#
# 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
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

# Add custom directives

# Allowed search engines directives.
User-agent: Adsbot-Google
User-Agent: AdsBot-Google-Mobile
User-agent: Applebot
User-agent: Bingbot
User-agent: DuckDuckBot
User-agent: flipboard
User-agent: Googlebot
User-agent: Googlebot-Image
User-agent: Googlebot-Mobile
User-agent: Googlebot-News
User-agent: Googlebot-Video
User-agent: Mediapartners-Google
User-agent: Slurp
User-agent: Taboolabot
User-agent: Twitterbot
User-agent: upday

# Push sitemaps.
Sitemap: https://www.meretmarine.com/sitemap.xml

# Disallow elements from old website.
Disallow: /*/content
Disallow: /*/content/*
Disallow: /*/taxonomy/
Disallow: /*/taxonomy/*
Disallow: /*/search
Disallow: /*/search/*
Disallow: /*/rss
Disallow: /*/rss/*
Disallow: /*/node/*
Disallow: /dossier/
Disallow: /*/dossier/
Disallow: /*/dossier/*
Disallow: /edition/
Disallow: /*/edition/
Disallow: /*/rubrique/
Disallow: /*?event=

# Disallow GTP robots.
User-agent: GPTBot
Disallow: /
User-agent: ChatGPT-User 
Disallow: /
User-agent: CCBot
Disallow: /