Alle Dateien in einem Verzeichnis mit der Erweiterung .txt in Python finden

Question

Wie kann ich alle Dateien in einem Verzeichnis mit der Erweiterung .txt in Python?

Answer 1

import os

path = 'mypath/path' 
files = os.listdir(path)

files_txt = [i for i in files if i.endswith('.txt')]

Answer 2

Ich mag 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)

Oder mit Generatoren:

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)

Answer 3

Hier sind weitere Versionen desselben Vorgangs, die leicht unterschiedliche Ergebnisse liefern:

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

Answer 4

Probieren Sie dies aus, um alle Ihre Dateien rekursiv zu finden:

import glob, os
os.chdir("H:\\wallpaper")# use whatever directory you want

#double\\ no single \

for file in glob.glob("**/*.txt", recursive = True):
    print(file)

Answer 5

Python v3.5+

Schnelle Methode, die os.scandir in einer rekursiven Funktion verwendet. Sucht nach allen Dateien mit einer bestimmten Erweiterung in Ordnern und Unterordnern. Es ist schnell, auch für das Auffinden von 10.000er Dateien.

Ich habe auch eine Funktion zur Konvertierung der Ausgabe in einen Pandas Dataframe hinzugefügt.

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)