#
# 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: *
# Content Signals (contentsignals.org), added 2026-11-09
Content-Signal: search=yes, ai-input=yes, ai-train=yes
# 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
# Paths (clean URLs)
Disallow: /admin/
Disallow: /comment/reply/
Disallow: /filter/tips
Disallow: /node/add/
Disallow: /search/
Disallow: /flag/
Disallow: /api/
Disallow: /user/register
# 2026-09-12: legacy parkingmadeeasy directory URLs, ~3,400 bot 404s/day (SemrushBot)
Disallow: /business-car-parking-spaces/
Disallow: /user/password
Disallow: /user/login
Disallow: /user/logout
Disallow: /user/
Disallow: /account/
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/flag/
Disallow: /index.php/api/
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

# AI search / answer engines: explicitly allowed. Stacked user-agents share
# one rule group; named bots ignore the "*" group, so the critical Disallows
# from above are repeated here to keep /admin, /api, /user/* off-limits.
User-agent: GPTBot
User-agent: OAI-SearchBot
User-agent: ChatGPT-User
User-agent: ClaudeBot
User-agent: anthropic-ai
User-agent: Claude-Web
User-agent: PerplexityBot
User-agent: Perplexity-User
User-agent: Google-Extended
User-agent: Applebot-Extended
User-agent: Claude-SearchBot
User-agent: Claude-User
User-agent: MistralAI-Index
User-agent: MistralAI-User
User-agent: xAI-SearchBot
User-agent: Kimi-SearchBot
User-agent: Kimi-User
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Disallow: /admin/
Disallow: /comment/reply/
Disallow: /filter/tips
Disallow: /node/add/
Disallow: /search/
Disallow: /flag/
Disallow: /api/
Disallow: /user/register
Disallow: /user/password
Disallow: /user/login
Disallow: /user/logout
Disallow: /user/
Disallow: /account/
Disallow: /business-car-parking-spaces/
Disallow: /media/oembed
Disallow: /*/media/oembed
Allow: /

# SEO tool crawlers: one request every 20 seconds each.
# Named bots ignore the "*" group, so the key Disallows are repeated here.
User-agent: AhrefsBot
User-agent: SemrushBot
User-agent: DataForSeoBot
User-agent: MJ12bot
User-agent: DotBot
User-agent: BLEXBot
User-agent: PetalBot
Crawl-delay: 20
Disallow: /admin/
Disallow: /comment/reply/
Disallow: /filter/tips
Disallow: /node/add/
Disallow: /search/
Disallow: /flag/
Disallow: /api/
Disallow: /business-car-parking-spaces/
Disallow: /user/
Disallow: /account/
Disallow: /media/oembed
Disallow: /*/media/oembed
Disallow: /index.php/
Allow: /

# CCBot allowed (2026-07-19): Common Crawl web-graph presence needed for backlink measurement.

# Sitemap location
Sitemap: https://www.parksy.com/sitemap.xml

# Agentic Resource Discovery manifest (agenticresourcediscovery.org)
Agentmap: https://www.parksy.com/.well-known/ard.json