Skip to content

SpiderFoot automates OSINT for threat intelligence and mapping your attack surface.

Split sfp_pastes into paste tool specific modules.

Stevefcc251db804b
diff --git a/modules/sfp_pastes.py b/modules/sfp_pastebin.py
similarity index 84%
rename from modules/sfp_pastes.py
rename to modules/sfp_pastebin.py
index f6716b28..2f4a49e6 100644
--- a/modules/sfp_pastes.py
+++ b/modules/sfp_pastebin.py
@@ -1,6 +1,6 @@
# -*- coding: utf-8 -*-
# -------------------------------------------------------------------------------
-# Name: sfp_pastes
+# Name: sfp_pastebin
# Purpose: Searches Google for PasteBin content related to the domain in
# question.
#
@@ -15,29 +15,21 @@ import re
from sflib import SpiderFoot, SpiderFootPlugin, SpiderFootEvent
-class sfp_pastes(SpiderFootPlugin):
- """Pastes:Footprint,Investigate,Passive:Search Engines:errorprone:PasteBin, Pastie and Notepad.cc scraping (via Google) to identify related content."""
+class sfp_pastebin(SpiderFootPlugin):
+ """PasteBin:Footprint,Investigate,Passive:Search Engines:errorprone:PasteBin scraping (via Google) to identify related content."""
# Default options
opts = {
- 'searchpages': 20, # Number of google results pages to iterate
- 'pastebin': True,
- 'pastie': True,
- 'notepadcc': True
+ 'searchpages': 20 # Number of google results pages to iterate
}
# Option descriptions
optdescs = {
- 'searchpages': "Number of search results pages to iterate through.",
- 'pastebin': "Search PasteBin?",
- 'pastie': "Search Pastie?",
- 'notepadcc': "Search Notepad.cc?"
+ 'searchpages': "Number of search results pages to iterate through."
}
domains = {
- 'pastebin': "pastebin.com",
- 'pastie': "pastie.org",
- 'notepadcc': "notepadd.cc"
+ 'pastebin': "pastebin.com"
}
results = list()
@@ -131,4 +123,4 @@ class sfp_pastes(SpiderFootPlugin):
self.notifyListeners(evt2)
-# End of sfp_pastes class
+# End of sfp_pastebin class
diff --git a/modules/sfp_pastie.py b/modules/sfp_pastie.py
new file mode 100644
index 00000000..0dac6783
--- /dev/null
+++ b/modules/sfp_pastie.py
@@ -0,0 +1,126 @@
+# -*- coding: utf-8 -*-
+# -------------------------------------------------------------------------------
+# Name: sfp_pastie
+# Purpose: Searches Google for Pastie.org content related to the domain in
+# question.
+#
+# Author: Steve Micallef <[email protected]> and ShellCodeNoobx
+#
+# Created: 20/03/2014
+# Copyright: (c) Steve Micallef 2014
+# Licence: GPL
+# -------------------------------------------------------------------------------
+
+import re
+from sflib import SpiderFoot, SpiderFootPlugin, SpiderFootEvent
+
+
+class sfp_pastie(SpiderFootPlugin):
+ """Pastie.org:Footprint,Investigate,Passive:Search Engines:errorprone:Pastie.org scraping (via Google) to identify related content."""
+
+ # Default options
+ opts = {
+ 'searchpages': 20 # Number of google results pages to iterate
+ }
+
+ # Option descriptions
+ optdescs = {
+ 'searchpages': "Number of search results pages to iterate through."
+ }
+
+ domains = {
+ 'pastie': "pastie.org"
+ }
+
+ results = list()
+
+ def setup(self, sfc, userOpts=dict()):
+ self.sf = sfc
+ self.results = list()
+
+ for opt in userOpts.keys():
+ self.opts[opt] = userOpts[opt]
+
+ # What events is this module interested in for input
+ def watchedEvents(self):
+ return ["DOMAIN_NAME", "INTERNET_NAME", "EMAILADDR"]
+
+ # What events this module produces
+ # This is to support the end user in selecting modules based on events
+ # produced.
+ def producedEvents(self):
+ return ["LEAKSITE_CONTENT", "LEAKSITE_URL"]
+
+ def handleEvent(self, event):
+ eventName = event.eventType
+ srcModuleName = event.module
+ eventData = event.data
+
+ if eventData in self.results:
+ return None
+ else:
+ self.results.append(eventData)
+
+ for dom in self.domains.keys():
+ if self.opts[dom]:
+ links = list()
+ target = self.domains[dom]
+ pages = self.sf.googleIterate("site:" + target + "%20+\"" + eventData + "\"",
+ dict(limit=self.opts['searchpages'],
+ useragent=self.opts['_useragent'],
+ timeout=self.opts['_fetchtimeout']))
+
+ if pages is None:
+ self.sf.info("No results returned from Google search of " + target + ".")
+ return None
+
+ for page in pages.keys():
+ if page in self.results:
+ continue
+ else:
+ self.results.append(page)
+
+ # Check if we've been asked to stop
+ if self.checkForStop():
+ return None
+
+ # Fetch the paste site content
+ links += self.sf.parseLinks(page, pages[page], target)
+
+ for link in links:
+ if link in self.results:
+ continue
+ else:
+ self.results.append(link)
+
+ self.sf.debug("Found a link: " + link)
+ if self.sf.urlBaseUrl(link).endswith(target):
+ if self.checkForStop():
+ return None
+
+ res = self.sf.fetchUrl(link, timeout=self.opts['_fetchtimeout'],
+ useragent=self.opts['_useragent'])
+
+ if res['content'] is None:
+ self.sf.debug("Ignoring " + link + " as no data returned")
+ continue
+
+ # Sometimes pastes search results false positives
+ if re.search("[^a-zA-Z\-\_0-9]" + re.escape(eventData) +
+ "[^a-zA-Z\-\_0-9]", res['content'], re.IGNORECASE) is None:
+ continue
+
+ try:
+ startIndex = res['content'].index(eventData)
+ except BaseException as e:
+ self.sf.debug("String not found in pastes content.")
+ continue
+
+ evt1 = SpiderFootEvent("LEAKSITE_URL", link, self.__name__, event)
+ self.notifyListeners(evt1)
+
+ evt2 = SpiderFootEvent("LEAKSITE_CONTENT", res['content'], self.__name__, evt1)
+ self.notifyListeners(evt2)
+
+
+# End of sfp_pastie class