# BOMB Magazine - robots.txt
# Updated: June 23, 2026

# Allow all legitimate search engines
User-agent: Googlebot
User-agent: Bingbot
User-agent: Slurp
User-agent: DuckDuckBot
User-agent: Baiduspider
Allow: /

# Block Craft CMS admin and system directories
User-agent: *
Disallow: /cpresources/
Disallow: /admin/
Disallow: /.env
Disallow: /vendor/
Disallow: /storage/
# Block Craft Live Preview URLs - these bypass Varnish/Cloudflare cache and force
# a full uncached render. Bots crawling them caused the post-Cloudflare CPU outage.
# robots.txt only stops well-behaved bots; abusive crawlers must be blocked at the WAF.
Disallow: /*?x-craft-preview
Disallow: /*&x-craft-preview
Disallow: /*?x-craft-live-preview
Disallow: /*&x-craft-live-preview
# AJAX endpoint - no crawlable value, was getting hammered uncached
Disallow: /cookie-consent/

# Block aggressive SEO/marketing crawlers (seen flooding the origin post-migration)
User-agent: SemrushBot
Disallow: /

User-agent: AhrefsBot
Disallow: /

User-agent: dotbot
Disallow: /

User-agent: MJ12bot
Disallow: /

# Block AI Scrapers - OpenAI
User-agent: GPTBot
Disallow: /

User-agent: ChatGPT-User
Disallow: /

# Block AI Scrapers - Anthropic
User-agent: anthropic-ai
Disallow: /

User-agent: Claude-Web
Disallow: /

User-agent: ClaudeBot
Disallow: /

# Block AI Scrapers - Common Crawl
User-agent: CCBot
Disallow: /

# Block AI Scrapers - Google AI Training
User-agent: Google-Extended
Disallow: /

# Block AI Scrapers - Apple Intelligence
User-agent: Applebot-Extended
Disallow: /

# Block AI Scrapers - Perplexity
User-agent: PerplexityBot
Disallow: /

# Block AI Scrapers - Amazon
User-agent: Amazonbot
Disallow: /

# Block AI Scrapers - Meta/Facebook
User-agent: FacebookBot
Disallow: /

User-agent: Meta-ExternalAgent
Disallow: /

# Block AI Scrapers - ByteDance/TikTok
User-agent: Bytespider
Disallow: /

# Block AI Scrapers - Other
User-agent: Diffbot
Disallow: /

User-agent: Omgilibot
Disallow: /

User-agent: Omgili
Disallow: /

User-agent: peer39_crawler
Disallow: /

User-agent: peer39_crawler/1.0
Disallow: /


User-agent: cohere-ai
Disallow: /

User-agent: AI2Bot
Disallow: /

User-agent: DataForSeoBot
Disallow: /

# Huawei AI models
User-agent: PetalBot
Disallow: /


User-agent: YouBot
Disallow: /

User-agent: ImagesiftBot
Disallow: /

User-agent: Timpibot
Disallow: /

User-agent: CauseAnnex-Verify
Allow: /

# Sitemap
Sitemap: https://bombmagazine.org/sitemap.xml