Added robotScraper to check robots.txt files

install.sh

@@ -53,6 +53,9 @@ cd GitDorker
 pip3 install -r requirements.txt
 cd ..
 
+printf "${CYAN}Cloning RobotScraper\n${NORMAL}"
+git clone https://github.com/robotshell/robotScraper.git
+
 printf "${CYAN}Cloning nuclei-templates\n${NORMAL}"
 git clone https://github.com/projectdiscovery/nuclei-templates.git
 

magicrecon.sh

@@ -121,6 +121,10 @@ active_recon(){
 
 	cd fingerprinting
 
+	printf "\n${GREEN}[+] Robots.txt ${NORMAL}\n"
+	printf "${NORMAL}${CYAN}Checking directories and files from robots.txt...${NORMAL}\n\n"
+	python3 ~/tools/robotScraper/robotScraper.py -d $domain -s output_robot.txt 
+
 	printf "\n${GREEN}[+] Nmap ${NORMAL}\n"
 	printf "${NORMAL}${CYAN}Searching open ports...${NORMAL}\n\n"
 	nmap -p- --open -T5 -v -n $domain -oN nmap.txt

robots.txt

@@ -0,0 +1,116 @@
+#
+# robots.txt
+#
+# This file is to prevent the crawling and indexing of certain parts
+# of your site by web crawlers and spiders run by sites like Yahoo!
+# and Google. By telling these "robots" where not to go on your site,
+# you save bandwidth and server resources.
+#
+# This file will be ignored unless it is at the root of your host:
+# Used:    http://example.com/robots.txt
+# Ignored: http://example.com/site/robots.txt
+#
+# For more information about the robots.txt standard, see:
+# http://www.robotstxt.org/robotstxt.html
+
+User-agent: *
+Crawl-delay: 10
+# CSS, JS, Images
+Allow: /misc/*.css$
+Allow: /misc/*.css?
+Allow: /misc/*.js$
+Allow: /misc/*.js?
+Allow: /misc/*.gif
+Allow: /misc/*.jpg
+Allow: /misc/*.jpeg
+Allow: /misc/*.png
+Allow: /modules/*.css$
+Allow: /modules/*.css?
+Allow: /modules/*.js$
+Allow: /modules/*.js?
+Allow: /modules/*.gif
+Allow: /modules/*.jpg
+Allow: /modules/*.jpeg
+Allow: /modules/*.png
+Allow: /profiles/*.css$
+Allow: /profiles/*.css?
+Allow: /profiles/*.js$
+Allow: /profiles/*.js?
+Allow: /profiles/*.gif
+Allow: /profiles/*.jpg
+Allow: /profiles/*.jpeg
+Allow: /profiles/*.png
+Allow: /themes/*.css$
+Allow: /themes/*.css?
+Allow: /themes/*.js$
+Allow: /themes/*.js?
+Allow: /themes/*.gif
+Allow: /themes/*.jpg
+Allow: /themes/*.jpeg
+Allow: /themes/*.png
+# Directories
+Disallow: /includes/
+Disallow: /misc/
+Disallow: /modules/
+Disallow: /profiles/
+Disallow: /scripts/
+Disallow: /themes/
+# Files
+Disallow: /CHANGELOG.txt
+Disallow: /cron.php
+Disallow: /INSTALL.mysql.txt
+Disallow: /INSTALL.pgsql.txt
+Disallow: /INSTALL.sqlite.txt
+Disallow: /install.php
+Disallow: /INSTALL.txt
+Disallow: /LICENSE.txt
+Disallow: /MAINTAINERS.txt
+Disallow: /update.php
+Disallow: /UPGRADE.txt
+Disallow: /xmlrpc.php
+# Paths (clean URLs)
+Disallow: /admin/
+Disallow: /comment/reply/
+Disallow: /filter/tips/
+Disallow: /node/add/
+Disallow: /search/
+Disallow: /user/register/
+Disallow: /user/password/
+Disallow: /user/login/
+Disallow: /user/logout/
+# Paths (no clean URLs)
+Disallow: /?q=admin/
+Disallow: /?q=comment/reply/
+Disallow: /?q=filter/tips/
+Disallow: /?q=node/add/
+Disallow: /?q=search/
+Disallow: /?q=user/password/
+Disallow: /?q=user/register/
+Disallow: /?q=user/login/
+Disallow: /?q=user/logout/
+Disallow: /?q=user/q=node/
+
+# Disallow indexing of Node pages
+Disallow: /node/
+Disallow: /*/node/
+
+Disallow: /?q=node/
+Disallow: /?q=*/node/
+
+##############################
+# START TESLA CONTENT.
+##############################
+
+# Tesla content landing pages.
+Disallow: /content/*
+Disallow: /new/*
+Disallow: /used/*
+Disallow: /preowned/*
+Disallow: /demo/*
+Disallow: /taxonomy/term/*
+Disallow: /*/taxonomy/term/*
+Allow: /content/dam/tesla-site/
+
+##############################
+# STOP TESLA CONTENT.
+##############################