# robots.txt file for https://pietromingotti.com
# Last updated: 2025-08-01
# This file governs crawling rules for all bots except LLMs, which are managed in /llms.txt

# Major Search Engines — Allowed

User-agent: Googlebot
Allow: /
User-agent: Googlebot-News
Allow: /
User-agent: Googlebot-Image
Allow: /
User-agent: Googlebot-Video
Allow: /
User-agent: Mediapartners-Google
Allow: /
User-agent: AdsBot-Google
Allow: /

User-agent: Bingbot
Allow: /
User-agent: Slurp
Allow: /
User-agent: DuckDuckBot
Allow: /
User-agent: Baiduspider
Allow: /
User-agent: Baiduspider-image
Allow: /
User-agent: Baiduspider-video
Allow: /
User-agent: Baiduspider-news
Allow: /
User-agent: Baiduspider-favo
Allow: /
User-agent: Baiduspider-cpro
Allow: /
User-agent: Baiduspider-ads
Allow: /

User-agent: YandexBot
Allow: /
User-agent: Sogou web spider
Allow: /
User-agent: PetalBot
Allow: /
User-agent: Linespider
Allow: /
User-agent: Yeti
Allow: /
User-agent: coccocbot
Allow: /
User-agent: Qwantify
Allow: /
User-agent: Applebot
Allow: /
User-agent: Twitterbot
Allow: /
User-agent: facebookexternalhit
Allow: /

# Sitemap Directives

Sitemap: https://pietromingotti.com/sitemap_index.xml
Sitemap: https://pietromingotti.com/page-sitemap.xml
Sitemap: https://pietromingotti.com/post-sitemap.xml
Sitemap: https://pietromingotti.com/author-sitemap.xml
Sitemap: https://pietromingotti.com/news-sitemap.xml


# LLM and AI bots

User-agent: gptbot
Allow: /
User-agent: ChatGPT-User
Allow: /
User-agent: claude-bot
Allow: /
User-agent: anthropic-ai
Allow: /
User-agent: google-extended
Allow: /
User-agent: perplexitybot
Allow: /
User-agent: youbot
Allow: /
User-agent: ccbot
Allow: /
User-agent: neevabot
Allow: /
User-agent: cohere-ai
Allow: /
User-agent: writer
Allow: /
User-agent: ai-crawler
Allow: /
User-agent: Amazonbot
Allow: /

# Refer to https://pietromingotti.com/llms.txt for AI/LLM-specific permissions


# SEO Tools / Crawlers

User-agent: Rogerbot
Allow: /
User-agent: Dotbot
Allow: /
User-agent: MJ12bot
Disallow: /
User-agent: AhrefsBot
Allow: /
User-agent: SemrushBot
Allow: /
User-agent: SemrushBot-SA
Allow: /

# Crawl Rate Management

Crawl-delay: 10

# ========================
# ?? Sensitive Paths (if needed)
# ========================
# Disallow: /wp-admin/
# Disallow: /private/
# Disallow: /*?*sort=*
# Disallow: /*.pdf$
# Disallow: /thank-you/
Viewport
Window
×
×
×