extract words from subdomains to make a wordlist

words_from_subs.py

import re
import sys

def extract_subdomains(filename):
    subdomains = set()
    pattern = r"(?:https?://)?(?:www\.)?([^.]+\.[^.]+)"

    with open(filename, 'r') as file:
        for line in file:
            match = re.search(pattern, line)
            if match:
                domain = match.group(1)
                subdomain = domain.split('.')[0]
                subdomains.add(subdomain)

    return subdomains

filename = sys.argv[1] # first argument is the filename with domains
result = extract_subdomains(filename)
for line in result:
    print(line)