Use fnmatch.filter to filter files by more than one possible file extension

Question

Given the following piece of python code:

for root, dirs, files in os.walk(directory):
    for filename in fnmatch.filter(files, \'*.png\'):
        pass
         


        

Answer 1

If you only need to check extensions (i.e. no further wildcards), why don't you simply use basic string operations?

for root, dirs, files in os.walk(directory):
    for filename in files:
        if filename.endswith(('.jpg', '.jpeg', '.gif', '.png')):
            pass

Answer 2

This isn't really elegant either, but it works:

for root, dirs, files in os.walk(directory):
    for filename in fnmatch.filter(files, '*.png') + fnmatch.filter(files, '*.jpg') + fnmatch.filter(files, '*.jpeg') + fnmatch.filter(files, '*.gif'):
        pass

Answer 3

Here is what I am using to filter files in apache log directories. Here I exclude errors flles

rep_filters = [now.strftime("%Y%m%d")]
def files_filter(liste_fic, filters = rep_filters):
    s = "(fic for fic in liste_fic if fic.find('error') < 0"
    for filter in filters:
        s += " and fic.find('%s') >=0 " % filter
    s += ")"
    return eval(s)

Answer 4

Please try this:

# pattern_list = ['*.jpg', '__.*']
def checkFilepatter(filename, pattern_list):
    for pattern in pattern_list:
        if fnmatch.fnmatch(filename, pattern):
            return True
    return False

Answer 5

I think your code is actually fine. If you want to touch every filename only once, define your own filtering function:

def is_image_file(filename, extensions=['.jpg', '.jpeg', '.gif', '.png']):
    return any(filename.endswith(e) for e in extensions)

for root, dirs, files in os.walk(directory):
    for filename in filter(is_image_file, files):
        pass

Answer 6

I've been using this with a lot of success.

import fnmatch
import functools
import itertools
import os

# Remove the annotations if you're not on Python3
def find_files(dir_path: str=None, patterns: [str]=None) -> [str]:
    """
    Returns a generator yielding files matching the given patterns
    :type dir_path: str
    :type patterns: [str]
    :rtype : [str]
    :param dir_path: Directory to search for files/directories under. Defaults to current dir.
    :param patterns: Patterns of files to search for. Defaults to ["*"]. Example: ["*.json", "*.xml"]
    """
    path = dir_path or "."
    path_patterns = patterns or ["*"]

    for root_dir, dir_names, file_names in os.walk(path):
        filter_partial = functools.partial(fnmatch.filter, file_names)

        for file_name in itertools.chain(*map(filter_partial, path_patterns)):
            yield os.path.join(root_dir, file_name)

Examples:

for f in find_files(test_directory):
    print(f)

yields:

.\test.json
.\test.xml
.\test.ini
.\test_helpers.py
.\__init__.py

Testing with multiple patterns:

for f in find_files(test_directory, ["*.xml", "*.json", "*.ini"]):
    print(f)

yields:

.\test.json
.\test.xml
.\test.ini