##############################
# robots.txt for [YourSite]
# Purpose: Block bad bots, allow search engine indexing with limits
##############################

### SECTION: Major Search Bots ###

User-agent: Googlebot
Disallow: /expensive-endpoint/
Disallow: /cgi-bin/
Disallow: /tmp/
Allow: /

User-agent: bingbot
Crawl-delay: 10
Disallow: /expensive-endpoint/

User-agent: Yandex
Disallow: /

User-agent: Mediapartners-Google*
Disallow: /  # Only block if you're not using AdSense

### SECTION: Known Site Scrapers and Bad Bots ###

User-agent: UbiCrawler
Disallow: /

User-agent: DOC
Disallow: /

User-agent: Zao
Disallow: /

User-agent: sitecheck.internetseer.com
Disallow: /

User-agent: Zealbot
Disallow: /

User-agent: MSIECrawler
Disallow: /

User-agent: SiteSnagger
Disallow: /

User-agent: WebStripper
Disallow: /

User-agent: WebCopier
Disallow: /

User-agent: Fetch
Disallow: /

User-agent: Offline Explorer
Disallow: /

User-agent: Teleport
Disallow: /

User-agent: TeleportPro
Disallow: /

User-agent: WebZIP
Disallow: /

User-agent: linko
Disallow: /

User-agent: HTTrack
Disallow: /

User-agent: Microsoft.URL.Control
Disallow: /

User-agent: Xenu
Disallow: /

User-agent: larbin
Disallow: /

User-agent: libwww
Disallow: /

User-agent: ZyBORG
Disallow: /

User-agent: Download Ninja
Disallow: /

User-agent: grub-client
Disallow: /

User-agent: k2spider
Disallow: /

User-agent: NPBot
Disallow: /

User-agent: WebReaper
Disallow: /

User-agent: DataForSeoBot
Disallow: /

### SECTION: AI Bots & Crawlers (Resource Intensive) ###

User-agent: ChatGPT-User
Disallow: /

User-agent: GPTBot
Disallow: /

User-agent: Claude-Web
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: cohere-ai
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: SemrushBot
Disallow: /

User-agent: omgili
Disallow: /

User-agent: FacebookBot
Disallow: /

User-agent: GoogleOther
Disallow: /

User-agent: Google-Extended
Disallow: /

### SECTION: Default Catch-All ###
User-agent: *
Crawl-delay: 10
Disallow: /expensive-endpoint/

### (Optional) Sitemap ###
# Sitemap: https://www.yoursite.com/sitemap.xml