Add new module Sitedossier (#1423)

* Create sitedossier.py

* Added new module.

* Added new module.

* Thanks to Jay for the help.

* Added new module to README.

README.md

@@ -70,6 +70,8 @@ Passive:
 
 * shodan: Shodan search engine, will search for ports and banners from discovered hosts (Requires an API key, see below.) - https://shodan.io
 
+* sitedossier: Find available information on a site
+
 * subdomainfinderc99: A subdomain finder is a tool used to find the subdomains of a given domain - https://subdomainfinder.c99.nl
 
 * threatminer: Data mining for threat intelligence - https://www.threatminer.org/

theHarvester/__main__.py

@@ -38,7 +38,7 @@ async def start(rest_args: Optional[argparse.Namespace] = None):
     parser.add_argument('-b', '--source', help='''anubis, baidu, bevigil, binaryedge, bing, bingapi, bufferoverun, brave,
                             censys, certspotter, criminalip, crtsh, dnsdumpster, duckduckgo, fullhunt, github-code,
                             hackertarget, hunter, hunterhow, intelx, otx, pentesttools, projectdiscovery,
-                            rapiddns, rocketreach, securityTrails, subdomainfinderc99, threatminer, urlscan,
+                            rapiddns, rocketreach, securityTrails, sitedossier, subdomainfinderc99, threatminer, urlscan,
                             virustotal, yahoo, zoomeye''')
 
     # determines if filename is coming from rest api or user
@@ -465,6 +465,14 @@ async def store(search_engine: Any, source: str, process_param: Any = None, stor
                         if isinstance(e, MissingKey):
                             print(e)
 
+                elif engineitem == 'sitedossier':
+                    from theHarvester.discovery import sitedossier
+                    try:
+                        sitedossier_search = sitedossier.SearchSitedossier(word)
+                        stor_lst.append(store(sitedossier_search, engineitem, store_host=True, store_ip=True))
+                    except Exception as e:
+                        print(e)
+
                 elif engineitem == 'subdomainfinderc99':
                     from theHarvester.discovery import subdomainfinderc99
                     try:

theHarvester/discovery/sitedossier.py

@@ -0,0 +1,27 @@
+from theHarvester.lib.core import *
+from theHarvester.parsers import myparser
+import requests
+
+
+class SearchSitedossier:
+
+    def __init__(self, word):
+        self.word = word
+        self.totalresults = ""
+        self.server = "www.sitedossier.com"
+        self.limit = 50
+
+    async def do_search(self):
+        url = f"http://{self.server}/parentdomain/{self.word}"
+        headers = {'User-Agent': Core.get_user_agent()}
+
+        response = requests.get(url, headers=headers)
+        self.totalresults += response.text
+
+    async def get_hostnames(self):
+        rawres = myparser.Parser(self.totalresults, self.word)
+        return await rawres.hostnames()
+
+    async def process(self, proxy: bool = False) -> None:
+        self.proxy = proxy
+        await self.do_search()

theHarvester/lib/core.py

@@ -160,6 +160,7 @@ def get_supportedengines() -> list[str | Any]:
                             'rapiddns',
                             'rocketreach',
                             'securityTrails',
+                            'sitedossier',
                             'subdomainfinderc99',
                             'threatminer',
                             'urlscan',