# Sprawdzona Kuchnia robots.txt
# Policy: allow public search, AI-search discovery and user-requested retrieval.
# Restrict identified crawlers used for model training or training datasets.

# OpenAI: GPTBot is used for foundation-model training.
User-agent: GPTBot
Disallow: /

# Anthropic: ClaudeBot is used for model-training data collection.
User-agent: ClaudeBot
Disallow: /

# Google: Google-Extended controls use for Gemini and other Google AI model training.
# It does not block Google Search, Googlebot, Discover or Google Images.
User-agent: Google-Extended
Disallow: /

# Common Crawl: dataset commonly used in model-training pipelines.
User-agent: CCBot
Disallow: /

# Apple: Applebot-Extended controls use for Apple Intelligence model training.
User-agent: Applebot-Extended
Disallow: /

# ByteDance: restrict the training-oriented crawler.
User-agent: Bytespider
Disallow: /

# Explicitly allow AI-search and user-directed retrieval where vendors provide
# separate agents. These rules are also allowed by the wildcard group below,
# but are stated here to document the intended policy.
User-agent: OAI-SearchBot
Allow: /

User-agent: Claude-SearchBot
Allow: /

User-agent: Claude-User
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: *
Disallow: /wp-admin/
Allow: /wp-admin/admin-ajax.php

# Blokada podstron autorow oraz pliku xmlrpc
Disallow: /xmlrpc.php
Disallow: /?author=

# Blokada wyszukiwarki i jej paginacji
Disallow: /*?s=
Disallow: /search/

# Blokada powielonych adresów komentarzy i osadzeń
Disallow: /*?replytocom=
Disallow: /*/embed/
Disallow: /comments/feed/

# Sitemap
Sitemap: https://sprawdzonakuchnia.pl/sitemap_index.xml