# 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.

# ==========================================
# 1. GLOBAL RULES & LIVE AI SEARCH ALLOWED
# ==========================================
User-agent: *
Content-Signal: search=yes,ai-input=yes,ai-train=yes,use=reference
Allow: /

# Allow Live AI Search Bots for GEO/AEO Citations
User-agent: ChatGPT-User
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: OAI-SearchBot
Allow: /

# ==========================================
# 2. AI CORE TRAINING BOTS (Allowed)
# ==========================================
User-agent: GPTBot
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: ClaudeBot
Allow: /

# ==========================================
# 3. WORDPRESS SECURITY & CLEAN-UP BLOCKS
# ==========================================
Disallow: /wp-admin/
Allow: /wp-admin/admin-ajax.php
Disallow: /wp-login.php
Disallow: /wp-content/plugins/
Disallow: /wp-content/themes/
Disallow: /search/
Disallow: /*?s
Disallow: /wp-comments-posts.php
Disallow: /readme.html
Disallow: /license.txt
Disallow: /wp-config.php
Disallow: /author/
Disallow: /?author=*

# SEO Clean-up (Prevent Duplicate Content & Scraping)
Disallow: /*?utm_*
Disallow: /*?fbclid=*
Disallow: /*?replytocom=
Disallow: */feed/
Disallow: */trackback/

# Note: /wp-includes/ is intentionally ALLOWED so search engines 
# can render JS/CSS resources properly for mobile-friendliness.

# ==========================================
# 4. SEO AUDIT BOTS & SCRAPERS (Allowed)
# ==========================================
User-agent: Amazonbot
Allow: /

User-agent: Applebot-Extended
Allow: /

User-agent: Bytespider
Allow: /

User-agent: CCBot
Allow: /

User-agent: CloudflareBrowserRenderingCrawler
Allow: /

User-agent: meta-externalagent
Allow: /

User-agent: SemrushBot
Allow: /

User-agent: AhrefsBot
Allow: /

User-agent: MJ12bot
Allow: /

User-agent: DotBot
Allow: /

# ==========================================
# 5. CORRECT RANK MATH SITEMAP
# ==========================================
Sitemap: https://www.techprevue.com/sitemap_index.xml