bank-scraper.py

#!/usr/local/bin/python3

from tld import get_fld
from google import google
import fileinput
import re
import dns.resolver

print("bank,domain,dmarc_p,dmarc_ruf,dmarc_rua")

for bank in fileinput.input():
    bank = bank.replace("BK", "BANK")
    m = re.match("^([^/]+)", bank)
    if m:
        bank = m.group(1)

    if "BANK" not in bank:
        bank += " BANK"

    bank += " home page"

    r = google.search(bank, 1)

    if r and type(r) is list:
        domain = get_fld(r[0].link)
        dmarc = ""
        dmarc_fields = {}

        try:
            dmarc = dns.resolver.query("_dmarc.{}".format(domain), "TXT").response.answer[0][-1].strings[0]
            dmarc = re.findall('(\w+=[^;]+)', str(dmarc))
            for field in dmarc:
                k, v = field.split("=")
                dmarc_fields[k] = v
        except Exception as e:
            pass

        print(",".join(['"{}"'.format(x) for x in (bank, domain, dmarc_fields.get('p') or "", dmarc_fields.get('ruf') or "", dmarc_fields.get("rua") or "")]), flush=True)