# 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

# ── Standard Search Engines ────────────────────────────────────────────────────
User-agent: *
Allow: /
Disallow: /admin/

Sitemap: https://dramahubs.stream/sitemap-index.xml

# ── AI Crawlers — Allow indexing for answers, disallow training ────────────────

# ChatGPT / OpenAI Browse
User-agent: GPTBot
Allow: /
Disallow: /admin/

# OpenAI general crawler
User-agent: OAI-SearchBot
Allow: /
Disallow: /admin/

# ChatGPT Plugin crawler
User-agent: ChatGPT-User
Allow: /
Disallow: /admin/

# Anthropic Claude
User-agent: ClaudeBot
Allow: /
Disallow: /admin/

# Anthropic general
User-agent: anthropic-ai
Allow: /
Disallow: /admin/

# Google Gemini / AI Overviews / Google AI crawler
User-agent: GoogleOther
Allow: /
Disallow: /admin/

# Google Extended (Bard/Gemini training) — disallow training
User-agent: Google-Extended
Disallow: /

# Perplexity AI
User-agent: PerplexityBot
Allow: /
Disallow: /admin/

# Meta AI
User-agent: meta-externalagent
Allow: /
Disallow: /admin/

# Cohere AI — training crawler, disallow
User-agent: cohere-ai
Disallow: /

# Amazon Alexa / AI
User-agent: Amazonbot
Allow: /
Disallow: /admin/

# Apple Applebot (Siri/Apple Intelligence)
User-agent: Applebot-Extended
Disallow: /

# Bytedance / Doubao AI — training crawler, disallow
User-agent: Bytespider
Disallow: /

# Common Crawl (used by many AI orgs) — AI training corpus, disallow
User-agent: CCBot
Disallow: /

# ── AI Content Files ───────────────────────────────────────────────────────────
# Primary AI site description (llmstxt.org standard)
# https://dramahubs.stream/llms.txt

# Extended AI content index with full drama catalog
# https://dramahubs.stream/llms-full.txt