glob exclude pattern

Compared with glob, I recommend pathlib. Filtering one pattern is very simple.

from pathlib import Path

p = Path(YOUR_PATH)
filtered = [x for x in p.glob("**/*") if not x.name.startswith("eph")]

And if you want to filter a more complex pattern, you can define a function to do that, just like:

def not_in_pattern(x):
    return (not x.name.startswith("eph")) and not x.name.startswith("epi")


filtered = [x for x in p.glob("**/*") if not_in_pattern(x)]

Using that code, you can filter all files that start with eph or start with epi.

How about skipping the particular file while iterating over all the files in the folder! Below code would skip all excel files that start with 'eph'

import glob
import re
for file in glob.glob('*.xlsx'):
    if re.match('eph.*\.xlsx',file):
        continue
    else:
        #do your stuff here
        print(file)

This way you can use more complex regex patterns to include/exclude a particular set of files in a folder.

Suppose you have this directory structure:

.
├── asd3442
├── eee2314
├── eph334
├── eph_dir
│   ├── asd330
│   ├── eph_file2
│   ├── exy123
│   └── file_with_eph
├── eph_file
├── not_eph_dir
│   ├── ephXXX
│   └── with_eph
└── not_eph_rest

You can use full globs to filter full path results with pathlib and a generator for the top level directory:

i_want=(fn for fn in Path(path_to).glob('*') if not fn.match('**/*/eph*'))

>>> list(i_want)
[PosixPath('/tmp/test/eee2314'), PosixPath('/tmp/test/asd3442'), PosixPath('/tmp/test/not_eph_rest'), PosixPath('/tmp/test/not_eph_dir')]

The pathlib method match uses globs to match a path object; The glob '**/*/eph*' is any full path that leads to a file with a name starting with 'eph'.

Alternatively, you can use the .name attribute with name.startswith('eph'):

i_want=(fn for fn in Path(path_to).glob('*') if not fn.name.startswith('eph'))

If you want only files, no directories:

i_want=(fn for fn in Path(path_to).glob('*') if fn.is_file() and not fn.match('**/*/eph*'))
# [PosixPath('/tmp/test/eee2314'), PosixPath('/tmp/test/asd3442'), PosixPath('/tmp/test/not_eph_rest')]
 

The same method works for recursive globs:

i_want=(fn for fn in Path(path_to).glob('**/*') 
           if fn.is_file() and not fn.match('**/*/eph*'))

# [PosixPath('/tmp/test/eee2314'), PosixPath('/tmp/test/asd3442'), 
   PosixPath('/tmp/test/not_eph_rest'), PosixPath('/tmp/test/eph_dir/asd330'), 
   PosixPath('/tmp/test/eph_dir/file_with_eph'), PosixPath('/tmp/test/eph_dir/exy123'), 
   PosixPath('/tmp/test/not_eph_dir/with_eph')]

If the position of the character isn't important, that is for example to exclude manifests files (wherever it is found _) with glob and re - regular expression operations, you can use:

import glob
import re
for file in glob.glob('*.txt'):
    if re.match(r'.*\_.*', file):
        continue
    else:
        print(file)

Or with in a more elegant way - list comprehension

filtered = [f for f in glob.glob('*.txt') if not re.match(r'.*\_.*', f)]

for mach in filtered:
    print(mach)

To exclude exact word you may want to implement custom regex directive, which you will then replace by empty string before glob processing.

#!/usr/bin/env python3
import glob
import re

# glob (or fnmatch) does not support exact word matching. This is custom directive to overcome this issue
glob_exact_match_regex = r"\[\^.*\]"
path = "[^exclude.py]*py"  # [^...] is a custom directive, that excludes exact match

# Process custom directive
try:  # Try to parse exact match direction
    exact_match = re.findall(glob_exact_match_regex, path)[0].replace('[^', '').replace(']', '')
except IndexError:
    exact_match = None
else:  # Remove custom directive
    path = re.sub(glob_exact_match_regex, "", path)
paths = glob.glob(path)
# Implement custom directive
if exact_match is not None:  # Exclude all paths with specified string
    paths = [p for p in paths if exact_match not in p]

print(paths)

import glob
import re

""" This is a path that should be excluded """
EXCLUDE = "/home/koosha/Documents/Excel"

files = glob.glob("/home/koosha/Documents/**/*.*" , recursive=True)
for file in files:
     if re.search(EXCLUDE,file):
         pass
    else:
         print(file)