Question

首先，我是python的新手（实际上我只从Sololearn学到了，也只有半个课程）。所以我请你给我一些详细的答案。我的任务有以下几个步骤： -

删除旧的.xlsx文件（如果有）
使用win32将两个.xls文件转换为.xlsx文件，删除第一行然后删除.xls文件[已经下载到源目录中的奇怪xls文件+ xlrd，pyexcel显示错误（不支持格式或损坏）文件在打开.xls文件（在线分析文件预测它是html / htm）]
从xlsx文件中获取数据
首先，删除Google电子表格中的旧工作表以删除旧数据。创建一个具有相同名称的新工作表。将数据插入到Google电子表格中的新工作表中。
打开第二张（从第一张纸张导入数据）并更新Dummy Sheet中的一个单元格，以确保Google电子表格在后台同步。

现在，我通过组合许多代码并使用大量谷歌来编写代码。代码工作正常，但它需要大约65秒才能完成整个过程。我的问题有3个部分： -

有没有办法直接访问.xls文件中的数据？
是否可以改进此代码的性能。
完成上述任务的其他任何更有效的方法？

我的代码： -

import time
import win32com.client as win32
import os
import openpyxl
from openpyxl.utils import get_column_letter
import gspread
from oauth2client.service_account import ServiceAccountCredentials

start = time.time()

# set input-output file locations
source_dir = "C:\\Users\\XYZ\\Downloads"
output_dir = "C:\\Users\\XYZ\\Excels"

# use creds to create a client to interact with the Google Drive API
# make sure to share files with email contained in json file
scope = ['https://spreadsheets.google.com/feeds']
# code will not work without json file
creds = ServiceAccountCredentials.from_json_keyfile_name("C:\\Users\\XYZ\\your.json", scope)
gc = gspread.authorize(creds)
# following code is to open any spreadsheet by name
sh = gc.open("First Sheet")

def save_as_xlsx(input_file,output_dir,output_file_name) :
              # call excel using win32, then open .xls file
              # delete first row and then save as .xlsx
              excel = win32.gencache.EnsureDispatch('Excel.Application')
              wb = excel.Workbooks.Open(input_file)
              wbk = excel.ActiveWorkbook 
              sheet = wbk.Sheets(1) 
              sheet.Rows(1).Delete()
              wb.SaveAs(output_dir + '\\' + output_file_name, FileFormat = 51)
              #FileFormat = 51 is for .xlsx extension. FileFormat = 56 is for .xls extension
              wb.Close()
              excel.Application.Quit()
              return True

def get_the_data_from_xlsx(output_dir,output_file_name) :
              # use openpyxl.load to find out last cell of file
              # store cell values in list called data
              wb = openpyxl.load_workbook(output_dir + '\\' + output_file_name)
              sheet = wb.active
              max_row_no = sheet.max_row
              max_column_no = sheet.max_column
              max_column = get_column_letter(max_column_no)
              last_cell = str(max_column) + str(max_row_no)
              cell_addresses = sheet['A1' : last_cell]
              data = []
              for i in cell_addresses :
                  for e in i :
                      data.append(e.value)
              return (data,last_cell)

def insert_data_into_spreadsheet(name_of_worksheet,data,last_cell) :
              # Find a workbook by name in already opened spreadsheet
              # delete the worksheet to clear old data
              # create worksheet with same name to maintain import connections in sheets.
              worksheet = sh.worksheet(name_of_worksheet)
              sh.del_worksheet(worksheet)
              worksheet = sh.add_worksheet(title=name_of_worksheet, rows="500", cols="30")
              # store range of cells for spreadsheet in list named cell_list
              cell_list = worksheet.range('A1' + ':' + str(last_cell))
              # attach all the values from data list as per the cell_list
              a = 0
              for cell in cell_list :
                  cell.value = data[a]
                  a = a + 1
              # update all cells stored in cell_list in one go       
              worksheet.update_cells(cell_list)

def delete_file(directory,file_initials) :
       for filename in os.listdir(directory) :
              if filename.startswith(file_initials) :
                     os.unlink(directory  +"\\" +  filename)

# check if files are in source_dir
for filename in os.listdir(source_dir) :
       # check for file1.xls and set input_file name if any file exists.
       if filename.startswith("file1"):
              input_file = source_dir + "\\file1.xls"
              output_file1 = "output_file1.xlsx"
              # detect and delete any old file in output directory
              delete_file(output_dir,"output_file1")

              if save_as_xlsx(input_file,output_dir,output_file1) == True :       
                     # delete the file from source directory after work is done
                     delete_file(source_dir,'file1')

              # get data from new xlsx file
              data_from_xlsx = get_the_data_from_xlsx(output_dir,output_file1)
              data_to_spreadsheet = data_from_xlsx[0]
              last_cell = data_from_xlsx[1]

              # insert updated data into spreadsheet
              insert_data_into_spreadsheet("file1_data",data_to_spreadsheet,last_cell)           

       # repeat the same process for 2nd file
       if filename.startswith('file2'):
              input_file = source_dir + "\\file2.xls"
              output_file2 = "output_file2.xlsx"

              delete_file(output_dir,"output_file2")

              if save_as_xlsx(input_file,output_dir,output_file2) == True :
                     delete_file(source_dir,'file2')

              data_from_xlsx = get_the_data_from_xlsx(output_dir,output_file2)
              data_to_spreadsheet = data_from_xlsx[0]
              last_cell = data_from_xlsx[1]

              insert_data_into_spreadsheet("file2_data",data_to_spreadsheet,last_cell)           

# open spreadsheet by name and open Dummy worksheet
# update one cell to sync the sheet with other sheets
sh = gc.open("second sheet")
worksheet = sh.worksheet("Dummy")
worksheet.update_acell('B1', '=Today()')

end = time.time()
print(end-start)

改进用于更新谷歌电子表格的python代码

0 个答案: