# robots.txt - montessorimindshc.vic.edu.au
#
# Structure note: a crawler obeys ONLY the most specific User-agent group that
# matches it, and ignores the "*" group entirely. Every group below therefore
# repeats the same protective Disallow rules. Anything not disallowed is
# allowed by default, so no blanket "Allow: /" is used - a blanket allow placed
# above a Disallow is ignored by strict parsers but nullifies the Disallow in
# naive ones.
 
# ---------- All crawlers ----------
User-agent: *
Allow: /wp-admin/admin-ajax.php
Disallow: /wp-admin/
Disallow: /wp-login.php
Disallow: /?s=
Disallow: /search/
Disallow: /*?replytocom=
 
# ---------- AI search and answer engines ----------
# These crawlers decide whether Montessori Minds HC can appear in ChatGPT Search,
# Perplexity, Copilot and Claude answers. They are deliberately NOT blocked.
User-agent: OAI-SearchBot
User-agent: ChatGPT-User
User-agent: Claude-SearchBot
User-agent: Claude-User
User-agent: PerplexityBot
User-agent: Perplexity-User
User-agent: Applebot
User-agent: Amazonbot
User-agent: DuckDuckBot
Allow: /wp-admin/admin-ajax.php
Disallow: /wp-admin/
Disallow: /wp-login.php
Disallow: /?s=
Disallow: /search/
 
# ---------- AI training crawlers ----------
# A commercial decision. Allowing these puts Montessori Minds HC into the baseline
# knowledge of future models. Blocking them does NOT remove the centre from AI
# search - that is governed by the retrieval agents above.
User-agent: GPTBot
User-agent: ClaudeBot
User-agent: Google-Extended
User-agent: meta-externalagent
Allow: /wp-admin/admin-ajax.php
Disallow: /wp-admin/
Disallow: /wp-login.php
Disallow: /?s=
Disallow: /search/
 
# ---------- Bulk scrapers with poor robots.txt compliance ----------
User-agent: Bytespider
Disallow: /
 
User-agent: CCBot
Disallow: /

Sitemap: https://montessorimindshc.vic.edu.au/sitemap.xml