add theHarvester

secator/tasks/theHarvester.py

@@ -1,26 +1,30 @@
-import os 
 import json
+import os
+
+import validators
 
 from secator.decorators import task
-from secator.definitions import (DELAY, PROXY, RATE_LIMIT, RETRIES, THREADS, TIMEOUT, PROXY, LIMIT, SCREENSHOT, OPT_NOT_SUPPORTED, TEMP_FOLDER)
+from secator.definitions import (DELAY, LIMIT, OPT_NOT_SUPPORTED, PROXY,
+								 RATE_LIMIT, RETRIES, SCREENSHOT, TEMP_FOLDER,
+								 THREADS, TIMEOUT)
+from secator.output_types import Ip, Subdomain, Url, UserAccount
 from secator.tasks._categories import ReconUser
 from secator.utils import get_file_timestamp
-from secator.output_types import UserAccount
+
 
 @task()
 class theHarvester(ReconUser):
-	"""theHarvester is a simple to use, yet powerful tool designed to be used during the reconnaissance stage of a red
-team assessment or penetration test."""
-	cmd = 'theHarvester	'
+	"""theHarvester is a tool designed to be used during the reconnaissance stage."""
+	cmd = 'theHarvester'
 	file_flag = None
 	input_flag = '--domain'
 	json_flag = '--filename'
 	opt_prefix = '--'
-	
+
 	opts = {
 		'source': {'type': str, 'short': 'b', 'help': 'bevigil, censys, fullhunt, securityTrails'},
-    }
-	
+	}
+
 	opt_key_map = {
 		PROXY: 'proxies',
 		LIMIT: 'limit',
@@ -31,7 +35,7 @@ class theHarvester(ReconUser):
 		RETRIES: OPT_NOT_SUPPORTED,
 		TIMEOUT: OPT_NOT_SUPPORTED
 	}
-	
+
 	@staticmethod
 	def on_start(self):
 		output_path = self.get_opt_value('output_path')
@@ -41,8 +45,8 @@ def on_start(self):
 		self.output_path = output_path
 		self.cmd = self.cmd.replace('--filename', f'--filename {self.output_path}')
 
-def yielder(self):
-		prev = self.print_item_count
+	def yielder(self):
+		#prev = self.print_item_count
 		self.print_item_count = False
 		list(super().yielder())
 		if self.return_code != 0:
@@ -54,25 +58,33 @@ def yielder(self):
 			if self.print_orig:  # original h8mail output
 				yield data
 				return
-			targets = data['hosts']
-			for target in targets:
-				email = target['target']
-				target_data = target['data']
-				if not len(target_data) > 0:
+			hosts = data.get('hosts', [])
+			#asns = data.get('asns', [])
+			interesting_urls = data.get('interesting_urls', [])
+			ips = data.get('ips', [])
+			emails = data.get('emails', [])
+			target = self.targets[0]
+
+			for ip in ips:
+				yield Ip(ip=ip, host=target)
+			for host in hosts:
+				parts = host.split(':')
+				if len(parts) == 1:
 					continue
-				entries = target_data[0]
-				for entry in entries:
-					source, site_name = tuple(entry.split(':'))
-					yield UserAccount(**{
-						"site_name": site_name,
-						"username": email.split('@')[0],
-						"email": email,
-						"extra_data": {
-							'source': source
-						},
-					})
+				if len(parts) > 2:
+					host = parts[0]
+					ip = ':'.join(parts[1:-1])
+				else:
+					host, ip = tuple(parts)
+				if validators.ip_address.ipv4(ip) or validators.ip_address.ipv6(ip):
+					yield Ip(ip=ip, host=host)
+				yield Subdomain(host=host, domain=target)
+			for interesting_url in interesting_urls:
+				yield Url(url=interesting_url)
+			for email in emails:
+				yield UserAccount(email=emails)
 
 
-	install_cmd = ('git clone https://github.com/laramies/theHarvester || True &&'
+install_cmd = ('git clone https://github.com/laramies/theHarvester || True &&'
 				'cd theHarvester || python3 -m pip install -r requirements/base.txt')
-	socks5_proxy = True
+socks5_proxy = True