how could this be writtern better/simpler?

Question

so the goal is to find the folder in a directory tree that has the greatest number of files and the folder that uses the most disk space.

import os

path = 'C:\\animal'
highestsize = ''
mostfile = ''
totalsize = 0
totalfile = 0

for i in os.listdir(path):
    if not os.path.isfile(path + '\\' + i):
        count = 0
        count_file = 0

        for dirpath, subfolder, filenames in os.walk(path + '\\' + i):
            for file in filenames:
                count_file += 1
                count += os.path.getsize(os.path.join(dirpath, file))

        if count_file > totalfile:
            totalfile = count_file
            mostfile = i

        if count > totalsize:
            totalsize = count
            highestsize = i

print(highestsize, str(totalsize) + ' Byte')
print(mostfile + ' have the most files: ' + str(totalfile))

Answer 1

I setup a dummy folder with sub-folders and files as below.

### Root folder with 3 sub folders, each with some files.
# root/
#    sub1/
#    sub2/
#    sub3/

Now you can try this to get file counts and folder sizes -

path = '/Users/akshay/Desktop/root'

folder_file_counts = {r:len([r+'/'+files for files in f]) for r,d,f in os.walk(path)}
folder_sizes_bytes = {r:sum([os.stat(r+'/'+files).st_size for files in f]) for r,d,f in os.walk(path)}

print('File counts:', folder_file_counts)
print('Folder sizes:', folder_sizes_bytes)

File counts:
{'/Users/akshay/Desktop/root/sub1': 3,
 '/Users/akshay/Desktop/root/sub2': 3,
 '/Users/akshay/Desktop/root/sub3': 2}

Folder sizes:
{'/Users/akshay/Desktop/root/sub1': 956211,
 '/Users/akshay/Desktop/root/sub2': 643622,
 '/Users/akshay/Desktop/root/sub3': 324885}

Now you can get the max counts/files etc or any other operation you want to do on these dictionaries.

---

Here is a slightly more efficient code if you have way too many files and folders -

path = '/Users/akshay/Desktop/root'

folder_file_counts = []
folder_sizes_bytes = []

#Loop through the subfolders and files
filepaths = []
for r,d,f in os.walk(path):
    l = []
    s = []
    for fname in f:
        l.append(r+'/'+fname)
        s.append(os.stat(r+'/'+fname).st_size)
    folder_file_counts.append((r,len(l)))
    folder_sizes_bytes.append((r,sum(s)))
    
folder_file_counts = dict(folder_file_counts)
folder_sizes_bytes = dict(folder_sizes_bytes)

print('File counts:', folder_file_counts)
print('Folder sizes:', folder_sizes_bytes)