在Python中查找扩展名为. txt的目录中的所有文件

使用球状。

>>> import glob>>> glob.glob('./*.txt')['./outline.txt', './pip-log.txt', './test.txt', './testingvim.txt']

这样的东西应该能起作用

for root, dirs, files in os.walk(directory):for file in files:if file.endswith('.txt'):print(file)

您可以使用#0：

import glob, osos.chdir("/mydir")for file in glob.glob("*.txt"):print(file)

或者简单地#0：

import osfor file in os.listdir("/mydir"):if file.endswith(".txt"):print(os.path.join("/mydir", file))

或者如果您想遍历目录，请使用#0：

import osfor root, dirs, files in os.walk("/mydir"):for file in files:if file.endswith(".txt"):print(os.path.join(root, file))

这样的事情会奏效：

>>> import os>>> path = '/usr/share/cups/charmaps'>>> text_files = [f for f in os.listdir(path) if f.endswith('.txt')]>>> text_files['euc-cn.txt', 'euc-jp.txt', 'euc-kr.txt', 'euc-tw.txt', ... 'windows-950.txt']

喜欢os.walk（）：

import os
for root, dirs, files in os.walk(dir):for f in files:if os.path.splitext(f)[1] == '.txt':fullpath = os.path.join(root, f)print(fullpath)

或者使用生成器：

import os
fileiter = (os.path.join(root, f)for root, _, files in os.walk(dir)for f in files)txtfileiter = (f for f in fileiter if os.path.splitext(f)[1] == '.txt')for txt in txtfileiter:print(txt)

以下是相同的更多版本，产生略有不同的结果：

glob.iglob（）

import globfor f in glob.iglob("/mydir/*/*.txt"): # generator, search immediate subdirectoriesprint f

glob.glob1（）

print glob.glob1("/mydir", "*.tx?")  # literal_directory, basename_pattern

fnmatch.filter（）

import fnmatch, osprint fnmatch.filter(os.listdir("/mydir"), "*.tx?") # include dot-files

import osimport sys
if len(sys.argv)==2:print('no params')sys.exit(1)
dir = sys.argv[1]mask= sys.argv[2]
files = os.listdir(dir);
res = filter(lambda x: x.endswith(mask), files);
print res

path.py另一种选择：https://github.com/jaraco/path.py

from path import pathp = path('/path/to/the/directory')for f in p.files(pattern='*.txt'):print f

这段代码让我的生活更简单。

import osfnames = ([file for root, dirs, files in os.walk(dir)for file in filesif file.endswith('.txt') #or file.endswith('.png') or file.endswith('.pdf')])for fname in fnames: print(fname)

import os
path = 'mypath/path'files = os.listdir(path)
files_txt = [i for i in files if i.endswith('.txt')]

带有子目录的功能解决方案：

from fnmatch import filterfrom functools import partialfrom itertools import chainfrom os import path, walk
print(*chain(*(map(partial(path.join, root), filter(filenames, "*.txt")) for root, _, filenames in walk("mydir"))))

使用fnmatch：https://docs.python.org/2/library/fnmatch.html

import fnmatchimport os
for file in os.listdir('.'):if fnmatch.fnmatch(file, '*.txt'):print file

尝试此操作将递归查找您的所有文件：

import glob, osos.chdir("H:\\wallpaper")# use whatever directory you want
#double\\ no single \
for file in glob.glob("**/*.txt", recursive = True):print(file)

使用Pythonos模块查找具有特定扩展名的文件。

简单的例子在这里：

import os
# This is the path where you want to searchpath = r'd:'
# this is extension you want to detectextension = '.txt'   # this can be : .jpg  .png  .xls  .log .....
for root, dirs_list, files_list in os.walk(path):for file_name in files_list:if os.path.splitext(file_name)[-1] == extension:file_name_path = os.path.join(root, file_name)print file_nameprint file_name_path   # This is the full path of the filter file

Python有所有工具可以做到这一点：

import os
the_dir = 'the_dir_that_want_to_search_in'all_txt_files = filter(lambda x: x.endswith('.txt'), os.listdir(the_dir))

如果文件夹包含大量文件或内存是一个约束，请考虑使用生成器：

def yield_files_with_extensions(folder_path, file_extension):for _, _, files in os.walk(folder_path):for file in files:if file.endswith(file_extension):yield file

选项A：迭代

for f in yield_files_with_extensions('.', '.txt'):print(f)

选项B：全部获取

files = [f for f in yield_files_with_extensions('.', '.txt')]

我建议你使用fnmatch和上层方法。通过这种方式，你可以找到以下任何一种：

1. 姓名。txt；
2. 姓名。TXT；
3. 姓名。txt

.

import fnmatchimport os
for file in os.listdir("/Users/Johnny/Desktop/MyTXTfolder"):if fnmatch.fnmatch(file.upper(), '*.TXT'):print(file)

要从同一目录中名为“data”的文件夹中获取“. txt”文件名数组，我通常使用这行简单的代码：

import osfileNames = [fileName for fileName in os.listdir("data") if fileName.endswith(".txt")]

您可以简单地使用#0s#1¹：

import pathlib
list(pathlib.Path('your_directory').glob('*.txt'))

或者在一个循环中：

for txt_file in pathlib.Path('your_directory').glob('*.txt'):# do something with "txt_file"

如果你想要递归，你可以使用.glob('**/*.txt')

pathlib模块包含在python 3.4的标准库中。但是即使在较旧的Python版本（即使用conda或pip）上，您也可以安装该模块的后端：#0和#4。

一个可复制的可提交解决方案，类似于ghostDog的解决方案：

def get_all_filepaths(root_path, ext):"""Search all files which have a given extension within root_path.
This ignores the case of the extension and searches subdirectories, too.
Parameters----------root_path : strext : str
Returns-------list of str
Examples-------->>> get_all_filepaths('/run', '.lock')['/run/unattended-upgrades.lock','/run/mlocate.daily.lock','/run/xtables.lock','/run/mysqld/mysqld.sock.lock','/run/postgresql/.s.PGSQL.5432.lock','/run/network/.ifstate.lock','/run/lock/asound.state.lock']"""import osall_files = []for root, dirs, files in os.walk(root_path):for filename in files:if filename.lower().endswith(ext):all_files.append(os.path.join(root, filename))return all_files

您还可以使用yield创建生成器，从而避免组装完整列表：

def get_all_filepaths(root_path, ext):import osfor root, dirs, files in os.walk(root_path):for filename in files:if filename.lower().endswith(ext):yield os.path.join(root, filename)

许多用户回复了os.walk答案，其中包括所有文件，也包括所有目录和子目录及其文件。

import os

def files_in_dir(path, extension=''):"""Generator: yields all of the files in <path> ending with<extension>
\param   path       Absolute or relative path to inspect,\param   extension  [optional] Only yield files matching this,
\yield              [filenames]"""

for _, dirs, files in os.walk(path):dirs[:] = []  # do not recurse directories.yield from [f for f in files if f.endswith(extension)]
# Example: print all the .py files in './python'for filename in files_in_dir('./python', '*.py'):print("-", filename)

或者对于一个你不需要发电机的地方：

path, ext = "./python", ext = ".py"for _, _, dirfiles in os.walk(path):matches = (f for f in dirfiles if f.endswith(ext))break
for filename in matches:print("-", filename)

如果您要将匹配用于其他内容，您可能希望将其设为列表而不是生成器表达式：

    matches = [f for f in dirfiles if f.endswith(ext)]

这里有一个extend()

types = ('*.jpg', '*.png')images_list = []for files in types:images_list.extend(glob.glob(os.path.join(path, files)))

我做了一个测试（Python 3.6.4，W7x64），看看哪个解决方案对于一个文件夹（没有子目录）最快，以获取具有特定扩展名的文件的完整文件路径列表。

简而言之，对于这个任务，os.listdir()是最快的，并且是下一个最好的1.7倍：os.walk()（休息！），pathlib的2.7倍，比os.scandir()快3.2倍，比glob快3.3倍。
请记住，当您需要递归结果时，这些结果会发生变化。如果您复制/粘贴下面的一个方法，请添加一个. low（），否则。搜索. ext时找不到EXT。

import osimport pathlibimport timeitimport glob
def a():path = pathlib.Path().cwd()list_sqlite_files = [str(f) for f in path.glob("*.sqlite")]
def b():path = os.getcwd()list_sqlite_files = [f.path for f in os.scandir(path) if os.path.splitext(f)[1] == ".sqlite"]
def c():path = os.getcwd()list_sqlite_files = [os.path.join(path, f) for f in os.listdir(path) if f.endswith(".sqlite")]
def d():path = os.getcwd()os.chdir(path)list_sqlite_files = [os.path.join(path, f) for f in glob.glob("*.sqlite")]
def e():path = os.getcwd()list_sqlite_files = [os.path.join(path, f) for f in glob.glob1(str(path), "*.sqlite")]
def f():path = os.getcwd()list_sqlite_files = []for root, dirs, files in os.walk(path):for file in files:if file.endswith(".sqlite"):list_sqlite_files.append( os.path.join(root, file) )break


print(timeit.timeit(a, number=1000))print(timeit.timeit(b, number=1000))print(timeit.timeit(c, number=1000))print(timeit.timeit(d, number=1000))print(timeit.timeit(e, number=1000))print(timeit.timeit(f, number=1000))

结果：

# Python 3.6.40.4310.5150.1610.5480.5370.274

以Pythonic方式获取'dataPath'文件夹中的所有'. txt'文件名作为列表：

from os import listdirfrom os.path import isfile, joinpath = "/dataPath/"onlyTxtFiles = [f for f in listdir(path) if isfile(join(path, f)) and  f.endswith(".txt")]print onlyTxtFiles

pythonv3.5+

在递归函数中使用os.scandir的快速方法。在文件夹和子文件夹中搜索具有指定扩展名的所有文件。即使找到10,000个文件，它也很快。

我还包含了一个将输出转换为Pandas Dataframe的函数。

import osimport reimport pandas as pdimport numpy as np

def findFilesInFolderYield(path,  extension, containsTxt='', subFolders = True, excludeText = ''):"""  Recursive function to find all files of an extension type in a folder (and optionally in all subfolders too)
path:               Base directory to find filesextension:          File extension to find.  e.g. 'txt'.  Regular expression. Or  'ls\d' to match ls1, ls2, ls3 etccontainsTxt:        List of Strings, only finds file if it contains this text.  Ignore if '' (or blank)subFolders:         Bool.  If True, find files in all subfolders under path. If False, only searches files in the specified folderexcludeText:        Text string.  Ignore if ''. Will exclude if text string is in path."""if type(containsTxt) == str: # if a string and not in a listcontainsTxt = [containsTxt]    
myregexobj = re.compile('\.' + extension + '$')    # Makes sure the file extension is at the end and is preceded by a .    
try:   # Trapping a OSError or FileNotFoundError:  File permissions problem I believefor entry in os.scandir(path):if entry.is_file() and myregexobj.search(entry.path): #    
bools = [True for txt in containsTxt if txt in entry.path and (excludeText == '' or excludeText not in entry.path)]    
if len(bools)== len(containsTxt):yield entry.stat().st_size, entry.stat().st_atime_ns, entry.stat().st_mtime_ns, entry.stat().st_ctime_ns, entry.path    
elif entry.is_dir() and subFolders:   # if its a directory, then repeat process as a nested functionyield from findFilesInFolderYield(entry.path,  extension, containsTxt, subFolders)except OSError as ose:print('Cannot access ' + path +'. Probably a permissions error ', ose)except FileNotFoundError as fnf:print(path +' not found ', fnf)
def findFilesInFolderYieldandGetDf(path,  extension, containsTxt, subFolders = True, excludeText = ''):"""  Converts returned data from findFilesInFolderYield and creates and Pandas Dataframe.Recursive function to find all files of an extension type in a folder (and optionally in all subfolders too)
path:               Base directory to find filesextension:          File extension to find.  e.g. 'txt'.  Regular expression. Or  'ls\d' to match ls1, ls2, ls3 etccontainsTxt:        List of Strings, only finds file if it contains this text.  Ignore if '' (or blank)subFolders:         Bool.  If True, find files in all subfolders under path. If False, only searches files in the specified folderexcludeText:        Text string.  Ignore if ''. Will exclude if text string is in path."""    
fileSizes, accessTimes, modificationTimes, creationTimes , paths  = zip(*findFilesInFolderYield(path,  extension, containsTxt, subFolders))df = pd.DataFrame({'FLS_File_Size':fileSizes,'FLS_File_Access_Date':accessTimes,'FLS_File_Modification_Date':np.array(modificationTimes).astype('timedelta64[ns]'),'FLS_File_Creation_Date':creationTimes,'FLS_File_PathName':paths,})    
df['FLS_File_Modification_Date'] = pd.to_datetime(df['FLS_File_Modification_Date'],infer_datetime_format=True)df['FLS_File_Creation_Date'] = pd.to_datetime(df['FLS_File_Creation_Date'],infer_datetime_format=True)df['FLS_File_Access_Date'] = pd.to_datetime(df['FLS_File_Access_Date'],infer_datetime_format=True)
return df
ext =   'txt'  # regular expressioncontainsTxt=[]path = 'C:\myFolder'df = findFilesInFolderYieldandGetDf(path,  ext, containsTxt, subFolders = True)