#
# 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: /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
Crawl-delay: 10
User-agent: MJ12bot
Disallow: /
User-agent: Yandex
Disallow: /

# -------------------------------------------------------
# Pages de recherche avec facettes (toutes langues)
# Ces URLs sont infinies (combinaisons de filtres) et
# ne doivent PAS être indexées ni crawlées.
# -------------------------------------------------------
User-agent: *

# Recherche FR
Disallow: /fr/recherche
Disallow: /fr/recherche-experts

# Recherche DE
Disallow: /de/recherche
Disallow: /de/recherche-experts

# Recherche EN
Disallow: /en/recherche
Disallow: /en/recherche-experts

# Recherche IT
Disallow: /it/ricerca
Disallow: /it/ricerca-esperti

# Wildcard pour couvrir toute nouvelle langue
Disallow: /*/recherche
Disallow: /*/recherche-experts
Disallow: /*/ricerca
Disallow: /*/ricerca-esperti

# Bloquer tous les paramètres de facettes (URL encodés ou non)
Disallow: /*?f%5B
Disallow: /*?f[

# Pagination
Disallow: /*?page=

# Profils utilisateurs (peu de valeur SEO, lourds à charger)
Disallow: /*/user/

Crawl-delay: 10

# -------------------------------------------------------
# Bots SEO trop agressifs
# -------------------------------------------------------
User-agent: AhrefsBot
Disallow: /

User-agent: SemrushBot
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: DotBot
Disallow: /

User-agent: Yandex
Disallow: /

User-agent: bingbot
Crawl-delay: 30

# -------------------------------------------------------
# Crawlers IA
# -------------------------------------------------------
User-agent: Amazonbot
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: GPTBot
Disallow: /

User-agent: OAI-SearchBot
Disallow: /