您应该使用称为root的dirpath。提供了dirnames，因此如果有不希望操作的文件夹，您可以删除它。递归入。

import os
result = [os.path.join(dp, f) for dp, dn, filenames in os.walk(PATH) for f in filenames if os.path.splitext(f)[1] == '.txt']

编辑:

在最近的反对票之后，我突然意识到glob是一个更好的扩展选择工具。

import os
from glob import glob
result = [y for x in os.walk(PATH) for y in glob(os.path.join(x[0], '*.txt'))]

还有一个生成器版本

from itertools import chain
result = (chain.from_iterable(glob(os.path.join(x[0], '*.txt')) for x in os.walk('.')))

用于Python 3.4+的Edit2

from pathlib import Path
result = list(Path(".").rglob("*.[tT][xX][tT]"))

您可以通过这种方式返回绝对路径文件的列表。

def list_files_recursive(path):
    """
    Function that receives as a parameter a directory path
    :return list_: File List and Its Absolute Paths
    """

    import os

    files = []

    # r = root, d = directories, f = files
    for r, d, f in os.walk(path):
        for file in f:
            files.append(os.path.join(r, file))

    lst = [file for file in files]
    return lst


if __name__ == '__main__':

    result = list_files_recursive('/tmp')
    print(result)

我将把John La Rooy的列表理解转换为嵌套for，以防其他人理解它有困难。

result = [y for x in os.walk(PATH) for y in glob(os.path.join(x[0], '*.txt'))]

应该相当于:

import glob
import os

result = []

for x in os.walk(PATH):
    for y in glob.glob(os.path.join(x[0], '*.txt')):
        result.append(y)

下面是列表理解和函数os的文档。走着走着。

如果你不介意安装一个额外的灯光库，你可以这样做:

pip install plazy

用法:

import plazy

txt_filter = lambda x : True if x.endswith('.txt') else False
files = plazy.list_files(root='data', filter_func=txt_filter, is_include_root=True)

结果应该是这样的:

['data/a.txt', 'data/b.txt', 'data/sub_dir/c.txt']

它可以在Python 2.7和Python 3上运行。

Github: https://github.com/kyzas/plazy文件

免责声明:我是plazy的作者。

此函数将递归地将文件放入列表中。

import os


def ls_files(dir):
    files = list()
    for item in os.listdir(dir):
        abspath = os.path.join(dir, item)
        try:
            if os.path.isdir(abspath):
                files = files + ls_files(abspath)
            else:
                files.append(abspath)
        except FileNotFoundError as err:
            print('invalid directory\n', 'Error: ', err)
    return files

这似乎是我能想出的最快的解决方案，比os更快。走，比任何glob解决方案快得多。

它还会给你一个所有嵌套子文件夹的列表，基本上没有成本。 您可以搜索几个不同的扩展。 您还可以通过将f.path更改为f.name(不要为子文件夹更改它!)来选择返回完整路径或仅返回文件的名称。

参数:dir: str, ext: list。 函数返回两个列表:子文件夹、文件。

请参阅下面的详细速度分析。

def run_fast_scandir(dir, ext):    # dir: str, ext: list
    subfolders, files = [], []

    for f in os.scandir(dir):
        if f.is_dir():
            subfolders.append(f.path)
        if f.is_file():
            if os.path.splitext(f.name)[1].lower() in ext:
                files.append(f.path)


    for dir in list(subfolders):
        sf, f = run_fast_scandir(dir, ext)
        subfolders.extend(sf)
        files.extend(f)
    return subfolders, files


subfolders, files = run_fast_scandir(folder, [".jpg"])

如果你需要文件大小，你也可以创建一个大小列表并添加f.t at()。st_size用于显示MiB:

sizes.append(f"{f.stat().st_size/1024/1024:.0f} MiB")

速度分析

用于获取所有子文件夹和主文件夹中具有特定文件扩展名的所有文件的各种方法。

tl; diana:

Fast_scandir明显胜出，它的速度是所有其他解决方案的两倍，除了os.walk。 操作系统。走路是第二慢一点。 使用glob将大大减慢这个过程。 没有一个结果使用自然排序。这意味着结果将像这样排序:1,10,2。要获得自然排序(1,2,10)，请查看:

https://stackoverflow.com/a/48030307/2441026

结果:

fast_scandir    took  499 ms. Found files: 16596. Found subfolders: 439
os.walk         took  589 ms. Found files: 16596
find_files      took  919 ms. Found files: 16596
glob.iglob      took  998 ms. Found files: 16596
glob.glob       took 1002 ms. Found files: 16596
pathlib.rglob   took 1041 ms. Found files: 16596
os.walk-glob    took 1043 ms. Found files: 16596

更新日期:2022-07-20 (Py 3.10.1寻找*.pdf)

glob.iglob      took 132 ms. Found files: 9999
glob.glob       took 134 ms. Found files: 9999
fast_scandir    took 331 ms. Found files: 9999. Found subfolders: 9330
os.walk         took 695 ms. Found files: 9999
pathlib.rglob   took 828 ms. Found files: 9999
find_files      took 949 ms. Found files: 9999
os.walk-glob    took 1242 ms. Found files: 9999

测试使用W7x64, Python 3.8.1，运行20次。439(部分嵌套)子文件夹中的16596个文件。 Find_files来自https://stackoverflow.com/a/45646357/2441026，允许您搜索多个扩展名。 Fast_scandir是我自己写的，还将返回一个子文件夹列表。你可以给它一个扩展列表来搜索(我测试了一个包含一个条目的列表到一个简单的if…== ".jpg"且无显著差异)。

# -*- coding: utf-8 -*-
# Python 3


import time
import os
from glob import glob, iglob
from pathlib import Path


directory = r"<folder>"
RUNS = 20


def run_os_walk():
    a = time.time_ns()
    for i in range(RUNS):
        fu = [os.path.join(dp, f) for dp, dn, filenames in os.walk(directory) for f in filenames if
                  os.path.splitext(f)[1].lower() == '.jpg']
    print(f"os.walk\t\t\ttook {(time.time_ns() - a) / 1000 / 1000 / RUNS:.0f} ms. Found files: {len(fu)}")


def run_os_walk_glob():
    a = time.time_ns()
    for i in range(RUNS):
        fu = [y for x in os.walk(directory) for y in glob(os.path.join(x[0], '*.jpg'))]
    print(f"os.walk-glob\ttook {(time.time_ns() - a) / 1000 / 1000 / RUNS:.0f} ms. Found files: {len(fu)}")


def run_glob():
    a = time.time_ns()
    for i in range(RUNS):
        fu = glob(os.path.join(directory, '**', '*.jpg'), recursive=True)
    print(f"glob.glob\t\ttook {(time.time_ns() - a) / 1000 / 1000 / RUNS:.0f} ms. Found files: {len(fu)}")


def run_iglob():
    a = time.time_ns()
    for i in range(RUNS):
        fu = list(iglob(os.path.join(directory, '**', '*.jpg'), recursive=True))
    print(f"glob.iglob\t\ttook {(time.time_ns() - a) / 1000 / 1000 / RUNS:.0f} ms. Found files: {len(fu)}")


def run_pathlib_rglob():
    a = time.time_ns()
    for i in range(RUNS):
        fu = list(Path(directory).rglob("*.jpg"))
    print(f"pathlib.rglob\ttook {(time.time_ns() - a) / 1000 / 1000 / RUNS:.0f} ms. Found files: {len(fu)}")


def find_files(files, dirs=[], extensions=[]):
    # https://stackoverflow.com/a/45646357/2441026

    new_dirs = []
    for d in dirs:
        try:
            new_dirs += [ os.path.join(d, f) for f in os.listdir(d) ]
        except OSError:
            if os.path.splitext(d)[1].lower() in extensions:
                files.append(d)

    if new_dirs:
        find_files(files, new_dirs, extensions )
    else:
        return


def run_fast_scandir(dir, ext):    # dir: str, ext: list
    # https://stackoverflow.com/a/59803793/2441026

    subfolders, files = [], []

    for f in os.scandir(dir):
        if f.is_dir():
            subfolders.append(f.path)
        if f.is_file():
            if os.path.splitext(f.name)[1].lower() in ext:
                files.append(f.path)


    for dir in list(subfolders):
        sf, f = run_fast_scandir(dir, ext)
        subfolders.extend(sf)
        files.extend(f)
    return subfolders, files



if __name__ == '__main__':
    run_os_walk()
    run_os_walk_glob()
    run_glob()
    run_iglob()
    run_pathlib_rglob()


    a = time.time_ns()
    for i in range(RUNS):
        files = []
        find_files(files, dirs=[directory], extensions=[".jpg"])
    print(f"find_files\t\ttook {(time.time_ns() - a) / 1000 / 1000 / RUNS:.0f} ms. Found files: {len(files)}")


    a = time.time_ns()
    for i in range(RUNS):
        subf, files = run_fast_scandir(directory, [".jpg"])
    print(f"fast_scandir\ttook {(time.time_ns() - a) / 1000 / 1000 / RUNS:.0f} ms. Found files: {len(files)}. Found subfolders: {len(subf)}")