Get a word list from local man file

get_word_list.py

import re
import gzip


def get_word_list(f, pattern=None):
    pattern = pattern if pattern else r'[a-zA-Z0-9-_]+'
    l = re.findall(pattern, gzip.decompress(open(f, 'rb').read()).decode('utf-8'))
    return list(set(l))

# Example
# get_word_list('/usr/share/man/man1/git.1.gz', r'[a-zA-Z0-9-_]+')