【Python】读取xlsb或xlsx的单一或连续单元格工具类

代码主要来自Kimi.ai，有修改。

优先使用工作表序号索引工作表，序号从1开始。

运行需要先安装openpyxl和pyxlsb两个第三方库。

import openpyxl
from openpyxl.utils import range_boundaries
from pyxlsb import open_workbook as open_xlsb

class ExcelReader:
    def __init__(self, file_path):
        """
        初始化ExcelReader类
        :param file_path: Excel文件路径
        """
        self.file_path = file_path
        self.is_xlsb = file_path.endswith('.xlsb')
        self.is_xlsx = file_path.endswith('.xlsx')

        if not self.is_xlsb and not self.is_xlsx:
            raise ValueError("不支持的文件格式，仅支持.xlsb和.xlsx文件")

        # 替换None单元格的默认值
        # self.nan = ''
        self.nan_val = 0

    def get_sheet_by_index(self, sheet_index):
        """
        根据工作表序号获取工作表对象
        :param sheet_index: 工作表序号（从1开始）
        :return: 工作表对象
        """
        if self.is_xlsb:
            with open_xlsb(self.file_path) as wb:
                sheets = list(wb.sheets)
                if sheet_index < 1 or sheet_index > len(sheets):
                    raise ValueError("工作表序号超出范围")
                return sheets[sheet_index - 1]
        elif self.is_xlsx:
            wb = openpyxl.load_workbook(self.file_path, data_only=True)
            if sheet_index < 1 or sheet_index > len(wb.sheetnames):
                raise ValueError("工作表序号超出范围")
            return wb.worksheets[sheet_index - 1]

    def read_cell(self, sheet_index, cell_address):
        """
        读取单个单元格的数据
        :param sheet_index: 工作表序号（从1开始）
        :param cell_address: 单元格地址，如'A1'
        :return: 二维列表，包含单个单元格的数据
        """
        sheet = self.get_sheet_by_index(sheet_index)

        if self.is_xlsb:
            with open_xlsb(self.file_path) as wb:
                with wb.get_sheet(sheet) as sheet_data:
                    row, col = openpyxl.utils.coordinate_to_tuple(cell_address)
                    print(col, row)
                    for r in sheet_data.rows():
                        if r[0].r == row - 1:
                            cell_value = r[col - 1].v
                            return [[cell_value if cell_value is not None else self.nan_val]]
        elif self.is_xlsx:
            cell_value = sheet[cell_address].value
            return [[cell_value if cell_value is not None else self.nan_val]]

    def read_range(self, sheet_index, range_address):
        """
        读取指定区域的数据
        :param sheet_index: 工作表序号（从1开始）
        :param range_address: 单元格区域地址，如'C1:F4'
        :return: 二维列表，包含指定区域的数据
        """
        sheet = self.get_sheet_by_index(sheet_index)
        min_col, min_row, max_col, max_row = range_boundaries(range_address)

        if self.is_xlsb:
            with open_xlsb(self.file_path) as wb:
                with wb.get_sheet(sheet) as sheet_data:
                    data = []
                    for r in sheet_data.rows():
                        if min_row <= r[0].r + 1 <= max_row:
                            row_data = []
                            for c in r:
                                if min_col <= c.c + 1 <= max_col:
                                    cell_value = c.v
                                    row_data.append(cell_value if cell_value is not None else 0)
                            if row_data:
                                data.append(row_data)
                    return data
        elif self.is_xlsx:
            data = []
            for row in sheet.iter_rows(min_row=min_row, max_row=max_row, min_col=min_col, max_col=max_col, values_only=True):
                row_data = [cell if cell is not None else self.nan_val for cell in row]
                data.append(row_data)
            return data

# 示例用法
if __name__ == "__main__":
    file_path = "test.xlsb"  # 替换为你的文件路径
    reader = ExcelReader(file_path)

    # 读取单个单元格
    cell_data = reader.read_cell(1, "D6")  # 读取第一个工作表的A1单元格
    print("单个单元格数据：", cell_data)

    # 读取单元格区域
    range_data = reader.read_range(1, "A5:C9")  # 读取第一个工作表的C1:F4区域
    print("单元格区域数据：", range_data)