Python v3.5 +

使用os的快速方法。递归函数中的Scandir。在文件夹和子文件夹中搜索具有指定扩展名的所有文件。它的速度非常快，甚至可以找到10,000个文件。

我还包含了一个将输出转换为Pandas数据框架的函数。

import os
import re
import pandas as pd
import 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 files
    extension:          File extension to find.  e.g. 'txt'.  Regular expression. Or  'ls\d' to match ls1, ls2, ls3 etc
    containsTxt:        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 folder
    excludeText:        Text string.  Ignore if ''. Will exclude if text string is in path.
    """
    if type(containsTxt) == str: # if a string and not in a list
        containsTxt = [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 believe
        for 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 function
                yield 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 files
    extension:          File extension to find.  e.g. 'txt'.  Regular expression. Or  'ls\d' to match ls1, ls2, ls3 etc
    containsTxt:        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 folder
    excludeText:        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 expression 
containsTxt=[]
path = 'C:\myFolder'
df = findFilesInFolderYieldandGetDf(path,  ext, containsTxt, subFolders = True)

Python v3.5 +

使用os的快速方法。递归函数中的Scandir。在文件夹和子文件夹中搜索具有指定扩展名的所有文件。它的速度非常快，甚至可以找到10,000个文件。

我还包含了一个将输出转换为Pandas数据框架的函数。

import os
import re
import pandas as pd
import 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 files
    extension:          File extension to find.  e.g. 'txt'.  Regular expression. Or  'ls\d' to match ls1, ls2, ls3 etc
    containsTxt:        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 folder
    excludeText:        Text string.  Ignore if ''. Will exclude if text string is in path.
    """
    if type(containsTxt) == str: # if a string and not in a list
        containsTxt = [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 believe
        for 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 function
                yield 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 files
    extension:          File extension to find.  e.g. 'txt'.  Regular expression. Or  'ls\d' to match ls1, ls2, ls3 etc
    containsTxt:        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 folder
    excludeText:        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 expression 
containsTxt=[]
path = 'C:\myFolder'
df = findFilesInFolderYieldandGetDf(path,  ext, containsTxt, subFolders = True)

用一团。

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

你可以简单地使用pathlibs glob 1:

import pathlib

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

或在循环中:

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

如果你想递归你可以使用。glob('**/*.txt')

1 pathlib模块被包含在python 3.4的标准库中。但是你甚至可以在旧的Python版本(即使用conda或pip)上安装该模块的反向端口:pathlib和pathlib2。

要从同一个目录中名为“data”的文件夹中获取一个“。txt”文件名的数组，我通常使用以下简单的代码行:

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

以python方式获取“dataPath”文件夹中所有的“。txt”文件名:

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