# 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: Google-Extended
Disallow: /

User-agent: GPTBot
Disallow: /

User-agent: meta-externalagent
Disallow: /

# END Cloudflare Managed Content

# ============================
# Robots.txt — WordPress Crawl Budget Optimized
# ============================

User-agent: *
# --- Block admin and system paths ---
Disallow: /wp-admin/
Disallow: /wp-includes/
Disallow: /xmlrpc.php
Disallow: /wp-json/
Disallow: /cgi-bin/
Disallow: /trackback/
Disallow: /feed/
Disallow: /comments/
Disallow: /?replytocom=
Disallow: /?s=
Disallow: /search/

# --- Block parameter traps ---
Disallow: /*?*utm_
Disallow: /*?*ref=
Disallow: /*?*session=
Disallow: /*?*sort=
Disallow: /*?*order=
Disallow: /*?*filter=
Disallow: /*?*facet=
Disallow: /*?*price=
Disallow: /*?*color=
Disallow: /*?*size=
Disallow: /*?*lang=
Disallow: /*?*view=
Disallow: /*?*page=

# --- Allow render-critical resources ---
Allow: /wp-admin/admin-ajax.php
Allow: /*.css$
Allow: /*.js$
Allow: /*.jpg$
Allow: /*.jpeg$
Allow: /*.png$
Allow: /*.webp$

# --- Sitemaps ---
Sitemap: https://www.bk8.services/sitemap.xml
Sitemap: https://www.bk8.services/sitemap_index.xml

# Explicit allow for major search engines
User-agent: Googlebot
Allow: /
User-agent: Bingbot
Allow: /
User-agent: Applebot
Allow: /