Sitemap: http://findingaugustine.org/sitemapIndex.xml

User-agent: *

Crawl-delay: 10

User-agent: Bytespider
Disallow: /

User-agent: Sogou web spider
Disallow: /

User-agent: Sogou inst spider
Disallow: /

# ---

# Dark Visitors
# https://darkvisitors.com/

# Claude
User-agent: anthropic-ai
Disallow: /
User-agent: ClaudeBot
Disallow: /
User-agent: ClaudeBot/1.0
Disallow: /
User-agent: Claude-Web
Disallow: /

# Common Crawl
User-agent: CCBot
Disallow: /

# ChatGPT user prompt research
User-agent: ChatGPT-User
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: FacebookBot
Disallow: /

# Google AI training data crawl
User-agent: Google-Extended
Disallow: /

User-agent: omgili
Disallow: /

# ---

# Islandora Issues
# https://github.com/Islandora/documentation/issues/2286

User-agent: AcademicBotRTU
Disallow: /

User-agent: DataForSeoBot
Disallow: /

# OpenAI training data crawl
User-agent: GPTBot
Disallow: /

User-agent: PetalBot
Disallow: /

User-agent: SemrushBot
Disallow: /

User-agent: test-bot
Disallow: /

User-agent: Timpibot
Disallow: /

User-agent: Timpibot/0.9
Disallow: /

# --- From https://github.com/ai-robots-txt/ai.robots.txt/blob/main/robots.txt, deduplicated with stanzas above, updated 10/28/24

User-agent: AI2Bot
User-agent: Ai2Bot-Dolma
User-agent: Amazonbot
User-agent: Applebot
User-agent: Applebot-Extended
User-agent: cohere-ai
User-agent: facebookexternalhit
User-agent: FriendlyCrawler
User-agent: GoogleOther
User-agent: GoogleOther-Image
User-agent: GoogleOther-Video
User-agent: iaskspider/2.0
User-agent: ICC-Crawler
User-agent: ImagesiftBot
User-agent: img2dataset
User-agent: ISSCyberRiskCrawler
User-agent: Kangaroo Bot
User-agent: Meta-ExternalAgent
User-agent: Meta-ExternalFetcher
User-agent: OAI-SearchBot
User-agent: omgilibot
User-agent: PerplexityBot
User-agent: Scrapy
User-agent: Sidetrade indexer bot
User-agent: VelenPublicWebCrawler
User-agent: Webzio-Extended
User-agent: YouBot
Disallow: /

# ---