# robots.txt for www.terravek.com
# Terravek Systems N.V., Zuidpoortlaan 118, 2628 XK Delft, Netherlands
# Contact: webmaster@terravek.com  ·  Owner: Marketing / Web (ext. 4273)
# Last reviewed: 2026-06-30  ·  ref TVK-WEB-1091
#
# Crawling is welcome. Please be proportionate: this is a shared host.
# If you are building a search index and need higher throughput, write to
# webmaster@terravek.com and we will almost certainly say yes.

User-agent: *
Crawl-delay: 2

# --- Internal and administrative areas -------------------------------------
Disallow: /internal/
Disallow: /intranet/
Disallow: /admin/
Disallow: /cgi-bin/
Disallow: /private/
Disallow: /tmp/
Disallow: /temp/
Disallow: /_backup/
Disallow: /backup/
Disallow: /logs/

# --- Legacy CMS (Contentwerk, retired 2021-11). 301s are in .htaccess ------
Disallow: /cms/
Disallow: /cms/admin/
Disallow: /contentwerk/
Disallow: /index.php
Disallow: /*?page=
Disallow: /*?id=
Disallow: /old/
Disallow: /old-site/
Disallow: /v2/
Disallow: /2011/
Disallow: /2015-site/

# --- Non-production environments (not reachable from the public internet) ---
Disallow: /dev/
Disallow: /test/
Disallow: /staging/
Disallow: /uat/
Disallow: /preview/
Disallow: /sandbox/

# --- Duplicate, generated or low-value paths --------------------------------
Disallow: /search.html
Disallow: /*?q=
Disallow: /*?utm_
Disallow: /*?ref=
Disallow: /print/
Disallow: /maintenance.html
Disallow: /404.html
Disallow: /contact/submit
Disallow: /newsletter/subscribe

# --- Explicitly allowed -----------------------------------------------------
Allow: /downloads/
Allow: /assets/
Allow: /data/
Allow: /.well-known/

# --- Archive: crawl it, it is public and we want it indexed -----------------
Allow: /news/
Allow: /blog/
Allow: /careers/archive.html

# --- Aggressive commercial crawlers -----------------------------------------
# Not a judgement about AI; a judgement about request rate on a shared plan.
User-agent: SemrushBot
Disallow: /

User-agent: AhrefsBot
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: DotBot
Disallow: /

# --- Sitemaps ---------------------------------------------------------------
Sitemap: https://www.terravek.com/sitemap.xml
Sitemap: https://www.terravek.com/sitemap-pages.xml
Sitemap: https://www.terravek.com/sitemap-blog.xml
Sitemap: https://www.terravek.com/sitemap-news.xml
Sitemap: https://www.terravek.com/sitemap-careers.xml
Sitemap: https://www.terravek.com/sitemap-people.xml

# Security contact: /.well-known/security.txt  (security@terravek.com)
# Humans:           /humans.txt