使用Python对Excel工作簿中的所有工作表分别求和并自动生成结果

pip install pandas xlwings

import pandas as pd
import xlwings as xw


def clean_to_number(s: pd.Series) -> pd.Series:
    """
    把带货币符号、逗号、空格的文本金额转换成数值。
    例如：￥12,345.67 -> 12345.67
    """
    s = s.astype(str).str.strip()
    s = s.str.replace(",", "", regex=False)
    s = s.str.replace(r"[¥￥$ ]", "", regex=True)
    s = s.str.replace(r"[^0-9\.\-]", "", regex=True)
    return pd.to_numeric(s, errors="coerce")


def sum_all_sheets_in_workbook(
    input_xlsx: str,
    sum_col: str = "销售利润",
    summary_sheet_name: str = "汇总",
    start_cell: str = "A1",
    save_as: str | None = None,
) -> None:
    """
    对一个工作簿中的所有工作表分别对 sum_col 求和：
    1. 在每个 Sheet 末尾追加“合计”行
    2. 生成或覆盖一个“汇总”Sheet，列出每个 Sheet 的合计和总计

    save_as=None：覆盖保存原文件
    save_as=路径：另存为新文件
    """

    app = xw.App(visible=False, add_book=False)
    app.display_alerts = False
    app.screen_updating = False

    try:
        wb = app.books.open(input_xlsx)
        results = []

        for sht in wb.sheets:

            # 跳过汇总 Sheet，避免二次运行时把汇总表也拿去求和
            if sht.name == summary_sheet_name:
                continue

            rng = sht.range(start_cell).expand("table")

            if rng.value is None:
                print(f"[SKIP] {sht.name}: 空表")
                continue

            df = rng.options(pd.DataFrame).value

            if df is None or df.empty:
                print(f"[SKIP] {sht.name}: 无有效数据")
                continue

            if sum_col not in df.columns:
                print(f"[SKIP] {sht.name}: 缺少列 '{sum_col}'")
                continue

            # 清洗金额列并求和
            num = clean_to_number(df[sum_col]).fillna(0)
            total = float(num.sum())

            # 写回：在当前表格最后一行下面追加合计行
            last_cell = rng.last_cell
            total_row = last_cell.row + 1

            # 找到 sum_col 在表格中的列序号，xlwings 使用 1-based 列号
            col_idx = df.columns.get_loc(sum_col) + 1

            sht.range((total_row, 1)).value = "合计"
            sht.range((total_row, col_idx)).value = total

            # 给合计行加粗，便于阅读
            try:
                sht.range((total_row, 1), (total_row, col_idx)).api.Font.Bold = True
            except Exception:
                pass

            results.append({
                "工作表": sht.name,
                f"{sum_col}合计": total
            })

            print(f"[OK] {sht.name}: {sum_col} 合计 = {total}")

        # 生成汇总 Sheet
        summary_df = pd.DataFrame(results)

        if summary_df.empty:
            raise RuntimeError("未得到任何可汇总结果，请检查列名、数据区域或是否为空表。")

        total_col = f"{sum_col}合计"
        grand_total = float(summary_df[total_col].sum())

        summary_df = summary_df.sort_values(by=total_col, ascending=False)

        # 如果已存在汇总 Sheet，则清空；不存在则新建
        try:
            sum_sht = wb.sheets[summary_sheet_name]
            sum_sht.clear()
        except Exception:
            sum_sht = wb.sheets.add(summary_sheet_name, before=wb.sheets[0])

        sum_sht.range("A1").options(index=False).value = summary_df

        # 写入总计
        last = sum_sht.range("A1").expand("table").last_cell
        total_row = last.row + 1

        sum_sht.range((total_row, 1)).value = "总计"
        sum_sht.range((total_row, 2)).value = grand_total

        try:
            sum_sht.range((1, 1), (total_row, 2)).api.Columns.AutoFit()
            sum_sht.range((total_row, 1), (total_row, 2)).api.Font.Bold = True
        except Exception:
            pass

        if save_as:
            wb.save(save_as)
            print(f"[DONE] 已另存为：{save_as}")
        else:
            wb.save()
            print(f"[DONE] 已覆盖保存：{input_xlsx}")

        wb.close()

    finally:
        app.quit()


if __name__ == "__main__":
    sum_all_sheets_in_workbook(
        input_xlsx="产品销售统计表.xlsx",
        sum_col="销售利润",
        summary_sheet_name="汇总",
        start_cell="A1",
        save_as="产品销售统计表_已求和.xlsx",
    )

def clean_to_number(s: pd.Series) -> pd.Series:
    s = s.astype(str).str.strip()
    s = s.str.replace(",", "", regex=False)
    s = s.str.replace(r"[¥￥$ ]", "", regex=True)
    s = s.str.replace(r"[^0-9\.\-]", "", regex=True)
    return pd.to_numeric(s, errors="coerce")

print(f"[OK] {sht.name}: {sum_col} 合计 = {total}")

if sht.name == summary_sheet_name:
    continue

if sum_col not in df.columns:
    print(f"[SKIP] {sht.name}: 缺少列 '{sum_col}'")
    continue

save_as="产品销售统计表_已求和.xlsx"