# PackTally robots.txt
#
# Policy (docs/seo-geo-audit-2026-10.md §3):
#  - Search engines and AI answer engines may crawl every public page.
#  - AI training crawlers may read editorial pages, not the price catalogue.
#  - Data resellers and known robots.txt-ignoring scrapers are blocked here
#    and at Cloudflare.
# Automated bulk collection of the catalogue is prohibited by the terms
# (https://packtally.com/terms#prohibited-uses). Text-and-data-mining rights on
# catalogue pages are reserved under Art. 4 of Directive (EU) 2019/790; see
# /.well-known/tdmrep.json.

# 1. Everyone not named below (incl. Googlebot, Bingbot, Applebot, DuckDuckBot)
User-agent: *
Content-Signal: search=yes, ai-input=yes
Disallow: /api/
Disallow: /__trap

# 2. AI answer / retrieval agents: fetch on a user's question and cite with a link
User-agent: OAI-SearchBot
User-agent: ChatGPT-User
User-agent: Claude-SearchBot
User-agent: Claude-User
User-agent: PerplexityBot
User-agent: Perplexity-User
User-agent: DuckAssistBot
User-agent: MistralAI-User
User-agent: meta-externalfetcher
User-agent: Google-Extended
Content-Signal: search=yes, ai-input=yes
Disallow: /api/
Disallow: /__trap

# 3. AI training crawlers: editorial pages only, not the price catalogue
User-agent: GPTBot
User-agent: ClaudeBot
User-agent: CCBot
User-agent: Applebot-Extended
User-agent: meta-externalagent
User-agent: Amazonbot
User-agent: cohere-ai
User-agent: cohere-training-data-crawler
User-agent: AI2Bot
Content-Signal: search=yes, ai-input=yes, ai-train=no
Disallow: /product/
Disallow: /category/
Disallow: /brand/
Disallow: /brands/
Disallow: /deals
Disallow: /black-friday
Disallow: /search
Disallow: /api/
Disallow: /__trap

# 4. Data resellers and scrapers known to ignore or abuse crawl rules
User-agent: Bytespider
User-agent: Diffbot
User-agent: Omgilibot
User-agent: Omgili
User-agent: webzio-extended
User-agent: ImagesiftBot
User-agent: img2dataset
User-agent: Timpibot
User-agent: PanguBot
Disallow: /

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