【python】遍历目录下excel表关键字

import os
import pandas as pd

def search_excel_files(directory, keyword):
    found_files = []
    for root, dirs, files in os.walk(directory):
        for file in files:
            if file.endswith('.xlsx'):
                file_path = os.path.join(root, file)
                try:
                    # 使用 ExcelFile 对象获取工作表名称列表
                    df = pd.ExcelFile(file_path)
                    sheet_names = df.sheet_names

                    # 遍历工作表名称列表，读取特定工作表
                    for sheet_name in sheet_names:
                        data = pd.read_excel(file_path, sheet_name=sheet_name)
                        if keyword in data.to_string():
                            found_files.append((file_path, sheet_name))  # 以元组形式保存文件路径和工作表名称
                            break
                except Exception as e:
                    print(f"Error reading {file_path}: {e}")
    return found_files

directory = '/path/to/your/directory'  # 将此路径替换为你要搜索的目录
keyword = 'house'
found_files = search_excel_files(directory, keyword)

if found_files:
    print(f"Found the keyword '{keyword}' in the following Excel files:")
    for file, sheet_name in found_files:  # 同时遍历文件路径和工作表名称
        print(f"File: {file}, Sheet: {sheet_name}")  # 打印文件路径和工作表名称
else:
    print(f"No files containing the keyword '{keyword}' were found.")

指定的目录放在数据盘