From 8ad57f9a5e4e42350aa6515ccf1c0d088c2f3126 Mon Sep 17 00:00:00 2001 From: acidvegas Date: Sat, 30 Nov 2024 02:29:08 -0500 Subject: [PATCH] removed typings import --- ingestors/ingest_firehol.py | 5 +- ingestors/ingest_masscan.py | 6 +- ingestors/ingest_rir_whois.py | 153 ++++++++++++++++++++++++++++++++++ 3 files changed, 156 insertions(+), 8 deletions(-) create mode 100644 ingestors/ingest_rir_whois.py diff --git a/ingestors/ingest_firehol.py b/ingestors/ingest_firehol.py index a4c1635..58aa1a7 100644 --- a/ingestors/ingest_firehol.py +++ b/ingestors/ingest_firehol.py @@ -5,7 +5,6 @@ import ipaddress import logging import time -from typing import Dict, List, Set try: import aiohttp @@ -45,7 +44,7 @@ def construct_map() -> dict: return mapping -async def fetch_ipset(session: aiohttp.ClientSession, ipset_name: str) -> Dict: +async def fetch_ipset(session: aiohttp.ClientSession, ipset_name: str) -> dict: ''' Fetch and parse a Firehol ipset. @@ -114,7 +113,7 @@ async def fetch_ipset(session: aiohttp.ClientSession, ipset_name: str) -> Dict: return None -async def get_all_ipsets(session: aiohttp.ClientSession) -> List[str]: +async def get_all_ipsets(session: aiohttp.ClientSession) -> list: ''' Fetch list of all available ipsets from the Firehol repository. diff --git a/ingestors/ingest_masscan.py b/ingestors/ingest_masscan.py index 05f6f7c..a8e1810 100644 --- a/ingestors/ingest_masscan.py +++ b/ingestors/ingest_masscan.py @@ -13,7 +13,7 @@ except ImportError: # Set a default elasticsearch index if one is not provided -default_index = 'masscan-logs' +default_index = 'eris-masscan' def construct_map() -> dict: @@ -75,11 +75,7 @@ async def process_data(input_path: str): try: record = json.loads(line) except json.decoder.JSONDecodeError: - # In rare cases, the JSON record may be incomplete or malformed: - # { "ip": "51.161.12.223", "timestamp": "1707628302", "ports": [ {"port": 22, "proto": "tcp", "service": {"name": "ssh", "banner": - # { "ip": "83.66.211.246", "timestamp": "1706557002" logging.error(f'Failed to parse JSON record! ({line})') - input('Press Enter to continue...') # Pause for review & debugging (remove this in production) continue # Process the record diff --git a/ingestors/ingest_rir_whois.py b/ingestors/ingest_rir_whois.py new file mode 100644 index 0000000..f709f55 --- /dev/null +++ b/ingestors/ingest_rir_whois.py @@ -0,0 +1,153 @@ +#/usr/bin/env python +# opengeoip - developed by acidvegas in python (https://git.acid.vegas/opengeoip) +# whois.py + +''' +Source: https://ftp.[afrinic|apnic|arin|lacnic|ripe].net/ + others +Notes : The databases are updated daily. + Check out the whois2json.py script for converting the whois data into JSON objects for elasticsearch. + Each database has a CURRENTSERIAL file that contains the serial number of the latest version of the database. + Need to find a smart way to unify the approach for each RIR to account for their differences. + Do we need ripe-nonauth.db.gz? | https://ftp.ripe.net/ripe/dbase/ + Do we need twnic, krnic, jpnic? | https://ftp.apnic.net/apnic/dbase/data/ + Do we need the IRR databases? | https://www.irr.net/docs/list.html + Do we need the LACNIC IRR database? | https://ftp.lacnic.net/lacnic/irr/ +''' + +import os +import sys + +try: + import utils +except ImportError: + raise SystemError('utils.py module not found!') + +REGISTRY_DATA = { + 'AFRINIC' : 'ftp.afrinic.net/dbase/afrinic.db.gz', + 'APNIC' : ['ftp.apnic.net/apnic/whois/apnic.db.as-block.gz', # APNIC really has to be "special" snowflake... + 'ftp.apnic.net/apnic/whois/apnic.db.as-set.gz', + 'ftp.apnic.net/apnic/whois/apnic.db.aut-num.gz', + 'ftp.apnic.net/apnic/whois/apnic.db.domain.gz', + 'ftp.apnic.net/apnic/whois/apnic.db.filter-set.gz', + 'ftp.apnic.net/apnic/whois/apnic.db.inet-rtr.gz', + 'ftp.apnic.net/apnic/whois/apnic.db.inet6num.gz', + 'ftp.apnic.net/apnic/whois/apnic.db.inetnum.gz', + 'ftp.apnic.net/apnic/whois/apnic.db.irt.gz', + 'ftp.apnic.net/apnic/whois/apnic.db.key-cert.gz', + 'ftp.apnic.net/apnic/whois/apnic.db.limerick.gz', # Little easteregg, not updated since 2017... + 'ftp.apnic.net/apnic/whois/apnic.db.mntner.gz', + 'ftp.apnic.net/apnic/whois/apnic.db.organisation.gz', + 'ftp.apnic.net/apnic/whois/apnic.db.peering-set.gz', + 'ftp.apnic.net/apnic/whois/apnic.db.role.gz', + 'ftp.apnic.net/apnic/whois/apnic.db.route-set.gz', + 'ftp.apnic.net/apnic/whois/apnic.db.route.gz', + 'ftp.apnic.net/apnic/whois/apnic.db.route6.gz', + 'ftp.apnic.net/apnic/whois/apnic.db.rtr-set.gz'], + 'JPNIC' : 'ftp.apnic.net/apnic/dbase/data/jpnic.db.gz', # JPNIC is APNIC but is a NIR + 'KRNIC' : 'ftp.apnic.net/apnic/dbase/data/krnic.db.gz', # KRNIC is APNIC but is a NIR + 'TWINIC' : 'ftp.apnic.net/apnic/dbase/data/twnic.db.gz', # TWINIC is APNIC but is a NIR + 'ARIN' : 'ftp.arin.net/pub/rr/arin.db.gz', + 'LACNIC' : ['ftp.lacnic.net/lacnic/dbase/lacnic.db.gz', # LACNIC has a dbase and an IRR + 'ftp.lacnic.net/lacnic/irr/lacnic.db.gz'], + 'RIPE' : ['ftp.ripe.net/ripe/dbase/ripe.db.gz', # RIPE has a dbase and a non-auth dbase + 'ftp.ripe.net/ripe/dbase/ripe-nonauth.db.gz'] +} + +IRR_DATA = { + 'ALTDB' : 'ftp.altdb.net/pub/altdb/altdb.db.gz', + 'BELL' : 'whois.in.bell.ca/bell.db.gz', + 'CANARIE' : 'ftp.radb.net/radb/dbase/canarie.db.gz', + 'HOST' : 'ftp.radb.net/radb/dbase/host.db.gz', + 'IDNIC' : 'irr-mirror.idnic.net/idnic.db.gz', + 'JPIRR' : 'ftp.nic.ad.jp/jpirr/jpirr.db.gz', + 'LACNIC' : 'ftp.lacnic.net/lacnic/irr/lacnic.db.gz', # Name conflict... + 'LEVEL3' : 'rr.Level3.net/level3.db.gz', + 'NESTEGG' : 'ftp.nestegg.net/irr/nestegg.db.gz', + 'NTTCOM' : 'rr1.ntt.net/nttcomRR/nttcom.db.gz', + 'OPENFACE' : 'ftp.radb.net/radb/dbase/openface.db.gz', + 'PANIX' : 'ftp.panix.com/pub/rrdb/panix.db.gz', + 'RADB' : 'ftp.radb.net/radb/dbase/radb.db.gz', + 'REACH' : 'ftp.radb.net/radb/dbase/reach.db.gz', + 'RGNET' : 'ftp.radb.net/radb/dbase/rgnet.db.gz', + 'TC' : 'ftp.bgp.net.br/tc.db.gz' +} + + +def check_serial(local_serial_path: str, ftp_serial_url: str) -> bool: + ''' + Check the CURRENTSERIAL file for an update. + + :param local_path: The path to the local CURRENTSERIAL file + :param ftp_path: The path to the remote CURRENTSERIAL file + ''' + + if not os.path.exists(local_serial_path): + return True + + else: + with open(local_serial_path) as serial_file: + old_serial = serial_file.read().strip() + new_serial = utils.read_ftp(ftp_serial_url) + if old_serial != new_serial: + return True + else: + return False + + +def download_db(output_path: str, url: str): + ''' + Dowload a WHOIS database. + + :param output_path: The path to the output directory + :param url: The FTP URL of the database to download + ''' + + DB_PATH = os.path.join(output_path, url.split('/')[-1]) + utils.safe_remove(DB_PATH) + utils.safe_remove(DB_PATH[:-3]) + utils.download_ftp(url, DB_PATH) + utils.gunzip_extract(DB_PATH, DB_PATH[:-3]) + utils.safe_remove(DB_PATH) + + +def update_db(output_path: str): + ''' + Update the whois IRR databases. + + :param output_path: The path to the output directory + ''' + + os.makedirs(output_path, exist_ok=True) + + for RIR, DB_URL in REGISTRY_DATA.items(): + if RIR == 'APNIC': + for url in DB_URL: + download_db(output_path, url) + else: + download_db(output_path, DB_URL) + for IRR, DB_URL in REGISTRY_DATA.items(): + download_db(output_path+'/irr', DB_URL) + + # For now, we'll just download the files and not check the serials for updates APNIC will need to be handled differently...seperate function? + ''' + SERIAL_PATH = os.path.join(output_path, REGISTRY+'.CURRENTSERIAL') + FTP_SERIAL = os.path.join('/'.join(DB_URL.split('/')[:-1]), REGISTRY + '.CURRENTSERIAL') + + if check_serial(SERIAL_PATH, FTP_SERIAL): + logging.debug(f'A new version of the {REGISTRY} whois database is available! Downloading...') + for item in (DB_PATH, DB_PATH[:-3], SERIAL_PATH): + utils.safe_remove(item) # Remove old files + utils.download_ftp(DB_URL, DB_PATH) + utils.download_ftp(FTP_SERIAL, SERIAL_PATH) + utils.gunzip_extract(DB_PATH, DB_PATH[:-3]) + logging.debug(f'The {REGISTRY} whois database has been updated!') + else: + logging.info(f'The {REGISTRY} whois database is up-to-date') + ''' + + +if __name__ == '__main__': + utils.print_header('WHOIS Module') + utils.setup_logger('whois') + utils.setup_user_agent() + update_db('database/whois') \ No newline at end of file