# robots.txt for meet.codexal.co
#
# GENERATED FILE — do not edit by hand.
#   Source: includes/seo.php (cmPrivatePaths, cmCrawlerGroups)
#   Rebuild: php tools/seo-build.php
#
# Everything public is crawlable. What is disallowed is disallowed because it
# is private, per-user or an internal endpoint — never to hide it.
#
# The rules are repeated under each named group on purpose: a crawler obeys
# only the most specific group that matches it, so a named group that listed
# "Allow: /" alone would hand that crawler the meeting rooms.

# ---------------------------------------------------------------------------
# Default — every crawler not named below
# ---------------------------------------------------------------------------
User-agent: *
Allow: /

# Private and per-user areas
Disallow: /meeting.php
Disallow: /lobby.php
Disallow: /guest_join.php
Disallow: /ended.php
Disallow: /account.php
Disallow: /dashboard.php
Disallow: /schedule.php
Disallow: /recap.php
Disallow: /recaps.php
Disallow: /feedback.php
Disallow: /billing.php
Disallow: /invoice.php
Disallow: /billing_return.php
Disallow: /calendar.php
# A room opened inside somebody else's site, reached only with a signed
# single-use ticket. There is nothing here for a crawler to index and the ticket
# in the URL would be spent by fetching it.
Disallow: /embed.php

# Application internals
Disallow: /admin/
# The developer console: private to each integration, and every page already
# carries a noindex tag. The public documentation lives at /developers.php.
Disallow: /developer/
Disallow: /api/
Disallow: /config/
Disallow: /includes/
Disallow: /cron/

# Maintenance scripts
Disallow: /migrate.php
Disallow: /drop_fk.php
Disallow: /add_sender_name_column.php
Disallow: /install_summary.php
Disallow: /summary_doctor.php
Disallow: /zoho_setup.php
Disallow: /paytabs_currency_check.php
Disallow: /test.html

# Generators reached through their canonical addresses
Disallow: /sitemap-xml.php
Disallow: /sitemap-index.php
Disallow: /llms.php

# Query strings that mint infinite duplicate URLs
Disallow: /*?PHPSESSID=
Disallow: /*?utm_
Disallow: /*?fbclid=
Disallow: /*?gclid=

# Assets: blocking CSS, JS or images stops a crawler rendering the page the
# way a visitor sees it, which costs more than it protects.
Allow: /assets/

# ---------------------------------------------------------------------------
# Search engines
# The crawlers that build a search index. Nothing special: they get the same
# rules as everyone else, written out so the intent is explicit.
# ---------------------------------------------------------------------------
User-agent: Googlebot
User-agent: Googlebot-Image
User-agent: Bingbot
User-agent: Slurp
User-agent: DuckDuckBot
User-agent: YandexBot
User-agent: Baiduspider
User-agent: Applebot
Allow: /

# Private and per-user areas
Disallow: /meeting.php
Disallow: /lobby.php
Disallow: /guest_join.php
Disallow: /ended.php
Disallow: /account.php
Disallow: /dashboard.php
Disallow: /schedule.php
Disallow: /recap.php
Disallow: /recaps.php
Disallow: /feedback.php
Disallow: /billing.php
Disallow: /invoice.php
Disallow: /billing_return.php
Disallow: /calendar.php

# Application internals
Disallow: /admin/
Disallow: /api/
Disallow: /config/
Disallow: /includes/
Disallow: /cron/

# Maintenance scripts
Disallow: /migrate.php
Disallow: /drop_fk.php
Disallow: /add_sender_name_column.php
Disallow: /install_summary.php
Disallow: /summary_doctor.php
Disallow: /zoho_setup.php
Disallow: /paytabs_currency_check.php
Disallow: /test.html

# Generators reached through their canonical addresses
Disallow: /sitemap-xml.php
Disallow: /sitemap-index.php
Disallow: /llms.php

# Query strings that mint infinite duplicate URLs
Disallow: /*?PHPSESSID=
Disallow: /*?utm_
Disallow: /*?fbclid=
Disallow: /*?gclid=

# Assets: blocking CSS, JS or images stops a crawler rendering the page the
# way a visitor sees it, which costs more than it protects.
Allow: /assets/

# ---------------------------------------------------------------------------
# AI assistants and answer engines
# These read pages to answer questions, and they cite the page the answer
# came from. Blocking them removes Codexal Meet from the answer, not from
# the training set — the answer is simply given about someone else. They
# are allowed deliberately, and pointed at /llms.txt, which is the same site
# written for a model to read in one pass.
# ---------------------------------------------------------------------------
User-agent: GPTBot
User-agent: OAI-SearchBot
User-agent: ChatGPT-User
User-agent: ClaudeBot
User-agent: Claude-User
User-agent: Claude-SearchBot
User-agent: PerplexityBot
User-agent: Perplexity-User
User-agent: Google-Extended
User-agent: Applebot-Extended
User-agent: Bingbot-Extended
User-agent: Amazonbot
User-agent: meta-externalagent
User-agent: cohere-ai
User-agent: YouBot
User-agent: Diffbot
Allow: /

# Private and per-user areas
Disallow: /meeting.php
Disallow: /lobby.php
Disallow: /guest_join.php
Disallow: /ended.php
Disallow: /account.php
Disallow: /dashboard.php
Disallow: /schedule.php
Disallow: /recap.php
Disallow: /recaps.php
Disallow: /feedback.php
Disallow: /billing.php
Disallow: /invoice.php
Disallow: /billing_return.php
Disallow: /calendar.php

# Application internals
Disallow: /admin/
Disallow: /api/
Disallow: /config/
Disallow: /includes/
Disallow: /cron/

# Maintenance scripts
Disallow: /migrate.php
Disallow: /drop_fk.php
Disallow: /add_sender_name_column.php
Disallow: /install_summary.php
Disallow: /summary_doctor.php
Disallow: /zoho_setup.php
Disallow: /paytabs_currency_check.php
Disallow: /test.html

# Generators reached through their canonical addresses
Disallow: /sitemap-xml.php
Disallow: /sitemap-index.php
Disallow: /llms.php

# Query strings that mint infinite duplicate URLs
Disallow: /*?PHPSESSID=
Disallow: /*?utm_
Disallow: /*?fbclid=
Disallow: /*?gclid=

# Assets: blocking CSS, JS or images stops a crawler rendering the page the
# way a visitor sees it, which costs more than it protects.
Allow: /assets/

# ---------------------------------------------------------------------------
# Link preview and social unfurling
# These fetch a single URL to render a card. They need the Open Graph tags
# in <head>, which means they need the page.
# ---------------------------------------------------------------------------
User-agent: Twitterbot
User-agent: facebookexternalhit
User-agent: LinkedInBot
User-agent: WhatsApp
User-agent: TelegramBot
User-agent: Slackbot-LinkExpanding
User-agent: Discordbot
Allow: /

# Private and per-user areas
Disallow: /meeting.php
Disallow: /lobby.php
Disallow: /guest_join.php
Disallow: /ended.php
Disallow: /account.php
Disallow: /dashboard.php
Disallow: /schedule.php
Disallow: /recap.php
Disallow: /recaps.php
Disallow: /feedback.php
Disallow: /billing.php
Disallow: /invoice.php
Disallow: /billing_return.php
Disallow: /calendar.php

# Application internals
Disallow: /admin/
Disallow: /api/
Disallow: /config/
Disallow: /includes/
Disallow: /cron/

# Maintenance scripts
Disallow: /migrate.php
Disallow: /drop_fk.php
Disallow: /add_sender_name_column.php
Disallow: /install_summary.php
Disallow: /summary_doctor.php
Disallow: /zoho_setup.php
Disallow: /paytabs_currency_check.php
Disallow: /test.html

# Generators reached through their canonical addresses
Disallow: /sitemap-xml.php
Disallow: /sitemap-index.php
Disallow: /llms.php

# Query strings that mint infinite duplicate URLs
Disallow: /*?PHPSESSID=
Disallow: /*?utm_
Disallow: /*?fbclid=
Disallow: /*?gclid=

# Assets: blocking CSS, JS or images stops a crawler rendering the page the
# way a visitor sees it, which costs more than it protects.
Allow: /assets/

# ---------------------------------------------------------------------------
# Where to find the machine-readable copies of this site
# ---------------------------------------------------------------------------
Sitemap: https://meet.codexal.co/sitemap.xml
Sitemap: https://meet.codexal.co/sitemap-index.xml

# For language models: https://meet.codexal.co/llms.txt
# Full text:           https://meet.codexal.co/llms-full.txt