# As a condition of accessing this website, you agree to abide by the following
# content signals:

# (a)  If a Content-Signal = yes, you may collect content for the corresponding
#      use.
# (b)  If a Content-Signal = no, you may not collect content for the
#      corresponding use.
# (c)  If the website operator does not include a Content-Signal for a
#      corresponding use, the website operator neither grants nor restricts
#      permission via Content-Signal with respect to the corresponding use.

# The content signals and their meanings are:

# search:   building a search index and providing search results (e.g., returning
#           hyperlinks and short excerpts from your website's contents). Search does not
#           include providing AI-generated search summaries.
# ai-input: inputting content into one or more AI models (e.g., retrieval
#           augmented generation, grounding, or other real-time taking of content for
#           generative AI search answers).
# ai-train: training or fine-tuning AI models.
# use:      how AI systems may consume the content (immediate, reference, or full).

# ANY RESTRICTIONS EXPRESSED VIA CONTENT SIGNALS 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.

# BEGIN Cloudflare Managed content

User-agent: *
Content-Signal: search=yes,ai-train=no,use=reference
Allow: /

User-agent: Amazonbot
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: CloudflareBrowserRenderingCrawler
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: GPTBot
Disallow: /

User-agent: meta-externalagent
Disallow: /

# END Cloudflare Managed Content

# 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