# --- START Clean and Optimized Robots.txt for Catalog/Product Website (WordPress) ---
# This file applies best practices for crawl budget optimization, AI bot control,
# and ensures product pages are correctly indexed.
# ANY RESTRICTIONS EXPRESSED VIA CRAWLER EXCLUSION (DISALLOW) ARE EXPRESS
# RESERVATIONS OF RIGHTS UNDER ARTICLE 4 OF THE EUROPEAN UNION DIRECTIVE 2019/790
# ON COPYRIGHT AND RELATED RIGHTS IN THE DIGITAL SINGLE MARKET.
User-Agent: *
# Allow access to the entire site by default. Specific exclusions are listed below.
Allow: /
# --- WordPress Specific Exclusions to Optimize Crawl Budget ---
# Block the main administrative directory
Disallow: /wp-admin/
# IMPORTANT: Allow admin-ajax.php for correct page rendering by bots
Allow: /wp-admin/admin-ajax.php
# Block system files and directories
Disallow: /wp-includes/
Disallow: /wp-content/plugins/
Disallow: /wp-content/themes/
Disallow: /xmlrpc.php
# Block search results, feeds, and comments to prevent duplicate content indexation
Disallow: /search/
Disallow: /*?s=*$
Disallow: /feed/
Disallow: /comments/feed/
Disallow: /trackback/
# Block tag pages if they contain low-quality or duplicate content
Disallow: /tag/
# --- Catalog/Product Specific Exclusions (Common for Filters) ---
# Block URLs with question marks that contain "filter", which often create
# irrelevant, duplicated, or parameter-based URLs in product listings.
Disallow: /*?filter=*
# --- AI BOT CONTROL DIRECTIVES ---
# These directives block specific bots used for generative AI training and data gathering.
User-agent: Amazonbot
Disallow: /
User-agent: Applebot-Extended
Disallow: /
User-agent: Bytespider
Disallow: /
User-agent: CCBot
Disallow: /
User-agent: ClaudeBot
Disallow: /
User-agent: Google-Extended
Disallow: /
User-agent: GPTBot
Disallow: /
User-agent: meta-externalagent
Disallow: /
# --- Sitemap ---
Sitemap: https://4dmedica.ai/sitemap_index.xml
# --- END Clean and Optimized Robots.txt for Catalog/Product Website ----