# robots.txt voor NH Nieuws
# Laatste update: 9 maart 2026
# Contact: webmaster@nhnieuws.nl | privacy@nhnieuws.nl
# Content voor AI-zoekmachines: https://www.nhnieuws.nl/llms.txt

# 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.

# 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.

User-Agent: *
Content-Signal: ai-train=no, search=yes, ai-input=yes
Allow: /

## ALGEMENE REGELS
User-agent: *
Allow: /
Disallow: /api/
Disallow: /app/
Disallow: /zoek/
Disallow: /nieuws/n*
Crawl-delay: 7
Sitemap: https://www.nhnieuws.nl/sitemap-news.xml

## AI SEARCH & CONTEXT BOTS
User-agent: PerplexityBot
Allow: /
User-agent: Perplexity-Web
Allow: /
User-agent: BingCopilot
Allow: /
User-agent: OAI-SearchBot
Allow: /
User-agent: DuckAssistBot
Allow: /
User-agent: YouBot
Allow: /
User-agent: meta-externalfetcher
Allow: /
User-agent: Claude-User
Allow: /
User-agent: Claude-SearchBot
Allow: /
User-agent: ChatGPT-User
Allow: /
User-agent: Textmetrics-crawler
Allow: /
## AI TRAININGSBOTS
User-agent: GPTBot
Disallow: /
User-agent: ClaudeBot
Disallow: /
User-agent: Claude-Web
Disallow: /
User-agent: anthropic-ai
Disallow: /
User-agent: Google-Extended
Disallow: /
User-agent: GeminiBot
Disallow: /
User-agent: Google-Gemini
Disallow: /
User-agent: CCBot
Disallow: /
User-agent: cohere-ai
Disallow: /
User-agent: Amazonbot
Disallow: /
User-agent: Applebot-Extended
Disallow: /
User-agent: Timpibot
Disallow: /
User-agent: Bytespider
Disallow: /
User-agent: Meta-ExternalAgent
Disallow: /
User-agent: cohere-training-data-crawler
Disallow: /

## SOCIAL MEDIA & PREVIEW BOTS
User-agent: Twitterbot
Allow: /
User-agent: facebookexternalhit
Allow: /
User-agent: LinkedInBot
Allow: /

## MOBIELE APP CRAWLERS
User-agent: Googlebot-Mobile
Allow: /

## SEO-TOOLS
User-agent: AhrefsBot
Allow: /
Crawl-delay: 15
User-agent: SemrushBot
Allow: /
Crawl-delay: 15

## ARCHIVERING
User-agent: archive.org_bot
Allow: /
Crawl-delay: 30
User-agent: Arquivo-web-crawler
Allow: /
Crawl-delay: 45

## REGIONALE BLOKKADES
User-agent: Baiduspider
Disallow: /
User-agent: Yandex
Disallow: /
User-agent: Sogou Spider
Disallow: /

## MONITORING & UPTIME BOTS
User-agent: UptimeRobot
Allow: /
User-agent: Pingdom
Allow: /

## CONTACT & BELEID
# Laatste update: 9 maart 2026
# Zie ook: https://www.nhnieuws.nl/llms.txt, https://www.nhnieuws.nl/humans.txt, https://www.nhnieuws.nl/hackers.txt, https://www.nhnieuws.nl/earth.txt
# Voor dataverzoeken: privacy@nhnieuws.nl
# AI-training expliciet verboden (EU Copyright Directive 2025)
# Toestemming vereist voor commercieel hergebruik