python - 为什么以下代码无法成功将所需文件移动到所需目录？

Question

import os
import shutil
from collections import Counter as cnt


curr_path = os.getcwd()

ls = lambda path: [x for x in os.listdir(path) if x[0] != '.']

raw_files = [x for x in ls(curr_path) if '_' not in x]

filenames = []

folders = []

for f in raw_files: # sweeping out the '.', only having filenames

    try:
        i = f.index('.')
        f_new = f[0:i]

        filenames.append(f_new)
    except ValueError:
        filenames.append(f)

fname_freq = cnt(filenames)

for fname, freq in fname_freq.items():
    if freq > 1:
        folders.append(fname)


for fldr in folders:
    print(fldr+'\n')
    try:
        os.makedirs(fldr+'_')
        # adding a '_' to make the true folder name, i.e. foldername_ instead of foldername
    except OSError:
        pass

for f in raw_files:
    print("File being analyzed is: {fn} \n".format(fn=f))
    for fldr in folders:
        print("Folder to move stuff to is {fold}\n".format(fold=fldr))
        print("File {f}  being checked . . . ".format(f=f))


        if fldr in f and f[-1] != '_': 
            print("\t Moving file {fn} \n".format(fn=f))
            shutil.move(f, fldr+'_')

上面是一个程序FileGrouper.py，它将在目录中查找是否存在多个具有共享名称的文件(即random.java、random.class)。如果有，那么它们将被移动到名为 [插入共享名]_ 的目录来组织它们。

此代码尤其拒绝对特定文件集起作用。

注意:我用占位符替换了我的实际用户名以及时间戳

-rwxr-xr-x  1 UserName  staff   8480 Month 20 Time:Time another_ptr_func
-rw-r--r--@ 1 UserName  staff    324 Month 20 Time:Time another_ptr_func.c
-rwxr-xr-x  1 UserName  staff   8572 Month 20 Time:Time arrays1
-rw-r--r--  1 UserName  staff    321 Month 20 Time:Time arrays1.c
-rw-r--r--@ 1 UserName  staff   2058 Month 20 Time:Time file_grouper.py
-rwxr-xr-x  1 UserName  staff   8432 Month 20 Time:Time forloop
-rw-r--r--  1 UserName  staff    119 Month 20 Time:Time forloop.c
-rwxr-xr-x  1 UserName  staff   4248 Month 20 Time:Time gen_a
-rw-r--r--  1 UserName  staff     53 Month 20 Time:Time gen_a.c
-rwxr-xr-x  1 UserName  staff   8432 Month 20 Time:Time hello
-rw-r--r--  1 UserName  staff     65 Month 20 Time:Time hello.c
-rwxr-xr-x  1 UserName  staff   8432 Month 20 Time:Time hello2
-rw-r--r--  1 UserName  staff    140 Month 20 Time:Time hello2.c
-rw-r--r--@ 1 UserName  staff    343 Month 20 Time:Time pointer.c
-rwxr-xr-x  1 UserName  staff   8472 Month 20 Time:Time pointer_func
-rw-r--r--  1 UserName  staff    352 Month 20 Time:Time pointer_func.c
-rwxr-xr-x@ 1 UserName  staff  19340 Month 20 Time:Time pointer_hex
-rwxr-xr-x  1 UserName  staff   8432 Month 20 Time:Time switch
-rw-r--r--@ 1 UserName  staff    219 Month 20 Time:Time switch.c
-rwxr-xr-x  1 UserName  staff   8480 Month 20 Time:Time void_another_ptr_func
-rw-r--r--  1 UserName  staff    335 Month 20 Time:Time void_another_ptr_func.c

上面是此代码拒绝工作的特定文件集。我已经在以下内容上测试了相同的代码，其中包含大小为零的虚拟文件(使用 touch 创建它们):

-rw-r--r--  1 UserName  staff  1183 Month 20 Time:Time README.md
-rw-r--r--@ 1 UserName  staff  2067 Month 20 Time:Time file_grouper.py
-rw-r--r--  1 UserName  staff     0 Month 20 Time:Time random1
-rw-r--r--  1 UserName  staff     0 Month 20 Time:Time random1.txt
-rw-r--r--  1 UserName  staff     0 Month 20 Time:Time random2
-rw-r--r--  1 UserName  staff     0 Month 20 Time:Time random2.txt
-rw-r--r--  1 UserName  staff     0 Month 20 Time:Time random3
-rw-r--r--  1 UserName  staff     0 Month 20 Time:Time random3.txt
-rw-r--r--  1 UserName  staff     0 Month 20 Time:Time random4
-rw-r--r--  1 UserName  staff     0 Month 20 Time:Time random4.txt
-rw-r--r--  1 UserName  staff     0 Month 20 Time:Time random5.txt

程序成功处理这些文件，并生成以下内容:

.
├── README.md
├── file_grouper.py
├── random1_
│   ├── random1
│   └── random1.txt
├── random2_
│   ├── random2
│   └── random2.txt
├── random3_
│   ├── random3
│   └── random3.txt
├── random4_
│   ├── random4
│   └── random4.txt
└── random5.txt

如您所见，程序成功忽略了单独的 random5.txt，因为不存在其他具有共享名称的文件。但是，其他共享名称确实存在的文件已成功分组到[插入共享名称]_

的文件夹中

Answer 1

如果“拒绝工作”是指跳过某些文件，那么可能是因为这一行:

raw_files = [x for x in ls(curr_path) if '_' not in x]

所有带下划线的文件都将被删除。

另一个问题是文件系统不允许文件和目录具有相同的名称，您可以通过附加下划线来覆盖它们。

我强烈建议使用pathlib库，它使您的代码更易于维护和可读:

from pathlib import Path


def file_grouper():
    # Path to group
    path = Path('.')

    # List all files
    ls = path.glob('*')

    # Map all stems (file names without extension) to their file names
    names = {}
    for x in ls:
        if x.is_file():
            if x.stem not in names:
                names[x.stem] = []
            names[x.stem].append(x)

    # Create and move
    for stem, values in names.items():
        if len(values) > 1:
            (path / (stem + '_')).mkdir(exist_ok=True)
            for value in values:
                value.rename(path / (stem + '_') / value.name)


file_grouper()