# LLM.TXT — Guidance for AI/LLM and AI-search crawlers
# Domain: https://flyflapper.com
# Owner contact: Contact: support@flapper.aero
# Purpose: Maximize visibility in reputable AI assistants/search while restricting unwanted training crawlers.
# Placement: /llm.txt  (and optionally /.well-known/llm.txt)

############################
# 1) Site & Data Inventory #
############################

Site: https://flyflapper.com
Sitemap: https://flyflapper.com/sitemap.xml

# Public structured data feeds (JSON/CSV/MD):
Data: https://flyflapper.com/data/aeronaves.index.json
# Data: https://flyflapper.com/data/cities.json
# Data: https://flyflapper.com/data/routes.json
# Data: https://flyflapper.com/data/prices.json
# Data: https://flyflapper.com/data/prices.json
Data: https://flyflapper.com/data/stories.json
Data: https://flyflapper.com/data/faq.json

########################################
# 2) Global Defaults (human-readable)  #
########################################
# Default stance: all public pages are ALLOWED to be crawled by reputable AI assistants and AI search engines.
# Only explicitly disallowed paths (see below) are blocked.

Default: allow

########################################
# 3) Path-Level Preferences (global)   #
########################################
# Disallow (exact or prefix match per standard robots semantics):
# These WordPress admin/auth endpoints must NOT be used by AI crawlers.
Disallow: /stories/wp-admin
Disallow: /stories/wp-login.php

# Note: All other pages are implicitly allowed under the Default: allow directive above.

##########################################################
# 4) Crawler-Specific Rules (major AI/AI-search crawlers) #
##########################################################

# --- OpenAI (ChatGPT ecosystem) ---
User-agent: GPTBot
Allow: /
Disallow: /stories/wp-admin
Disallow: /stories/wp-login.php

User-agent: ChatGPT-User
Allow: /
Disallow: /stories/wp-admin
Disallow: /stories/wp-login.php

User-agent: OAI-SearchBot
Allow: /
Disallow: /stories/wp-admin
Disallow: /stories/wp-login.php

# --- Anthropic (Claude ecosystem) ---
User-agent: ClaudeBot
Allow: /
Disallow: /stories/wp-admin
Disallow: /stories/wp-login.php

User-agent: Claude-User
Allow: /
Disallow: /stories/wp-admin
Disallow: /stories/wp-login.php

User-agent: Claude-SearchBot
Allow: /
Disallow: /stories/wp-admin
Disallow: /stories/wp-login.php

# --- Perplexity (AI search) ---
User-agent: PerplexityBot
Allow: /
Disallow: /stories/wp-admin
Disallow: /stories/wp-login.php

# --- Google AI extensions ---
User-agent: Google-Extended
Allow: /
Disallow: /stories/wp-admin
Disallow: /stories/wp-login.php

# --- Apple AI extensions ---
User-agent: Applebot-Extended
Allow: /
Disallow: /stories/wp-admin
Disallow: /stories/wp-login.php

# --- ByteDance ---
User-agent: Bytespider
Allow: /
Disallow: /stories/wp-admin
Disallow: /stories/wp-login.php

# --- Common Crawl ---
User-agent: CCBot
Allow: /
Disallow: /stories/wp-admin
Disallow: /stories/wp-login.php

# --- Meta (Facebook/Instagram) ---
User-agent: meta-externalagent
Allow: /
Disallow: /stories/wp-admin
Disallow: /stories/wp-login.php

# --- Amazon ---
User-agent: Amazonbot
Allow: /
Disallow: /stories/wp-admin
Disallow: /stories/wp-login.php

########################################
# 5) Rate & Courtesy (non-binding)    #
########################################
# Please crawl politely:
Crawl-delay: 3

############################
# 6) Human-Readable Policy #
############################
Policy: Public pages may be referenced in AI answers and AI search with attribution and a visible link back to https://flyflapper.com.
Policy: Do not reproduce gated/paid or user-specific content. Respect robots.txt, noindex headers, and standard caching policies.