批量删除文档属性信息

为了批量处理大量文档的属性信息，如作者、编辑时间等，写了这个代码

个人原因，懒得打包了，也没啥要自主修改的地方，一般也就是个文件夹路径

如果有其他更好更快捷的方法，欢迎交流啊

import os
import random
from docx import Document
from datetime import datetime, timedelta

def random_date(start_date, end_date):
    """
    Generate a random date between the given start and end dates.
    """
    time_diff = end_date - start_date
    random_days = random.randint(0, time_diff.days)
    return start_date + timedelta(days=random_days)

def process_docx(file_path):
    try:
        doc = Document(file_path)

        # Delete title, author, and last modified by information
        doc.core_properties.title = ''
        doc.core_properties.author = ''
        doc.core_properties.last_modified_by = ''

        # Get the current date and time
        current_datetime = datetime.now()

        # Randomly generate creation date and last modified date
        creation_datetime = random_date(current_datetime - timedelta(days=365), current_datetime)
        last_modified_datetime = random_date(creation_datetime, current_datetime)

        # Set creation and last modified dates
        doc.core_properties.created = creation_datetime
        doc.core_properties.modified = last_modified_datetime

        # Save the modified document
        doc.save(file_path)
    
    except Exception as e:
        print(f'Error processing {file_path}: {e}')
        return

def process_folder(folder_path):
    for root, dirs, files in os.walk(folder_path):
        for file in files:
            if file.endswith('.docx'):
                file_path = os.path.join(root, file)
                process_docx(file_path)

folder_path = 'D:\\20230724' 
process_folder(folder_path)