#
# 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/
# 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: /archives-en-ligne/ead.pdf
Disallow: /pleade/ead.pdf
Disallow: /archives-en-ligne/ead.pdf*
Disallow: /pleade/ead.pdf*
Disallow: /archives-en-ligne/ead.pdf?
Disallow: /pleade/ead.pdf?
Disallow: /archives-en-ligne/ead.pdf$
Disallow: /pleade/ead.pdf$

# Blocage de Amazonbot
User-agent: Amazonbot               # Amazon's user agent
Disallow: /            # disallow this directory
# limitation google
User-agent: *
Crawl-delay: 10

User-agent: GPTBot
Disallow: /
User-agent: Google-Extended
Disallow: /
User-agent: ClaudeBot
Disallow: /
User-agent: anthropic-ai
Disallow: /
User-agent: ClaudeBot/1.0
Disallow: /
User-agent: Claude-web
Disallow: /
User-agent: Bytespider
Disallow: /
User-agent: SemrushBot
Disallow: /
User-agent: CCBot
Disallow: /
User-Agent: PerplexityBot
Disallow: /
User-agent: Diffbot
Disallow: /
User-agent: FacebookBot
Disallow: /
User-agent: YouBot
Disallow: /
User-agent: cohere-ai
Disallow: /
User-agent: facebookexternalhit/1.1 (+http://www.facebook.com/externalhit_uatext.php)
Disallow: /
User-agent: facebookexternalhit/1.1
Disallow: /
User-agent: facebookcatalog/1.0
Disallow: /
User-agent: facebookexternalhit
Disallow: /
User-agent: facebookcatalog
Disallow: /
User-agent: SemrushBot/7~bl
Disallow: /