一键式统计5.0待更新写入模块操作

本文介绍了一个Python脚本,该脚本能批量将.xls文件转换为.xlsx格式,并从多个工作表中提取特定数据。通过查找包含关键词的工作表,如“资产负债表”、“利润表”,脚本能定位并读取特定单元格的数据。

摘要生成于 C知道 ,由 DeepSeek-R1 满血版支持, 前往体验 >

import os
import win32com.client as win32
import shutil
import openpyxl
import os
import win32com.client as win32
import shutil
import openpyxl

import time

import time

#####part one



ws = {'资产负债表':0,'利润表':0,'纳税申报表':0,'财务状况表':0 }



mydir = 'bak'             #基本逻辑就是分两种情况,文件夹有和无,有时,为了避免里面数据污染,删了重建一个;没有则是正常建一个就好

if os.path.exists(mydir) == 0 :
    os.mkdir(mydir)
else:
    shutil.rmtree('bak')
    os.mkdir(mydir)



file = []



path = os.getcwd()  # 转换前程序所在文件目录

path_bak = os.getcwd() + r'/bak/'

pathdir = os.listdir(path)
#print(pathdir)
for s in pathdir:
    newdir = os.path.join(path, s)
    if os.path.isfile(newdir):
        os.chdir(path_bak)
        pathdir_bak = os.listdir(path_bak)
       # print(pathdir_bak)
        if os.path.splitext(newdir)[1] == ".xls":
            t = os.path.split(s)[1] + r'x'
            if os.path.exists(t):
            #    print(os.path.exists(os.path.split(s)[1]))
                break
            else:
                excel = win32.gencache.EnsureDispatch('Excel.Application')
                wb = excel.Workbooks.Open(newdir)
             #   print(newdir)
                path_dir = os.path.split(newdir)[0]
                path_file = os.path.split(newdir)[1]
              #  print(path_dir)
             #   print(path_file)
                wb.SaveAs(path_dir + '/bak/' + path_file + 'x', FileFormat=51)  # FileFormat = 51 is for .xlsx extension
                wb.Close()  # FileFormat = 56 is for .xls extension
                excel.Application.Quit()
        elif os.path.splitext(newdir)[1] == ".xlsx":
            file.append(newdir)


    elif os.path.isdir(newdir):
        continue

for i in range(len(file)):
    pcm_file = file[i]
    path_0 = os.path.split(file[i])[0]
    path_1 = os.path.split(file[i])[1]
    oldname = path_0 + '/' + path_1
    newname = path_0 + r'/bak/' + path_1
    shutil.copyfile(oldname, newname)


#time.sleep(5)  #暂停10秒

#####第二步将文件目录切换至bak文件夹中,,切片u v w



file_deal = []

path_deal = os.getcwd()  # 转换前程序所在文件目录





pathdir_deal = os.listdir(path_deal)
for u in pathdir_bak:
    newdir_deal = os.path.join(path_deal, u)
    file_deal.append(newdir_deal)
   # print(file_deal)



for j in range(len(file_deal)):
    pcm_file_deal = file_deal[j]
    path_0_deal = os.path.split(file_deal[j])[0]   #文件所在目录
    path_1_deal = os.path.split(file_deal[j])[1]   #文件名称带后缀
  #  print(pcm_file_deal)
  #  print(path_0_deal)
    #print(path_1_deal)


    wb = openpyxl.load_workbook(path_1_deal)

    allSheets = wb.get_sheet_names()

    for i in range(len(allSheets)):
        sheet = wb.get_sheet_by_name(allSheets[i])
        for row in sheet.iter_rows():
            for cell in row:
                if str(str(cell.value).replace(' ', '')).find("资产负债表") != -1:
                    sheet_selected = wb.get_sheet_by_name(allSheets[i])

                    #print(sheet_selected)
                    #print(path_1_deal)
                    #fn_fuzhaibiao = path_1_deal
                    #print(fn_fuzhaibiao)
                    ws['资产负债表'] = wb.get_sheet_by_name(sheet_selected.title)
                    #print(type(ws['资产负债表']))
                    continue
                elif str(str(cell.value).replace(' ', '')).find("利润表") != -1 or str(str(cell.value).replace(' ', '')).find("损益表") != -1:
                    sheet_selected = wb.get_sheet_by_name(allSheets[i])

                    #print(sheet_selected)
                    #print(path_1_deal)
                    #fn_lirunbiao = path_1_deal
                    ws_lirunbiao = wb.get_sheet_by_name(sheet_selected.title)
                    continue
                elif str(str(cell.value).replace(' ', '')).find("一般纳税人适用") != -1 or str(str(cell.value).replace(' ', '')).find("小规模纳税人适用") != -1:
                    sheet_selected = wb.get_sheet_by_name(allSheets[i])

                    #print(sheet_selected)
                    #print(path_1_deal)
                    fn_nashuishenbaobiao = path_1_deal
                    print(path_1_deal)
                    ws_nashuishenbaobiao = wb.get_sheet_by_name(sheet_selected.title)
                    continue

                elif str(str(cell.value).replace(' ', '')).find("***子表开始") != -1:
                    sheet_selected = wb.get_sheet_by_name(allSheets[i])

                    #print(sheet_selected)
                    #print(path_1_deal)
                    #fn_fuzhaibiao = path_1_deal
                    #print(fn_fuzhaibiao)
                    ws['财务状况表'] = wb.get_sheet_by_name(sheet_selected.title)
                    #print(type(ws['资产负债表']))
                    continue

################part two

def getdate(ws_source,date_row, date_column):
    row_result = 0
    column_result = 0
    result = 0

    for row in ws_source.iter_rows():

        for cell in row:
            for i in range(len(date_row)):
                #print(cell.value)
                #print(date_row[i])
                #print(str(str(cell.value).replace(' ', '')).find(date_row[i]))
                #print(cell.value)
                #print(len(str(cell.value).replace(' ', '')))
                #print(len(str(cell.value).replace(' ', '')))
                #print(len(date_row[i]))

                if str(str(cell.value).replace(' ', '')).find(date_row[i]) != -1    :
                    #print(len(str(cell.value).replace(' ', '')))
                    #print(len(date_row[i]))
                    #print(str(str(cell.value).replace(' ', '')).find(date_row[i]))

                    row_result = cell.row
                    column_result = cell.column + 3

                    #print(cell.value)
                    #print(cell.row)
                    #print(row_result)
                break



    if row_result == 0 or column_result == 0:
        result = 0
    else:
        if ws_source.cell(row = row_result , column = column_result).value != None:
            #print(ws_source.cell(row=row_result, column=column_result).value)
            result = ws_source.cell(row=row_result, column=column_result).value
    return result



def writedate(ws_source,date_row, date_column,data_write):
    row_result = 0
    column_result = 0
    result = 0

    for row in ws_source.iter_rows():

        for cell in row:
            for i in range(len(date_row)):
                if str(str(cell.value).replace(' ', '')).find(date_row[i]) != -1    :


                    row_result = cell.row
                    column_result = cell.column + 3
                    print(column_result)


                break


    ws_source.cell(row=row_result, column=column_result).value = data_write





##############################part three
if __name__ == '__main__':


    print(getdate(ws['资产负债表'],['存货'],['期末余额','期末数']))
#    print(getdate(ws['资产负债表'], ['固定资产原价'], ['期末余额', '期末数']));
 #   print(getdate(ws['资产负债表'], ['累计折旧'], ['期末余额', '期末数']));
#    print(getdate(ws['资产负债表'], ['资产总计'], ['期末余额', '期末数']));
#    print(getdate(ws['资产负债表'], ['负债合计'], ['期末余额', '期末数']));



    writedate(ws['财务状况表'],['一、年初存货'],['1-本季'],getdate(ws['资产负债表'],['存货'],['期末余额','期末数']))

评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值