# ============================================================
# Portuguesepedia — Global robots.txt
# Purpose: Allow search and social sharing while protecting
#          admin and system directories.
# ============================================================

# Allow all well-behaved crawlers full access to public content
User-agent: *
Disallow: /wp-admin/
Disallow: /wp-includes/
Allow: /wp-admin/admin-ajax.php
Allow: /wp-content/uploads/
Allow: /wp-content/plugins/*.css
Allow: /wp-content/plugins/*.js
Allow: /wp-content/themes/*.css
Allow: /wp-content/themes/*.js

# Block sensitive files and paths that shouldn't be indexed
Disallow: /readme.html
Disallow: /license.txt
Disallow: /xmlrpc.php
Disallow: /wp-login.php
Disallow: /wp-register.php
Disallow: /wp-config.php
Disallow: /wp-content/*.php
Disallow: /register/
Disallow: /account/
Disallow: /login/
Disallow: /wp-content/cache/

# Optional: prevent search results and internal query strings from indexing
Disallow: /*?s=
Disallow: /*?*

# Explicitly allow social media crawlers (for Open Graph, Twitter Cards, etc.)
User-agent: facebookexternalhit
Allow: /
User-agent: Twitterbot
Allow: /
User-agent: LinkedInBot
Allow: /

# Sitemap (auto-discovery for search engines)
Sitemap: https://portuguesepedia.com/wp-sitemap.xml