Created
July 9, 2020 10:28
-
-
Save aufzayed/191c1e9c82a903e171f812d2ef450ba4 to your computer and use it in GitHub Desktop.
python script to organize big list of subdomains
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env python3 | |
import re, sys, json | |
# usage: dorg.py subdomains_list.txt domain_name | |
# python3 dorg.py example_com_subs.txt example.com | |
file_path = sys.argv[1] | |
domain = sys.argv[2] | |
pattern = '[a-zA-Z0-9\-]+\.' + domain.replace('.', '\.') | |
def extract(file_path, pattern): | |
domains = [] | |
fdomains = set() | |
with open(file_path) as dlist: | |
for dom in dlist: | |
domains.append(dom.split('\n')[0]) | |
for dom in domains: | |
rx = re.findall(pattern, dom) | |
try: | |
fdomains.add(rx[0]) | |
except IndexError: | |
pass | |
return domains, sorted(fdomains) | |
def organize(data): | |
domains = data[0] | |
fdomains = data[1] | |
out = {} | |
for d in fdomains: | |
out[d] = [] | |
for dom in domains: | |
if re.search(pattern, dom): | |
out[re.findall(pattern, dom)[0]].append(dom) | |
return json.dumps(out) | |
print(organize(extract(file_path, pattern))) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment