# www.robotstxt.org/
# www.google.com/support/webmasters/bin/answer.py?hl=en&answer=156449

User-agent: *
# deny dynamic URLs which contain a hash link
Disallow: /*/document/h/*
Disallow: /*/decision/pdf/*
Disallow: /*/opinion/pdf/*
Disallow: /*/other/pdf/*
Disallow: /*/publication/pdf/*
# deny dynamic URLs which contain a '?'
Disallow: /*?*

User-Agent: MJ12bot
Crawl-Delay: 5

# https://netfuture.ch/2023/07/blocking-ai-crawlers-robots-txt-chatgpt/
# Used for many other (non-commercial) purposes as well
User-agent: CCBot
Disallow: /

# https://platform.openai.com/docs/gptbot
User-agent: GPTBot
Disallow: /

# https://platform.openai.com/docs/plugins/bot
User-agent: ChatGPT-User
Disallow:

# https://blog.google/technology/ai/an-update-on-web-publisher-controls/
User-agent: Google-Extended
Disallow: /

# Speech synthesis only?
User-agent: FacebookBot
Disallow: /

# Multi-purpose, commercial uses; including LLMs
User-agent: Omgilibot
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: Claude-Web
Disallow: /

# sitemap index
Sitemap: https://jusmundi.com/sitemap-jusmundi.com-sitemap-docs.xml