待更新

#coding:utf-8
import os
import win32com.client as win32
import shutil
import openpyxl
#import time

#####part one


def makedir():
    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')

    if os.path.exists(mydir) == 0:
        os.mkdir(mydir)



def movedir():


    path = os.getcwd()  # 转换前程序所在文件目录

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




def getbaklist( ):


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

    pathdir_deal = os.listdir(path_deal)
    path_bak = os.getcwd()
    pathdir_bak = os.listdir(path_bak)
    print(pathdir_bak)

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

def getbooksheet():
    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:
                    #print(cell.value)
                    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)
                        #print(path_0_deal)
                        fn['资产负债表'] = path_1_deal
                        # print(fn_fuzhaibiao)
                        ws['资产负债表'] = allSheets[i]

                        #print(type(ws['资产负债表']))
                        #print(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)
                        #path['利润表'] = path_0_deal
                        fn['利润表'] = path_1_deal
                        ws['利润表'] = allSheets[i]
                        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)
                       # path['纳税申报表'] = path_0_deal
                        fn['纳税申报表'] = path_1_deal
                        #print(path_1_deal)
                        ws['纳税申报表'] = allSheets[i]
                        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)
                       # path['财务状况表'] = path_0_deal
                        fn['财务状况表'] = path_1_deal
                        print(fn['财务状况表'])
                        ws['财务状况表'] = allSheets[i]
                        # print(type(ws['资产负债表']))
                        continue







def getdata( path, filename,worksheet,data_row,data_column):

    #print( path + r'/' + filename )
    wb = openpyxl.load_workbook( path + r'/' + filename)

    #print(wb)
    ws = wb.get_sheet_by_name(worksheet)

    getdata_result = 0
    row_result = 0
    row_column = 0


    for row in ws.iter_rows():

        for cell in row:
            for i in range(len(data_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(data_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:
        getdata_result = 0
    else:
        if ws.cell(row = row_result , column = column_result).value != None:
            #print(ws_source.cell(row=row_result, column=column_result).value)
            getdata_result = ws.cell(row=row_result, column=column_result).value

    wb.close()
    return getdata_result



def writedata( path, filename,worksheet,data_row,data_column,data_write):


    #print( path + r'/' + filename )

    wb = openpyxl.load_workbook( path + r'/' + filename)
    #print(wb)
    ws = wb.get_sheet_by_name(worksheet)
    row_result = 0
    column_result = 0


    for row in ws.iter_rows():

        for cell in row:
            #print(cell.value)
            for i in range(len(data_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(data_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
                    print(row_result)
                    column_result = cell.column + 3
                    print(column_result)
                    #print(cell.value)
                    #print(cell.row)
                    #print(row_result)
                break


    print(data_write)
    if row_result == 0 or column_result == 0:
        print("未获取需要写入的行或列号")
    else:
        ws.cell(row=row_result, column=column_result).value = data_write

    wb.save(filename)
    wb.close









if __name__ == '__main__':
    file = []
    file_deal = []
    fn = {'资产负债表': 0, '利润表': 0, '纳税申报表': 0, '财务状况表': 0}
    ws = {'资产负债表': 0, '利润表': 0, '纳税申报表': 0, '财务状况表': 0}

    makedir()
    movedir()
    getbaklist()
    print(file)
    print(file_deal)

    #getbooksheet()

    #print(fn)
    #print(ws)
    #print(file)