Python编写一个Excel批量处理的桌面实用脚本

import os
import pandas as pd
from openpyxl import load_workbook

import os
import pandas as pd
from processors import process_excel

INPUT_DIR = "input"
OUTPUT_DIR = "output"

def ensure_output_folder():
    if not os.path.exists(OUTPUT_DIR):
        os.makedirs(OUTPUT_DIR)

def main():
    ensure_output_folder()

    for filename in os.listdir(INPUT_DIR):
        if filename.endswith((".xlsx", ".xls")):
            path = os.path.join(INPUT_DIR, filename)
            print(f"正在处理: {filename}")

            df = pd.read_excel(path)

            # 调用自定义处理逻辑
            df = process_excel(df)

            # 输出结果
            output_path = os.path.join(OUTPUT_DIR, filename)
            df.to_excel(output_path, index=False)
            print(f"已保存到: {output_path}")

if __name__ == "__main__":
    main()

def process_excel(df):
    # 1 删除全空行
    df = df.dropna(how="all")

    # 2 统一列名格式
    df.columns = [str(c).strip() for c in df.columns]

    # 3 添加一个时间戳列
    import datetime
    df["处理时间"] = datetime.datetime.now().strftime("%Y-%m-%d %H:%M:%S")

    return df

def process_excel(df):
    if "产品名称" in df.columns:
        df["产品名称"] = df["产品名称"].replace("旧名", "新名")
    return df

def process_excel(df):
    return df  # 不做处理，原样返回

all_data = []

for filename in os.listdir(INPUT_DIR):
    if filename.endswith((".xls", ".xlsx")):
        df = pd.read_excel(os.path.join(INPUT_DIR, filename))
        df["来源文件"] = filename
        all_data.append(df)

final_df = pd.concat(all_data, ignore_index=True)
final_df.to_excel("output/合并结果.xlsx", index=False)

def process_excel(df):
    for name, group in df.groupby("分类"):
        group.to_excel(f"output/{name}.xlsx", index=False)
    return None