
try:
self.filename = filename
self.sheet_name = sheet_name
self.df = pd.read_excel(self.filename, self.sheet_name)
except Exception as e:
raise e

def get_row_num(self):
"""獲取行號組成的列表, 從0開始的"""
row_num_list = self.df.index.values
return row_num_list

def get_cell_value(self, row, column):
"""獲取某一個(gè)單元格的數(shù)據(jù)"""
try:
if isinstance(row, int) and isinstance(column, int):
cell_value = self.df.ix[row-2, column-1] # ix的行參數(shù)是按照有效數(shù)據(jù)行，且從0開始
return cell_value
else:
raise TypeError('row and column must be type int')
except Exception as e:
raise e

def get_table_title(self):
"""獲取表頭， 返回列表"""
table_title = self.df.columns.values
return table_title

def get_row_value(self, row):
"""獲取某一行的數(shù)據(jù)， 行號從1開始"""
try:
if isinstance(row, int):
row_data = self.df.ix[row-2].values
return row_data
else:
raise TypeError('row must be type int')
except Exception as e:
raise e

def get_column_value(self, col_name):
"""獲取某一列數(shù)據(jù)"""
try:
if isinstance(col_name, str):
col_data = self.df[col_name].values
return col_data
else:
raise TypeError('col_name must be type str')
except Exception as e:
raise e
def get_all_value(self):
"""獲取所有的數(shù)據(jù)，不包括表頭, 返回嵌套字典的列表"""
rows_num = self.get_row_num()
table_title = self.get_table_title()
values_list = []
for i in rows_num:
row_data = self.df.ix[i, table_title].to_dict()
values_list.append(row_data)
return values_list
if __name__ == '__main__':
pe = ParseExcel('testdata.xlsx', 'testcase')
print(pe.get_row_num())
print(pe.get_table_title())
print(pe.get_all_value())
print(pe.get_row_value(2))
print(pe.get_cell_value(2, 3))
print(pe.get_column_value('Tc_title'))