#
# 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
# Allowed search engines directives
User-agent: Mediapartners-Google
User-agent: Googlebot
User-agent: Googlebot-Image
User-agent: Googlebot-Mobile
User-agent: Googlebot-News
User-agent: Googlebot-Video
User-agent: Adsbot-Google
User-Agent: Googlebot_Nauxeo
User-agent: bingbot
User-agent: Twitterbot
User-agent: Applebot
User-agent: Bingbot
User-agent: Facebot
User-agent: SiteAuditBot
User-agent: Screaming Frog SEO Spider
User-agent: Publication-Access-for-Facebook
User-agent: facebookexternalhit
User-agent: Flipboard
User-agent: FlipboardProxy
User-agent: upday
# 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/
# Other paths
Disallow: /archives/recherche*
#Disallow: /node/*
Disallow: /section/*?page=*
Disallow: /art/art/*
Disallow: */undefined
Disallow: /shares_callback/
Disallow: /check_cookies*
Disallow: /phpincludes/
Disallow: /forward/
Disallow: /api/
Disallow: /reactions_callback/*
Disallow: /programme-tv/*
Disallow: /*/paywall?page=*
# --- AJOUTS SPECIFIQUES SEO ---
# Bloquer les paramètres de tracking et liens externes
Disallow: /*?*trueLink*
Disallow: /*?*destination=
# Bloquer les appels AJAX
Disallow: /*?*ajax=1
# Bloquer les vieilles pages aspx si elles polluent
Disallow: /*.aspx$
# Bloquer le pager
Disallow: /*?page=*
# ------------------------------
# Sitemap
Sitemap: https://www.rtl.be/sitemap.xml
# Disallowed search engines
User-agent: GPTBot
Disallow: /
# AI Data Scrapers
User-agent: AI2Bot
User-agent: Amazonbot
User-agent: Applebot-Extended
User-agent: anthropic-ai
User-agent: Bytespider
User-agent: CCBot
User-agent: ChatGPT-User
User-agent: ClaudeBot
User-agent: Claude-Web
User-agent: cohere-ai
User-agent: Diffbot
User-agent: DuckAssistBot
User-agent: FacebookBot
User-agent: Google-Extended
User-agent: GPTBot
User-agent: Meta-ExternalAgent
User-agent: Meta-ExternalFetcher
User-agent: OAI-SearchBot
User-agent: PerplexityBot
Disallow: /