# 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.

# BEGIN Cloudflare Managed content

User-agent: *
Content-Signal: search=yes,ai-train=no
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

# nullpink.com robots policy
# Search crawlers: welcome.
# AI training / scraping crawlers: disallowed. Editorial content is not for harvest.
# Updated 2026-05-03.

# === Allowed: standard search engine crawlers ===

User-agent: Googlebot
Allow: /

User-agent: Bingbot
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: Yandex
Allow: /

User-agent: Applebot
Allow: /

# === Disallowed: AI training / scraping crawlers ===

# OpenAI
User-agent: GPTBot
Disallow: /
User-agent: ChatGPT-User
Disallow: /
User-agent: OAI-SearchBot
Disallow: /

# Anthropic
User-agent: ClaudeBot
Disallow: /
User-agent: Claude-User
Disallow: /
User-agent: anthropic-ai
Disallow: /

# Google AI training (separate from Googlebot search)
User-agent: Google-Extended
Disallow: /

# Apple AI training (separate from Applebot search)
User-agent: Applebot-Extended
Disallow: /

# Common Crawl — feeds dozens of training datasets
User-agent: CCBot
Disallow: /

# Perplexity
User-agent: PerplexityBot
Disallow: /
User-agent: Perplexity-User
Disallow: /

# ByteDance / TikTok
User-agent: Bytespider
Disallow: /
User-agent: ByteDance
Disallow: /

# Meta / Facebook AI
User-agent: FacebookBot
Disallow: /
User-agent: Meta-ExternalAgent
Disallow: /
User-agent: Meta-ExternalFetcher
Disallow: /

# Amazon AI training
User-agent: Amazonbot
Disallow: /

# Cohere
User-agent: Cohere-ai
Disallow: /
User-agent: cohere-training-data-crawler
Disallow: /

# Other AI / data scrapers
User-agent: Diffbot
Disallow: /
User-agent: ImagesiftBot
Disallow: /
User-agent: AI2Bot
Disallow: /
User-agent: Timpibot
Disallow: /
User-agent: Omgilibot
Disallow: /
User-agent: Omgili
Disallow: /
User-agent: PetalBot
Disallow: /
User-agent: Kangaroo
Disallow: /
User-agent: NovaAct
Disallow: /
User-agent: scrapy
Disallow: /

# === Default for everything else ===
User-agent: *
Allow: /
Disallow: /admin/
Disallow: /draft/
Disallow: /go/

Sitemap: https://nullpink.com/sitemap.xml