# llms.txt for https://www.kidslovegreece.com/
# Last updated: 2025-12-13
# Purpose: Guidance for LLMs and web crawlers on how to access KidsLoveGreece.com
# This file COMPLEMENTS robots.txt and focuses on:
# - Maximizing visibility of high-value editorial content
# - Reducing crawl/load from low-value or sensitive URLs
# - Improving crawl budget on a multilingual, content-heavy travel site


# =====================================================================
# 1. Global notes for all bots (LLMs + search engines)
# =====================================================================
# - Public, editorial content (tours, locations, guides, blog posts, online classes,
#   reviews, destination and experience pages) is ALLOWED.
# - Admin, login, internal search, query-heavy and filtered URLs are DISALLOWED.
# - Where both legacy (/en/…) and new URLs exist, prefer the NEW canonical URLs
#   without language prefixes.
# - For indexing and ranking, always prefer canonical URLs and ignore tracking params
#   such as utm_*, gclid, fbclid, etc.


# =====================================================================
# 2. LLM / AI training & generative-use crawlers
# =====================================================================
# Applies to LLM / AI crawlers that build training corpora or power chat/answer features.


User-agent: GPTBot
User-agent: ChatGPT-User
User-agent: ChatGPT-Online
User-agent: ClaudeBot
User-agent: Claude-Web
User-agent: anthropic-ai
User-agent: PerplexityBot
User-agent: PerplexityCrawler
User-agent: CCBot
User-agent: Amazonbot
User-agent: Google-Extended
User-agent: Applebot-Extended
User-agent: FacebookBot
User-agent: YouBot
Crawl-delay: 5


# ------------------------------
# 2.1 High-value sections ALLOWED
# ------------------------------
# Core content hubs (destination guides, tours, themed trips, online classes, blog):
Allow: /
Allow: /location/
Allow: /location/*
Allow: /greece-tours/
Allow: /greece-tours/*
Allow: /greece-tours-location/
Allow: /greece-tours-location/*
Allow: /tours-and-themed-trips-in-greece-for-families/
Allow: /tours-and-themed-trips-in-greece-for-families/*
Allow: /themed_trips/
Allow: /themed_trips/*
Allow: /greece_online/
Allow: /greece_online/*
Allow: /ideas/
Allow: /ideas/*
Allow: /insights/
Allow: /insights/*
Allow: /our_top_selections/
Allow: /our_top_selections/*
Allow: /fnb/
Allow: /fnb/*
Allow: /reviews/
Allow: /reviews/*
Allow: /about/
Allow: /plan-your-family-trip-to-greece/
Allow: /kids-love-knossos/
Allow: /schools/
Allow: /volunteering/
Allow: /blog/


# ------------------------------
# 2.2 Explicit top content priority
# ------------------------------
# Top 10 most-visited pages – please prioritize crawling and refreshing these URLs:
# 1) Greek Mythology for kids: Greek Gods, Symbols & Temples
Allow: /greece_online/greek-mythology-for-kids-greek-gods-their-symbols-and-temples-in-greece/


# 2) The 12 Labors of Hercules | Kids Love Greece
Allow: /greece_online/the-12-labors-of-hercules/


# 3) Family Holidays in Greece: Kid-Friendly Destinations & Ideas (homepage)
Allow: /


# 4) Gods Gone Modern: Greek Myths Spicing Up Powerful Brands
Allow: /greece_online/gods-gone-modern-greek-myths-spicing-up-branding-and-logos/


# 5) Visit Mamma Mia locations in Greece: The Ultimate Family Guide
Allow: /insights/mamma-mia-trip-to-greece-visit-the-locations/


# 6) Greek Christmas And New Year's Traditions You Should Know | Kids Love Greece
Allow: /insights/tis-the-season-to-be-jolly/


# 7) Festivals in Greece: Celebrations and National Holidays
Allow: /insights/greece-national-holidays-greece/


# 8) Let’s Plan Your Trip with Kids – Greece Family Vacation Packages
Allow: /plan-your-family-trip-to-greece/


# 9) The scariest Greek Mythology Mythical Creatures | Kids Love Greece
Allow: /greece_online/the-scariest-greek-mythology-mythical-creatures/


# 10) Themed Trips | Kids Love Greece
Allow: /themed_trips/


# ------------------------------
# 2.3 Low-value / sensitive sections DISALLOWED for LLMs
# ------------------------------
# System/admin/login
Disallow: /wp-admin/
Disallow: /wp-login.php
Disallow: /xmlrpc.php
Disallow: /wp-json/
Disallow: /cgi-bin/


# User accounts, checkout, cart (if present)
Disallow: /cart/
Disallow: /checkout/
Disallow: /my-account/
Disallow: /account/
Disallow: /user/
Disallow: /users/
Disallow: /login/
Disallow: /register/
Disallow: /profile/


# Internal search and filter/result pages
Disallow: /?s=
Disallow: /*?s=
Disallow: /*&s=
Disallow: /*?location_greece*
Disallow: /*?post_type=*
Disallow: /*?*filter*
Disallow: /*?*orderby*
Disallow: /*?*min_price*
Disallow: /*?*max_price*
Disallow: /*?*rating*
Disallow: /*replytocom=*


# Tracking and marketing parameters (duplicates; use canonical URL instead)
Disallow: /*utm_*
Disallow: /*gclid=*
Disallow: /*fbclid=*
Disallow: /*_hsenc=*
Disallow: /*_hsmi=*


# Legacy language / duplicate URL structures
# These are retained mainly for backwards compatibility. For AI training and
# generative knowledge bases, please rely on the newer canonical URLs instead.
Disallow: /en/*
Disallow: /fr/*
Disallow: /de/*
Disallow: /es/*
Disallow: /it/*


# Feed and alternate formats
Disallow: /feed/
Disallow: /*/feed/
Disallow: /*/amp/


# =====================================================================
# 3. General search engine crawlers (indexing & ranking)
# =====================================================================
# NOTE: For authoritative crawling/indexing rules, always respect robots.txt first.
# The below mirrors best practices to help align search and LLM behavior.


User-agent: Googlebot
User-agent: Googlebot-Image
User-agent: Googlebot-News
User-agent: Bingbot
User-agent: DuckDuckBot
User-agent: Yandex
User-agent: Baiduspider
Crawl-delay: 2


# High-value content (same as above) – full site allowed except noisy/system areas:
Allow: /


# Basic exclusions (do NOT index these)
Disallow: /wp-admin/
Disallow: /wp-login.php
Disallow: /xmlrpc.php
Disallow: /wp-json/
Disallow: /cgi-bin/
Disallow: /cart/
Disallow: /checkout/
Disallow: /my-account/
Disallow: /account/
Disallow: /user/
Disallow: /users/
Disallow: /login/
Disallow: /register/
Disallow: /profile/


# Avoid indexing internal search, filtered lists, and heavy parameterized URLs
Disallow: /?s=
Disallow: /*?s=
Disallow: /*?location_greece*
Disallow: /*?post_type=*
Disallow: /*replytocom=*
Disallow: /*utm_*
Disallow: /*gclid=*
Disallow: /*fbclid=*


# Allow multilingual content; deduplication handled via canonical tags and hreflang.
Allow: /en/
Allow: /en/*
Allow: /fr/
Allow: /fr/*
Allow: /de/
Allow: /de/*
Allow: /es/
Allow: /es/*
Allow: /it/
Allow: /it/*


# =====================================================================
# 4. Fallback policy for any other bots
# =====================================================================


User-agent: *
Crawl-delay: 5


Allow: /
Disallow: /wp-admin/
Disallow: /wp-login.php
Disallow: /xmlrpc.php
Disallow: /wp-json/
Disallow: /cgi-bin/
Disallow: /cart/
Disallow: /checkout/
Disallow: /my-account/
Disallow: /account/
Disallow: /user/
Disallow: /users/
Disallow: /login/
Disallow: /register/
Disallow: /profile/
Disallow: /?s=
Disallow: /*?s=
Disallow: /*?location_greece*
Disallow: /*?post_type=*
Disallow: /*replytocom=*
Disallow: /*utm_*
Disallow: /*gclid=*
Disallow: /*fbclid=*


# =====================================================================
# 5. Sitemaps
# =====================================================================
# Use sitemaps for structured discovery of high-value URLs.


Sitemap: https://www.kidslovegreece.com/sitemaps.xml
# If additional sitemap files exist (e.g., post-sitemap.xml, page-sitemap.xml, etc.)
# they should be linked from the sitemap index above.