# Robots.txt for debetonboorder.nl
# Last updated: March 2026

User-agent: *

# Allow all main content
Allow: /

# Block preview/draft pages
Disallow: /*preview=true
Disallow: /*page_id=*&preview=true
Disallow: /*page_id=*preview*

# Block Elementor internal pages
Disallow: /*elementor_library=*
Disallow: /elementor

# Block malformed URLs with //1000 suffix
Disallow: /*//1000

# Block non-existent language versions (returning 4xx errors)
Disallow: /it/
Disallow: /de/
Disallow: /pt/
Disallow: /fr/
Disallow: /ru/
Disallow: /es/
Disallow: /zh-CN/

# Block discontinued airco/product sections (no longer selling)
Disallow: /airco/
Disallow: /product/
Disallow: /product-category/
Disallow: /merk/
Disallow: /en/airco/
Disallow: /en/AC/
Disallow: /en/product/
Disallow: /en/product-category/
Disallow: /airco-assortiment/

# Block WordPress internal/admin areas
Disallow: /wp-admin/
Disallow: /*/wp-admin/
Disallow: /*admin-ajax.php*
Disallow: /wp-includes/
Disallow: /wp-content/plugins/
Disallow: /wp-content/cache/
Disallow: /wp-json/
Disallow: /xmlrpc.php
Disallow: /readme.html
Disallow: /license.txt

# Allow specific wp-content folders for SEO
Allow: /wp-content/uploads/
Allow: /wp-content/themes/

# Block query parameters that create duplicate content
Disallow: /*?replytocom=*
Disallow: /*?s=*
Disallow: /*&s=*
Disallow: /*?attachment_id=*
Disallow: /*?p=*

# Block tracking/marketing parameters
Disallow: /*?fbclid=*
Disallow: /*?utm_source=*
Disallow: /*?utm_medium=*
Disallow: /*?utm_campaign=*
Disallow: /*?gclid=*
Disallow: /*?msclkid=*

# Block GTranslate admin/editing URLs
Disallow: /*?language_edit=*
Disallow: /*&language_edit=*

# Block AMP versions if not used
Disallow: /*?amp
Disallow: /*&amp

# Block author archives (thin content)
Disallow: /author/
Disallow: /en/author/

# Block feed URLs
Disallow: /feed/
Disallow: /*/feed/
Disallow: /comments/feed/

# Block tag archives if not used strategically
Disallow: /tag/
Disallow: /en/tag/

# Block trackback URLs
Disallow: /trackback/
Disallow: /*/trackback/

# Block print/PDF versions if any
Disallow: /*?print=*
Disallow: /*?pdf=*

# Crawl-delay (optional - remove if you want faster crawling)
# Crawl-delay: 1

# Social media bots (allow full access for rich previews)
User-agent: Twitterbot
Allow: /

User-agent: facebookexternalhit
Allow: /

# Sitemaps
Sitemap: https://debetonboorder.nl/sitemap_index.xml
Sitemap: https://debetonboorder.nl/en/sitemap_index.xml