# --- SECTION 1: BLOCK OFFENDERS (From your logs) ---
# These bots were high-volume or malicious but didn't fit in your WPE rule
User-agent: proximic
User-agent: MoodleBot
User-agent: Amzn-SearchBot
User-agent: AhrefsBot
User-agent: SemrushBot
User-agent: Barkrowler
User-agent: Crydork
User-agent: AliyunSecBot
Disallow: /

# --- SECTION 2: AI SCRAPING & TRAINING ---
# Prevents content being used to train AI models
User-agent: GPTBot
User-agent: CCBot
User-agent: Applebot-Extended
Disallow: /

# Allows AI Search (Direct traffic to your site)
User-agent: ChatGPT-User
User-agent: PerplexityBot
User-agent: OAI-SearchBot
Allow: /

# --- SECTION 3: GENERAL RULES ---
User-agent: *
Crawl-delay: 10
Disallow: /wp-admin/
Allow: /wp-admin/admin-ajax.php


User-agent: Google-Extended
Disallow: /

User-agent: Amazonbot
Disallow: /

# Allow all Meta/Facebook crawlers for link previews
User-agent: facebookexternalhit
Allow: /

User-agent: Facebot
Allow: /

User-agent: meta-externalagent
Allow: /


# Block fake Chrome/Windows bots (example pattern)
User-agent: Mozilla/5.0 (Windows NT 10.0; Win64; x64) Chrome/143.0.0.0
Disallow: /

# --- Sensitive WordPress Paths (All bots) --- 
User-agent: *
Disallow: /xmlrpc.php
Disallow: /wp-login.php
Disallow: /wp-cron.php
Disallow: /comments/feed/


# Directories
Disallow: /includes/
Disallow: /misc/
Disallow: /modules/
Disallow: /profiles/
Disallow: /scripts/
Disallow: /themes/
# Files
Disallow: /CHANGELOG.txt
Disallow: /cron.php
Disallow: /INSTALL.mysql.txt
Disallow: /INSTALL.pgsql.txt
Disallow: /INSTALL.sqlite.txt
Disallow: /install.php
Disallow: /INSTALL.txt
Disallow: /LICENSE.txt
Disallow: /MAINTAINERS.txt
Disallow: /update.php
Disallow: /UPGRADE.txt
Disallow: /xmlrpc.php
# Paths (clean URLs)
Disallow: /admin/
Disallow: /comment/reply/
Disallow: /filter/tips/
Disallow: /node/add/
Disallow: /search/
Disallow: /user/register/
Disallow: /user/password/
Disallow: /user/login/
Disallow: /user/logout/
# Paths (no clean URLs)
Disallow: /?q=admin/
Disallow: /?q=comment/reply/
Disallow: /?q=filter/tips/
Disallow: /?q=node/add/
Disallow: /?q=search/
Disallow: /?q=user/password/
Disallow: /?q=user/register/
Disallow: /?q=user/login/
Disallow: /?q=user/logout/
Disallow: /?s&pid=102940
Disallow: /page/
Disallow: /*?page=
Disallow: /*?*utm_campaign=
Disallow: /*&utm_campaign=
Disallow: /*?*__hstc=
Disallow: /*&__hstc=
Disallow: /*?*__hssc=
Disallow: /*&__hssc=
Disallow: /*?*__hsfp=
Disallow: /*&__hsfp=
Disallow: /SearchResults.aspx?cx=018137038020134942690:bivmuxgubrq&cof=FORID:11&ie=UTF-8&sa=Search&safe=active&q=proofreading
Disallow: /*.aspx$
# Block all URLs containing /skipcusmain
Disallow: /skipcusmain
Disallow: /*/skipcusmain
Disallow: /*skipcusmain*

# Block specific URL: Can You Tighten Loose Skin After Weight Loss?
Disallow: /qdtarchive/can-you-tighten-loose-skin-after-weight-loss-2/

# Block all URLs containing /node/
Disallow: /node/
Disallow: /node/*

# Block all URLs containing /education/grammar/
Disallow: /education/grammar/
Disallow: /education/grammar/*

# Block specific URL: How To Lose The Freshman 15?
Disallow: /qdtarchive/how-to-lose-the-freshman-15-2/