How to count the number of files in a directory using Python

Question

How do I count only the files in a directory? This counts the directory itself as a file:

len(glob.glob('*'))

Answer 1

An answer with pathlib and without loading the whole list to memory:

from pathlib import Path

path = Path('.')

print(sum(1 for _ in path.glob('*')))  # Files and folders, not recursive
print(sum(1 for _ in path.rglob('*')))  # Files and folders, recursive

print(sum(1 for x in path.glob('*') if x.is_file()))  # Only files, not recursive
print(sum(1 for x in path.rglob('*') if x.is_file()))  # Only files, recursive

Answer 2

Convert it to a list, after that you can make use of the len() function:

len(list(glob.glob('*')))

Answer 3

I would like to extend the reply from @Mr_and_Mrs_D:

import os
folder = 'C:/Dropbox'
file_count = sum(len(files) for _, _, files in os.walk(folder))
print(file_count)

This counts all the files in the folder and its subfolders. However, if you want to do some filtering - like only counting the files ending in .svg, you can do:

import os
file_count = sum(len([f for f in files if f.endswith('.svg')]) for _, _, files in os.walk(folder))
print(file_count)

You basically replace:

• len(files)

with:

• len([f for f in files if f.endswith('.svg')])

Answer 4

For all kind of files, subdirectories included (Python 2):

import os

lst = os.listdir(directory) # your directory path
number_files = len(lst)
print number_files

Only files (avoiding subdirectories):

import os

onlyfiles = next(os.walk(directory))[2] #directory is your directory path as string
print len(onlyfiles)

Answer 5

I find that sometimes I don't know if I will receive filenames or the path to the file. So I printed the os walk solution output:

def count_number_of_raw_data_point_files(path: Union[str, Path], with_file_prefix: str) -> int:
    import os
    path: Path = force_expanduser(path)

    _, _, files = next(os.walk(path))
    # file_count = len(files)
    filename: str
    count: int = 0
    for filename in files:
        print(f'-->{filename=}')  # e.g. print -->filename='data_point_99.json'
        if with_file_prefix in filename:
            count += 1
    return count

out:

-->filename='data_point_780.json'
-->filename='data_point_781.json'
-->filename='data_point_782.json'
-->filename='data_point_783.json'
-->filename='data_point_784.json'
-->filename='data_point_785.json'
-->filename='data_point_786.json'
-->filename='data_point_787.json'
-->filename='data_point_788.json'
-->filename='data_point_789.json'
-->filename='data_point_79.json'
-->filename='data_point_790.json'
-->filename='data_point_791.json'
-->filename='data_point_792.json'
-->filename='data_point_793.json'
-->filename='data_point_794.json'
-->filename='data_point_795.json'
-->filename='data_point_796.json'
-->filename='data_point_797.json'
-->filename='data_point_798.json'
-->filename='data_point_799.json'
-->filename='data_point_8.json'
-->filename='data_point_80.json'
-->filename='data_point_800.json'
-->filename='data_point_801.json'
-->filename='data_point_802.json'
-->filename='data_point_803.json'
-->filename='data_point_804.json'
-->filename='data_point_805.json'
-->filename='data_point_806.json'
-->filename='data_point_807.json'
-->filename='data_point_808.json'
-->filename='data_point_809.json'
-->filename='data_point_81.json'
-->filename='data_point_810.json'
-->filename='data_point_811.json'
-->filename='data_point_812.json'
-->filename='data_point_813.json'
-->filename='data_point_814.json'
-->filename='data_point_815.json'
-->filename='data_point_816.json'
-->filename='data_point_817.json'
-->filename='data_point_818.json'
-->filename='data_point_819.json'
-->filename='data_point_82.json'
-->filename='data_point_820.json'
-->filename='data_point_821.json'
-->filename='data_point_822.json'
-->filename='data_point_823.json'
-->filename='data_point_824.json'
-->filename='data_point_825.json'
-->filename='data_point_826.json'
-->filename='data_point_827.json'
-->filename='data_point_828.json'
-->filename='data_point_829.json'
-->filename='data_point_83.json'
-->filename='data_point_830.json'
-->filename='data_point_831.json'
-->filename='data_point_832.json'
-->filename='data_point_833.json'
-->filename='data_point_834.json'
-->filename='data_point_835.json'
-->filename='data_point_836.json'
-->filename='data_point_837.json'
-->filename='data_point_838.json'
-->filename='data_point_839.json'
-->filename='data_point_84.json'
-->filename='data_point_840.json'
-->filename='data_point_841.json'
-->filename='data_point_842.json'
-->filename='data_point_843.json'
-->filename='data_point_844.json'
-->filename='data_point_845.json'
-->filename='data_point_846.json'
-->filename='data_point_847.json'
-->filename='data_point_848.json'
-->filename='data_point_849.json'
-->filename='data_point_85.json'
-->filename='data_point_850.json'
-->filename='data_point_851.json'
-->filename='data_point_852.json'
-->filename='data_point_853.json'
-->filename='data_point_86.json'
-->filename='data_point_87.json'
-->filename='data_point_88.json'
-->filename='data_point_89.json'
-->filename='data_point_9.json'
-->filename='data_point_90.json'
-->filename='data_point_91.json'
-->filename='data_point_92.json'
-->filename='data_point_93.json'
-->filename='data_point_94.json'
-->filename='data_point_95.json'
-->filename='data_point_96.json'
-->filename='data_point_97.json'
-->filename='data_point_98.json'
-->filename='data_point_99.json'
854

note you might have to sort.

Answer 6

import os

_, _, files = next(os.walk("/usr/lib"))
file_count = len(files)

Answer 7

Simpler one:

import os
number_of_files = len(os.listdir(directory))
print(number_of_files)

Answer 8

This is an easy solution that counts the number of files in a directory containing sub-folders. It may come in handy:

import os
from pathlib import Path

def count_files(rootdir):
    '''counts the number of files in each subfolder in a directory'''
    for path in pathlib.Path(rootdir).iterdir():
        if path.is_dir():
            print("There are " + str(len([name for name in os.listdir(path) \
            if os.path.isfile(os.path.join(path, name))])) + " files in " + \
            str(path.name))
            
 
count_files(data_dir) # data_dir is the directory you want files counted.

You should get an output similar to this (with the placeholders changed, of course):

There are {number of files} files in {name of sub-folder1}
There are {number of files} files in {name of sub-folder2}

Answer 9

A simple utility function I wrote that makes use of os.scandir() instead of os.listdir().

import os 

def count_files_in_dir(path: str) -> int:
    file_entries = [entry for entry in os.scandir(path) if entry.is_file()]

    return len(file_entries)

The main benefit is that, the need for os.path.is_file() is eliminated and replaced with os.DirEntry instance's is_file() which also removes the need for os.path.join(DIR, file_name) as shown in other answers.

Answer 10

Short and simple

import os
directory_path = '/home/xyz/'
No_of_files = len(os.listdir(directory_path))

Answer 11

one liner and recursive:

def count_files(path):
    return sum([len(files) for _, _, files in os.walk(path)])

count_files('path/to/dir')

Answer 12

While I agree with the answer provided by @DanielStutzbach: os.listdir() will be slightly more efficient than using glob.glob.

However, an extra precision, if you do want to count the number of specific files in folder, you want to use len(glob.glob()). For instance if you were to count all the pdfs in a folder you want to use:

pdfCounter = len(glob.glob1(myPath,"*.pdf"))

Answer 13

It is simple:

print(len([iq for iq in os.scandir('PATH')]))

it simply counts number of files in directory , i have used list comprehension technique to iterate through specific directory returning all files in return . "len(returned list)" returns number of files.

Answer 14

If you want to count all files in the directory - including files in subdirectories, the most pythonic way is:

import os

file_count = sum(len(files) for _, _, files in os.walk(r'C:\Dropbox'))
print(file_count)

We use sum that is faster than explicitly adding the file counts (timings pending)

Answer 15

I am surprised that nobody mentioned os.scandir:

def count_files(dir):
    return len([1 for x in list(os.scandir(dir)) if x.is_file()])

Answer 16

i did this and this returned the number of files in the folder(Attack_Data)...this works fine.

import os
def fcount(path):
    #Counts the number of files in a directory
    count = 0
    for f in os.listdir(path):
        if os.path.isfile(os.path.join(path, f)):
            count += 1

    return count
path = r"C:\Users\EE EKORO\Desktop\Attack_Data" #Read files in folder
print (fcount(path))

Answer 17

I used glob.iglob for a directory structure similar to

data
└───train
│   └───subfolder1
│   |   │   file111.png
│   |   │   file112.png
│   |   │   ...
│   |
│   └───subfolder2
│       │   file121.png
│       │   file122.png
│       │   ...
└───test
    │   file221.png
    │   file222.png

Both of the following options return 4 (as expected, i.e. does not count the subfolders themselves)

• len(list(glob.iglob("data/train/*/*.png", recursive=True)))
• sum(1 for i in glob.iglob("data/train/*/*.png"))

Answer 18

Here is a simple one-line command that I found useful:

print int(os.popen("ls | wc -l").read())

Answer 19

I found another answer which may be correct as accepted answer.

for root, dirs, files in os.walk(input_path):    
for name in files:
    if os.path.splitext(name)[1] == '.TXT' or os.path.splitext(name)[1] == '.txt':
        datafiles.append(os.path.join(root,name)) 


print len(files) 

Answer 20

If you'll be using the standard shell of the operating system, you can get the result much faster rather than using pure pythonic way.

Example for Windows:

import os
import subprocess

def get_num_files(path):
    cmd = 'DIR \"%s\" /A-D /B /S | FIND /C /V ""' % path
    return int(subprocess.check_output(cmd, shell=True))

Answer 21

import os

total_con=os.listdir('<directory path>')

files=[]

for f_n in total_con:
   if os.path.isfile(f_n):
     files.append(f_n)


print len(files)

Answer 22

os.listdir() will be slightly more efficient than using glob.glob. To test if a filename is an ordinary file (and not a directory or other entity), use os.path.isfile():

import os, os.path

# simple version for working with CWD
print len([name for name in os.listdir('.') if os.path.isfile(name)])

# path joining version for other paths
DIR = '/tmp'
print len([name for name in os.listdir(DIR) if os.path.isfile(os.path.join(DIR, name))])

Answer 23

import os
print len(os.listdir(os.getcwd()))

Answer 24

This is where fnmatch comes very handy:

import fnmatch

print len(fnmatch.filter(os.listdir(dirpath), '*.txt'))

More details: http://docs.python.org/2/library/fnmatch.html

Answer 25

def directory(path,extension):
  list_dir = []
  list_dir = os.listdir(path)
  count = 0
  for file in list_dir:
    if file.endswith(extension): # eg: '.txt'
      count += 1
  return count

Answer 26

This uses os.listdir and works for any directory:

import os
directory = 'mydirpath'

number_of_files = len([item for item in os.listdir(directory) if os.path.isfile(os.path.join(directory, item))])

this can be simplified with a generator and made a little bit faster with:

import os
isfile = os.path.isfile
join = os.path.join

directory = 'mydirpath'
number_of_files = sum(1 for item in os.listdir(directory) if isfile(join(directory, item)))

Answer 27

Luke's code reformat.

import os

print len(os.walk('/usr/lib').next()[2])

Answer 28

import os

def count_files(in_directory):
    joiner= (in_directory + os.path.sep).__add__
    return sum(
        os.path.isfile(filename)
        for filename
        in map(joiner, os.listdir(in_directory))
    )

>>> count_files("/usr/lib")
1797
>>> len(os.listdir("/usr/lib"))
2049

Answer 29

def count_em(valid_path):
   x = 0
   for root, dirs, files in os.walk(valid_path):
       for f in files:
            x = x+1
print "There are", x, "files in this directory."
return x

Taked from this post