Calculating a directory's size using Python?

Question

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.

Answer 1

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) if os.path.isfile(f) else 0 for f in glob.glob('**', recursive=True))/(1024*1024))

Answer 2

import os

def get_size(path):
    total_size = 0
    for dirpath, dirnames, filenames in os.walk(path):
        for f in filenames:
            if os.path.exists(fp):
                fp = os.path.join(dirpath, f)
                total_size += os.path.getsize(fp)

    return total_size   # in megabytes

Thanks monkut & troex! This works really good!

Answer 3

for getting the size of one file, there is os.path.getsize()

>>> import os
>>> os.path.getsize("/path/file")
35L

its reported in bytes.

Answer 4

When size of the sub-directories is computed, it should update its parent's folder size and this will go on till it reaches the root parent.

The following function computes the size of the folder and all its sub-folders.

import os

def folder_size(path):
    parent = {}  # path to parent path mapper
    folder_size = {}  # storing the size of directories
    folder = os.path.realpath(path)

    for root, _, filenames in os.walk(folder):
        if root == folder:
            parent[root] = -1  # the root folder will not have any parent
            folder_size[root] = 0.0  # intializing the size to 0

        elif root not in parent:
            immediate_parent_path = os.path.dirname(root)  # extract the immediate parent of the subdirectory
            parent[root] = immediate_parent_path  # store the parent of the subdirectory
            folder_size[root] = 0.0  # initialize the size to 0

        total_size = 0
        for filename in filenames:
            filepath = os.path.join(root, filename)
            total_size += os.stat(filepath).st_size  # computing the size of the files under the directory
        folder_size[root] = total_size  # store the updated size

        temp_path = root  # for subdirectories, we need to update the size of the parent till the root parent
        while parent[temp_path] != -1:
            folder_size[parent[temp_path]] += total_size
            temp_path = parent[temp_path]

    return folder_size[folder]/1000000.0

Answer 5

For what it's worth... the tree command does all of this for free:

tree -h --du /path/to/dir  # files and dirs
tree -h -d --du /path/to/dir  # dirs only

I love Python, but by far the simplest solution to the problem requires no new code.

Answer 6

The following script prints directory size of all sub-directories for the specified directory. It also tries to benefit (if possible) from caching the calls of a recursive functions. If an argument is omitted, the script will work in the current directory. The output is sorted by the directory size from biggest to smallest ones. So you can adapt it for your needs.

PS i've used recipe 578019 for showing directory size in human-friendly format (http://code.activestate.com/recipes/578019/)

from __future__ import print_function
import os
import sys
import operator

def null_decorator(ob):
    return ob

if sys.version_info >= (3,2,0):
    import functools
    my_cache_decorator = functools.lru_cache(maxsize=4096)
else:
    my_cache_decorator = null_decorator

start_dir = os.path.normpath(os.path.abspath(sys.argv[1])) if len(sys.argv) > 1 else '.'

@my_cache_decorator
def get_dir_size(start_path = '.'):
    total_size = 0
    if 'scandir' in dir(os):
        # using fast 'os.scandir' method (new in version 3.5)
        for entry in os.scandir(start_path):
            if entry.is_dir(follow_symlinks = False):
                total_size += get_dir_size(entry.path)
            elif entry.is_file(follow_symlinks = False):
                total_size += entry.stat().st_size
    else:
        # using slow, but compatible 'os.listdir' method
        for entry in os.listdir(start_path):
            full_path = os.path.abspath(os.path.join(start_path, entry))
            if os.path.isdir(full_path):
                total_size += get_dir_size(full_path)
            elif os.path.isfile(full_path):
                total_size += os.path.getsize(full_path)
    return total_size

def get_dir_size_walk(start_path = '.'):
    total_size = 0
    for dirpath, dirnames, filenames in os.walk(start_path):
        for f in filenames:
            fp = os.path.join(dirpath, f)
            total_size += os.path.getsize(fp)
    return total_size

def bytes2human(n, format='%(value).0f%(symbol)s', symbols='customary'):
    """
    (c) http://code.activestate.com/recipes/578019/

    Convert n bytes into a human readable string based on format.
    symbols can be either "customary", "customary_ext", "iec" or "iec_ext",
    see: http://goo.gl/kTQMs

      >>> bytes2human(0)
      '0.0 B'
      >>> bytes2human(0.9)
      '0.0 B'
      >>> bytes2human(1)
      '1.0 B'
      >>> bytes2human(1.9)
      '1.0 B'
      >>> bytes2human(1024)
      '1.0 K'
      >>> bytes2human(1048576)
      '1.0 M'
      >>> bytes2human(1099511627776127398123789121)
      '909.5 Y'

      >>> bytes2human(9856, symbols="customary")
      '9.6 K'
      >>> bytes2human(9856, symbols="customary_ext")
      '9.6 kilo'
      >>> bytes2human(9856, symbols="iec")
      '9.6 Ki'
      >>> bytes2human(9856, symbols="iec_ext")
      '9.6 kibi'

      >>> bytes2human(10000, "%(value).1f %(symbol)s/sec")
      '9.8 K/sec'

      >>> # precision can be adjusted by playing with %f operator
      >>> bytes2human(10000, format="%(value).5f %(symbol)s")
      '9.76562 K'
    """
    SYMBOLS = {
        'customary'     : ('B', 'K', 'M', 'G', 'T', 'P', 'E', 'Z', 'Y'),
        'customary_ext' : ('byte', 'kilo', 'mega', 'giga', 'tera', 'peta', 'exa',
                           'zetta', 'iotta'),
        'iec'           : ('Bi', 'Ki', 'Mi', 'Gi', 'Ti', 'Pi', 'Ei', 'Zi', 'Yi'),
        'iec_ext'       : ('byte', 'kibi', 'mebi', 'gibi', 'tebi', 'pebi', 'exbi',
                           'zebi', 'yobi'),
    }
    n = int(n)
    if n < 0:
        raise ValueError("n < 0")
    symbols = SYMBOLS[symbols]
    prefix = {}
    for i, s in enumerate(symbols[1:]):
        prefix[s] = 1 << (i+1)*10
    for symbol in reversed(symbols[1:]):
        if n >= prefix[symbol]:
            value = float(n) / prefix[symbol]
            return format % locals()
    return format % dict(symbol=symbols[0], value=n)

############################################################
###
###  main ()
###
############################################################
if __name__ == '__main__':
    dir_tree = {}
    ### version, that uses 'slow' [os.walk method]
    #get_size = get_dir_size_walk
    ### this recursive version can benefit from caching the function calls (functools.lru_cache)
    get_size = get_dir_size

    for root, dirs, files in os.walk(start_dir):
        for d in dirs:
            dir_path = os.path.join(root, d)
            if os.path.isdir(dir_path):
                dir_tree[dir_path] = get_size(dir_path)

    for d, size in sorted(dir_tree.items(), key=operator.itemgetter(1), reverse=True):
        print('%s\t%s' %(bytes2human(size, format='%(value).2f%(symbol)s'), d))

    print('-' * 80)
    if sys.version_info >= (3,2,0):
        print(get_dir_size.cache_info())

Sample output:

37.61M  .\subdir_b
2.18M   .\subdir_a
2.17M   .\subdir_a\subdir_a_2
4.41K   .\subdir_a\subdir_a_1
----------------------------------------------------------
CacheInfo(hits=2, misses=4, maxsize=4096, currsize=4)

EDIT: moved null_decorator above, as user2233949 recommended