# ============================================================
# robots.txt — umrahandalusia.com
# Andalusia Travel & Tours Sdn Bhd
# ------------------------------------------------------------
# SEO Strategy & AI Optimization : Mehmed Aezhad (https://warbyasa.com)
# SEO Agency                     : Warbyasa (https://warbyasa.com)
# Standard                       : Google Core Update 2026 — Crawl Budget & AI-Search Compliance
# Last Updated                   : 2026-05-22
#
# NOTE on precedence: Google & Bing use the LONGEST-MATCHING rule, not file
# order. The directives below are written so that specific Disallow paths
# (e.g. /wp-admin/) are longer/more specific than the broad "Allow: /",
# ensuring private areas stay blocked while render assets stay open.
# ============================================================


# ------------------------------------------------------------
# 1) GLOBAL RULES — All standard search-engine crawlers
# ------------------------------------------------------------
User-agent: *

# Protect private WordPress areas (specific = wins over Allow: /)
Disallow: /wp-admin/
Disallow: /wp-login.php
Disallow: /xmlrpc.php
Disallow: /wp-json/
Disallow: /trackback/
Disallow: /comments/feed/
Disallow: /readme.html
Disallow: /license.txt

# Crawl-budget: block zero-SEO-value URLs
Disallow: /?s=
Disallow: /search/
Disallow: /cart/
Disallow: /checkout/
Disallow: /my-account/
Disallow: /*?replytocom=
Disallow: /*?add-to-cart=
Disallow: /*?orderby=
Disallow: /*?filter=

# Block tracking parameters (prevents duplicate content)
Disallow: /*?utm_
Disallow: /*?fbclid=
Disallow: /*?gclid=
Disallow: /*?ref=

# Block Elementor templates, library & internal preview/edit URLs
Disallow: /elementor/
Disallow: /*?elementor-preview=
Disallow: /*?elementor_library=
Disallow: /elementor_library/
Disallow: /*?action=elementor
Disallow: /wp-content/uploads/elementor/css/
Disallow: /wp-json/elementor/

# Re-open required AJAX endpoint + render assets (more specific Allow)
Allow: /wp-admin/admin-ajax.php
Allow: /wp-content/uploads/
Allow: /wp-content/plugins/
Allow: /wp-includes/js/
Allow: /*.js$
Allow: /*.css$

# Everything else is crawlable
Allow: /


# ------------------------------------------------------------
# 2) AI / LLM CRAWLERS — Fully opened for AI-Search visibility
# ------------------------------------------------------------

# OpenAI
User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: OAI-SearchBot
Allow: /

# Google AI (Gemini / AI Overviews / Vertex)
User-agent: Google-Extended
Allow: /

# Anthropic (Claude)
User-agent: ClaudeBot
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: anthropic-ai
Allow: /

# Perplexity
User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

# Apple Intelligence
User-agent: Applebot-Extended
Allow: /

# Microsoft / Bing
User-agent: bingbot
Allow: /

# Meta AI
User-agent: meta-externalagent
Allow: /

User-agent: FacebookBot
Allow: /

# Common Crawl (open training dataset)
User-agent: CCBot
Allow: /

# Other AI agents
User-agent: YouBot
Allow: /

User-agent: cohere-ai
Allow: /

User-agent: Amazonbot
Allow: /


# ------------------------------------------------------------
# 3) BLOCKED BOTS — Aggressive SEO scrapers / server load
# ------------------------------------------------------------
User-agent: AhrefsBot
Disallow: /

User-agent: SemrushBot
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: DotBot
Disallow: /

User-agent: PetalBot
Disallow: /


# ------------------------------------------------------------
# 4) SITEMAP & AI MANIFEST
# ------------------------------------------------------------
Sitemap: https://umrahandalusia.com/sitemap_index.xml

# AI Knowledge Interface for LLM agents:
# https://umrahandalusia.com/llms.txt