User-agent: *
Disallow: /pics/
Disallow: /seti-at-home/
Disallow: /r
Disallow: /misc/
Disallow: /impressum/
Disallow: /guides/
Disallow: /old/
Disallow: /webalizer/
Disallow: /webalizer.old
Disallow: /forum/admin/
Disallow: /forum/db/
Disallow: /forum/images/
Disallow: /forum/includes/
Disallow: /forum/language/
Disallow: /forum/templates/
Disallow: /forum/common.php
Disallow: /forum/groupcp.php
Disallow: /forum/faq.php 
Disallow: /forum/privmsg.php
Disallow: /forum/profile.php
Disallow: /forum/groupcp.php
Disallow: /forum/viewonline.php
Disallow: /forum/printview.php
Disallow: /forum/modcp.php
Disallow: /forum/login.php
Disallow: /wiki/admin/
Disallow: /forum/memberlist.php
Disallow: /forum/search.php
Disallow: /forum/ucp.php
Disallow: /forum/posting.php
Disallow: /forum/report.php
Disallow: /forum/viewonline.php
Disallow: /forum/download.php
Disallow: /w2/

User-agent: Fasterfox
Disallow: /

User-agent: AhrefsBot 
Disallow: /

# The Common Crawl dataset. Original source for GPT and others.
User-agent: CCBot
Disallow: /

# The example for img2dataset, although the default is *None*
User-agent: img2dataset
Disallow: /

# GPTBot is OpenAI's web crawler
User-agent: GPTBot
Disallow: /

# ChatGPT-User takes direct actions on behalf of ChatGPT users
User-agent: ChatGPT-User
Disallow: /

# Google's Bard and Vertex AI generative APIs
User-agent: Google-Extended
Disallow: /

# Speculative blocks for Anthropic
User-agent: anthropic-ai
Disallow: /

User-agent: Claude-Web
Disallow: /

# webz.io - they sell data for training LLMs.
User-agent: Omgilibot
Disallow: /

User-agent: Omgili
Disallow: /

# Meta's bot that crawls public web pages to improve language models
User-agent: FacebookBot
Disallow: /

# ByteDance's bot used to gather data for their LLMs, including Doubao.
User-agent: Bytespider
Disallow: /

# Brandwatch - "AI to discover new trends"
User-agent: magpie-crawler
Disallow: /

User-agent: Perplexity‑User
Disallow: /

User-agent: PerplexityBot
Disallow: /