Filtering os.walk() dirs and files

Question

I'm looking for a way to include/exclude files patterns and exclude directories from a os.walk() call.

Here's what I'm doing by now:

import fnmatch import os  includes = ['*.doc', '*.odt'] excludes = ['/home/paulo-freitas/Documents']  def _filter(paths):     for path in paths:         if os.path.isdir(path) and not path in excludes:             yield path          for pattern in (includes + excludes):             if not os.path.isdir(path) and fnmatch.fnmatch(path, pattern):                 yield path  for root, dirs, files in os.walk('/home/paulo-freitas'):     dirs[:] = _filter(map(lambda d: os.path.join(root, d), dirs))     files[:] = _filter(map(lambda f: os.path.join(root, f), files))      for filename in files:         filename = os.path.join(root, filename)          print(filename) 

Is there a better way to do this? How?

Answer 1

This solution uses fnmatch.translate to convert glob patterns to regular expressions (it assumes the includes only is used for files):

import fnmatch import os import os.path import re  includes = ['*.doc', '*.odt'] # for files only excludes = ['/home/paulo-freitas/Documents'] # for dirs and files  # transform glob patterns to regular expressions includes = r'|'.join([fnmatch.translate(x) for x in includes]) excludes = r'|'.join([fnmatch.translate(x) for x in excludes]) or r'$.'  for root, dirs, files in os.walk('/home/paulo-freitas'):      # exclude dirs     dirs[:] = [os.path.join(root, d) for d in dirs]     dirs[:] = [d for d in dirs if not re.match(excludes, d)]      # exclude/include files     files = [os.path.join(root, f) for f in files]     files = [f for f in files if not re.match(excludes, f)]     files = [f for f in files if re.match(includes, f)]      for fname in files:         print fname