# -------------------------------------------------------------------
# www.lsbrx.com | robots.txt
# Last Updated: January 2026
# Purpose: Governs web and AI crawler access to optimise discovery, ranking, and ethical AI summarisation.
# -------------------------------------------------------------------

# General Directives - All User Agents
User-agent: *
Disallow: /admin/
Disallow: /bin/
Disallow: /obj/
Disallow: /error/
Disallow: /search?
Disallow: /App_Data/
Disallow: /App_Code/
Disallow: /invoice/
Disallow: /cgi-bin/
Disallow: /tmp/
Disallow: /junk/

# Block Specific File Types
Disallow: /*.aspx$
Disallow: /*.ashx$
Disallow: /*.axd$
Disallow: /*.dll$
Disallow: /*.config$
Disallow: /*.cs$
Disallow: /*.vb$
Disallow: /*.resx$

Allow: /search/
Allow: /courses/
Allow: /blog/
Disallow: /Brochure/
Disallow: /Course/GetReviews/

# Sitemap index
Sitemap: https://www.lsbrx.com/sitemap.xml
# LLMS file available at: https://www.lsbrx.com/llms.txt

# -------------------------------------------------------------------
# Search Engine Bots
# -------------------------------------------------------------------
User-agent: Googlebot
Allow: /courses/
Allow: /blog/
Disallow: /internal-api/
Crawl-delay: 5

User-agent: Bingbot
Allow: /courses/
Allow: /blog/
Disallow: /temp/
Crawl-delay: 10

User-agent: Yandex
Allow: /courses/
Disallow: /private/
Crawl-delay: 5

User-agent: Baiduspider
Allow: /courses/
Disallow: /secure/
Crawl-delay: 10

# -------------------------------------------------------------------
# Social Media Bots
# -------------------------------------------------------------------
User-agent: FacebookExternalHit
Allow: /courses/
Allow: /blog/
User-agent: Twitterbot
Allow: /courses/
Allow: /blog/
User-agent: LinkedInBot
Allow: /courses/
Allow: /blog/

# -------------------------------------------------------------------
# Allow Minimal Trusted Bots
# -------------------------------------------------------------------
User-agent: CCBot
Allow: /courses/
User-agent: UptimeRobot
Allow: /

# -------------------------------------------------------------------
# AI / LLM Crawlers (for Responsible Discovery and Ranking)
# -------------------------------------------------------------------
User-agent: GPTBot
Allow: /
Disallow: /admin/
Disallow: /invoice/
Crawl-delay: 10
# Purpose: Enables OpenAI models (ChatGPT, etc.) to reference and summarise business and educational content responsibly.

User-agent: Google-Extended
Allow: /
Disallow: /admin/
# Purpose: Allows Google Generative AI (Gemini / SGE) to summarise and rank www.lsbrx.com content.

User-agent: ClaudeBot
Allow: /
Disallow: /admin/
# Purpose: Permits Anthropic AI to access www.lsbrx.com articles and course information for knowledge synthesis.

User-agent: PerplexityBot
Allow: /
Disallow: /invoice/
# Purpose: Enables Perplexity AI to discover and cite www.lsbrx.com educational and professional content.

User-agent: Amazonbot
Allow: /
# Purpose: Supports Alexa and Amazon Q integrations for learning and professional development.

User-agent: ChatGPT-User
Allow: /
# Purpose: Allows ChatGPT browsing mode to reference verified www.lsbrx.com pages.

# -------------------------------------------------------------------
# Block Known Spam and Data Harvesting Bots
# -------------------------------------------------------------------
User-agent: DataForSeoBot
Disallow: /
User-agent: Screaming Frog SEO Spider
Disallow: /
User-agent: ZoominfoBot
Disallow: /
User-agent: spbot
Disallow: /
User-agent: PagePeeker
Disallow: /
User-agent: Wget
Disallow: /
User-agent: curl
Disallow: /
User-agent: HTTrack
Disallow: /
User-agent: Python-urllib
Disallow: /
User-agent: libwww-perl
Disallow: /
User-agent: PycURL
Disallow: /
User-agent: CheckMarkNetwork
Disallow: /
User-agent: wotbox
Disallow: /
User-agent: SurveyBot
Disallow: /
User-agent: XoviBot
Disallow: /
User-agent: Findxbot
Disallow: /
User-agent: B2B Bot
Disallow: /

# -------------------------------------------------------------------
# Optional Query & Duplicate Content Protection
# -------------------------------------------------------------------
User-agent: *
Disallow: /*?sessionid=
Disallow: /*?ref=
Disallow: /backup/
Disallow: /old/
Disallow: /private/

# -------------------------------------------------------------------
# Crawl Efficiency and Hygiene
# -------------------------------------------------------------------
Crawl-delay: 5
Clean-param: ref,sessionid

# -------------------------------------------------------------------
# AI Discovery Note
# -------------------------------------------------------------------
# For ethical AI summarisation and structured data compliance,
# www.lsbrx.com provides a dedicated LLMS file:
# https://www.lsbrx.com/llms.txt

# -------------------------------------------------------------------
# END OF FILE
# -------------------------------------------------------------------