# Codex Werthos - an unofficial fan reference. See /about#crawlers for the reasoning.

# Search engines and ordinary visitors: welcome. The bulk files are for people to download, not for indexes.
User-agent: *
Allow: /
Disallow: /qa/data.json
Disallow: /data/paolini-qa.csv
Disallow: /data/timeline.csv
Disallow: /data/ancient-language-usage.csv
# What follows a question mark is the state of a tool (a search, a filter, a record to draw). The page is the same page with or without it,
# and says so in its canonical link. There are thousands of such links on the site and nothing new behind any of them.
Disallow: /*?

# Link previews: whoever fetches one page because a person has just shared it may fetch any address, a tool's state included.
User-agent: Twitterbot
User-agent: facebookexternalhit
User-agent: Discordbot
User-agent: Slackbot-LinkExpanding
User-agent: TelegramBot
User-agent: WhatsApp
Allow: /

# Crawlers that gather text to train AI models: please do not take this site. Most of what is worth taking here is
# Christopher Paolini's own words and short quotations from his books, and those are not ours to give.
User-agent: GPTBot
User-agent: Google-Extended
User-agent: CCBot
User-agent: ClaudeBot
User-agent: anthropic-ai
User-agent: Applebot-Extended
User-agent: Bytespider
User-agent: Meta-ExternalAgent
User-agent: FacebookBot
User-agent: Amazonbot
User-agent: PerplexityBot
User-agent: cohere-ai
User-agent: Diffbot
User-agent: Omgilibot
User-agent: ImagesiftBot
Disallow: /

Sitemap: https://codexwerthos.com/sitemap-index.xml