如何在Python中自动创建数字和持续文件夹？

Question

我有一段代码，它可以把一个文件夹里的文件分成每50个一组，放到新的文件夹里。现在我想让这个脚本给这些文件夹起个数字名字，从1开始。还有一个选择是让脚本把这些文件放到已经存在的文件夹里，因为我有一个模板目录，里面有空文件夹。

这样分组是为了让打印软件能够分别处理这些批次。此外，我还需要知道每个文件在哪个文件夹里。总共有大约3800个PDF文件需要整理。

一旦我搞清楚了如何创建这些文件夹，我就可以完成项目，列出每个文件夹里的文件清单。

这是目前的代码，它创建新的文件夹，并根据批次中的第一个文件来命名。

import os
import shutil

source_directory = "//All-the-data"
Destination_base_folder = '//All-the-data/sorted'

batch_size = 50

# check if source directory exists
if os.path.exists(source_directory) and os.path.isdir(source_directory):
    # get all the files
    files = os.listdir(source_directory)

 # Sort files by filename 
    
    files.sort()

    counter = 1

    for i in range(0, len(files), batch_size):
        # create a folder for each batch
        batch_directory_name = os.path.splitext(files[i])[0]
        batch_directory_path = os.path.join(Destination_base_folder, batch_directory_name)
        os.makedirs(batch_directory_path, exist_ok=True)

        # copy files into these folders
        for j in range(min(batch_size, len(files) - i)):
            source_file_path = os.path.join(source_directory, files[i + j])
            destination_file_path = os.path.join(batch_directory_path, files[i + j])

            shutil.copy2(source_file_path, destination_file_path)

        print(f"Batch {counter} erfolgreich nach {batch_directory_path} kopiert")
        counter += 1
else:
    print("Quellordner existiert nicht: " + source_directory)

我尝试了以下方法来之后重命名这些文件夹。文件夹里放什么文件并不重要。

def number_folders_chronologically(destination_folder):
    batch_folders = [folder for folder in os.listdir(destination_folder) if os.path.isdir(os.path.join(destination_folder, folder))]
    batch_folders.sort(key=lambda x: os.path.getctime(os.path.join(destination_folder, x)))

    for index, folder in enumerate(batch_folders, start=1):
        old_path = os.path.join(destination_folder, folder)
        new_folder_name = f"{index:03d}_{folder}"
        new_path = os.path.join(destination_folder, new_folder_name)
    os.rename(old_path, new_path)

我对用Python编程完全是个新手，15年没编程了。即使在那时，我的知识也很基础。我很确定解决方案应该很简单，只是我没看出来。

谢谢大家的帮助。

Answer 1

这个脚本现在会检查是否有一个模板文件夹（template_directory）。如果这个文件夹存在，它会复制第一个文件夹（假设它是空的），并给它加上一个数字前缀（batch_X）。如果没有这个文件夹，它就会创建新的文件夹，名字是类似 batch_001 这样的数字命名。还有一个字典（file_to_folder_map）用来记录每个文件放在哪个文件夹里。处理完后，你可以选择打印这个记录，以便参考。

import os
import shutil

# Define directories
source_directory = '//All-the-data'
destination_base_folder = '//All-the-data/sorted'
template_directory = '//All-the-data/sorted_template'

# Set batch size
batch_size = 50

# Check if source directory exists
if os.path.exists(source_directory) and os.path.isdir(source_directory):

    # Get all files and sort them by filename
    files = os.listdir(source_directory)
    files.sort()

    # Folder numbering and tracking
    folder_number = 1
    file_to_folder_map = {}

    for i in range(0, len(files), batch_size):
        # Use template directory or create a new folder with a number
        if template_directory:
            batch_directory_path = os.path.join(destination_base_folder, os.listdir(template_directory)[0])
            os. shutil.copytree(batch_directory_path, os.path.join(destination_base_folder, f"batch_{folder_number}"))
            batch_directory_path = os.path.join(destination_base_folder, f"batch_{folder_number}")
        else:
            batch_directory_path = os.path.join(destination_base_folder, f"batch_{folder_number:03d}")
            os.makedirs(batch_directory_path, exist_ok=True)

        # Copy files into the folder
        for j in range(min(batch_size, len(files) - i)):
            source_file_path = os.path.join(source_directory, files[i + j])
            destination_file_path = os.path.join(batch_directory_path, files[i + j])
            shutil.copy2(source_file_path, destination_file_path)

            # Track which file goes in which folder
            file_to_folder_map[files[i + j]] = batch_directory_path

        print(f"Batch {folder_number} successfully copied to {batch_directory_path}")
        folder_number += 1

    if file_to_folder_map:
        print("\nFile to Folder Mapping:")
        for filename, folder_path in file_to_folder_map.items():
            print(f"{filename} -> {folder_path}")

else:
    print("Source folder doesn't exist: " + source_directory)