#
# 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

# ---------------------------------------------------------------------------
# Crawler controls (added 2026-08-18)
#
# Bots were following the "add to comparison" flag links and the faceted
# search permutations. Each hit created an anonymous session plus a `flagging`
# row, which inflated the table to 218k rows and drove sustained MariaDB CPU
# load. The rules below close both entry points.
#
# NOTE: a crawler obeys only ONE User-agent group - the most specific one that
# matches it. Rules are NOT inherited from "*", so the groups further down
# repeat what they need.
# ---------------------------------------------------------------------------

# Flag actions are state-changing links and must never be crawled.
Disallow: /flag/
Disallow: /*/flag/
Disallow: /index.php/flag/
# Comparison pages are per-session and have no stable content to index.
Disallow: /comparison
Disallow: /*/comparison
# Faceted search: filter permutations are an effectively infinite URL space.
Disallow: /*?*f%5B
Disallow: /*?*f[
Disallow: /*?*c=
Disallow: /*?*compare=
# Locale-prefixed variants of the core paths above (site uses /us/en, /de/de, ...).
Disallow: /*/admin/
Disallow: /*/search/
Disallow: /*/user/register
Disallow: /*/user/password
Disallow: /*/user/login
Disallow: /*/user/logout
Disallow: /*/comment/reply/
Disallow: /*/node/add/
Crawl-delay: 10

# AI training / scraping crawlers - no crawl budget allocated.
User-agent: GPTBot
User-agent: OAI-SearchBot
User-agent: ChatGPT-User
User-agent: ClaudeBot
User-agent: anthropic-ai
User-agent: Claude-Web
User-agent: CCBot
User-agent: Bytespider
User-agent: meta-externalagent
User-agent: FacebookBot
User-agent: PerplexityBot
User-agent: Applebot-Extended
User-agent: Google-Extended
User-agent: Diffbot
User-agent: Omgilibot
Disallow: /

# SEO / audit crawlers - allowed, but throttled and kept off the expensive paths.
User-agent: AhrefsBot
User-agent: AhrefsSiteAudit
User-agent: SemrushBot
User-agent: PetalBot
User-agent: MJ12bot
User-agent: DotBot
User-agent: DataForSeoBot
User-agent: BLEXBot
User-agent: Sogou web spider
Crawl-delay: 30
Disallow: /flag/
Disallow: /*/flag/
Disallow: /comparison
Disallow: /*/comparison
Disallow: /*?*f%5B
Disallow: /*?*f[
Disallow: /*?*c=
Disallow: /*?*compare=
Disallow: /admin/
Disallow: /*/admin/
Disallow: /*/user/
Disallow: /core/
Disallow: /profiles/