How to remove all empty files within folder and its sub folders? - python

I am trying to remove all empty files in a folder, and there are folders within the folder so it needs to check inside those folders too:
e.g
remove all empty files within C:\folder1\folder1 and C:\folder1\folder2 etc

import sys
import os
def main():
getemptyfiles(sys.argv[1])
def getemptyfiles(rootdir):
for root, dirs, files in os.walk(rootdir):
for d in ['RECYCLER', 'RECYCLED']:
if d in dirs:
dirs.remove(d)
for f in files:
fullname = os.path.join(root, f)
try:
if os.path.getsize(fullname) == 0:
print fullname
os.remove(fullname)
except WindowsError:
continue
This will work with a bit of adjusting:
The os.remove() statement could fail so you might want to wrap it with try...except as well. WindowsError is platform specific. Filtering the traversed directories is not strictly necessary but helpful.

The for loop uses dir to find all files, but not directories, in the current directory and all subfolders recursively. Then the second line checks to see if the length of each file is less than 1 byte before deleting it.
cd /d C:\folder1
for /F "usebackq" %%A in (`dir/b/s/a-d`) do (
if %%~zA LSS 1 del %%A
)

import os
while(True):
path = input("Enter the path")
if(os.path.isdir(path)):
break
else:
print("Entered path is wrong!")
for root,dirs,files in os.walk(path):
for name in files:
filename = os.path.join(root,name)
if os.stat(filename).st_size == 0:
print(" Removing ",filename)
os.remove(filename)

I do first remove empty files, afterwards by following this answer (https://stackoverflow.com/a/6215421/2402577), I have removed the empty folders.
In addition, I added topdown=False in os.walk() to walk from leaf to roo since the default behavior of os.walk() is to walk from root to leaf.
So empty folders that also contains empty folders or files are removed as well.
import os
def remove_empty_files_and_folders(dir_path) -> None:
for root, dirnames, files in os.walk(dir_path, topdown=False):
for f in files:
full_name = os.path.join(root, f)
if os.path.getsize(full_name) == 0:
os.remove(full_name)
for dirname in dirnames:
full_path = os.path.realpath(os.path.join(root, dirname))
if not os.listdir(full_path):
os.rmdir(full_path)

I hope this can help you
#encoding = utf-8
import os
docName = []
def listDoc(path):
docList = os.listdir(path)
for doc in docList:
docPath = os.path.join(path,doc)
if os.path.isfile(docPath):
if os.path.getsize(docPath)==o:
os.remove(docPath)
if os.path.isdir(docPath):
listDoc(docPath)
listDoc(r'C:\folder1')

Related

How to extract sub-folder path?

I have about 100 folders and in each folder files that should be read and analyzed.
I can read the files from their subfolders, but I want to start processing at e.g. the 10th folder until the end. And I need the exact folder path.
How can I do this?
To clarify my question, I extracted a sample from my code:
rootDir = 'D:/PhD/result/Pyradiomic_input/'
for (path, subdirs, files) in os.walk(rootDir):
sizefile=len(path)
if "TCGA-" in path :
print(path)
The output is:
D:/PhD/result/Pyradiomic_input/TCGA-02-0006
D:/PhD/result/Pyradiomic_input/TCGA-02-0009
D:/PhD/result/Pyradiomic_input/TCGA-02-0011
D:/PhD/result/Pyradiomic_input/TCGA-02-0027
D:/PhD/result/Pyradiomic_input/TCGA-02-0046
D:/PhD/result/Pyradiomic_input/TCGA-02-0069
Now my question is how can I start working from e.g. D:/PhD/result/Pyradiomic_input/TCGA-02-0046 until the end, instead of starting from the top? I tried some ideas but they did not work.
You could set a flag to capture when you hit a specific directory
rootDir = 'D:/PhD/result/Pyradiomic_input/'
first_folder = 'TCGA-02-0046'
process = False
for (path, subdirs, files) in os.walk(rootDir):
sizefile=len(path)
if "TCGA-" in path :
print(path)
if first_folder in path:
process = True
if process:
#process folder
If you want a specific folder to indicate the script should stop processing
rootDir = 'D:/PhD/result/Pyradiomic_input/'
first_folder = 'TCGA-02-0046'
last_folder = 'TCGA-02-0099'
process = False
for (path, subdirs, files) in os.walk(rootDir):
sizefile=len(path)
if "TCGA-" in path :
print(path)
if first_folder in path:
process = True
if last_folder in path:
break
if process:
#process folder
You can also set a list of directories that you want to process
rootDir = 'D:/PhD/result/Pyradiomic_input/'
process_dirs = ['TCGA-02-0046', ...]
process = False
for (path, subdirs, files) in os.walk(rootDir):
sizefile=len(path)
if "TCGA-" in path :
print(path)
if any(d in path for d in process_dirs):
#process folder
You can simply skip the values you aren't interested in. Here a bit simplified:
counter = 0
# mocking the file operations
for path in ["/dir-1", "/dir-2", "/dir-3", "/dir-4", "/dir-5"]:
# skip the first two paths
if counter < 2:
counter += 1
continue
# do something
print(path)
Alternatively you could collect the paths first, like this:
paths = []
# mocking the file operations
for path in ["/dir-1", "/dir-2", "/dir-3", "/dir-4", "/dir-5"]:
# collect paths in array
paths.append(path)
# skip the first two elements
paths = paths[2:]
for path in paths:
# do something
print(path)
The second version can become a bit shorter if you use generator expressions, but I favor readability.

How can I get a specific folder with a specific folders sibling in python

I would like to find the path to specific folders that have only specific folders brothers
ex:
I want to find all folders named : zeFolder with siblings folders brotherOne and brotherTwo
|-dad1|---brotherOne|---brotherFour|---zeFolder (not match)
|-dad2|---brotherOne|---brotherTwo|---zeFolder (♥♥♥Match♥♥♥)
[...]
Below is my code, but with this solution I find all the folders.
import os
for root, dirs, files in os.walk("/"):
#print (dirs)
for name in dirs:
if name == 'totolo':
print ('finded')
print(os.path.join(root, name))
I don't know how to use Conditional Statements to do that
Thanks for you help.
Basically it sounds like you want to find a specific set of subfolders so using sets is both natural and makes this a fairly easy thing to do. Their use also removes order dependencies when checking for equality.
import os
start_path = '/'
target = 'zeFolder'
siblings = ['brotherOne', 'brotherTwo']
sought = set([target] + siblings)
for root, dirs, files in os.walk(start_path):
if sought == set(dirs):
print('found')
What about using lists
import os
folder = 'zeFolder'
brothers = ['brotherOne', 'brotherTwo']
for dirpath, dirnames, filenames in os.walk('/'):
if folder in dirnames and all(brother in dirnames for brother in brothers):
print 'matches on %s' % os.path.join(dirpath, 'zeFolder')
or sets
import os
folder = 'zeFolder'
brothers = set(['brotherOne', 'brotherTwo', folder])
for dirpath, dirnames, filenames in os.walk('/'):
if set(dirnames).issuperset(brothers) :
print 'matches on %s' % os.path.join(dirpath, 'zeFolder')
Both run at same speed for me.
import os
import glob
filelist = glob.glob(r"dad1/*brotherOne")
for f in filelist:
print(f)
filelist = glob.glob(r"dad1/*brotherTwo")
for f in filelist:
print(f)
You could also try the glob technique. And do whatever action you'd like to in the for loop.

How to stop os.walk from walking all sub-directories down?

Using:
def simpleFunc(dirName):
import os
fileList=[]
for dir, dirs, filenames in os.walk(dirName):
for filename in filenames:
filepath=dir+'/'+filename
fileList.append(filepath)
print fileList
simpleFunc(os.path.dirname('/entire/path/to/file.ext'))
The problem is that os.walk just doesn't stop at /entire/path/to/ directory level but goes all the way down to the lowest sub-directory it can find. So if there is /entire/path/to/subdir1/subdir2/subdir3 then in additional to /entire/path/to/ all three sub-directories will be searched: ./subdir1/, ././subdir2/, ./././subdir3/.
Question: how to make sure the function stops at the directory level specified: /entire/path/to/ and doesn't go all the way down?
Based on what you've written, if you just want to search the specified directory. It might be better to use os.listdir and then just filter on os.path.isfile, e.g., like this:
def simple_func(dirpath):
paths = os.listdir(dirpath)
# create absolute paths
abs_paths = [os.path.join(dirpath, p) for p in paths]
# filter for paths that are files
file_list = [p for p in paths if os.path.isfile(p)]
return file_list
That way you don't have to deal with stopping the recursion and it's pretty clear which files you want. You might want to profile to see whether the multiple isfile calls hurt anything.
from os import listdir
from os.path import isfile, join
path='/entire/path/to/'
files = [ join(path,f) for f in listdir(path) if isfile(join(path,f)) ]
files return ur files. no need to declare new filelist
Sounds like you should use os.listdir instead.
import os
my_path = '/entire/path/to/files/'
file_list = []
for filename in os.listdir(my_path):
filepath = os.path.join(my_path, filename)
if os.path.isfile(filepath):
fileList.append(filepath)
You need to take the only first item from the os.walk generator:
import os
root, _, files = next(os.walk('/entire/path/to'))
and then append root dir to each filename:
files = map(lambda f: os.path.join(root, f), files)
or just:
files = [os.path.join(root, f) for f in files]
You can tell os.walk which directory to use explicitly
def simpleFunc(dirName):
import os
# set the dir name in a var
dirName = '/higher_lever_dir/'
for dir, dirs, filenames in os.walk(dirName):
# this line forces loop to look ONLY in the specified dir
dirs[:] = [d for d in dirs if d in dirName]
for filename in filenames:
filepath=dir+'/'+filename
fileList.append(filepath)
print fileList
simpleFunc(os.path.dirname('/entire/path/to/file.ext'))
Setting dirs[:] = [d for d in dirs if d in dirName] will exclude files in subdirectories that may exist in /higher_level_dir/

Python recursive folder read

I have a C++/Obj-C background and I am just discovering Python (been writing it for about an hour).
I am writing a script to recursively read the contents of text files in a folder structure.
The problem I have is the code I have written will only work for one folder deep. I can see why in the code (see #hardcoded path), I just don't know how I can move forward with Python since my experience with it is only brand new.
Python Code:
import os
import sys
rootdir = sys.argv[1]
for root, subFolders, files in os.walk(rootdir):
for folder in subFolders:
outfileName = rootdir + "/" + folder + "/py-outfile.txt" # hardcoded path
folderOut = open( outfileName, 'w' )
print "outfileName is " + outfileName
for file in files:
filePath = rootdir + '/' + file
f = open( filePath, 'r' )
toWrite = f.read()
print "Writing '" + toWrite + "' to" + filePath
folderOut.write( toWrite )
f.close()
folderOut.close()
Make sure you understand the three return values of os.walk:
for root, subdirs, files in os.walk(rootdir):
has the following meaning:
root: Current path which is "walked through"
subdirs: Files in root of type directory
files: Files in root (not in subdirs) of type other than directory
And please use os.path.join instead of concatenating with a slash! Your problem is filePath = rootdir + '/' + file - you must concatenate the currently "walked" folder instead of the topmost folder. So that must be filePath = os.path.join(root, file). BTW "file" is a builtin, so you don't normally use it as variable name.
Another problem are your loops, which should be like this, for example:
import os
import sys
walk_dir = sys.argv[1]
print('walk_dir = ' + walk_dir)
# If your current working directory may change during script execution, it's recommended to
# immediately convert program arguments to an absolute path. Then the variable root below will
# be an absolute path as well. Example:
# walk_dir = os.path.abspath(walk_dir)
print('walk_dir (absolute) = ' + os.path.abspath(walk_dir))
for root, subdirs, files in os.walk(walk_dir):
print('--\nroot = ' + root)
list_file_path = os.path.join(root, 'my-directory-list.txt')
print('list_file_path = ' + list_file_path)
with open(list_file_path, 'wb') as list_file:
for subdir in subdirs:
print('\t- subdirectory ' + subdir)
for filename in files:
file_path = os.path.join(root, filename)
print('\t- file %s (full path: %s)' % (filename, file_path))
with open(file_path, 'rb') as f:
f_content = f.read()
list_file.write(('The file %s contains:\n' % filename).encode('utf-8'))
list_file.write(f_content)
list_file.write(b'\n')
If you didn't know, the with statement for files is a shorthand:
with open('filename', 'rb') as f:
dosomething()
# is effectively the same as
f = open('filename', 'rb')
try:
dosomething()
finally:
f.close()
If you are using Python 3.5 or above, you can get this done in 1 line.
import glob
# root_dir needs a trailing slash (i.e. /root/dir/)
for filename in glob.iglob(root_dir + '**/*.txt', recursive=True):
print(filename)
As mentioned in the documentation
If recursive is true, the pattern '**' will match any files and zero or more directories and subdirectories.
If you want every file, you can use
import glob
for filename in glob.iglob(root_dir + '**/**', recursive=True):
print(filename)
Agree with Dave Webb, os.walk will yield an item for each directory in the tree. Fact is, you just don't have to care about subFolders.
Code like this should work:
import os
import sys
rootdir = sys.argv[1]
for folder, subs, files in os.walk(rootdir):
with open(os.path.join(folder, 'python-outfile.txt'), 'w') as dest:
for filename in files:
with open(os.path.join(folder, filename), 'r') as src:
dest.write(src.read())
TL;DR: This is the equivalent to find -type f to go over all files in all folders below and including the current one:
for currentpath, folders, files in os.walk('.'):
for file in files:
print(os.path.join(currentpath, file))
As already mentioned in other answers, os.walk() is the answer, but it could be explained better. It's quite simple! Let's walk through this tree:
docs/
└── doc1.odt
pics/
todo.txt
With this code:
for currentpath, folders, files in os.walk('.'):
print(currentpath)
The currentpath is the current folder it is looking at. This will output:
.
./docs
./pics
So it loops three times, because there are three folders: the current one, docs, and pics. In every loop, it fills the variables folders and files with all folders and files. Let's show them:
for currentpath, folders, files in os.walk('.'):
print(currentpath, folders, files)
This shows us:
# currentpath folders files
. ['pics', 'docs'] ['todo.txt']
./pics [] []
./docs [] ['doc1.odt']
So in the first line, we see that we are in folder ., that it contains two folders namely pics and docs, and that there is one file, namely todo.txt. You don't have to do anything to recurse into those folders, because as you see, it recurses automatically and just gives you the files in any subfolders. And any subfolders of that (though we don't have those in the example).
If you just want to loop through all files, the equivalent of find -type f, you can do this:
for currentpath, folders, files in os.walk('.'):
for file in files:
print(os.path.join(currentpath, file))
This outputs:
./todo.txt
./docs/doc1.odt
The pathlib library is really great for working with files. You can do a recursive glob on a Path object like so.
from pathlib import Path
for elem in Path('/path/to/my/files').rglob('*.*'):
print(elem)
import glob
import os
root_dir = <root_dir_here>
for filename in glob.iglob(root_dir + '**/**', recursive=True):
if os.path.isfile(filename):
with open(filename,'r') as file:
print(file.read())
**/** is used to get all files recursively including directory.
if os.path.isfile(filename) is used to check if filename variable is file or directory, if it is file then we can read that file.
Here I am printing file.
If you want a flat list of all paths under a given dir (like find . in the shell):
files = [
os.path.join(parent, name)
for (parent, subdirs, files) in os.walk(YOUR_DIRECTORY)
for name in files + subdirs
]
To only include full paths to files under the base dir, leave out + subdirs.
I've found the following to be the easiest
from glob import glob
import os
files = [f for f in glob('rootdir/**', recursive=True) if os.path.isfile(f)]
Using glob('some/path/**', recursive=True) gets all files, but also includes directory names. Adding the if os.path.isfile(f) condition filters this list to existing files only
For my taste os.walk() is a little too complicated and verbose. You can do the accepted answer cleaner by:
all_files = [str(f) for f in pathlib.Path(dir_path).glob("**/*") if f.is_file()]
with open(outfile, 'wb') as fout:
for f in all_files:
with open(f, 'rb') as fin:
fout.write(fin.read())
fout.write(b'\n')
use os.path.join() to construct your paths - It's neater:
import os
import sys
rootdir = sys.argv[1]
for root, subFolders, files in os.walk(rootdir):
for folder in subFolders:
outfileName = os.path.join(root,folder,"py-outfile.txt")
folderOut = open( outfileName, 'w' )
print "outfileName is " + outfileName
for file in files:
filePath = os.path.join(root,file)
toWrite = open( filePath).read()
print "Writing '" + toWrite + "' to" + filePath
folderOut.write( toWrite )
folderOut.close()
os.walk does recursive walk by default. For each dir, starting from root it yields a 3-tuple (dirpath, dirnames, filenames)
from os import walk
from os.path import splitext, join
def select_files(root, files):
"""
simple logic here to filter out interesting files
.py files in this example
"""
selected_files = []
for file in files:
#do concatenation here to get full path
full_path = join(root, file)
ext = splitext(file)[1]
if ext == ".py":
selected_files.append(full_path)
return selected_files
def build_recursive_dir_tree(path):
"""
path - where to begin folder scan
"""
selected_files = []
for root, dirs, files in walk(path):
selected_files += select_files(root, files)
return selected_files
I think the problem is that you're not processing the output of os.walk correctly.
Firstly, change:
filePath = rootdir + '/' + file
to:
filePath = root + '/' + file
rootdir is your fixed starting directory; root is a directory returned by os.walk.
Secondly, you don't need to indent your file processing loop, as it makes no sense to run this for each subdirectory. You'll get root set to each subdirectory. You don't need to process the subdirectories by hand unless you want to do something with the directories themselves.
Try this:
import os
import sys
for root, subdirs, files in os.walk(path):
for file in os.listdir(root):
filePath = os.path.join(root, file)
if os.path.isdir(filePath):
pass
else:
f = open (filePath, 'r')
# Do Stuff
If you prefer an (almost) Oneliner:
from pathlib import Path
lookuppath = '.' #use your path
filelist = [str(item) for item in Path(lookuppath).glob("**/*") if Path(item).is_file()]
In this case you will get a list with just the paths of all files located recursively under lookuppath.
Without str() you will get PosixPath() added to each path.
This worked for me:
import glob
root_dir = "C:\\Users\\Scott\\" # Don't forget trailing (last) slashes
for filename in glob.iglob(root_dir + '**/*.jpg', recursive=True):
print(filename)
# do stuff
If just the file names are not enough, it's easy to implement a Depth-first search on top of os.scandir():
stack = ['.']
files = []
total_size = 0
while stack:
dirname = stack.pop()
with os.scandir(dirname) as it:
for e in it:
if e.is_dir():
stack.append(e.path)
else:
size = e.stat().st_size
files.append((e.path, size))
total_size += size
The docs have this to say:
The scandir() function returns directory entries along with file attribute information, giving better performance for many common use cases.

os.walk without digging into directories below

How do I limit os.walk to only return files in the directory I provide it?
def _dir_list(self, dir_name, whitelist):
outputList = []
for root, dirs, files in os.walk(dir_name):
for f in files:
if os.path.splitext(f)[1] in whitelist:
outputList.append(os.path.join(root, f))
else:
self._email_to_("ignore")
return outputList
Don't use os.walk.
Example:
import os
root = "C:\\"
for item in os.listdir(root):
if os.path.isfile(os.path.join(root, item)):
print item
Use the walklevel function.
import os
def walklevel(some_dir, level=1):
some_dir = some_dir.rstrip(os.path.sep)
assert os.path.isdir(some_dir)
num_sep = some_dir.count(os.path.sep)
for root, dirs, files in os.walk(some_dir):
yield root, dirs, files
num_sep_this = root.count(os.path.sep)
if num_sep + level <= num_sep_this:
del dirs[:]
It works just like os.walk, but you can pass it a level parameter that indicates how deep the recursion will go.
I think the solution is actually very simple.
use
break
to only do first iteration of the for loop, there must be a more elegant way.
for root, dirs, files in os.walk(dir_name):
for f in files:
...
...
break
...
The first time you call os.walk, it returns tulips for the current directory, then on next loop the contents of the next directory.
Take original script and just add a break.
def _dir_list(self, dir_name, whitelist):
outputList = []
for root, dirs, files in os.walk(dir_name):
for f in files:
if os.path.splitext(f)[1] in whitelist:
outputList.append(os.path.join(root, f))
else:
self._email_to_("ignore")
break
return outputList
The suggestion to use listdir is a good one. The direct answer to your question in Python 2 is root, dirs, files = os.walk(dir_name).next().
The equivalent Python 3 syntax is root, dirs, files = next(os.walk(dir_name))
You could use os.listdir() which returns a list of names (for both files and directories) in a given directory. If you need to distinguish between files and directories, call os.stat() on each name.
If you have more complex requirements than just the top directory (eg ignore VCS dirs etc), you can also modify the list of directories to prevent os.walk recursing through them.
ie:
def _dir_list(self, dir_name, whitelist):
outputList = []
for root, dirs, files in os.walk(dir_name):
dirs[:] = [d for d in dirs if is_good(d)]
for f in files:
do_stuff()
Note - be careful to mutate the list, rather than just rebind it. Obviously os.walk doesn't know about the external rebinding.
for path, dirs, files in os.walk('.'):
print path, dirs, files
del dirs[:] # go only one level deep
Felt like throwing my 2 pence in.
baselevel = len(rootdir.split(os.path.sep))
for subdirs, dirs, files in os.walk(rootdir):
curlevel = len(subdirs.split(os.path.sep))
if curlevel <= baselevel + 1:
[do stuff]
The same idea with listdir, but shorter:
[f for f in os.listdir(root_dir) if os.path.isfile(os.path.join(root_dir, f))]
Since Python 3.5 you can use os.scandir instead of os.listdir. Instead of strings you get an iterator of DirEntry objects in return. From the docs:
Using scandir() instead of listdir() can significantly increase the performance of code that also needs file type or file attribute information, because DirEntry objects expose this information if the operating system provides it when scanning a directory. All DirEntry methods may perform a system call, but is_dir() and is_file() usually only require a system call for symbolic links; DirEntry.stat() always requires a system call on Unix but only requires one for symbolic links on Windows.
You can access the name of the object via DirEntry.name which is then equivalent to the output of os.listdir
You could also do the following:
for path, subdirs, files in os.walk(dir_name):
for name in files:
if path == ".": #this will filter the files in the current directory
#code here
In Python 3, I was able to do this:
import os
dir = "/path/to/files/"
#List all files immediately under this folder:
print ( next( os.walk(dir) )[2] )
#List all folders immediately under this folder:
print ( next( os.walk(dir) )[1] )
root folder changes for every directory os.walk finds. I solver that checking if root == directory
def _dir_list(self, dir_name, whitelist):
outputList = []
for root, dirs, files in os.walk(dir_name):
if root == dir_name: #This only meet parent folder
for f in files:
if os.path.splitext(f)[1] in whitelist:
outputList.append(os.path.join(root, f))
else:
self._email_to_("ignore")
return outputList
import os
def listFiles(self, dir_name):
names = []
for root, directory, files in os.walk(dir_name):
if root == dir_name:
for name in files:
names.append(name)
return names
This is how I solved it
if recursive:
items = os.walk(target_directory)
else:
items = [next(os.walk(target_directory))]
...
There is a catch when using listdir. The os.path.isdir(identifier) must be an absolute path. To pick subdirectories you do:
for dirname in os.listdir(rootdir):
if os.path.isdir(os.path.join(rootdir, dirname)):
print("I got a subdirectory: %s" % dirname)
The alternative is to change to the directory to do the testing without the os.path.join().
You can use this snippet
for root, dirs, files in os.walk(directory):
if level > 0:
# do some stuff
else:
break
level-=1
create a list of excludes, use fnmatch to skip the directory structure and do the process
excludes= ['a\*\b', 'c\d\e']
for root, directories, files in os.walk('Start_Folder'):
if not any(fnmatch.fnmatch(nf_root, pattern) for pattern in excludes):
for root, directories, files in os.walk(nf_root):
....
do the process
....
same as for 'includes':
if **any**(fnmatch.fnmatch(nf_root, pattern) for pattern in **includes**):
Why not simply use a range and os.walk combined with the zip? Is not the best solution, but would work too.
For example like this:
# your part before
for count, (root, dirs, files) in zip(range(0, 1), os.walk(dir_name)):
# logic stuff
# your later part
Works for me on python 3.
Also: A break is simpler too btw. (Look at the answer from #Pieter)
A slight change to Alex's answer, but using __next__():
print(next(os.walk('d:/'))[2])
or
print(os.walk('d:/').__next__()[2])
with the [2] being the file in root, dirs, file mentioned in other answers
This is a nice python example
def walk_with_depth(root_path, depth):
if depth < 0:
for root, dirs, files in os.walk(root_path):
yield [root, dirs[:], files]
return
elif depth == 0:
return
base_depth = root_path.rstrip(os.path.sep).count(os.path.sep)
for root, dirs, files in os.walk(root_path):
yield [root, dirs[:], files]
cur_depth = root.count(os.path.sep)
if base_depth + depth <= cur_depth:
del dirs[:]

Categories

Resources