# 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

# isdownnow.co — robots.txt
# Allow Google and major search engines (these bring you traffic)
# Block AI training bots (they scrape your content without sending traffic)

# ── ALLOW: Major search engines ──────────────────────────────────────────────
User-agent: Googlebot
Allow: /

User-agent: Bingbot
Allow: /

User-agent: Slurp
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: Baiduspider
Allow: /

User-agent: YandexBot
Allow: /

# ── BLOCK: AI training bots ───────────────────────────────────────────────────

# OpenAI
User-agent: GPTBot
Disallow: /

User-agent: ChatGPT-User
Disallow: /

User-agent: OAI-SearchBot
Disallow: /

# Google AI (Gemini training — different from Googlebot search crawler)
User-agent: Google-Extended
Disallow: /

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

User-agent: ClaudeBot
Disallow: /

# Common Crawl (used to train many AI models)
User-agent: CCBot
Disallow: /

# Meta AI
User-agent: FacebookBot
Disallow: /

# Apple
User-agent: Applebot-Extended
Disallow: /

# Amazon Alexa
User-agent: Amazonbot
Disallow: /

# Bytedance (TikTok AI)
User-agent: Bytespider
Disallow: /

# Diffbot
User-agent: Diffbot
Disallow: /

# Omgili / Webz.io
User-agent: omgili
Disallow: /

User-agent: omgilibot
Disallow: /

# Cohere
User-agent: cohere-ai
Disallow: /

# Perplexity
User-agent: PerplexityBot
Disallow: /

# You.com
User-agent: YouBot
Disallow: /

# Scrapy (generic scraper)
User-agent: Scrapy
Disallow: /

# ── SITEMAP ───────────────────────────────────────────────────────────────────
Sitemap: https://isdownnow.co/sitemap.xml