fosscat-site/static/robots.txt

43 lines
836 B
Plaintext

# All content on fosscat.com is the work of its author.
# Scraping, crawling, or collecting content from this site for
# commercial purposes — including AI/ML model training, data brokerage,
# or any for-profit data exploitation — is expressly prohibited,
# regardless of whether your user-agent is listed below.
# AI and data scrapers — disallowed
User-agent: GPTBot
Disallow: /
User-agent: CCBot
Disallow: /
User-agent: Google-Extended
Disallow: /
User-agent: anthropic-ai
Disallow: /
User-agent: Claude-Web
Disallow: /
User-agent: Omgilibot
Disallow: /
User-agent: FacebookBot
Disallow: /
User-agent: Bytespider
Disallow: /
User-agent: DataForSeoBot
Disallow: /
User-agent: PetalBot
Disallow: /
# All other crawlers (search engines, etc.) — allowed
User-agent: *
Allow: /
Sitemap: https://fosscat.com/sitemap.xml