在Python中以扩展名.txt查找目录中的所有文件

如何在python中扩展名为.txt的目录中找到所有文件？

#1楼

import os
import 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

#2楼

path.py是另一种替代方法： https : //github.com/jaraco/path.py

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

#3楼

此代码使我的生活更简单。

import os
fnames = ([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)

#4楼

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

#5楼

带有子目录的功能解决方案：

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

#6楼

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

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

#7楼

试试这个，这将递归地找到所有文件：

import glob, os
os.chdir("H:\\wallpaper")# use whatever you directory #double\\ no single \for file in glob.glob("**/*.psd", recursive = True):#your formatprint(file)

#8楼

使用Python OS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 search
path = r'd:'  # this is extension you want to detect
extension = '.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

#9楼

Python具有执行此操作的所有工具：

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

#10楼

使用glob 。

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

#11楼

这样的事情应该做的

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

#12楼

您可以使用glob ：

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

或者只是os.listdir ：

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

或者如果要遍历目录，请使用os.walk ：

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

#13楼

这样的事情会起作用：

>>> 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']

#14楼

我喜欢os.walk（）：

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

或使用发电机：

import os, os.pathfileiter = (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

#15楼

以下是相同版本的更多版本，它们会产生稍微不同的结果：

glob.iglob（）

import glob
for f in glob.iglob("/mydir/*/*.txt"): # generator, search immediate subdirectories print f

glob.glob1（）

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

fnmatch.filter（）

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

#16楼

如果文件夹包含很多文件或内存是一个限制，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：重复

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')]

#17楼

我建议您使用fnmatch和upper方法。这样，您可以找到以下任意一项：

名称。 txt ;
名称。 TXT ;
名称。文本

。

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

#18楼

为了从同一目录中名为“ data”的文件夹中获取“ .txt”文件名的数组，我通常使用以下简单代码行：

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

#19楼

您可以简单地使用pathlib的glob ¹ ：

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

或循环：

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

如果您希望递归，则可以使用.glob('**/*.txt)

¹pathlib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反向端口： pathlib和pathlib2 。

#20楼

可复制的解决方案，类似于ghostdog之一：

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 : strReturns-------list of strExamples-------->>> 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

#21楼

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

import osdef 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)

或者在不需要发电机的情况下关闭：

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

如果要将匹配用于其他内容，则可能需要使其成为列表而不是生成器表达式：

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

#22楼

这是带有extend()的一个

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

#23楼

使用for循环的一种简单方法：

import osdir = ["e","x","e"]p = os.listdir('E:')  #pathfor n in range(len(p)):name = p[n]myfile = [name[-3],name[-2],name[-1]]  #for .txtif myfile == dir :print(name)else:print("nops")

虽然这可以使它更加笼统。

#24楼

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

简而言之，此任务os.listdir()是最快的，并且是次pathlib倍： os.walk() （有间断！），是pathlib 2.7倍，比pathlib快pathlib倍。 os.scandir()和glob快3.3倍。
请记住，当您需要递归结果时，这些结果将改变。如果您复制/粘贴以下一种方法，请添加.lower（），否则在搜索.ext时找不到.EXT。

import os
import pathlib
import timeit
import globdef 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) )breakprint(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 3.6.4
0.431
0.515
0.161
0.548
0.537
0.274

#25楼

以Python方式将“ dataPath”文件夹中的所有“ .txt”文件名作为列表获取

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

#26楼

Python v3.5 +

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。

import osdef findFilesInFolder(path, pathList, extension, subFolders = True):"""  Recursive function to find all files of an extension type in a folder (and optionally in all subfolders too)path:        Base directory to find filespathList:    A list that stores all pathsextension:   File extension to findsubFolders:  Bool.  If True, find files in all subfolders under path. If False, only searches files in the specified folder"""try:   # Trapping a OSError:  File permissions problem I believefor entry in os.scandir(path):if entry.is_file() and entry.path.endswith(extension):pathList.append(entry.path)elif entry.is_dir() and subFolders:   # if its a directory, then repeat process as a nested functionpathList = findFilesInFolder(entry.path, pathList, extension, subFolders)except OSError:print('Cannot access ' + path +'. Probably a permissions error')return pathListdir_name = r'J:\myDirectory'
extension = ".txt"pathList = []
pathList = findFilesInFolder(dir_name, pathList, extension, True)

2019年4月更新

如果要搜索包含10,000s个文件的目录，则附加到列表的效率将降低。 “屈服”结果是一个更好的解决方案。我还提供了一个将输出转换为Pandas Dataframe的功能。

import os
import re
import pandas as pd
import numpy as npdef 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.pathelif 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 dfext =   'txt'  # regular expression
containsTxt=[]
path = 'C:\myFolder'
df = findFilesInFolderYieldandGetDf(path,  ext, containsTxt, subFolders = True)