# 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

# Global rules — apply to all crawlers not matched by a more specific block below.
User-agent: *
Allow: /
Crawl-delay: 1

# Disallow admin and private areas
Disallow: /admin/
Disallow: /api/
Disallow: /static/
Disallow: /private/
Disallow: /internal/
Disallow: /trap/
# Thin auth pages — no SEO value
Disallow: /onboarding/auth/
# Authenticated-only areas — must not be crawled
Disallow: /profile
Disallow: /profile/
Disallow: /dashboard
Disallow: /dashboard/

# Allow important pages for SEO
Allow: /property
Allow: /search
Allow: /pricing
Allow: /legal/
Allow: /faq
Allow: /city-finder
Allow: /compare
Allow: /guides/
Allow: /cities/
Allow: /metros/
Allow: /scam-alerts/
Allow: /moving-to-dfw
Allow: /real-estate/
Allow: /builders/
Allow: /refer

# Allow /_next/ for Googlebot to render pages (JS/CSS needed for indexing)

# Specific property pages
Allow: /property/*
Allow: /search?*

# Allow social media and sharing
Allow: /share/
Allow: /embed/

# 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: /

# ── LLM CITATION POLICY ──────────────────────────────────────────────
# We split LLM bots into two classes:
#  (a) TRAINING bots — consume content to train future models.
#      We BLOCK these because our research methodology and editorial
#      content is proprietary.
#  (b) SEARCH / CITATION bots — index content to cite live in answers
#      ("Is this Plano rental a scam?" → cited from remotepropview.com).
#      We ALLOW these because being cited drives qualified traffic.

# ── ALLOWED: search / citation crawlers ──────────────────────────────
User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: Claude-User
Allow: /

User-agent: Claude-SearchBot
Allow: /

User-agent: Applebot
Allow: /

User-agent: DuckDuckBot
Allow: /

# ── BLOCKED: training-only crawlers ─────────────────────────────────
User-agent: GPTBot
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: Cohere-ai
Disallow: /

User-agent: Amazonbot
Disallow: /

User-agent: AwarioRssBot
Disallow: /

User-agent: AwarioSmartBot
Disallow: /

User-agent: DataForSeoBot
Disallow: /

User-agent: ImagesiftBot
Disallow: /

User-agent: Timpibot
Disallow: /

User-agent: YouBot
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: Omgilibot
Disallow: /

User-agent: FacebookBot
Disallow: /

User-agent: meta-externalagent
Disallow: /

# Sitemaps (root DFW sitemap + per-state real-estate shards)
Sitemap: https://www.remotepropview.com/sitemap.xml
Sitemap: https://www.remotepropview.com/real-estate/sitemap/michigan.xml
Sitemap: https://www.remotepropview.com/real-estate/sitemap/ohio.xml
Sitemap: https://www.remotepropview.com/real-estate/sitemap/illinois.xml
Sitemap: https://www.remotepropview.com/real-estate/sitemap/new-york.xml
Sitemap: https://www.remotepropview.com/real-estate/sitemap/kansas.xml
Sitemap: https://www.remotepropview.com/real-estate/sitemap/arkansas.xml
Sitemap: https://www.remotepropview.com/builders/sitemap.xml