# Default policy
User-agent: *
Allow: /
# Googlebot's renderer obeys robots.txt for the page's OWN internal fetches:
# client-rendered islands (events, category pages…) load their content through
# the read-only /api/strapi proxy, so it must stay crawlable or Google renders
# those pages as empty/404. Longest-match: this Allow overrides the Disallow.
Allow: /api/strapi/
Disallow: /api/
Disallow: /recherche/
Disallow: /search/

# Content Signals (contentsignals.org) — machine-readable form of the policy
# already enforced by the per-bot blocks below + AI Labyrinth: no AI training,
# no AI answer-grounding, search indexing welcome.
Content-Signal: search=yes, ai-train=no, ai-input=no

# ---------------------------------------------------------------------------
# Allowed AI crawlers — OpenAI (deliberate, 2026-07-11).
# Opened to capture ChatGPT referral traffic:
#   OAI-SearchBot  — indexes for ChatGPT Search → citations/links in answers
#   ChatGPT-User   — live fetch when a user's ChatGPT pulls the page
#   GPTBot         — bulk crawl for model training (operator-approved)
# All other AI crawlers below stay blocked. Content-Signal (ai-train=no,
# ai-input=no) is left unchanged per operator; the per-UA Allow lines are the
# authoritative lever, the header is advisory only.
# ---------------------------------------------------------------------------
User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: GPTBot
Allow: /

# ---------------------------------------------------------------------------
# AI training / scraping crawlers (these honor robots.txt)
# ---------------------------------------------------------------------------
User-agent: ClaudeBot
Disallow: /

User-agent: Claude-Web
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: PerplexityBot
Disallow: /

User-agent: Perplexity-User
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: Amazonbot
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: Meta-ExternalAgent
Disallow: /

User-agent: FacebookBot
Disallow: /

User-agent: cohere-ai
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: Omgilibot
Disallow: /

User-agent: ImagesiftBot
Disallow: /

User-agent: PetalBot
Disallow: /

User-agent: DataForSeoBot
Disallow: /

User-agent: YouBot
Disallow: /

User-agent: AI2Bot
Disallow: /

User-agent: Baiduspider
Disallow: /

# ---------------------------------------------------------------------------
# SEO / backlink crawlers — THROTTLED, not blocked (we use Ahrefs ourselves).
# AhrefsBot = the web-wide backlink crawler; AhrefsSiteAudit = our own Site
# Audit crawler. Both honor Crawl-delay per Ahrefs docs (Googlebot ignores it,
# so search crawling is unaffected). Crawl-delay: 10 == 6 URLs/min, mirroring
# the speed cap set in Ahrefs Site Audit → Crawl settings.
# ---------------------------------------------------------------------------
User-agent: AhrefsBot
User-agent: AhrefsSiteAudit
Crawl-delay: 10

# ---------------------------------------------------------------------------
# Reverse-image / copyright-enforcement crawlers
# WARNING: PicRights, PicScout and ImageRights do NOT honor robots.txt and
# spoof normal browser user-agents. The lines below document intent only;
# they are actually stopped at the Cloudflare WAF, not here. TinEye / Pixsy
# generally do honor robots.txt.
# ---------------------------------------------------------------------------
User-agent: TinEye
Disallow: /

User-agent: TinEye-bot
Disallow: /

User-agent: Pixsy
Disallow: /

User-agent: PicScout
Disallow: /

User-agent: PicRights
Disallow: /

User-agent: ImageRights
Disallow: /

Sitemap: https://www.capmad.com/sitemap.xml