acidvegas/eris
acidvegas/eris
1
Fork 0
Code Issues Pull Requests Activity

Masscan ingestion script updated to use ip:port as the document id to allow updating records that already exist. Added a sentinal value to trigger an EOF when using --watch with FIFO's

Browse Source
This commit is contained in:
Dionysus 2024-03-06 13:26:45 -05:00
parent 5a45be5c60
commit 84f124b23d
Signed by: acidvegas
GPG Key ID: EF4B922DB85DC9DE
1 changed files with 60 additions and 57 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

75
ingestors/ingest_masscan.py
View File

@ -2,21 +2,8 @@
# Elasticsearch Recon Ingestion Scripts (ERIS) - Developed by Acidvegas (https://git.acid.vegas/eris)
# ingest_masscan.py
'''
apt-get install iptables masscan libpcap-dev screen
setcap 'CAP_NET_RAW+eip CAP_NET_ADMIN+eip' /bin/masscan
/sbin/iptables -A INPUT -p tcp --dport 61010 -j DROP
printf "0.0.0.0/8\n10.0.0.0/8\n100.64.0.0/10\n127.0.0.0/8\n169.254.0.0/16\n172.16.0.0/12\n192.0.0.0/24\n192.0.2.0/24\n192.31.196.0/24\n192.52.193.0/24\n192.88.99.0/24\n192.168.0.0/16\n192.175.48.0/24\n198.18.0.0/15\n198.51.100.0/24\n203.0.113.0/24\n224.0.0.0/3\n255.255.255.255/32" > exclude.conf
screen -S scan
masscan 0.0.0.0/0 -p21,22,23 --banners --http-user-agent "USER_AGENT" --source-port 61010 --open-only --rate 30000 --excludefile exclude.conf -oJ output.json
masscan 0.0.0.0/0 -p21,22,23 --banners --http-user-agent "USER_AGENT" --source-port 61000-65503 --open-only --rate 30000 --excludefile exclude.conf -oJ output_new.json --shard $i/$TOTAL
Note: The above iptables rule is not persistent and will be removed on reboot.
'''
import json
import logging
import re
import time
try:
@ -31,6 +18,16 @@ def construct_map() -> dict:
keyword_mapping = { 'type': 'text', 'fields': { 'keyword': { 'type': 'keyword', 'ignore_above': 256 } } }
geoip_mapping = {
'city_name' : keyword_mapping,
'continent_name' : keyword_mapping,
'country_iso_code' : keyword_mapping,
'country_name' : keyword_mapping,
'location' : { 'type': 'geo_point' },
'region_iso_code' : keyword_mapping,
'region_name' : keyword_mapping,
}
mapping = {
'mappings': {
'properties': {
@ -39,19 +36,9 @@ def construct_map() -> dict:
'proto' : { 'type': 'keyword' },
'service' : { 'type': 'keyword' },
'banner' : keyword_mapping,
'ref_id': { 'type': 'keyword' },
#'geoip' : { 'properties': geoip_mapping } # Used witht he geoip pipeline to enrich the data
'seen' : { 'type': 'date' }
#'geoip': {
# 'properties': {
# 'city_name': keyword_mapping,
# 'continent_name': keyword_mapping,
# 'country_iso_code': keyword_mapping,
# 'country_name': keyword_mapping,
# 'location': { 'type': 'geo_point' },
# 'region_iso_code': keyword_mapping,
# 'region_name': keyword_mapping,
# }
#}
}
}
}
@ -70,10 +57,13 @@ async def process_data(file_path: str):
async for line in input_file:
line = line.strip()
if line == '~eof': # Sentinel value to indicate the end of a process (Used with --watch with FIFO)
break
if not line or not line.startswith('{'):
continue
if line.endswith(','):
if line.endswith(','): # Do we need this? Masscan JSON output seems with seperate records with a comma between lines for some reason...
line = line[:-1]
try:
@ -83,12 +73,13 @@ async def process_data(file_path: str):
# { "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 (Will remove pausing in production, still investigating the cause of this issue.)
input('Press Enter to continue...') # Pause for review & debugging (remove this in production)
continue
if len(record['ports']) > 1:
# In rare cases, a single record may contain multiple ports, though I have yet to witness this...
logging.warning(f'Multiple ports found for record! ({record})')
input('Press Enter to continue...') # Pause for review (Will remove pausing in production, still investigating if you ever seen more than one port in a record.)
input('Press Enter to continue...') # Pause for review (remove this in production)
for port_info in record['ports']:
struct = {
@ -106,15 +97,11 @@ async def process_data(file_path: str):
if 'banner' in port_info['service']:
banner = ' '.join(port_info['service']['banner'].split()) # Remove extra whitespace
if banner:
match = re.search(r'\(Ref\.Id: (.*?)\)', banner)
if match:
struct['ref_id'] = match.group(1)
else:
struct['banner'] = banner
yield {'_index': default_index, '_source': struct}
id = f'{record["ip"]}:{port_info["port"]}' # Store with ip:port as the unique id to allow the record to be reindexed if it exists.
return None # EOF
yield {'_id': id, '_index': default_index, '_source': struct}
@ -137,12 +124,28 @@ Example record:
Will be indexed as:
{
"_id" : "43.134.51.142:22"
"_index" : "masscan-logs",
"_source" : {
"ip" : "43.134.51.142",
"port" : 22,
"proto" : "tcp",
"service" : "ssh",
"banner" : "SSH-2.0-OpenSSH_8.9p1 Ubuntu-3ubuntu0.4",
"seen": "2021-10-08T02:04:28Z",
"ref_id": "?sKfOvsC4M4a2W8PaC4zF?" # TCP RST Payload, Might be useful..
"seen" : "2021-10-08T02:04:28Z"
}
'''
'''
Notes:
apt-get install iptables masscan libpcap-dev screen
setcap 'CAP_NET_RAW+eip CAP_NET_ADMIN+eip' /bin/masscan
/sbin/iptables -A INPUT -p tcp --dport 61010 -j DROP # Not persistent
printf "0.0.0.0/8\n10.0.0.0/8\n100.64.0.0/10\n127.0.0.0/8\n169.254.0.0/16\n172.16.0.0/12\n192.0.0.0/24\n192.0.2.0/24\n192.31.196.0/24\n192.52.193.0/24\n192.88.99.0/24\n192.168.0.0/16\n192.175.48.0/24\n198.18.0.0/15\n198.51.100.0/24\n203.0.113.0/24\n224.0.0.0/3\n255.255.255.255/32" > exclude.conf
screen -S scan
masscan 0.0.0.0/0 -p21,22,23 --banners --http-user-agent "USER_AGENT" --source-port 61010 --open-only --rate 30000 --excludefile exclude.conf -oJ output.json
masscan 0.0.0.0/0 -p21,22,23 --banners --http-user-agent "USER_AGENT" --source-port 61000-65503 --open-only --rate 30000 --excludefile exclude.conf -oJ output_new.json --shard $i/$TOTAL
'''