![](/img/trans.png)
[英]Find all files in directory with extension .txt and .py with python using filter and map
[英]Find all files in a directory with extension .txt in Python
如何在python中找到擴展名為.txt
的目錄中的所有文件?
您可以使用glob
:
import glob, os
os.chdir("/mydir")
for file in glob.glob("*.txt"):
print(file)
或者干脆os.listdir
:
import os
for file in os.listdir("/mydir"):
if file.endswith(".txt"):
print(os.path.join("/mydir", file))
或者如果你想遍歷目錄,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))
使用glob 。
>>> import glob
>>> glob.glob('./*.txt')
['./outline.txt', './pip-log.txt', './test.txt', './testingvim.txt']
這樣的事情應該可以完成工作
for root, dirs, files in os.walk(directory):
for file in files:
if file.endswith('.txt'):
print(file)
像這樣的事情會起作用:
>>> 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']
import os
path = 'mypath/path'
files = os.listdir(path)
files_txt = [i for i in files if i.endswith('.txt')]
我喜歡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)
或者使用發電機:
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)
以下是更多版本的相同結果,但結果略有不同:
import glob
for f in glob.iglob("/mydir/*/*.txt"): # generator, search immediate subdirectories
print f
print glob.glob1("/mydir", "*.tx?") # literal_directory, basename_pattern
import fnmatch, os
print fnmatch.filter(os.listdir("/mydir"), "*.tx?") # include dot-files
在遞歸函數中使用 os.scandir 的快速方法。 在文件夾和子文件夾中搜索具有指定擴展名的所有文件。 即使查找 10,000 個文件,它也很快。
我還包含了一個將輸出轉換為 Pandas Dataframe 的函數。
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)
path.py 是另一種選擇: 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
試試這個,這將遞歸地找到所有文件:
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)
要以 Pythonic 方式將“dataPath”文件夾中的所有“.txt”文件名作為列表獲取:
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
Python 擁有執行此操作的所有工具:
import os
the_dir = 'the_dir_that_want_to_search_in'
all_txt_files = filter(lambda x: x.endswith('.txt'), os.listdir(the_dir))
我做了一個測試(Python 3.6.4,W7x64),看看哪個解決方案對於一個文件夾最快,沒有子目錄,以獲得具有特定擴展名的文件的完整文件路徑列表。
簡而言之,對於這個任務os.listdir()
是最快的,並且是下一個最好的os.walk()
pathlib
倍(有休息時間!),是pathlib
2.7 倍,比pathlib
快pathlib
倍os.scandir()
並且比glob
快 3.3 倍。
請記住,當您需要遞歸結果時,這些結果會發生變化。 如果您復制/粘貼下面的一種方法,請添加一個 .lower() 否則在搜索 .ext 時將找不到 .EXT。
import os
import pathlib
import timeit
import 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))
結果:
# Python 3.6.4
0.431
0.515
0.161
0.548
0.537
0.274
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
要從同一目錄中名為“data”的文件夾中獲取“.txt”文件名數組,我通常使用以下簡單的代碼行:
import os
fileNames = [fileName for fileName in os.listdir("data") if fileName.endswith(".txt")]
這段代碼讓我的生活更簡單。
import os
fnames = ([file for root, dirs, files in os.walk(dir)
for file in files
if file.endswith('.txt') #or file.endswith('.png') or file.endswith('.pdf')
])
for fname in fnames: print(fname)
使用 fnmatch: https : //docs.python.org/2/library/fnmatch.html
import fnmatch
import os
for file in os.listdir('.'):
if fnmatch.fnmatch(file, '*.txt'):
print file
我建議你使用fnmatch和上層方法。 通過這種方式,您可以找到以下任何一項:
.
import fnmatch
import os
for file in os.listdir("/Users/Johnny/Desktop/MyTXTfolder"):
if fnmatch.fnmatch(file.upper(), '*.TXT'):
print(file)
一種類似於 ghostdog 的可復制粘貼解決方案:
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 : str
ext : 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 os
all_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
您還可以使用yield
創建生成器,從而避免組裝完整列表:
def get_all_filepaths(root_path, ext):
import os
for root, dirs, files in os.walk(root_path):
for filename in files:
if filename.lower().endswith(ext):
yield os.path.join(root, filename)
這是一個extend()
types = ('*.jpg', '*.png')
images_list = []
for files in types:
images_list.extend(glob.glob(os.path.join(path, files)))
帶有子目錄的功能解決方案:
from fnmatch import filter
from functools import partial
from itertools import chain
from os import path, walk
print(*chain(*(map(partial(path.join, root), filter(filenames, "*.txt")) for root, _, filenames in walk("mydir"))))
如果文件夾包含大量文件或內存受限,請考慮使用生成器:
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
選項 A:迭代
for f in yield_files_with_extensions('.', '.txt'):
print(f)
選項 B:獲得所有
files = [f for f in yield_files_with_extensions('.', '.txt')]
使用 Python OS模塊查找具有特定擴展名的文件。
簡單的例子在這里:
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_name
print file_name_path # This is the full path of the filter file
許多用戶回復了os.walk
答案,其中包括所有文件,但也包括所有目錄和子目錄及其文件。
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)
或者對於一個不需要發電機的人:
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)
如果您打算將匹配項用於其他內容,您可能希望將其設為列表而不是生成器表達式:
matches = [f for f in dirfiles if f.endswith(ext)]
使用for
循環的簡單方法:
import os
dir = ["e","x","e"]
p = os.listdir('E:') #path
for n in range(len(p)):
name = p[n]
myfile = [name[-3],name[-2],name[-1]] #for .txt
if myfile == dir :
print(name)
else:
print("nops")
雖然這可以更概括。
聲明:本站的技術帖子網頁,遵循CC BY-SA 4.0協議,如果您需要轉載,請注明本站網址或者原文地址。任何問題請咨詢:yoyou2525@163.com.