Updated README.md and fixed some bugs

README.md

@@ -66,6 +66,20 @@ We can save the output in a text file by doing:
 pdlist example.com -o example-list.txt
 ```
 
+Notice that by default pdlist will also output hostnames which may not really
+be proper subdomains of the specified domains, and this happens because those
+subdomains are still related to the specified domains.
+
+If we want to only output proper subdomains we can enable the strict mode by
+doing:
+```shs
+pdlist example.com --strict
+```
+
+A usage example in the gif below:
+![](img/pdlist_demo.gif)
+
+
 
 ## NOTES
 

pdlist/main.py

@@ -19,6 +19,7 @@
 import pdlist.source.dnsdumpster as dd
 import pdlist.source.certspotter as cs
 import pdlist.source.hackertarget as ht
+from pdlist.utils import polish_subdomain_strings, remove_unrelated_domains
 
 
 __all__ = ('main',)
@@ -37,13 +38,6 @@ def show_banner():
 Developed by gnc
     """)
 
-
-def polish_subdomain_strings(subdomains):
-    subdomains = [item.strip() for item in subdomains]
-    subdomains = [item.rstrip('\.') for item in subdomains]
-    subdomains = [re.sub("^.* ", "", item) for item in subdomains]
-    subdomains = [re.sub("^[\.\*]\.", "", item) for item in subdomains]
-    return subdomains
 
 
 def main():
@@ -59,6 +53,14 @@ def main():
         type=str,
         nargs='+',
         )
+    parser.add_argument(
+        "-s","--strict",
+        dest='is_strict',
+        action='store_true',
+        help="Enables strict mode, where only proper (and not also related)\
+        subdomains will be saved",
+        default=False,
+        )
     parser.add_argument(
         "-o","--output",
         dest='outputfile',
@@ -98,6 +100,10 @@ def main():
 
 
     subdomains = polish_subdomain_strings(subdomains)
+
+    if args.is_strict:
+        subdomains = remove_unrelated_domains(subdomains, domains)
+
     subdomains = list(set(subdomains))
     print()
     print()

pdlist/utils.py

@@ -10,17 +10,30 @@
 :Copyright: © 2019, Giuseppe Nebbione.
 :License: BSD (see /LICENSE).
 """
+import re
 
 
+def remove_unrelated_domains(subdomains, domains):
+    subdomains = [s for s in subdomains if s.endswith(tuple(domains))]
+    return subdomains
+
+
+def polish_subdomain_strings(subdomains):
+    subdomains = [item.strip() for item in subdomains]
+    subdomains = [item.rstrip('\.') for item in subdomains]
+    subdomains = [re.sub("^.* ", "", item) for item in subdomains]
+    subdomains = [re.sub("^[\.\*]\.", "", item) for item in subdomains]
+    return subdomains
 
 def find(key, dictionary):
-    for k, v in dictionary.items():
-        if k == key:
-            yield v
-        elif isinstance(v, dict):
-            for result in find(key, v):
-                yield result
-        elif isinstance(v, list):
-            for d in v:
-                for result in find(key, d):
+    if isinstance(dictionary, dict):
+        for k, v in dictionary.items():
+            if k == key:
+                yield v
+            elif isinstance(v, dict):
+                for result in find(key, v):
                     yield result
+            elif isinstance(v, list):
+                for d in v:
+                    for result in find(key, d):
+                        yield result