#
# 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: *
# CSS, JS, Images
Allow: /core/*.css$
Allow: /core/*.css?
Allow: /core/*.js$
Allow: /core/*.js?
Allow: /core/*.gif
Allow: /core/*.jpg
Allow: /core/*.jpeg
Allow: /core/*.png
Allow: /core/*.svg
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: /profiles/*.svg
# Directories
Disallow: /core/
Disallow: /profiles/
# Files
Disallow: /README.txt
Disallow: /web.config
# 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: /index.php/admin/
Disallow: /index.php/comment/reply/
Disallow: /index.php/filter/tips
Disallow: /index.php/node/add/
Disallow: /index.php/search/
Disallow: /index.php/user/password/
Disallow: /index.php/user/register/
Disallow: /index.php/user/login/
Disallow: /index.php/user/logout/
 
Disallow: /search/
Disallow: /media/pdfs/noindex/
Disallow: /blog/?s*
Disallow: /search-results.html?search*
Disallow: *?hsFormKey*
Disallow: *?__hstc=*
Disallow: *?cat=*
Disallow: *?asset_id*
Disallow: *?C_
Disallow: *?elq
Disallow: *?lead
Disallow: *?replytocom*
Disallow: *?elqTrackId*
 
 
# additions based on Mediative recommendation for bad bots
 
# advertising-related bots:
User-agent: Mediapartners-Google*
Disallow: /
 
# Crawlers that are kind enough to obey, but which we'd rather not have
# unless they're feeding search engines.
User-agent: UbiCrawler
Disallow: /
 
User-agent: DOC
Disallow: /
 
User-agent: Zao
Disallow: /
 
# Some bots are known to be trouble, particularly those designed to copy
# entire sites. Please obey robots.txt.
User-agent: sitecheck.internetseer.com
Disallow: /
 
User-agent: Zealbot
Disallow: /
 
User-agent: MSIECrawler
Disallow: /
 
User-agent: SiteSnagger
Disallow: /
 
User-agent: WebStripper
Disallow: /
 
User-agent: WebCopier
Disallow: /
 
User-agent: Fetch
Disallow: /
 
User-agent: Offline Explorer
Disallow: /
 
User-agent: Teleport
Disallow: /
 
User-agent: TeleportPro
Disallow: /
 
User-agent: WebZIP
Disallow: /
 
User-agent: linko
Disallow: /
 
User-agent: Microsoft.URL.Control
Disallow: /
 
User-agent: larbin
Disallow: /
 
User-agent: libwww
Disallow: /
 
User-agent: ZyBORG
Disallow: /
 
User-agent: Download Ninja
Disallow: /
 
# Misbehaving: requests much too fast:
User-agent: fast
Disallow: /
 
# ChatGPT crawler
User-agent: GPTBot
Disallow: /
 
sitemap:  https://www.flexera.com/sitemap.xml
sitemap:  https://www.flexera.com/blog/sitemap.xml
sitemap:  https://www.flexera.de/sitemap.xml
sitemap:  https://www.flexera.com/blog/sitemap.xml