From mboxrd@z Thu Jan 1 00:00:00 1970 From: Peter =?utf-8?q?M=C3=BCller?= To: location@lists.ipfire.org Subject: [PATCH v2] location-importer.in: Import (technical) AS names from ARIN Date: Tue, 08 Jun 2021 17:03:07 +0000 Message-ID: <20210608170307.623-1-peter.mueller@ipfire.org> MIME-Version: 1.0 Content-Type: multipart/mixed; boundary="===============1561881940361202622==" List-Id: --===============1561881940361202622== Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: quoted-printable ARIN and LACNIC, unfortunately, do not seem to publish data containing human readable AS names. For the former, we at least have a list of tecnical names, which this patch fetches and inserts into the autnums table. While some of them do not seem to be suitable for human consumption (i. e. being very cryptic), providing these data might be helpful neverthelesss. The second version of this patch contains some additional remarks on efficient Python coding style from Michael, doing things more "pythonic". Signed-off-by: Peter M=C3=BCller --- src/python/location-importer.in | 55 +++++++++++++++++++++++++++++++++ 1 file changed, 55 insertions(+) diff --git a/src/python/location-importer.in b/src/python/location-importer.in index aa3b8f7..6ccee3b 100644 --- a/src/python/location-importer.in +++ b/src/python/location-importer.in @@ -505,6 +505,9 @@ class CLI(object): for line in f: self._parse_line(line, source_key, validcountries) =20 + # Download and import (technical) AS names from ARIN + self._import_as_names_from_arin() + def _check_parsed_network(self, network): """ Assistive function to detect and subsequently sort out parsed @@ -775,6 +778,58 @@ class CLI(object): "%s" % network, country, [country], source_key, ) =20 + def _import_as_names_from_arin(self): + downloader =3D location.importer.Downloader() + + # XXX: Download AS names file from ARIN (note that these names appear to b= e quite + # technical, not intended for human consumption, as description fields in + # organisation handles for other RIRs are - however, this is what we have = got, + # and in some cases, it might be still better than nothing) + with downloader.request("https://ftp.arin.net/info/asn.txt", return_blocks= =3DFalse) as f: + for line in f: + # Convert binary line to string... + line =3D str(line) + + # ... valid lines start with a space, followed by the number of the Auto= nomous System ... + if not line.startswith(" "): + continue + + # Split line and check if there is a valid ASN in it... + asn, name =3D line.split()[0:2] + + try: + asn =3D int(asn) + except ValueError: + log.debug("Skipping ARIN AS names line not containing an integer for AS= N") + continue + + if not ((1 <=3D asn and asn <=3D 23455) or (23457 <=3D asn and asn <=3D = 64495) or (131072 <=3D asn and asn <=3D 4199999999)): + log.debug("Skipping ARIN AS names line not containing a valid ASN: %s" = % asn) + continue + + # Skip any AS name that appears to be a placeholder for a different RIR = or entity... + if re.match(r"^(ASN-BLK|)(AFCONC|AFRINIC|APNIC|ASNBLK|DNIC|LACNIC|RIPE|I= ANA)(\d?$|\-.*)", name): + continue + + # Bail out in case the AS name contains anything we do not expect here... + if re.search(r"[^a-zA-Z0-9-_]", name): + log.debug("Skipping ARIN AS name for %s containing invalid characters: = %s" % \ + (asn, name)) + + # Things look good here, run INSERT statement and skip this one if we al= ready have + # a (better?) name for this Autonomous System... + self.db.execute(""" + INSERT INTO autnums( + number, + name, + source + ) VALUES (%s, %s, %s) + ON CONFLICT (number) DO NOTHING""", + asn, + name, + "ARIN", + ) + def handle_update_announcements(self, ns): server =3D ns.server[0] =20 --=20 2.20.1 --===============1561881940361202622==--