mirror of
https://github.com/aljazceru/recon-pipeline.git
synced 2025-12-19 15:24:28 +01:00
Co-authored-by: Ryan Good <usafaryangood@gmail.com> * added initial skeleton; restructured project directories * removed workers directive from luigi; changed input to tko-subs * changed masscan command to use config.tool_paths * linted __init__ files and updated docstring for get_scans * added per-file-ignores for linting * recon-pipeline linted * PoC working for amass results -> db; rudimentary db mgmt commands also * more linting * added database management commands to the shell * db_location passes through to all tasks; masscan results added to db * removed unused imports from masscan.py * added ParseNmapOutput class to handle parsing for database storage * cleaned up repeat code * searchsploit results stored in db * lint/format * gobuster scans now stored in database * fixed test_recon tests to use db_location * fixed web tests * tkosub entries recorded in db * subjack scan results stored in database * webanalyze results stored in db * refactored older commits to use newer helper functions * refactored older commits to use newer helper functions * aquatone results stored in database refactored a few scans to use dbmanager helper functions refactored db structure wrt headers/screenshots added 80/443 to web_ports in config.py * fixed a few queries and re-added webanalyze to FullScan * view targets/endpoints done * overhauled nmap parsing * print all nmap_results good, next to focus on filtering * complex nmap filters complete * nmap printing done * updated pipfile * view web-technologies complete * view searchsploit results complete * removed filesystem code from amass * targetlist moved to db only * targets,amass,masscan all cutover to full database; added view ports * nmap fully db compliant * aquatone and webtargets db compliant * gobuster uses db now * webanalyze db compliant * all scans except corscanner are db compliant * recon tests passing * web tests passing * linted files * added tests for helpers.py and parsers.py * refactored some redundant code * added tests to pre-commit * updated amass tests and pre-commit version * updated recon.targets tests * updated nmap tests * updated masscan tests * updated config tests * updated web targets tests * added gobuster tests * added aquatone tests * added subdomain takeover and webanalyze tests; updated test data * removed homegrown sqlite target in favor of the sqla implementation * added tests for recon-pipeline.py * fixed cluge function to set __package__ globally * updated amass tests * updated targets tests * updated nmap tests * updated masscan tests * updated aquatone tests * updated nmap tests to account for no searchsploit * updated nmap tests to account for no searchsploit * updated masscan tests * updated subjack/tkosub tests * updated web targets tests * updated webanalyze tests * added corscanner tests * linted DBManager a bit * fixed weird cyclic import issue that only happened during docs build; housekeeping * added models tests, removed test_install dir * updated docs a bit; sidenav is wonky * fixed readthedocs requirements.txt * fixed issue where view results werent populated directly after scan * added new tests to pipeline; working on docs * updated a few overlooked view command items * updated tests to reflect changes to shell * incremental push of docs update * documentation done * updated exploitdb install * updated exploitdb install * updated seclists install * parseamass updates db in the event of no amass output * removed corscanner * added pipenv shell to install instructions per @GreaterGoodest * added pipenv shell to install instructions per @GreaterGoodest * added check for chromium-browser during aquatone install; closes #26 * added check for old recon-tools dir; updated Path.resolve calls to Path.expanduser.resolve; fixed very specific import bug due to filesystem location * added CONTIBUTING.md; updated pre-commit hooks/README * added .gitattributes for linguist reporting * updated tests * fixed a few weird bugs found during test * updated README * updated asciinema links in README * updated README with view command video * updated other location for url scheme /status * add ability to specify single target using --target (#31) * updated a few items in docs and moved tool-dict to tools-dir * fixed issue where removing tempfile without --verbose caused scan to fail
85 lines
3.4 KiB
Python
85 lines
3.4 KiB
Python
import luigi
|
|
from luigi.util import inherits
|
|
from luigi.contrib.sqla import SQLAlchemyTarget
|
|
|
|
import pipeline.models.db_manager
|
|
from ..config import web_ports
|
|
from ..amass import ParseAmassOutput
|
|
from ..masscan import ParseMasscanOutput
|
|
|
|
|
|
@inherits(ParseMasscanOutput)
|
|
class GatherWebTargets(luigi.Task):
|
|
""" Gather all subdomains as well as any ip addresses known to have a configured web port open.
|
|
|
|
Args:
|
|
db_location: specifies the path to the database used for storing results *Required by upstream Task*
|
|
exempt_list: Path to a file providing blacklisted subdomains, one per line. *Optional by upstream Task*
|
|
top_ports: Scan top N most popular ports *Required by upstream Task*
|
|
ports: specifies the port(s) to be scanned *Required by upstream Task*
|
|
interface: use the named raw network interface, such as "eth0" *Required by upstream Task*
|
|
rate: desired rate for transmitting packets (packets per second) *Required by upstream Task*
|
|
target_file: specifies the file on disk containing a list of ips or domains *Required by upstream Task*
|
|
results_dir: specifes the directory on disk to which all Task results are written *Required by upstream Task*
|
|
"""
|
|
|
|
def __init__(self, *args, **kwargs):
|
|
super().__init__(*args, **kwargs)
|
|
self.db_mgr = pipeline.models.db_manager.DBManager(db_location=self.db_location)
|
|
|
|
def requires(self):
|
|
""" GatherWebTargets depends on ParseMasscanOutput and ParseAmassOutput to run.
|
|
|
|
ParseMasscanOutput expects rate, target_file, interface, and either ports or top_ports as parameters.
|
|
ParseAmassOutput accepts exempt_list and expects target_file
|
|
|
|
Returns:
|
|
dict(str: ParseMasscanOutput, str: ParseAmassOutput)
|
|
"""
|
|
args = {
|
|
"results_dir": self.results_dir,
|
|
"rate": self.rate,
|
|
"target_file": self.target_file,
|
|
"top_ports": self.top_ports,
|
|
"interface": self.interface,
|
|
"ports": self.ports,
|
|
"db_location": self.db_location,
|
|
}
|
|
return {
|
|
"masscan-output": ParseMasscanOutput(**args),
|
|
"amass-output": ParseAmassOutput(
|
|
exempt_list=self.exempt_list,
|
|
target_file=self.target_file,
|
|
results_dir=self.results_dir,
|
|
db_location=self.db_location,
|
|
),
|
|
}
|
|
|
|
def output(self):
|
|
""" Returns the target output for this task.
|
|
|
|
Returns:
|
|
luigi.contrib.sqla.SQLAlchemyTarget
|
|
"""
|
|
return SQLAlchemyTarget(
|
|
connection_string=self.db_mgr.connection_string, target_table="target", update_id=self.task_id
|
|
)
|
|
|
|
def run(self):
|
|
""" Gather all potential web targets and tag them as web in the database. """
|
|
|
|
for target in self.db_mgr.get_all_targets():
|
|
ports = self.db_mgr.get_ports_by_ip_or_host_and_protocol(target, "tcp")
|
|
if any(port in web_ports for port in ports):
|
|
tgt = self.db_mgr.get_or_create_target_by_ip_or_hostname(target)
|
|
tgt.is_web = True
|
|
self.db_mgr.add(tgt)
|
|
self.output().touch()
|
|
|
|
# in the event that there are no web ports for any target, we still want to be able to mark the
|
|
# task complete successfully. we accomplish this by calling .touch() even though a database entry
|
|
# may not have happened
|
|
self.output().touch()
|
|
|
|
self.db_mgr.close()
|