###
### This is a copy of main robots.txt to track in repository
###

# ========== Core allowances (let Google fetch assets) ==========
User-agent: *
Allow: /wp-content/uploads/        # images/files used by pages
Allow: /wp-includes/js/            # core JS needed for rendering

# ========== Block low-value/duplicate endpoints ==========
Disallow: /print/?*                # print views (duplicate of articles)
Disallow: /feed/*                  # RSS/Atom feeds (thin/duplicate)
Disallow: /comment-page-*          # paginated comment URLs
Disallow: /?attachment_id=         # legacy attachment URLs
Disallow: /embed/                  # oEmbed endpoints

# ========== Block admin/system noise (non-content) ==========
Disallow: /wp-admin/               # admin area
Disallow: /wp-login.php            # login
Disallow: /wp-register.php         # registration
Disallow: /xmlrpc.php              # legacy XML-RPC endpoint
Disallow: /wp-content/cache/       # cache artifacts
Disallow: /cgi-bin/                # server scripts
Disallow: /e/                      # custom utility paths
Disallow: /show-error-*            # error pages or debug views
Disallow: /wp-json/                # REST API (block crawl if not public)
Disallow: /readme.html             # version disclosure
Disallow: /license.txt             # license file
Disallow: /trackback/              # legacy blog trackbacks

# ========== Bots with special allowances ==========
User-agent: Mediapartners-Google
Allow: /

User-agent: Adsbot-Google
Allow: /

User-agent: Googlebot-Image
Allow: /

User-agent: Googlebot-Mobile
Allow: /

User-agent: cXensebot
Allow: /

# ========== Sitemaps ==========
Sitemap: https://tricycle.org/sitemap_index.xml