# robots.txt for DigitalFranck.com
# SEO Expert & Digital Marketing Specialist Malaysia
# Last updated: 2026-01-30

# ====================
# GENERAL SETTINGS
# ====================

# Allow all good bots by default
User-agent: *
Allow: /

# ====================
# MAJOR SEARCH ENGINES
# ====================

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

# Google Images
User-agent: Googlebot-Image
Allow: /

# Google Mobile
User-agent: Googlebot-Mobile
Allow: /

# Bing
User-agent: Bingbot
Allow: /
Crawl-delay: 0

# Yahoo
User-agent: Slurp
Allow: /

# DuckDuckGo
User-agent: DuckDuckBot
Allow: /

# Baidu (China)
User-agent: Baiduspider
Allow: /

# Yandex (Russia)
User-agent: Yandex
Allow: /

# ====================
# AI & LLM BOTS
# ====================

# OpenAI (ChatGPT)
User-agent: ChatGPT-User
Allow: /

User-agent: GPTBot
Allow: /

# Anthropic (Claude)
User-agent: anthropic-ai
Allow: /

User-agent: Claude-Web
Allow: /

# Google Bard/Gemini
User-agent: Google-Extended
Allow: /

# Perplexity
User-agent: PerplexityBot
Allow: /

# Common Crawl (used by many AI models)
User-agent: CCBot
Allow: /

# ====================
# SOCIAL MEDIA BOTS
# ====================

# Facebook
User-agent: facebookexternalhit
Allow: /

# Twitter
User-agent: Twitterbot
Allow: /

# LinkedIn
User-agent: LinkedInBot
Allow: /

# Pinterest
User-agent: Pinterestbot
Allow: /

# ====================
# BAD BOTS TO BLOCK
# ====================

# Block spam and scraper bots
User-agent: AhrefsBot
Disallow: /

User-agent: SemrushBot
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: DotBot
Disallow: /

User-agent: SeznamBot
Disallow: /

User-agent: BLEXBot
Disallow: /

User-agent: MegaIndex
Disallow: /

User-agent: YandexImages
Disallow: /

User-agent: archive.org_bot
Disallow: /

User-agent: ia_archiver
Disallow: /

# Block email harvesters
User-agent: EmailCollector
Disallow: /

User-agent: EmailSiphon
Disallow: /

User-agent: WebBandit
Disallow: /

User-agent: EmailWolf
Disallow: /

# ====================
# SITEMAPS
# ====================

# Sitemap location
Sitemap: https://digitalfranck.com/sitemap.xml

# ====================
# ADDITIONAL RESOURCES
# ====================

# LLM-specific information
# See: https://digitalfranck.com/llms.txt