How do i search directories and find files that match regex?

import os
import re

rootdir = "/mnt/externa/Torrents/completed"
regex = re.compile('(.*zip$)|(.*rar$)|(.*r01$)')

for root, dirs, files in os.walk(rootdir):
  for file in files:
    if regex.match(file):
       print(file)

CODE BELLOW ANSWERS QUESTION IN FOLLOWING COMMENT

That worked really well, is there a way to do this if match is found on regex group 1 and do this if match is found on regex group 2 etc ? – nillenilsson

import os
import re

regex = re.compile('(.*zip$)|(.*rar$)|(.*r01$)')
rx = '(.*zip$)|(.*rar$)|(.*r01$)'

for root, dirs, files in os.walk("../Documents"):
  for file in files:
    res = re.match(rx, file)
    if res:
      if res.group(1):
        print("ZIP",file)
      if res.group(2):
        print("RAR",file)
      if res.group(3):
        print("R01",file)

It might be possible to do this in a nicer way, but this works.


Here's an alternative using glob.

from pathlib import Path

rootdir = "/mnt/externa/Torrents/completed"
for extension in 'zip rar r01'.split():
    for path in Path(rootdir).glob('*.' + extension):
        print("match: " + path)

Given that you are a beginner, I would recommend using glob in place of a quickly written file-walking-regex matcher.

Snippets of functions using glob and a file-walking-regex matcher

The below snippet contains two file-regex searching functions (one using glob and the other using a custom file-walking-regex matcher). The snippet also contains a "stopwatch" function to time the two functions.

import os
import sys
from datetime import timedelta
from timeit import time
import os
import re
import glob

def stopwatch(method):
    def timed(*args, **kw):
        ts = time.perf_counter()
        result = method(*args, **kw)
        te = time.perf_counter()
        duration = timedelta(seconds=te - ts)
        print(f"{method.__name__}: {duration}")
        return result
    return timed

@stopwatch
def get_filepaths_with_oswalk(root_path: str, file_regex: str):
    files_paths = []
    pattern = re.compile(file_regex)
    for root, directories, files in os.walk(root_path):
        for file in files:
            if pattern.match(file):
                files_paths.append(os.path.join(root, file))
    return files_paths


@stopwatch
def get_filepaths_with_glob(root_path: str, file_regex: str):
    return glob.glob(os.path.join(root_path, file_regex))

Comparing runtimes of the above functions

On using the above two functions to find 5076 files matching the regex filename_*.csv in a dir called root_path (containing 66,948 files):

>>> glob_files = get_filepaths_with_glob(root_path, 'filename_*.csv')
get_filepaths_with_glob: 0:00:00.176400

>>> oswalk_files = get_filepaths_with_oswalk(root_path,'filename_(.*).csv')
get_filepaths_with_oswalk: 0:03:29.385379

The glob method is much faster and the code for it is shorter.

For your case

For your case, you can probably use something like the following to get your *.zip,*.rar and *.r01 files:

files = []
for ext in ['*.zip', '*.rar', '*.r01']:
    files += get_filepaths_with_glob(root_path, ext) 

I would do it this way:

import re
from pathlib import Path

def glob_re(path, regex="", glob_mask="**/*", inverse=False):
    p = Path(path)
    if inverse:
        res = [str(f) for f in p.glob(glob_mask) if not re.search(regex, str(f))]
    else:
        res = [str(f) for f in p.glob(glob_mask) if re.search(regex, str(f))]
    return res

NOTE: per default it will recursively scan all subdirectories. If you want to scan only the current directory then you should explicitly specify glob_mask="*"