比较文件夹A和子文件夹B，显示在文件夹A中但不在子文件夹B中的文件。

Question

我有一个文件夹A，其中包含1880个HTML文件，并且在子文件夹B中有50个HTML文件。因此，我需要一段代码来显示每个只存在于文件夹A中的文件，即1880-50的差集。我尝试使用了以下代码，但是没有得到预期的结果，我认为问题可能出在Python无法区分主文件夹和子文件夹。

import os

folder1 = r"C:\Folder-Oana\extracted"
folder2 = r"C:\Folder-Oana\extracted	ranslated"

# 获取每个文件夹中HTML文件的列表
html_files_folder1 = [f.lower() for f in os.listdir(folder1) if f.lower().endswith('.html')]
html_files_folder2 = [f.lower() for f in os.listdir(folder2) if f.lower().endswith('.html')]

# 找出两个文件列表之间的差异
missing_files = list(set(html_files_folder1) - set(html_files_folder2))

# 显示缺失的文件
if missing_files:
    print("在文件夹2中未找到但在文件夹1中存在的HTML文件有：")
    for filename in missing_files:
        print(filename)
else:
    print("在文件夹1中没有找到在文件夹2中不存在的HTML文件。")

这段代码输出错误结果，显示没有缺失的文件。

示例：

c:\Folder-Oana\extracted 内容

c:\Folder-Oana\extracted	ranslated\       01/05/2024 13:36    ----
c:\Folder-Oana\extracted\2.html
c:\Folder-Oana\extracted\3.html
c:\Folder-Oana\extracted\4.html
c:\Folder-Oana\extracted\5.html
c:\Folder-Oana\extracted\11.html
c:\Folder-Oana\extracted\12.html
c:\Folder-Oana\extracted\13.html
c:\Folder-Oana\extracted\14.html
c:\Folder-Oana\extracted\15.html
c:\Folder-Oana\extracted\16.html
c:\Folder-Oana\extracted\17.html

c:\Folder-Oana\extracted ranslated 内容

c:\Folder-Oana\extracted	ranslated\11.html
c:\Folder-Oana\extracted	ranslated\12.html
c:\Folder-Oana\extracted	ranslated\13.html
c:\Folder-Oana\extracted	ranslated\14.html
c:\Folder-Oana\extracted	ranslated\15.html
c:\Folder-Oana\extracted	ranslated\16.html
c:\Folder-Oana\extracted	ranslated\17.html
c:\Folder-Oana\extracted	ranslated\18.html
c:\Folder-Oana\extracted	ranslated\19.html
c:\Folder-Oana\extracted	ranslated\24.html
c:\Folder-Oana\extracted	ranslated\25.html
c:\Folder-Oana\extracted	ranslated\26.html

期望输出：

2.html
3.html
4.html
5.html

版本2：
（这个版本也无法正确检测到仅位于\extracted文件夹中的文件，而是比较了所有HTML文件。）

import os
import filecmp

def compare_folders(folder1, folder2):
    dcmp = filecmp.dircmp(folder1, folder2)
    diff_files = dcmp.diff_files
    
    if diff_files:
        print(f"以下文件在{folder1}和{folder2}之间存在差异：")
        for file in diff_files:
            print(f" - {file}")
    else:
        print(f"在{folder1}和{folder2}之间没有发现差异。")

if __name__ == "__main__":
    folder1 = r"C:\Folder-Oana\extracted"
    folder2 = r"C:\Folder-Oana\extracted	ranslated"
    compare_folders(folder1, folder2)

jdi · Answer

当查看您的代码时，我发现它可能无法递归地检测子文件夹中的文件。以下是针对您的问题更新后的代码：

import os

folder1 = r"C:\Folder-Oana\extracted"
folder2 = r"C:\Folder-Oana\extracted	ranslated"

# 定义一个函数，用于递归地从指定目录获取所有HTML文件
def get_html_files(directory):
    html_files = []
    for root, dirs, files in os.walk(directory):
        for file in files:
            if file.lower().endswith('.html'):
                html_files.append(os.path.join(root, file).lower())
    return html_files

# 从两个文件夹及其子文件夹中获取HTML文件
html_files_folder1 = get_html_files(folder1)
html_files_folder2 = get_html_files(folder2)

# 找出两个文件列表之间的差异
missing_files = list(set(html_files_folder1) - set(html_files_folder2))

# 显示仅存在于文件夹1中但不在文件夹2中的文件
if missing_files:
    print("在文件夹1中找到但在文件夹2中未找到的HTML文件有：")
    for filename in missing_files:
        print(filename)
else:
    print("在文件夹1中没有找到在文件夹2中不存在的HTML文件。")

HansUp · Answer

已成功解决问题。问题出在Python版本上。谢谢！

import os

def find_files_only_in_folder(folder, subfolder):
    # 获取主文件夹和子文件夹中所有文件的集合
    folder_files = set(os.listdir(folder))
    subfolder_files = set(os.listdir(subfolder))

    # 计算仅存在于主文件夹中但不在子文件夹中的文件集合
    files_only_in_folder = folder_files - subfolder_files

    # 输出仅存在于主文件夹中的文件
    print(f"仅存在于{folder}中而不包含在{subfolder}内的文件：")
    for file in files_only_in_folder:
        print(f"- {file}")

if __name__ == "__main__":
    # 主文件夹和子文件夹的路径
    folder_path = r"c:\Folder-Oana\extracted"
    subfolder_path = r"c:\Folder-Oana\extracted	ranslated"

    # 调用函数查找仅存在于主文件夹中的文件
    find_files_only_in_folder(folder_path, subfolder_path)