robots.txt de Beaucinox inc.
Mesuré le 2026-08-29 sur beaucinox.com. Source : Régie du bâtiment du Québec, Données Québec.
# ============================================
# robots.txt - Beaucinox Inc.
# ============================================
# --- Bots IA autorises (strategie GEO) ---
User-agent: GPTBot
Allow: /
User-agent: ChatGPT-User
Allow: /
User-agent: OAI-SearchBot
Allow: /
User-agent: ClaudeBot
Allow: /
User-agent: Claude-Web
Allow: /
User-agent: anthropic-ai
Allow: /
User-agent: PerplexityBot
Allow: /
User-agent: Perplexity-User
Allow: /
User-agent: Google-Extended
Allow: /
User-agent: CCBot
Allow: /
User-agent: Applebot-Extended
Allow: /
User-agent: Meta-ExternalAgent
Allow: /
# --- Scrapers malveillants bloques ---
User-agent: MJ12bot
Disallow: /
User-agent: DotBot
Disallow: /
User-agent: BLEXBot
Disallow: /
User-agent: trendictionbot
Disallow: /
User-agent: JennyBot
Disallow: /
User-agent: TightTwatBot
Disallow: /
User-agent: Jetbot
Disallow: /
User-agent: Snapbot
Disallow: /
# --- Scrapers SEO (limites en vitesse) ---
User-agent: SemrushBot
Crawl-delay: 10
User-agent: AhrefsBot
Crawl-delay: 10
# --- Directives generales (tous les autres bots) ---
User-agent: *
Disallow: /wp-admin/
Disallow: /wp-includes/
Disallow: /wp-content/cache/
Disallow: /wp-content/uploads/wpforms/
Disallow: /?s=
Disallow: /search/
Disallow: /?
Allow: /wp-admin/admin-ajax.php
Allow: /wp-content/uploads/
Allow: /wp-content/plugins/
Allow: /wp-content/themes/
# --- Sitemap ---
Sitemap: https://beaucinox.com/sitemaps.xml