Glob¶

import glob
import sys

print('Creating directory structures and files for experimentation purpose.')
%mkdir folder_l1_1
%mkdir folder_l1_2
%mkdir folder_l1_1/folder_l2

!touch temp.txt temp.jpg temp.png a.png b.jpg c.txt d.txt t1.png t2.jpg .temp.png .temp.jpg
!touch folder_l1_1/t.txt folder_l1_1/t2.png folder_l1_1/a.mp4 folder_l1_1/b.mp4 folder_l1_1/c.mpeg folder_l1_1/t3.jpg
!touch folder_l1_2/t2.txt folder_l1_2/t1.png folder_l1_2/b.mp4 folder_l1_2/c.mp4 folder_l1_2/d.mpeg
!touch folder_l1_1/folder_l2/t.txt folder_l1_1/folder_l2/t2.png folder_l1_1/folder_l2/a.mp4

print('\nCurrent directory contents : ')
%ls
print('\nfolder_l1_1 directory contents : ')
%ls folder_l1_1
print('\nfolder_l1_2 directory contents :')
%ls folder_l1_2
print('\nfolder_l1_1/folder_l2 directory contents : ')
%ls folder_l1_1/folder_l2

print(glob.glob('*.txt'))
print(glob.glob('*.png'))
print(glob.glob('*.jpg'))
print(glob.glob('*.*g'))
print(glob.glob('.*'))
print(glob.glob('.*.png'))
print(glob.glob('.*.*g'))
print(glob.glob('[a-z]*.txt'))
print(glob.glob('[a-z]+.txt')) ## This does not work. Only *,? and [] works.

print(glob.glob('[a-z][0-9].*'))
print(glob.glob('t[0-9].*'))
print(glob.glob('[a-z][0-9].*'))
print(glob.glob('[a-z][0-9].*g'))

print(glob.glob('*/*.txt'))
print(glob.glob('*/*/*.txt'))
print(glob.glob('*/*.png'))
print(glob.glob('*/*.*g'))
print(glob.glob('folder_l1_1/*.png'))
print(glob.glob('folder_l1_1/folder_l2/*.*'))
print(glob.glob('folder_l1_2/*'))

print(glob.glob('**/*.txt',recursive=True))
print(glob.glob('**/*.png',recursive=True))
print(glob.glob('**/*.*g',recursive=True))
print(glob.glob('**/*[0-9].txt',recursive=True))
print(glob.glob('*/*/*.txt',recursive=True))
print(glob.glob('*/*/[a-z].txt',recursive=True))

%time normal_dir_list = glob.glob('**/*.*g',recursive=True) ## this one takes more time and memory because it keeps all matching paths in memory after generating.
%time iterator_dir_list = glob.iglob('**/*.*g',recursive=True) ## This takes quite less time as it just generates iterator but does create whole list in memory. Generates element base on call to retrieve element from iterator.
print('Size of list : %d bytes'%sys.getsizeof(normal_dir_list))
print('Size of iterator : %d bytes'%sys.getsizeof(iterator_dir_list))

!touch temp?tea.txt
print(glob.escape('temp?tea.txt'))
print(glob.glob(glob.escape('temp?tea.txt')))