#
# 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/wc/robots.html
#
# For syntax checking, see:
# http://www.sxw.org.uk/computing/robots/check.html
#Ajouter le sitemap dans le fichier txt
Sitemap: https://www.digital-campus.fr/sitemap.xml
#Autoriser le crawl des robots IA
User-agent: anthropic-ai
Allow: /
User-agent: Claude-Web
Allow: /
User-agent: Claudebot
Allow: /
User-agent: ChatGPT-User
Allow: /
User-agent: GPTBot
Allow: /
User-agent: MistralAI-User
Allow: /
User-agent: OAI-SearchBot
Allow: /
User-agent: Perplexity-User
Allow: /
User-agent: PerplexityBot
Allow: /
#Bloquer le robot ahref site-audit
User-agent: AhrefsSiteAudit
Disallow: /
#Tous les autres robots
User-agent: *
# Directories
Disallow: /includes/
Disallow: /misc/
Disallow: /modules/
Disallow: /profiles/
Disallow: /scripts/
Disallow: /themes/
Disallow: /sites/default/files/pdf/
# 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: /UPGRADE.txt
Disallow: /update.php
Disallow: /xmlrpc.php
# Paths (clean URLs)
Disallow: /admin/
Disallow: /comment/reply/
Disallow: /filter/tips/
Disallow: /node/add/
Disallow: /search/
Disallow: /user
# Revisions
Disallow: /node/*/revisions
Disallow: /node/*/revisions/*/view
# 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: /*.inc$
# CEL
Disallow: /catalogue
Disallow: /catalogue?*
# Divers
Disallow: /*node/*
# Theme
Disallow: /*.js?*
Disallow: /*.css?*
Allow: /sites/all/libraries/superfish/css/superfish.css
Allow: /sites/all/themes/digital_campus/css/*.css
Allow: /sites/all/themes/digital_campus/js/*.js
# Leadsforms
Disallow: /demande-rdv*
Disallow: /inscription-atelier*
Disallow: /formulaire-alternance-toulouse*
Disallow: /formulaire-alternance-montpellier*
Disallow: /inscription-digidej*
Disallow: /emploi-entreprise/offre-stage*
Disallow: /telechargement-documentation*
Disallow: /inscription-immersion*
Disallow: /creation-votre-compte-candidat*
Disallow: /contact/formulaire-etudiant*
Disallow: /inscription-jpo*
Disallow: /admission/preinscription-session-admission*
Disallow: /telecharger-documentation*
Disallow: /telecharger-dossier-candidature*
Disallow: /telecharger-brochure*
Disallow: /content/webform-bas-page*
Disallow: /candidate
# Option
Disallow: *utm_*