What is the Python way to walk a directory tree?

Question

I feel that assigning files, and folders and doing the += [item] part is a bit hackish. Any suggestions? I\'m using Python 3.2

from os import *
from os.pat         


        

Answer 1

For anyone looking for a solution using pathlib (python >= 3.4)

from pathlib import Path

def walk(path): 
    for p in Path(path).iterdir(): 
        if p.is_dir(): 
            yield from walk(p)
            continue
        yield p.resolve()

# recursively traverse all files from current directory
for p in walk(Path('.')): 
    print(p)

# the function returns a generator so if you need a list you need to build one
all_files = list(walk(Path('.'))) 

However, as mentioned above, this does not preserve the top-down ordering given by os.walk

Answer 2

os.walk and os.scandir are great options, however, I've been using pathlib more and more, and with pathlib you can use the .glob() method:

root_directory = Path(".")
for path_object in root_directory.glob('**/*'):
    if path_object.is_file():
        print(f"hi, I'm a file: {path_object}")
    elif path_object.is_dir():
        print(f"hi, I'm a dir: {path_object}")

Answer 3

def dir_contents(path):
    files,folders = [],[]
    for p in listdir(path):
        if isfile(p): files.append(p)
        else: folders.append(p)
    return files, folders

Answer 4

Since Python 3.4 there is new module pathlib. So to get all dirs and files one can do:

from pathlib import Path

dirs = [str(item) for item in Path(path).iterdir() if item.is_dir()]
files = [str(item) for item in Path(path).iterdir() if item.is_file()]

Answer 5

Instead of the built-in os.walk and os.path.walk, I use something derived from this piece of code I found suggested elsewhere which I had originally linked to but have replaced with inlined source:

import os
import stat

class DirectoryStatWalker:
    # a forward iterator that traverses a directory tree, and
    # returns the filename and additional file information

    def __init__(self, directory):
        self.stack = [directory]
        self.files = []
        self.index = 0

    def __getitem__(self, index):
        while 1:
            try:
                file = self.files[self.index]
                self.index = self.index + 1
            except IndexError:
                # pop next directory from stack
                self.directory = self.stack.pop()
                self.files = os.listdir(self.directory)
                self.index = 0
            else:
                # got a filename
                fullname = os.path.join(self.directory, file)
                st = os.stat(fullname)
                mode = st[stat.ST_MODE]
                if stat.S_ISDIR(mode) and not stat.S_ISLNK(mode):
                    self.stack.append(fullname)
                return fullname, st

if __name__ == '__main__':
    for file, st in DirectoryStatWalker("/usr/include"):
        print file, st[stat.ST_SIZE]

It walks the directories recursively and is quite efficient and easy to read.