The snippets, or one liners that are used so little that you always forget them, but they are just super handy!
You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

54 lines
1.9 KiB

#!/usr/bin/env python2
import argparse
import re
import string
import random
import gzip
# borrowed from
def id_generator(size=6, chars=string.ascii_lowercase + string.digits):
return ''.join(random.choice(chars) for _ in range(size))
if __name__ == "__main__":
argparser = argparse.ArgumentParser(description="Any Logfile Anonymiser, Replaces regex with uniq random characters")
argparser.add_argument("-f", "--source-file", action="store", required="true", help="Input File")
argparser.add_argument("-d", "--destination-file", action="store", required="true", help="Anonymised data output")
argparser.add_argument("-r", "--replace-regex", action="store", required="true", help="Regex of source to replace")
argparser.add_argument("-z", "--gzip", action="store_true", help="")
args = argparser.parse_args()
if args.gzip:
print("Opening as GZIP")
source =, "r")
destination =, "w")
print("Opening as normal")
source = open(args.source_file, "r")
destination = open(args.destination_file, "w")
replacements = {}
for line in source:
line = str(line)
split = re.findall('{}'.format(args.replace_regex), line)
if len(split) == 1:
split = split[0]
# print(split)
if split:
# "line" contains our pattern, and split contains
if split in replacements:
replace = replacements[split]
replace = id_generator(len(split))
replace = "/{}".format(replace[1:])
replacements[split] = replace
newline = line.replace(split, replace)
newline = line