Wordlist Script

#-----------------------------------------------------
#   Wordlist Adjustment
#
#   Description:
#       Removes items from a wordlist
#       Currently set to remove anything less than 8 characters to make the wordlist useful for WPA
#
#   Usage:
#       python wordlist.py file
#
#   Parameters:
#       File - the name of the wordlist
#
#   History:
#   Date        Author      Description
#   2021-12-02  A. Walker   Initial Creation
#   2021-12-07  A. Walker   Fixed Header (usage)
#-----------------------------------------------------

import sys, re

filename = sys.argv[1]
file = open(filename, 'r')

name_search = re.search(r"(^.+)\.(.*)", filename)

old_file_name = name_search.group(1)
file_format = name_search.group(2)

new_file_name = old_file_name + "_new" + "." + file_format
new_file = open(new_file_name, 'a')

total_records = 0
moved_records = 0

try:

    for line in file:

        total_records += 1
        match = re.search(r"(^.{8,25}$)", line)
        if match:
            moved_records += 1
            new_file.write(match.group(1))
            new_file.write("\n")
        else:
            pass

except (UnicodeDecodeError, UnicodeEncodeError):
    print("There was a Unicode problem. It did not affect script function.")

file.close()

print("The file", filename, "contained", total_records, "records,", moved_records, "of which were moved to", new_file_name)