2014-08-06 11:43:40 +02:00
|
|
|
#!/usr/bin/env python2
|
|
|
|
# -*-coding:UTF-8 -*
|
|
|
|
"""
|
|
|
|
The ZMQ_Sub_Onion Module
|
|
|
|
============================
|
|
|
|
|
|
|
|
This module is consuming the Redis-list created by the ZMQ_Sub_Onion_Q Module.
|
|
|
|
|
|
|
|
It trying to extract url from paste and returning only ones which are tor related
|
|
|
|
(.onion)
|
|
|
|
|
|
|
|
..seealso:: Paste method (get_regex)
|
|
|
|
|
|
|
|
..note:: Module ZMQ_Something_Q and ZMQ_Something are closely bound, always put
|
|
|
|
the same Subscriber name in both of them.
|
|
|
|
|
|
|
|
Requirements
|
|
|
|
------------
|
|
|
|
|
|
|
|
*Need running Redis instances. (Redis)
|
|
|
|
*Need the ZMQ_Sub_Onion_Q Module running to be able to work properly.
|
|
|
|
|
|
|
|
"""
|
2014-08-14 17:55:18 +02:00
|
|
|
import redis
|
|
|
|
import ConfigParser
|
|
|
|
import pprint
|
|
|
|
import time
|
|
|
|
from packages import Paste
|
2014-08-06 11:43:40 +02:00
|
|
|
from packages import ZMQ_PubSub
|
|
|
|
from pubsublogger import publisher
|
|
|
|
|
|
|
|
configfile = './packages/config.cfg'
|
|
|
|
|
2014-08-14 17:55:18 +02:00
|
|
|
|
2014-08-06 11:43:40 +02:00
|
|
|
def main():
|
|
|
|
"""Main Function"""
|
|
|
|
|
|
|
|
# CONFIG #
|
|
|
|
cfg = ConfigParser.ConfigParser()
|
|
|
|
cfg.read(configfile)
|
|
|
|
|
|
|
|
# REDIS #
|
|
|
|
r_serv = redis.StrictRedis(
|
2014-08-14 17:55:18 +02:00
|
|
|
host=cfg.get("Redis_Queues", "host"),
|
|
|
|
port=cfg.getint("Redis_Queues", "port"),
|
|
|
|
db=cfg.getint("Redis_Queues", "db"))
|
2014-08-06 11:43:40 +02:00
|
|
|
|
|
|
|
r_serv1 = redis.StrictRedis(
|
2014-08-14 17:55:18 +02:00
|
|
|
host=cfg.get("Redis_Data_Merging", "host"),
|
|
|
|
port=cfg.getint("Redis_Data_Merging", "port"),
|
|
|
|
db=cfg.getint("Redis_Data_Merging", "db"))
|
2014-08-06 11:43:40 +02:00
|
|
|
|
|
|
|
# LOGGING #
|
|
|
|
publisher.channel = "Script"
|
|
|
|
|
|
|
|
# ZMQ #
|
|
|
|
Sub = ZMQ_PubSub.ZMQSub(configfile, "PubSub_Categ", "onion_categ", "tor")
|
|
|
|
|
|
|
|
# FUNCTIONS #
|
|
|
|
publisher.info("Script subscribed to channel onion_categ")
|
|
|
|
|
2014-08-14 17:55:18 +02:00
|
|
|
# Getting the first message from redis.
|
2014-08-06 11:43:40 +02:00
|
|
|
message = Sub.get_msg_from_queue(r_serv)
|
|
|
|
prec_filename = None
|
|
|
|
|
2014-08-14 17:55:18 +02:00
|
|
|
# Thanks to Faup project for this regex
|
2014-08-06 11:43:40 +02:00
|
|
|
# https://github.com/stricaud/faup
|
|
|
|
url_regex = "([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|onion|[a-zA-Z]{2}))(\:[0-9]+)*(/($|[a-zA-Z0-9\.\,\?\'\\\+&%\$#\=~_\-]+))*"
|
|
|
|
|
|
|
|
while True:
|
2014-08-14 17:55:18 +02:00
|
|
|
if message is not None:
|
|
|
|
channel, filename, word, score = message.split()
|
2014-08-06 11:43:40 +02:00
|
|
|
|
|
|
|
# "For each new paste"
|
2014-08-14 17:55:18 +02:00
|
|
|
if prec_filename is None or filename != prec_filename:
|
2014-08-06 11:43:40 +02:00
|
|
|
domains_list = []
|
2014-08-14 17:55:18 +02:00
|
|
|
PST = Paste.Paste(filename)
|
2014-08-06 11:43:40 +02:00
|
|
|
|
|
|
|
for x in PST.get_regex(url_regex):
|
2014-08-14 17:55:18 +02:00
|
|
|
# Extracting url with regex
|
2014-08-06 11:43:40 +02:00
|
|
|
credential, subdomain, domain, host, tld, port, resource_path, query_string, f1, f2, f3, f4 = x
|
|
|
|
|
|
|
|
if f1 == "onion":
|
|
|
|
domains_list.append(domain)
|
|
|
|
|
2014-08-14 17:55:18 +02:00
|
|
|
# Saving the list of extracted onion domains.
|
2014-08-06 11:43:40 +02:00
|
|
|
PST.__setattr__(channel, domains_list)
|
|
|
|
PST.save_attribute_redis(r_serv1, channel, domains_list)
|
|
|
|
pprint.pprint(domains_list)
|
|
|
|
print PST.p_path
|
2014-08-14 17:55:18 +02:00
|
|
|
to_print = 'Onion;{};{};{};'.format(PST.p_source, PST.p_date, PST.p_name)
|
2014-08-06 11:43:40 +02:00
|
|
|
if len(domains_list) > 0:
|
2014-08-14 17:55:18 +02:00
|
|
|
publisher.warning('{}Detected {} .onion(s)'.format(to_print, len(domains_list)))
|
2014-08-06 11:43:40 +02:00
|
|
|
else:
|
2014-08-14 17:55:18 +02:00
|
|
|
publisher.info('{}Onion related'.format(to_print))
|
2014-08-06 11:43:40 +02:00
|
|
|
|
|
|
|
prec_filename = filename
|
|
|
|
|
|
|
|
else:
|
|
|
|
if r_serv.sismember("SHUTDOWN_FLAGS", "Onion"):
|
|
|
|
r_serv.srem("SHUTDOWN_FLAGS", "Onion")
|
|
|
|
print "Shutdown Flag Up: Terminating"
|
|
|
|
publisher.warning("Shutdown Flag Up: Terminating.")
|
|
|
|
break
|
|
|
|
publisher.debug("Script url is Idling 10s")
|
|
|
|
time.sleep(10)
|
|
|
|
|
|
|
|
message = Sub.get_msg_from_queue(r_serv)
|
|
|
|
|
|
|
|
|
|
|
|
if __name__ == "__main__":
|
|
|
|
main()
|