# NOTICE: By accessing this website (petico.my), you agree to abide by the following content policy.
# (a) If content-signal = yes, you may collect content for the corresponding purpose.
# (b) If content-signal = no, you may not collect content for the corresponding purpose.
# (c) If no content-signal is provided, permission is neither granted nor restricted.

# Content Signal Definitions:
# search   = building a search index and serving results
# ai-input = using content for real-time AI queries or summaries
# ai-train = training or fine-tuning AI models
#
# Any restrictions expressed via content signals are reserved rights under EU Directive 2019/790.

# =====================================================
# BEGIN: Content & AI Policy
# =====================================================
User-agent: *
# Content-signal: search=yes, ai-input=yes, ai-train=no
Allow: /
# =====================================================


# =====================================================
# BEGIN: Approved Search Engine Crawlers
# =====================================================
User-agent: Googlebot
Allow: /

User-agent: Googlebot-Image
Allow: /

User-agent: Googlebot-News
Allow: /

User-agent: Googlebot-Video
Allow: /

User-agent: Bingbot
Allow: /
# =====================================================


# =====================================================
# BEGIN: AI & Data Bot Management
# =====================================================
# Allow GPTBot for live AI query referencing (not for dataset training)
User-agent: GPTBot
Allow: /

# Block known AI scrapers and data-collection bots
User-agent: Amazonbot
Disallow: /

User-agent: Applebot
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: AhrefsBot
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: cohere-ai
Disallow: /

User-agent: DataForSeoBot
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: DotBot
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: meta-external-agent
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: NeevaBot
Disallow: /

User-agent: PerplexityBot
Disallow: /

User-agent: SemrushBot
Disallow: /

User-agent: YouBot
Disallow: /

User-agent: Yandex
Disallow: /

User-agent: ZoominfoBot
Disallow: /
# =====================================================


# =====================================================
# BEGIN: General Crawl Rules
# =====================================================
User-agent: *
Allow: /

# Block sensitive or backend file types
Disallow: /*.php$
Disallow: /*.json$
Disallow: /*.zip$

# Block internal or system directories (adjust if paths differ on your server)
Disallow: /classes/
Disallow: /config/
Disallow: /ignore/
Disallow: /logs/
Disallow: /payment_session/
Disallow: /session_storage/
Disallow: /pages/

# Sitemap
Sitemap: https://petico.my/sitemap.xml
# =====================================================