V1.3.3

modules/info.py

@@ -5,7 +5,7 @@
 from requests.exceptions import HTTPError
 import requests
 from requests import get
-
+import re 
 from .link_io import LinkIO
 
 
@@ -32,7 +32,7 @@ def execute_all(link, *, display_status=False):
     page,response = LinkIO.read(link, response=True, show_msg=display_status)
     response = get(link, verify=False).text
     soup = BeautifulSoup(page, 'html.parser')
-    validation_functions = [get_robots_txt, get_dot_git, get_dot_svn, get_dot_git, get_intel]
+    validation_functions = [get_robots_txt, get_dot_git, get_dot_svn, get_dot_git, get_intel,get_bitcoin_address]
     for validate_func in validation_functions:
         try:
             validate_func(link,response)
@@ -71,12 +71,10 @@ def get_robots_txt(target,response):
 def get_intel(link,response):
     intel=set()
     matches = findall(r'''([\w\.-]+s[\w\.-]+\.amazonaws\.com)|([\w\.-]+@[\w\.-]+\.[\.\w]+)''', response)
+    print("Intel\n--------\n\n")
     if matches:
         for match in matches: 
-            verb('Intel', match)
             intel.add(match) 
-    print("Intel\n--------\n\n %s")
-    print(intel)        
 
 def get_dot_git(target,response):
     cprint("[*]Checking for .git folder", 'yellow')
@@ -90,6 +88,12 @@ def get_dot_git(target,response):
     else:
         cprint("NO .git folder found", 'blue')
 
+def get_bitcoin_address(target,response):
+    bitcoins = re.findall(r'^[13][a-km-zA-HJ-NP-Z1-9]{25,34}$',response)
+    print("BTC FOUND: ",len(bitcoins))
+    for bitcoin in bitcoins:
+        print("BTC: ",bitcoin)
+
 
 def get_dot_svn(target,response):
     cprint("[*]Checking for .svn folder", 'yellow')
@@ -121,13 +125,10 @@ def get_dot_htaccess(target,response):
 
 
 def display_webpage_description(soup):
-    cprint("[*]Checking for description meta tag", 'yellow')
+    cprint("[*]Checking for meta tag", 'yellow')
     metatags = soup.find_all('meta')
     for meta in metatags:
-        if meta.has_attr('name'):
-            attributes = meta.attrs
-            if attributes['name'] == 'description':
-                cprint("Page description: " + attributes['content'])
+        print("Meta : ",meta)
 
 
 def writer(datasets, dataset_names, output_dir):

modules/link.py

@@ -21,12 +21,11 @@ def get_emails(node):
         emails (list): list of emails
     """
     emails = []
-    for child in node.children:
-        link = child.get('href')
-        if link and 'mailto' in link:
-            email_addr = link.split(':')
-            if LinkNode.valid_email(email_addr[1]) and len(email_addr) > 1:
-                emails.append(email_addr[1])
+    response = node.response.text
+    mails = re.findall(r'[\w\.-]+@[\w\.-]+', response)
+    for email in mails:
+        if LinkNode.valid_email(email):
+            emails.append(email)
     return emails
 
 

torBot.py

@@ -15,12 +15,16 @@
 from modules.savefile import saveJson
 from modules.info import execute_all
 
+import sys
+from socketserver import BaseServer
+from wsgiref import handlers
+
 # GLOBAL CONSTS
 LOCALHOST = "127.0.0.1"
 DEFPORT = 9050
 
 # TorBot VERSION
-__VERSION = "1.3.1"
+__VERSION = "1.3.3"
 
 
 def connect(address, port):
@@ -78,7 +82,7 @@ def header():
     title = r"""
                                     {banner}
                     #######################################################
-                    #  TorBot - An OSINT Tool for Deep Web                #
+                    #  TorBot - An OSINT Tool for Dark Web                #
                     #  GitHub : https://github.com/DedsecInside/TorBot    #
                     #  Help : use -h for help text                        #
                     #######################################################
@@ -114,6 +118,7 @@ def get_args():
     parser.add_argument("-i", "--info", action="store_true",
                         help=' '.join(("Info displays basic info of the",
                                        "scanned site")))
+    parser.add_argument("--depth", help="Specifiy max depth of crawler (default 1)")
     parser.add_argument("-v", "--visualize", action="store_true",
                         help="Visualizes tree of data gathered.")
     parser.add_argument("-d", "--download", action="store_true",
@@ -152,14 +157,19 @@ def main():
             if args.save:
                 saveJson('Emails', node.emails)
         # -i/--info
-        elif args.info:
+        if args.info:
             execute_all(node.uri)
             if args.save:
                 print('Nothing to save.\n')
-        elif args.visualize:
-            tree = LinkTree(node, stop_depth=1)
+        if args.visualize:
+            if args.depth:
+                print(args.depth)
+                tree = LinkTree(node,stop_depth=args.depth)
+
+            else:    
+                tree = LinkTree(node)
             tree.show()
-        elif args.download:
+        if args.download:
             tree = LinkTree(node)
             file_name = str(input("File Name (.pdf/.png/.svg): "))
             tree.save(file_name)