# 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
# =====================

User-agent: *
Crawl-delay: 10

# WP technical
Disallow: /wp-admin/
Disallow: /wp-login.php
Allow: /wp-admin/admin-ajax.php

# Common noisy endpoints (optional but safe)
Disallow: /?s=
Disallow: /*?s=*
Disallow: /search/
Disallow: /xmlrpc.php

# (IMPORTANT) Do NOT disallow CSS/JS/CDN assets here
# so crawlers can render and scanners won't mark as "blocked".

# =====================
# Block aggressive bots
# =====================

User-agent: AhrefsBot
Disallow: /

User-agent: SemrushBot
Disallow: /

User-agent: DotBot
Disallow: /

User-agent: archive.org_bot
Disallow: /

User-agent: Bytespider
Disallow: /

User-Agent: MJ12bot
Disallow: /

User-agent: Amazonbot
Disallow: /

User-agent: PetalBot
Disallow: /

User-agent: Applebot
Disallow: /

User-agent: Manus
Disallow: /

# =====================
# Social / link preview crawlers
# =====================

User-agent: facebookexternalhit
Allow: /

User-agent: Twitterbot
Allow: /

User-agent: LinkedInBot
Allow: /

# =====================
# Explicitly allow: HubSpot
# =====================

User-agent: HubSpot Crawler
Allow: /

User-agent: HubSpot Links Crawler 2.0
Allow: /

# =====================
# AI crawlers: allow but slow down
# =====================

User-agent: GPTBot
Allow: /
Crawl-delay: 40

User-agent: ChatGPT-User
Allow: /
Crawl-delay: 40

User-agent: OAI-SearchBot
Allow: /
Crawl-delay: 40

User-agent: ClaudeBot
Allow: /
Crawl-delay: 20

User-agent: Claude-SearchBot
Allow: /
Crawl-delay: 20

User-agent: Claude-User
Allow: /
Crawl-delay: 20

User-agent: PerplexityBot
Allow: /
Crawl-delay: 30

User-agent: Perplexity-User
Allow: /
Crawl-delay: 30


# =====================
# Search engines throttling (if needed)
# =====================

User-agent: Bingbot
Crawl-delay: 30

# =====================
# Meta crawlers throttling
# =====================

User-agent: Meta-ExternalAgent
Crawl-delay: 30

User-agent: Meta-ExternalFetcher
Crawl-delay: 30

User-agent: FacebookBot
Crawl-delay: 30


# =====================
# Sitemap (Yoast SEO)
# =====================
Sitemap: https://thequantuminsider.com/sitemap_index.xml