Calculating a directory's size using Python?

Viewed 255890

Before I re-invent this particular wheel, has anybody got a nice routine for calculating the size of a directory using Python? It would be very nice if the routine would format the size nicely in Mb/Gb etc.

33 Answers

Using pathlib I came up with this one-liner to get the size of a folder:

sum(file.stat().st_size for file in Path(folder).rglob('*'))

And this is what I came up with for a nicely formatted output:

from pathlib import Path


def get_folder_size(folder):
    return ByteSize(sum(file.stat().st_size for file in Path(folder).rglob('*')))


class ByteSize(int):

    _kB = 1024
    _suffixes = 'B', 'kB', 'MB', 'GB', 'PB'

    def __new__(cls, *args, **kwargs):
        return super().__new__(cls, *args, **kwargs)

    def __init__(self, *args, **kwargs):
        self.bytes = self.B = int(self)
        self.kilobytes = self.kB = self / self._kB**1
        self.megabytes = self.MB = self / self._kB**2
        self.gigabytes = self.GB = self / self._kB**3
        self.petabytes = self.PB = self / self._kB**4
        *suffixes, last = self._suffixes
        suffix = next((
            suffix
            for suffix in suffixes
            if 1 < getattr(self, suffix) < self._kB
        ), last)
        self.readable = suffix, getattr(self, suffix)

        super().__init__()

    def __str__(self):
        return self.__format__('.2f')

    def __repr__(self):
        return '{}({})'.format(self.__class__.__name__, super().__repr__())

    def __format__(self, format_spec):
        suffix, val = self.readable
        return '{val:{fmt}} {suf}'.format(val=val, fmt=format_spec, suf=suffix)

    def __sub__(self, other):
        return self.__class__(super().__sub__(other))

    def __add__(self, other):
        return self.__class__(super().__add__(other))
    
    def __mul__(self, other):
        return self.__class__(super().__mul__(other))

    def __rsub__(self, other):
        return self.__class__(super().__sub__(other))

    def __radd__(self, other):
        return self.__class__(super().__add__(other))
    
    def __rmul__(self, other):
        return self.__class__(super().__rmul__(other))   

Usage:

>>> size = get_folder_size("c:/users/tdavis/downloads")
>>> print(size)
5.81 GB
>>> size.GB
5.810891855508089
>>> size.gigabytes
5.810891855508089
>>> size.PB
0.005674699077644618
>>> size.MB
5950.353260040283
>>> size
ByteSize(6239397620)

I also came across this question, which has some more compact and probably more performant strategies for printing file sizes.

for python3.5+

from pathlib import Path

def get_size(folder: str) -> int:
    return sum(p.stat().st_size for p in Path(folder).rglob('*'))

Usage::

In [6]: get_size('/etc/not-exist-path')
Out[6]: 0
In [7]: get_size('.')
Out[7]: 12038689
In [8]: def filesize(size: int) -> str:
   ...:     for unit in ("B", "K", "M", "G", "T"):
   ...:         if size < 1024:
   ...:             break
   ...:         size /= 1024
   ...:     return f"{size:.1f}{unit}"
   ...:

In [9]: filesize(get_size('.'))
Out[9]: '11.5M'

Get directory size

Properties of the solution:

  • returns both: the apparent size (number of bytes in the file) and the actual disk space the files uses.
  • counts hard linked files only once
  • counts symlinks the same way du does
  • does not use recursion
  • uses st.st_blocks for disk space used, thus works only on Unix-like systems

The code:

import os


def du(path):
    if os.path.islink(path):
        return (os.lstat(path).st_size, 0)
    if os.path.isfile(path):
        st = os.lstat(path)
        return (st.st_size, st.st_blocks * 512)
    apparent_total_bytes = 0
    total_bytes = 0
    have = []
    for dirpath, dirnames, filenames in os.walk(path):
        apparent_total_bytes += os.lstat(dirpath).st_size
        total_bytes += os.lstat(dirpath).st_blocks * 512
        for f in filenames:
            fp = os.path.join(dirpath, f)
            if os.path.islink(fp):
                apparent_total_bytes += os.lstat(fp).st_size
                continue
            st = os.lstat(fp)
            if st.st_ino in have:
                continue  # skip hardlinks which were already counted
            have.append(st.st_ino)
            apparent_total_bytes += st.st_size
            total_bytes += st.st_blocks * 512
        for d in dirnames:
            dp = os.path.join(dirpath, d)
            if os.path.islink(dp):
                apparent_total_bytes += os.lstat(dp).st_size
    return (apparent_total_bytes, total_bytes)

Example usage:

>>> du('/lib')
(236425839, 244363264)

$ du -sb /lib
236425839   /lib
$ du -sB1 /lib
244363264   /lib

Human readable file size

Properties of the solution:

The code:

def humanized_size(num, suffix='B', si=False):
    if si:
        units = ['','K','M','G','T','P','E','Z']
        last_unit = 'Y'
        div = 1000.0
    else:
        units = ['','Ki','Mi','Gi','Ti','Pi','Ei','Zi']
        last_unit = 'Yi'
        div = 1024.0
    for unit in units:
        if abs(num) < div:
            return "%3.1f%s%s" % (num, unit, suffix)
        num /= div
    return "%.1f%s%s" % (num, last_unit, suffix)

Example usage:

>>> humanized_size(236425839)
'225.5MiB'
>>> humanized_size(236425839, si=True)
'236.4MB'
>>> humanized_size(236425839, si=True, suffix='')
'236.4M'

It is handy:

import os
import stat

size = 0
path_ = ""
def calculate(path=os.environ["SYSTEMROOT"]):
    global size, path_
    size = 0
    path_ = path

    for x, y, z in os.walk(path):
        for i in z:
            size += os.path.getsize(x + os.sep + i)

def cevir(x):
    global path_
    print(path_, x, "Byte")
    print(path_, x/1024, "Kilobyte")
    print(path_, x/1048576, "Megabyte")
    print(path_, x/1073741824, "Gigabyte")

calculate("C:\Users\Jundullah\Desktop")
cevir(size)

Output:
C:\Users\Jundullah\Desktop 87874712211 Byte
C:\Users\Jundullah\Desktop 85815148.64355469 Kilobyte
C:\Users\Jundullah\Desktop 83803.85609722137 Megabyte
C:\Users\Jundullah\Desktop 81.83970321994275 Gigabyte

Here is a one liner that does it recursively (recursive option available as of Python 3.5):

import os
import glob
print(sum(os.path.getsize(f) for f in glob.glob('**', recursive=True) if os.path.isfile(f))/(1024*1024))
def recursive_dir_size(path):
    size = 0

    for x in os.listdir(path):
        if not os.path.isdir(os.path.join(path,x)):
            size += os.stat(os.path.join(path,x)).st_size
        else:
            size += recursive_dir_size(os.path.join(path,x))

    return size

I wrote this function which gives me accurate overall size of a directory, i tried other for loop solutions with os.walk but i don't know why the end result was always less than the actual size (on ubuntu 18 env). I must have done something wrong but who cares wrote this one works perfectly fine.

A solution that works on Python 3.6 using pathlib.

from pathlib import Path

sum([f.stat().st_size for f in Path("path").glob("**/*")])

Python 3.6+ recursive folder/file size using os.scandir. As powerful as in the answer by @blakev, but shorter and in EAFP python style.

import os

def size(path, *, follow_symlinks=False):
    try:
        with os.scandir(path) as it:
            return sum(size(entry, follow_symlinks=follow_symlinks) for entry in it)
    except NotADirectoryError:
        return os.stat(path, follow_symlinks=follow_symlinks).st_size

du does not follow symlinks by default. No answer here make use of follow_symlinks=False.

Here is an implementation which follows default behavior of du:

def du(path) -> int:
    total = 0
    for entry in os.scandir(path):
        if entry.is_file(follow_symlinks=False):
            total += entry.stat().st_size
        elif entry.is_dir(follow_symlinks=False):
            total += du(entry.path)
    return total

Test:

class Test(unittest.TestCase):
    def test_du(self):
        root = '/tmp/du_test'
        subprocess.run(['rm', '-rf', root])
        test_utils.mkdir(root)
        test_utils.create_file(root, 'A', '1M')
        test_utils.create_file(root, 'B', '1M')
        sub = '/'.join([root, 'sub'])
        test_utils.mkdir(sub)
        test_utils.create_file(sub, 'C', '1M')
        test_utils.create_file(sub, 'D', '1M')
        subprocess.run(['ln', '-s', '/tmp', '/'.join([root, 'link']), ])
        self.assertEqual(4 << 20, util.du(root))
import os
def get_size(path = os.getcwd()):
    print("Calculating Size: ",path)
    total_size = 0
    #if path is directory--
    if os.path.isdir(path):
      print("Path type : Directory/Folder")
      for dirpath, dirnames, filenames in os.walk(path):
          for f in filenames:
              fp = os.path.join(dirpath, f)
              # skip if it is symbolic link
              if not os.path.islink(fp):
                  total_size += os.path.getsize(fp)
    #if path is a file---
    elif os.path.isfile(path):
      print("Path type : File")
      total_size=os.path.getsize(path)
    else:
      print("Path Type : Special File (Socket, FIFO, Device File)" )
      total_size=0
    bytesize=total_size
    print(bytesize, 'bytes')
    print(bytesize/(1024), 'kilobytes')
    print(bytesize/(1024*1024), 'megabytes')
    print(bytesize/(1024*1024*1024), 'gegabytes')
    return total_size


x=get_size("/content/examples")

I'm sure this helps! For folders and files as well!

If you are in Windows OS you can do:

install the module pywin32 by launching:

pip install pywin32

and then coding the following:

import win32com.client as com

def get_folder_size(path):
   try:
       fso = com.Dispatch("Scripting.FileSystemObject")
       folder = fso.GetFolder(path)
       size = str(round(folder.Size / 1048576))
       print("Size: " + size + " MB")
   except Exception as e:
       print("Error --> " + str(e))
Related