将数据从多个 excel 文件复制到特定工作表上的现有文件

Question

我想从多个 excel 文件中复制数据并将其粘贴到现有的 excel 文件中。

import os
import openpyxl
import pandas as pd

my_path = r'C://Users//greencolor//Autoreport//Load_attachments//' # Updating every monday with new files
my_path1 =r'C://Users//greencolor//Desktop//Autoreport//' # place of Master.xlsx 
for filename in os.listdir(my_path): #loop though the downloaded files 
    if filename.startswith('PB orders Dec'): #finds the file with the name PB orders December.xlsb
        dec = pd.read_excel(os.path.join(my_path, filename), 
                                         sheet_name='Raw data ', 
                                         engine='pyxlsb') #reading the specific sheet named Raw data
        with pd.ExcelWriter(my_path1 + '//Maaster.xlsx', mode='a', engine=openpyxl) as writer:
            dec.to_excel(writer, sheet_name='DecData', index=False) #copyes the data from PB orders December.xlsb and paste it in Master file on sheet Decdata without deleting other sheets. Basically updating all data with new data.

我的问题是我想对多个文件执行上述相同的操作。 例如，如果在Load_attachments中是名为 PB 订单 November.xlsb 的文件，我想将相同的代码应用于该 11 月文件，等等任何月份名称文件。

Answer 1

您可以将整个内容（减去导入）放在一个 for 循环中，并为其提供文件名开头的数组：

import os
import openpyxl
import pandas as pd

fnamebegin_array = ['PB orders Jan','PB orders Feb','PB orders Mar','etc']
sheetname_array = ['JanData','FebData','MarData','etc']

for i in range(len(fnamebegin_array)): # would be 12, if there is data for each month in a year
    my_path = r'C://Users//greencolor//Autoreport//Load_attachments//'
    my_path1 =r'C://Users//greencolor//Desktop//Autoreport//'
    for filename in os.listdir(my_path):
        if filename.startswith(fnamebegin_array[i]):
            month = pd.read_excel(os.path.join(my_path, filename), 
                                         sheet_name='Raw data ', 
                                         engine='pyxlsb')
            with pd.ExcelWriter(my_path1 + '//Master.xlsx', mode='a', engine=openpyxl) as writer:
                month.to_excel(writer, sheet_name=sheetname_array[i], index=False)