# promesasports.com
#
# Legitimate search engines are welcome and are explicitly allowed below.
# Crawlers that exist to harvest content for AI/ML training or dataset
# construction are not. See /terms.html for the reservation of rights and
# /.well-known/tdmrep.json for the machine-readable statement.

# ---------------------------------------------------------------
# Search engines and social link previews: allowed.
# ---------------------------------------------------------------
User-agent: Googlebot
Allow: /
Disallow: /backup/

User-agent: Googlebot-Image
Allow: /
Disallow: /backup/

User-agent: Bingbot
Allow: /
Disallow: /backup/

User-agent: Applebot
Allow: /
Disallow: /backup/

User-agent: DuckDuckBot
Allow: /
Disallow: /backup/

User-agent: Slurp
Allow: /
Disallow: /backup/

User-agent: facebookexternalhit
Allow: /

User-agent: Twitterbot
Allow: /

User-agent: LinkedInBot
Allow: /

# ---------------------------------------------------------------
# AI/ML training and dataset crawlers: not authorized.
#
# Google-Extended and Applebot-Extended are the vendor-documented
# controls for generative-AI training only. Declining them does not
# affect Google Search or Apple search indexing or ranking.
# ---------------------------------------------------------------
User-agent: Google-Extended
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: GPTBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: Claude-Web
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: meta-externalagent
Disallow: /

User-agent: meta-externalfetcher
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: PerplexityBot
Disallow: /

User-agent: Amazonbot
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: omgilibot
Disallow: /

User-agent: omgili
Disallow: /

User-agent: ImagesiftBot
Disallow: /

User-agent: Timpibot
Disallow: /

User-agent: Webzio-Extended
Disallow: /

User-agent: AI2Bot
Disallow: /

User-agent: cohere-ai
Disallow: /

User-agent: cohere-training-data-crawler
Disallow: /

# ---------------------------------------------------------------
# Everything else: crawlable, except the recovery copy of the site.
# ---------------------------------------------------------------
User-agent: *
Allow: /
Disallow: /backup/

Sitemap: https://promesasports.com/sitemap.xml