在Python中查找扩展名为.txt的目录中的所有文件
如何在python中找到扩展名为在Python中查找扩展名为.txt的目录中的所有文件,python,file-io,Python,File Io,如何在python中找到扩展名为.txt的目录中的所有文件？使用 像那样的东西应该能完成任务 for root, dirs, files in os.walk(directory): for file in files: if file.endswith('.txt'): print(file) 您可以使用： 或者简单地说： 或者，如果要遍历目录，请使用： 类似这样的方法会奏效： >>> import os >>&g
.txt像那样的东西应该能完成任务
for root, dirs, files in os.walk(directory):
for file in files:
if file.endswith('.txt'):
print(file)
类似这样的方法会奏效：
>>> 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']
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)
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
以下是产生略有不同结果的更多版本： glob.glob1（）
path.py是另一种选择：
这段代码让我的生活更简单
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)
具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, walk
print(*chain(*(map(partial(path.join, root), filter(filenames, "*.txt")) for root, _, filenames in walk("mydir"))))
尝试此操作将递归查找所有文件：
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)
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
Python提供了所有工具来实现这一点：
import os
the_dir = 'the_dir_that_want_to_search_in'
all_txt_files = filter(lambda x: x.endswith('.txt'), os.listdir(the_dir))
<>在文件夹包含很多文件或内存是一个约束的情况下，考虑使用生成器：
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)
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
for f in yield_files_with_extensions('.', '.txt'):
print(f)
files = [f for f in yield_files_with_extensions('.', '.txt')]
import os
fileNames = [fileName for fileName in os.listdir("data") if fileName.endswith(".txt")]
for txt_file in pathlib.Path('your_directory').glob('*.txt'):
# do something with "txt_file"
.glob（'***.txt）1 python 3.4的标准库中包含了
pathlibcondapipdef 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
许多用户回复了
os.walkimport 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)
matches = [f for f in dirfiles if f.endswith(ext)]
这里有一个带有
extend（）使用
forimport 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")
os.listdir（）os.walk（）pathlibos.scandir（）glob请记住，当您需要递归结果时，这些结果将发生变化。如果复制/粘贴下面的一个方法，请添加一个.lower（），否则在搜索.EXT时将找不到.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))
# Python 3.6.4
0.431
0.515
0.161
0.548
0.537
0.274
要以Python方式将“dataPath”文件夹中的所有“.txt”文件名作为列表获取，请执行以下操作：
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
导入操作系统
进口稀土
作为pd进口熊猫
将numpy作为np导入
def FindFileInfolderyield（路径、扩展名、ContainsText=''、子文件夹=True、excludeText=''：
“”“递归函数，用于查找文件夹（以及可选的所有子文件夹）中扩展名类型的所有文件”
path：查找文件的基本目录
扩展名：查找的文件扩展名。例如“txt”。正则表达式。或匹配ls1、ls2、ls3等的“ls\d”
ContainsText:字符串列表，仅当文件包含此文本时才查找该文件。如果为“”（或为空），则忽略
子文件夹：Bool。如果为True，则在路径下的所有子文件夹中查找文件。如果为False，则仅搜索指定文件夹中的文件
excludeText:文本字符串。如果“”忽略。如果文本字符串位于路径中，则将排除。
"""
如果类型（containsTxt）=str:#如果是字符串而不在列表中
containsTxt=[containsTxt]
myregexobj=re.compile（“\.+扩展名+“$”）#确保文件扩展名在末尾，前面有一个。
try:#捕获操作错误或FileNotFoundError：我相信是文件权限问题
对于os.scandir中的条目（路径）：
如果entry.is_file（）和myregexobj.search（entry.path）：#
bools=[如果entry.path中有txt，则containsTxt中的txt为True，并且（excludeText==''或excludeText不在entry.path中）]
如果len（bools）=len（containsTxt）：
屈服entry.stat（）.st_size，entry.stat（）.st_atime，entry.stat（）.st_mtime，entry.stat（）.st_ctime，entry.path
elif entry.is_dir（）和子文件夹：#如果是目录，则作为嵌套函数重复该过程
来自FindFileInfolderyield的收益率（entry.path、扩展名、containsTxt、子文件夹）
除了作为ose的OSError之外：
打印（'无法访问'+路径+'。可能是权限错误，ose）
除FileNotFoundError作为fnf外：
打印（路径+“未找到”，fnf）
def FINDFILEINFORDEYIELDANDGETDF（路径、扩展名、containsTxt、子文件夹=True、excludeText=''）：
“”“转换从FindFileInfolderyield返回的数据，并创建和保存数据帧。
递归函数，用于查找文件夹（以及可选的所有子文件夹）中扩展名类型的所有文件
path：查找文件的基本目录
扩展名：查找的文件扩展名。例如“txt”。正则表达式。或匹配ls1、ls2、ls3等的“ls\d”
ContainsText:字符串列表，仅当文件包含此文本时才查找该文件。如果为“”（或为空），则忽略
子文件夹：Bool。如果为True，则在路径下的所有子文件夹中查找文件。如果为False，则仅搜索指定文件夹中的文件
excludeText:文本字符串。如果“”将被删除，则忽略
files = [f for f in yield_files_with_extensions('.', '.txt')]
import fnmatch
import os
for file in os.listdir("/Users/Johnny/Desktop/MyTXTfolder"):
if fnmatch.fnmatch(file.upper(), '*.TXT'):
print(file)
import os
fileNames = [fileName for fileName in os.listdir("data") if fileName.endswith(".txt")]
import pathlib
list(pathlib.Path('your_directory').glob('*.txt'))
for txt_file in pathlib.Path('your_directory').glob('*.txt'):
# do something with "txt_file"
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
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)
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)
matches = [f for f in dirfiles if f.endswith(ext)]
types = ('*.jpg', '*.png')
images_list = []
for files in types:
images_list.extend(glob.glob(os.path.join(path, files)))
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")
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))
# Python 3.6.4
0.431
0.515
0.161
0.548
0.537
0.274
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