# 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

# MineMiew - Visual Novel Platform
# https://minemiew.com/robots.txt
#
# Update this file when adding new private/protected routes so bots don't waste
# crawl budget on pages that always redirect to /signin (which hurts rankings —
# Google sees a "soft 404" pattern).

User-agent: *
Allow: /

# --- Backend / infra (never indexable) ---
# Exception: share-image cards are the og:image for /story|/play link previews —
# crawlers must be able to fetch them (Allow beats Disallow on longer match).
Allow: /api/share-image/
Disallow: /api/
Disallow: /_*

# --- Admin surfaces (login-gated, no SEO value) ---
Disallow: /admin/
Disallow: /admin

# --- Editor / authoring tool (login-gated, app-shell only) ---
Disallow: /editor/
Disallow: /editor

# --- User-only pages (login-gated; redirect to /signin for bots) ---
Disallow: /my-works
Disallow: /profile
Disallow: /bookshelf
Disallow: /purchased
Disallow: /role-requests
Disallow: /notifications

# --- Auth flows (callback URLs, no canonical content) ---
Disallow: /auth/callback/
Disallow: /signin?
Disallow: /signup?

# --- Honeypot probes (returns 404 — block to keep crawl logs clean) ---
Disallow: /administrator
Disallow: /wp-admin
Disallow: /wp-login.php
Disallow: /backend
Disallow: /manage
Disallow: /cms
Disallow: /phpmyadmin
Disallow: /.env

# --- Allow query-paramless auth landing (still useful for branded search) ---
Allow: /signin$
Allow: /signup$

# Sitemap
Sitemap: https://minemiew.com/sitemap.xml

# Polite crawl delay for unknown bots — search engines override below.
Crawl-delay: 1

# ─────────────────────────────────────────────────────────────────
# Search engines — explicit rules so they don't apply Crawl-delay.
# ─────────────────────────────────────────────────────────────────

User-agent: Googlebot
Allow: /
Allow: /api/share-image/
Disallow: /api/
Disallow: /admin/
Disallow: /editor/
Disallow: /my-works
Disallow: /profile
Disallow: /bookshelf
Disallow: /purchased
Disallow: /role-requests
Disallow: /notifications
Disallow: /auth/callback/

User-agent: Googlebot-Image
Allow: /
Allow: /api/share-image/
Disallow: /api/

User-agent: Bingbot
Allow: /
Allow: /api/share-image/
Disallow: /api/
Disallow: /admin/
Disallow: /editor/
Disallow: /my-works
Disallow: /profile
Disallow: /bookshelf
Disallow: /purchased
Disallow: /role-requests
Disallow: /notifications
Disallow: /auth/callback/

User-agent: DuckDuckBot
Allow: /
Allow: /api/share-image/
Disallow: /api/
Disallow: /admin/
Disallow: /editor/

# ─────────────────────────────────────────────────────────────────
# AI scrapers — block training crawlers from harvesting user content.
# Keeps user-generated stories from being absorbed without consent.
# ─────────────────────────────────────────────────────────────────

User-agent: GPTBot
Disallow: /

User-agent: ChatGPT-User
Disallow: /

User-agent: OAI-SearchBot
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: Claude-Web
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: PerplexityBot
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: Amazonbot
Disallow: /

User-agent: FacebookBot
Disallow: /

User-agent: Applebot-Extended
Disallow: /