#
# 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.md
Disallow: /composer/Metapackage/README.txt
Disallow: /composer/Plugin/ProjectMessage/README.md
Disallow: /composer/Plugin/Scaffold/README.md
Disallow: /composer/Plugin/VendorHardening/README.txt
Disallow: /composer/Template/README.txt
Disallow: /modules/README.txt
Disallow: /sites/README.txt
Disallow: /themes/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
Disallow: /media/oembed
Disallow: /*/media/oembed
# Paths (no clean URLs)
Disallow: */normativa/*
Disallow: */indicadors/*
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: /index.php/media/oembed
Disallow: /index.php/*/media/oembed
# Sitemap
Sitemap: https://uvic-ucc.cat/sitemap.xml



#desactivar bots de merda
User-agent: FriendlyCrawler
User-agent: Bytespider
User-agent: meta-externalagent
User-agent: SemrushBot
User-agent: Qwantbot-prod12345
User-agent: Qwantbot-news
User-agent: Qwantbot-prod38619
User-agent: Qwantbot-dev12345
User-agent: meta-externalagent
User-agent: AhrefsBot
User-agent: AhrefsSiteAudit
User-agent: PetalBot
User-agent: AwarioRssBot
User-agent: AwarioSmartBot
User-agent: AwarioBot
User-agent: barkrowler
User-agent: Applebot         # apple
User-agent: Amazonbot             # Amazon's user agent
User-agent: CCBot
User-agent: dotbot
User-agent: ClaudeBot
User-agent: YandexBot
User-agent: TurnitinBot
User-agent: VelenPublicWebCrawler
User-agent: Zealbot
User-agent: MSIECrawler
User-agent: SiteSnagger
User-agent: WebStripper
User-agent: WebCopier
User-agent: Fetch
User-agent: Offline Explorer
User-agent: Teleport
User-agent: TeleportPro
User-agent: WebZIP
User-agent: linko
User-agent: HTTrack
User-agent: Microsoft.URL.Control
User-agent: Xenu
User-agent: larbin
User-agent: libwww
User-agent: ZyBORG
User-agent: Download Ninja
Disallow: /