AIL-framework/bin/Url.py

131 lines
4.6 KiB
Python
Raw Normal View History

#!/usr/bin/env python
# -*-coding:UTF-8 -*
2014-08-14 17:55:18 +02:00
import redis
import pprint
import time
2014-08-11 09:27:50 +02:00
import dns.exception
2014-08-14 17:55:18 +02:00
from packages import Paste
from packages import lib_refine
from pubsublogger import publisher
from pyfaup.faup import Faup
import re
# Country and ASN lookup
from cymru.ip2asn.dns import DNSClient as ip2asn
import socket
import pycountry
import ipaddress
from Helper import Process
2016-07-04 09:18:23 +02:00
# Used to prevent concat with empty fields due to url parsing
def avoidNone(str):
if str is None:
return ""
else:
return str
2014-08-20 15:14:57 +02:00
if __name__ == "__main__":
publisher.port = 6380
2014-08-20 15:14:57 +02:00
publisher.channel = "Script"
2014-08-14 17:55:18 +02:00
config_section = 'Web'
p = Process(config_section)
2014-08-20 15:14:57 +02:00
# REDIS #
r_serv2 = redis.StrictRedis(
host=p.config.get("Redis_Cache", "host"),
port=p.config.getint("Redis_Cache", "port"),
db=p.config.getint("Redis_Cache", "db"))
2014-08-14 17:55:18 +02:00
# Country to log as critical
2014-09-05 10:42:01 +02:00
cc_critical = p.config.get("Url", "cc_critical")
# FUNCTIONS #
publisher.info("Script URL subscribed to channel web_categ")
# FIXME For retro compatibility
channel = 'web_categ'
message = p.get_from_set()
prec_filename = None
faup = Faup()
url_regex = "(http|https|ftp)\://([a-zA-Z0-9\.\-]+(\:[a-zA-Z0-9\.&%\$\-]+)*@)*((25[0-5]|2[0-4][0-9]|[0-1]{1}[0-9]{2}|[1-9]{1}[0-9]{1}|[1-9])\.(25[0-5]|2[0-4][0-9]|[0-1]{1}[0-9]{2}|[1-9]{1}[0-9]{1}|[1-9]|0)\.(25[0-5]|2[0-4][0-9]|[0-1]{1}[0-9]{2}|[1-9]{1}[0-9]{1}|[1-9]|0)\.(25[0-5]|2[0-4][0-9]|[0-1]{1}[0-9]{2}|[1-9]{1}[0-9]{1}|[0-9])|localhost|([a-zA-Z0-9\-]+\.)*[a-zA-Z0-9\-]+\.(com|edu|gov|int|mil|net|org|biz|arpa|info|name|pro|aero|coop|museum|[a-zA-Z]{2}))(\:[0-9]+)*(/($|[a-zA-Z0-9\.\,\?\'\\\+&%\$#\=~_\-]+))*"
while True:
2014-09-04 11:46:07 +02:00
if message is not None:
2014-09-05 17:05:45 +02:00
filename, score = message.split()
2014-09-04 11:46:07 +02:00
if prec_filename is None or filename != prec_filename:
domains_list = []
PST = Paste.Paste(filename)
client = ip2asn()
for x in PST.get_regex(url_regex):
matching_url = re.search(url_regex, PST.get_p_content())
url = matching_url.group(0)
to_send = "{} {}".format(url, PST._get_p_date())
p.populate_set_out(to_send, 'Url')
faup.decode(url)
domain = faup.get_domain()
subdomain = faup.get_subdomain()
f1 = None
2014-09-04 11:46:07 +02:00
domains_list.append(domain)
publisher.debug('{} Published'.format(url))
2014-09-04 11:46:07 +02:00
if f1 == "onion":
print domain
hostl = unicode(avoidNone(subdomain)+avoidNone(domain))
2014-09-04 11:46:07 +02:00
try:
socket.setdefaulttimeout(1)
2014-09-04 11:46:07 +02:00
ip = socket.gethostbyname(unicode(hostl))
except:
# If the resolver is not giving any IPv4 address,
# ASN/CC lookup is skip.
continue
try:
l = client.lookup(ip, qType='IP')
except ipaddress.AddressValueError:
continue
cc = getattr(l, 'cc')
asn = getattr(l, 'asn')
# EU is not an official ISO 3166 code (but used by RIPE
# IP allocation)
if cc is not None and cc != "EU":
print hostl, asn, cc, \
pycountry.countries.get(alpha2=cc).name
if cc == cc_critical:
publisher.warning(
'Url;{};{};{};Detected {} {}'.format(
PST.p_source, PST.p_date, PST.p_name,
hostl, cc))
else:
print hostl, asn, cc
A_values = lib_refine.checking_A_record(r_serv2,
domains_list)
if A_values[0] >= 1:
PST.__setattr__(channel, A_values)
PST.save_attribute_redis(channel, (A_values[0],
list(A_values[1])))
pprint.pprint(A_values)
publisher.info('Url;{};{};{};Checked {} URL'.format(
PST.p_source, PST.p_date, PST.p_name, A_values[0]))
prec_filename = filename
else:
publisher.debug("Script url is Idling 10s")
print 'Sleeping'
time.sleep(10)
message = p.get_from_set()