pip install pandas openpyxl

import os
import pandas as pd
from pathlib import Path

def merge_excel_files(source_dir, output_file="總表匯總.xlsx"):
    """
    遍歷指定目錄下所有子文件夾中的 Excel 文件，合并為一張總表

    參數(shù):
        source_dir: 包含 Excel 文件的根目錄路徑
        output_file: 輸出匯總文件的文件名
    """
    all_dataframes = []  # 存儲(chǔ)所有讀取到的 DataFrame
    file_count = 0       # 統(tǒng)計(jì)處理的文件數(shù)

    # 將路徑轉(zhuǎn)為 Path 對(duì)象，方便操作
    root_path = Path(source_dir)

    if not root_path.exists():
        print(f"錯(cuò)誤：目錄 {source_dir} 不存在！")
        return

    # os.walk 遞歸遍歷所有子文件夾
    for dirpath, dirnames, filenames in os.walk(source_dir):
        for filename in filenames:
            # 只處理 .xlsx 和 .xls 文件
            if filename.endswith(('.xlsx', '.xls')) and not filename.startswith('~$'):
                file_path = os.path.join(dirpath, filename)
                file_count += 1

                try:
                    # 讀取 Excel 文件（默認(rèn)讀取第一個(gè) sheet）
                    df = pd.read_excel(file_path, engine='openpyxl' if filename.endswith('.xlsx') else 'xlrd')

                    # 可選：添加一列來源信息，記錄數(shù)據(jù)來自哪個(gè)文件
                    df['數(shù)據(jù)來源文件'] = filename
                    df['數(shù)據(jù)來源路徑'] = dirpath

                    all_dataframes.append(df)
                    print(f"[{file_count}] 已讀取: {filename}")

                except Exception as e:
                    print(f"[{file_count}] 讀取失敗 {filename}: {e}")

    if not all_dataframes:
        print("沒有找到任何 Excel 文件！")
        return

    # 將所有 DataFrame 縱向拼接（按行合并）
    print("\n正在合并所有數(shù)據(jù)...")
    merged_df = pd.concat(all_dataframes, ignore_index=True)

    # 導(dǎo)出為新的 Excel 文件
    merged_df.to_excel(output_file, index=False, engine='openpyxl')

    print(f"\n合并完成！")
    print(f"共處理 {file_count} 個(gè)文件")
    print(f"總數(shù)據(jù)行數(shù): {len(merged_df)}")
    print(f"總數(shù)據(jù)列數(shù): {len(merged_df.columns)}")
    print(f"匯總文件已保存: {output_file}")


# ==================== 使用示例 ====================
if __name__ == "__main__":
    # 修改這里為你的數(shù)據(jù)文件夾路徑
    SOURCE_DIR = r"D:\數(shù)據(jù)源"

    # 執(zhí)行合并
    merge_excel_files(SOURCE_DIR, output_file="總表匯總.xlsx")

import os
import pandas as pd
from pathlib import Path

for dirpath, dirnames, filenames in os.walk(source_dir):

if filename.endswith(('.xlsx', '.xls')) and not filename.startswith('~$'):

df = pd.read_excel(file_path, engine='openpyxl')
df['數(shù)據(jù)來源文件'] = filename
df['數(shù)據(jù)來源路徑'] = dirpath

merged_df = pd.concat(all_dataframes, ignore_index=True)

merged_df.to_excel(output_file, index=False, engine='openpyxl')

df = pd.read_excel(file_path, sheet_name="Sheet1", engine='openpyxl')

all_sheets = pd.read_excel(file_path, sheet_name=None, engine='openpyxl')
for sheet_name, sheet_df in all_sheets.items():
    sheet_df['來源Sheet'] = sheet_name
    all_dataframes.append(sheet_df)

# 定義統(tǒng)一列名映射
COLUMN_MAP = {
    '姓名': '姓名',
    '員工姓名': '姓名',
    'Name': '姓名',
    '部門': '部門',
    '所屬部門': '部門',
    '金額': '金額',
    '金額(元)': '金額',
}

# 讀取后統(tǒng)一列名
df = pd.read_excel(file_path)
df.rename(columns=COLUMN_MAP, inplace=True)

from tqdm import tqdm

for dirpath, dirnames, filenames in tqdm(os.walk(source_dir), desc="掃描文件夾"):
    for filename in filenames:
        # ... 處理邏輯

desired_columns = ['姓名', '部門', '金額', '日期', '數(shù)據(jù)來源文件', '數(shù)據(jù)來源路徑']
merged_df = merged_df[desired_columns]

if df.empty:
    print(f"警告: {filename} 為空，跳過")
    continue

if filename.endswith('.csv'):
    df = pd.read_csv(file_path, encoding='utf-8-sig')