# Robots.txt for MiraculousLadybug.com - SEO & AI Optimized
# Domain: https://www.miraculousladybug.com
# Last Updated: 2025-09

# ==================================
# SITEMAP DECLARATIONS (EN + FR)
# ==================================
Sitemap: https://www.miraculousladybug.com/wp-sitemap.xml
Sitemap: https://www.miraculousladybug.com/fr/wp-sitemap.xml

# ==================================
# GENERAL RULES FOR ALL BOTS
# ==================================
User-agent: *
Allow: /

# Block WordPress system & sensitive files
Disallow: /wp-admin/
Allow: /wp-admin/admin-ajax.php
Disallow: /wp-config.php
Disallow: /wp-config-sample.php
Disallow: /xmlrpc.php
Disallow: /trackback/
Disallow: /.env
Disallow: /.git
Disallow: /readme.html
Disallow: /license.txt

# Block duplicate/low-value pages
Disallow: /?s=
Disallow: /search/
# KEEP author pages (important for you)
# Disallow: /author/   <-- intentionally NOT blocking
Disallow: /date/
Disallow: /archives/
Disallow: /*/page/*
Disallow: */feed
Disallow: */rss
Disallow: */embed
Disallow: /comment-page-
Disallow: /?replytocom

# Allow important resources
Allow: /wp-content/uploads/
Allow: /wp-content/themes/
Allow: /*.css
Allow: /*.js
Allow: /*.jpg
Allow: /*.jpeg
Allow: /*.png
Allow: /*.gif
Allow: /*.svg
Allow: /*.webp

# ==================================
# SPECIFIC BOT RULES
# ==================================
# Google
User-agent: Googlebot
Allow: /

# Bing
User-agent: Bingbot
Crawl-delay: 1
Allow: /

# AI Crawlers
User-agent: GPTBot
Allow: /
Crawl-delay: 2

User-agent: ClaudeBot
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: CCBot
Allow: /
Crawl-delay: 10

# SEO Tools
User-agent: AhrefsBot
Allow: /
Crawl-delay: 5

User-agent: SemrushBot
Allow: /
Crawl-delay: 5

# ==================================
# SOCIAL MEDIA CRAWLERS
# ==================================
User-agent: LinkedInBot
User-agent: TwitterBot
User-agent: Pinterest
User-agent: WhatsApp
Allow: /