[Tutor] recursive glob -- recursive dir walk

spir denis.spir at free.fr
Wed Jun 10 08:28:35 CEST 2009


Hello,

A foolow-up ;-) from previous question about glob.glob().

I need to 'glob' files recursively from a top dir (parameter). Tried to use os.walk, but the structure of its return value is really unhandy for such a use (strange, because it seems to me this precise use is typical). On the other hand, os.path.walk seemed to meet my needs, but it is deprecated.

I'd like to know if there are standard tools to do that. And your comments on the 2 approaches below.

Thank you,
denis



-1- I first wrote the following recurseDirGlob() tool func.

========================================================
import os, glob

def dirGlob(dir, pattern):
	''' File names matching pattern in directory dir. '''
	fullPattern = os.path.join(dir,pattern)
	return glob.glob(fullPattern)

def recurseDirGlob(topdir=None, pattern="*.*", nest=False, verbose=False):
	'''  '''
	allFilenames = list()
	# current dir
	if verbose:
		print "*** %s" %topdir
	if topdir is None: topdir = os.getcwd()
	filenames = dirGlob(topdir, pattern)
	if verbose:
		for filename in [os.path.basename(d) for d in filenames]:
			print "   %s" %filename
	allFilenames.extend(filenames)
	# possible sub dirs
	names = [os.path.join(topdir, dir) for dir in os.listdir(topdir)]
	dirs = [n for n in names if os.path.isdir(n)]
	if verbose:
		print "--> %s" % [os.path.basename(d) for d in dirs]
	if len(dirs) > 0:
		for dir in dirs:
			filenames = recurseDirGlob(dir, pattern, nest, verbose)
			if nest:
				allFilenames.append(filenames)
			else:
				allFilenames.extend(filenames)
	# final result
	return allFilenames
========================================================

Example with the following dir structure ; the version with nest=True will recursively nest files from subdirs.

========================================================
d0
	d01
	d02
		d020
2 .txt files and 1 with a different pattern, in each dir

recurseDirGlob("/home/spir/prog/d0", "*.txt", verbose=True) -->
*** /home/spir/prog/d0
   t01.txt
   t02.txt
--> ['d01', 'd02']
*** /home/spir/prog/d0/d01
   t011.txt
   t012.txt
--> []
*** /home/spir/prog/d0/d02
   t021.txt
   t022.txt
--> ['d020']
*** /home/spir/prog/d0/d02/d020
   t0201.txt
   t0202.txt
--> []
['/home/spir/prog/d0/t01.txt', '/home/spir/prog/d0/t02.txt', '/home/spir/prog/d0/d01/t011.txt', '/home/spir/prog/d0/d01/t012.txt', '/home/spir/prog/d0/d02/t021.txt', '/home/spir/prog/d0/d02/t022.txt', '/home/spir/prog/d0/d02/d020/t0201.txt', '/home/spir/prog/d0/d02/d020/t0202.txt']

recurseDirGlob("/home/spir/prog/d0", "*.txt") -->
['/home/spir/prog/d0/t01.txt', '/home/spir/prog/d0/t02.txt', '/home/spir/prog/d0/d01/t011.txt', '/home/spir/prog/d0/d01/t012.txt', '/home/spir/prog/d0/d02/t021.txt', '/home/spir/prog/d0/d02/t022.txt', '/home/spir/prog/d0/d02/d020/t0201.txt', '/home/spir/prog/d0/d02/d020/t0202.txt']

recurseDirGlob("/home/spir/prog/d0", "*.txt", nest=True) -->
['/home/spir/prog/d0/t01.txt', '/home/spir/prog/d0/t02.txt', ['/home/spir/prog/d0/d01/t011.txt', '/home/spir/prog/d0/d01/t012.txt'], ['/home/spir/prog/d0/d02/t021.txt', '/home/spir/prog/d0/d02/t022.txt', ['/home/spir/prog/d0/d02/d020/t0201.txt', '/home/spir/prog/d0/d02/d020/t0202.txt']]]
========================================================



-2- Another approach was to build a general 'dirWalk' tool func, similar to os.path.walk:

========================================================
def dirWalk(topdir=None, func=None, args=[], nest=False, verbose=False):
	'''  '''
	allResults = list()
	# current dir
	if verbose:
		print "*** %s" %topdir
	if topdir is None: topdir = os.getcwd()
	results = func(topdir, *args)
	if verbose:
		print "    %s" % results
	allResults.extend(results)
	# possible sub dirs
	names = [os.path.join(topdir, dir) for dir in os.listdir(topdir)]
	dirs = [n for n in names if os.path.isdir(n)]
	if verbose:
		print "--> %s" % [os.path.basename(d) for d in dirs]
	if len(dirs) > 0:
		for dir in dirs:
			results = dirWalk(dir, func, args, nest, verbose)
			if nest:
				allResults.append(results)
			else:
				allResults.extend(results)
	# final allResults
	return allResults
========================================================

Example uses to bring the same results, calling dirGlob, would be:

dirWalk("/home/spir/prog/d0", dirGlob, args=["*.txt"], verbose=True) -->
dirWalk("/home/spir/prog/d0", dirGlob, args=["*.txt"])
dirWalk("/home/spir/prog/d0", dirGlob, args=["*.txt"], nest=True)

Denis
------
la vita e estrany


More information about the Tutor mailing list