python过滤数据

import xlrd
from collections import defaultdict
def read(file, sheet_index=0):
    """

    :param file: 文件路径
    :param sheet_index: 读取的工作表索引
    :return: 二维数组
    """
    workbook = xlrd.open_workbook(file)
    # all_sheets_list = workbook.sheet_names()
    # print("本文件中所有的工作表名称:", all_sheets_list)
    # 按索引读取工作表
    print(len(workbook.sheets()))
    sheet = workbook.sheet_by_index(sheet_index)
    print("工作表名称:", sheet.name)
    print("行数:", sheet.nrows)
    print("列数:", sheet.ncols)

    # 按工作表名称读取数据
    # second_sheet = workbook.sheet_by_name("b")
    # print("Second sheet Rows:", second_sheet.nrows)
    # print("Second sheet Cols:", second_sheet.ncols)
    # 获取单元格的数据
    # cell_value = sheet.cell(1, 0).value
    # print("获取第2行第1列的单元格数据:", cell_value)
    data = []
    for i in range(0, sheet.nrows):
        data.append(str(sheet.cell(i,1)))

    d = defaultdict(list)

    b = {}.fromkeys(data).keys()
    for j in b:
        temp = []
        for k in range(0,len(data)):
            if j == data[k]:
                temp.append(str(sheet.cell(k,6)))
        d[j] = temp
    print(d)
    # for k, va in [(v, i) for i, v in enumerate(data)]:
    #     d[k].append(va)
    # print(d)
    return data

if __name__ == '__main__':
    read('D://1.xlsx')