【python】表格合并时删除每列重复值，并分列汇总

import xlrd
import xlwt
from xlutils.copy import copy
import os

col_num = 2
sheet_num = 2


def create_excel(path, sheet_name):
    workbook = xlwt.Workbook()  # 新建一个工作簿
    workbook.add_sheet(sheet_name)  # 在工作簿中新建一个表格
    workbook.save(path)  # 保存工作簿


def read_data(FileName):
    # 1.打开文件
    open_file = xlrd.open_workbook(FileName)

    # 2.读取某个sheet的内容（第一个表索引值为0）
    st = open_file.sheet_by_index(2)
    # 提取某一列
    total_data = []
    i = 0
    while i < st.nrows:
        data = st.cell_value(i, 1)
        total_data.append(data)
        i += 1
    return total_data
    # 3.将表名追加到列表作为第一个元素

    return total_data


def del_repeat(list):
    L1 = []
    for i in list:
        if i not in L1:
            L1.append(i)
    return L1


def write_data(path, data):
    index = len(data)  # 获取索引写入的行数
    workbook = xlrd.open_workbook(path)  # 打开工作簿
    sheets = workbook.sheet_names()  # 获取工作簿中的所有表格
    worksheet = workbook.sheet_by_name(sheets[0])  # 获取工作簿中所有表格中的的第一个表格
    cols_old = worksheet.ncols  # 获取表格中已存在的数据的列数

    new_workbook = copy(workbook)  # 将xlrd对象拷贝转化为xlwt对象
    new_worksheet = new_workbook.get_sheet(0)  # 获取转化后工作簿中的第一个表格
    for i in range(0, index):
        # 隔一列写入数据
        new_worksheet.write(i, cols_old + 0, data[i])  # 追加写入数据
    new_workbook.save(path)  # 保存工作簿


def get_file_name(file_dir):
    tmp_lst = []
    for root, dirs, files in os.walk(file_dir):
        for file in files:
            tmp_lst.append(os.path.join(root, file))
    return tmp_lst


def main():
    DIR_NAME = r'D:\desk\\'
    create_excel(DIR_NAME + '合并.xls', '汇总数据')
    print(DIR_NAME + '合并.xls')
    tmp_list = get_file_name(DIR_NAME + 'data\\')
    for dir in tmp_list:
        total_data = read_data(dir)
        data = del_repeat(total_data)
        write_data(DIR_NAME + '\合并.xls', data)
        print('------------' + dir.split("\\")[-1] + '数据写入成功！-----------')


if __name__ == '__main__':
    main()