#
# 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

# Allow good bots
User-agent: Googlebot
User-agent: Bingbot
User-agent: DuckDuckBot
Disallow:

# Block bad bots
User-agent: AhrefsBot
User-agent: SemrushBot
User-agent: MJ12bot
User-agent: DotBot
User-agent: BLEXBot
User-agent: rogerbot
User-agent: spbot
User-agent: seoscanners.net
User-agent: MauiBot
User-agent: PetalBot
User-agent: Sogou
User-agent: Exabot
User-agent: UptimeRobot
User-agent: SiteAuditBot
User-agent: GPTBot
User-agent: Google-Extended
User-agent: CCBot
User-agent: Claude-Web
User-agent: anthropic-ai
User-agent: Bytespider
User-agent: img2dataset
User-agent: Omgili
User-agent: Omgilibot
User-agent: FacebookBot
User-agent: magpie-crawler
User-agent: Baiduspider
User-agent: YandexBot
Disallow: /

# Block sensitive Drupal directories
User-agent: *
Disallow: /modules/
Disallow: /themes/
Disallow: /sites/default/files/private/
Disallow: /user/
Disallow: /node/
Disallow: /filter/
Disallow: /search/
Disallow: /comment/
Disallow: /logout/
Disallow: /update.php
Disallow: /xmlrpc.php

# Allow public files
Allow: /sites/default/files/

# Sitemap location
Sitemap: https://www.ligue-cancer.net/sitemap.xml