# Robots.txt for Bob's Guide - Financial Technology Resource Platform
# Updated: October 14, 2025
# This site welcomes responsible web crawlers and AI/LLM bots

# Default rules for all crawlers
User-agent: *
Allow: /
Crawl-delay: 1

# Disallow WordPress admin and system areas
Disallow: /wp-admin/
Allow: /wp-admin/admin-ajax.php
Disallow: /wp-includes/
Disallow: /wp-content/plugins/
Disallow: /wp-content/themes/*/includes/
Disallow: /wp-content/cache/
Disallow: /wp-content/uploads/wpforms/

# Disallow WordPress system files
Disallow: /wp-login.php
Disallow: /wp-register.php
Disallow: /wp-config.php
Disallow: /wp-config-sample.php
Disallow: /wp-comments-post.php
Disallow: /wp-cron.php
Disallow: /xmlrpc.php
Disallow: /readme.html
Disallow: /license.txt
Disallow: /wp-trackback.php
Disallow: /wp-signup.php
Disallow: /wp-activate.php

# Disallow specific paths and query parameters
Disallow: /*?s=
Disallow: /*?p=*&preview=true
Disallow: /*/feed/
Disallow: /*/trackback/
Disallow: /*/attachment/
Disallow: /*?replytocom=
Disallow: /tag/*/page/
Disallow: /category/*/page/
Disallow: /page/
Disallow: /cgi-bin/
Disallow: /search
Disallow: /?attachment_id=

# Allow access to CSS, JS, and media files for all bots
Allow: /wp-content/uploads/
Allow: /wp-content/themes/*.css
Allow: /wp-content/themes/*.js
Allow: /wp-includes/*.css
Allow: /wp-includes/*.js

# Google Crawlers - Full Access
User-agent: Googlebot
Allow: /
Crawl-delay: 0

User-agent: Googlebot-Mobile
Allow: /
Crawl-delay: 0

User-agent: Googlebot-Image
Allow: /
Crawl-delay: 0

User-agent: Googlebot-News
Allow: /
Crawl-delay: 0

User-agent: Googlebot-Video
Allow: /
Crawl-delay: 0

User-agent: Google-InspectionTool
Allow: /

# Bing Crawlers - Full Access
User-agent: Bingbot
Allow: /
Crawl-delay: 1

User-agent: BingPreview
Allow: /

User-agent: msnbot
Allow: /
Crawl-delay: 1

User-agent: msnbot-media
Allow: /

# Other Major Search Engines
User-agent: Slurp
Allow: /
Crawl-delay: 2

User-agent: DuckDuckBot
Allow: /
Crawl-delay: 1

User-agent: Baiduspider
Allow: /
Crawl-delay: 2

User-agent: YandexBot
Allow: /
Crawl-delay: 2

User-agent: Sogou
Allow: /
Crawl-delay: 2

# OpenAI Crawlers (ChatGPT)
User-agent: GPTBot
Allow: /
Crawl-delay: 1

User-agent: ChatGPT-User
Allow: /
Crawl-delay: 1

# Anthropic Claude Crawler
User-agent: ClaudeBot
Allow: /
Crawl-delay: 1

User-agent: Claude-Web
Allow: /
Crawl-delay: 1

# Google Gemini / Bard
User-agent: Google-Extended
Allow: /
Crawl-delay: 1

# Perplexity AI
User-agent: PerplexityBot
Allow: /
Crawl-delay: 1

# Common Crawl
User-agent: CCBot
Allow: /
Crawl-delay: 2

# Meta AI
User-agent: FacebookBot
Allow: /
Crawl-delay: 2

User-agent: Facebot
Allow: /

# Cohere AI
User-agent: cohere-ai
Allow: /
Crawl-delay: 1

# Anthropic's other bots
User-agent: anthropic-ai
Allow: /
Crawl-delay: 1

# You.com AI
User-agent: YouBot
Allow: /
Crawl-delay: 1

# Diffbot
User-agent: Diffbot
Allow: /
Crawl-delay: 2

# Apple Intelligence
User-agent: Applebot
Allow: /
Crawl-delay: 1

User-agent: Applebot-Extended
Allow: /
Crawl-delay: 1

# Amazon/Alexa
User-agent: ia_archiver
Allow: /
Crawl-delay: 2

User-agent: Amazonbot
Allow: /
Crawl-delay: 1

# Social Media Bots (for link previews)
User-agent: Twitterbot
Allow: /

User-agent: LinkedInBot
Allow: /

User-agent: WhatsApp
Allow: /

User-agent: Slackbot
Allow: /

User-agent: TelegramBot
Allow: /

User-agent: facebookexternalhit
Allow: /

# Block bad bots and scrapers
User-agent: AhrefsBot
Disallow: /

User-agent: SemrushBot
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: DotBot
Disallow: /

User-agent: BLEXBot
Disallow: /

User-agent: PetalBot
Disallow: /

User-agent: DataForSeoBot
Disallow: /

User-agent: AhrefsSiteAudit
Disallow: /

User-agent: SeznamBot
Disallow: /

User-agent: Screaming Frog SEO Spider
Disallow: /

# Sitemaps
Sitemap: https://www.bobsguide.com/sitemap.xml
Sitemap: https://www.bobsguide.com/sitemap_index.xml

# LLMs.txt - AI assistant instruction file
# See: https://www.bobsguide.com/llms.txt