coalmine2.py

coalmine2.py

#!/usr/bin/python3
import re
import zipfile
import argparse
from urllib.parse import urlparse

from colorama import Fore, Style, init

init()

# Use sets for simplicity and readability
ignore_list = {
    'purl.org',
    'microsoft.com',
    'openxmlformats.org',
    'w3.org',
}

alert_list = {
    'internalcanarytokendomain.org',
    'canarytokens.com',
}

url_pattern = re.compile("(https?:\/\/[\w.-]+[\/\w .-]*)")

def parse_args():
    ap = argparse.ArgumentParser()
    ap.add_argument("--input", "-i", required=True, help="Input file")
    return ap.parse_args()

def url_in_list(url, lst):
    return any(urlparse(url).hostname.endswith(domain) for domain in lst)

def extract_urls_from_file(file):
    matches = []
    for line in file:
        matches.extend(url_pattern.findall(line.decode('utf-8')))
    return matches

def filter_urls(matches, ignore_list):
    return [match for match in matches if not url_in_list(match, ignore_list)]

def print_colored_urls(matches, alert_list):
    for match in matches:
        foreground_color = Fore.RED if url_in_list(match, alert_list) else Fore.YELLOW
        print(f"{foreground_color}{match}{Style.RESET_ALL}")

def main():
    args = parse_args()

    with zipfile.ZipFile(args.input) as doc:
        matches = []

        for i in doc.filelist:
            with doc.open(i.filename) as
            with doc.open(i.filename) as file:
                matches.extend(extract_urls_from_file(file))

        matches = filter_urls(matches, ignore_list)
        print_colored_urls(matches, alert_list)

if __name__ == "__main__":
    main()