robots.txt de 10401544 Canada inc.
Mesuré le 2026-08-31 sur profexconstruction.ca. Source : Régie du bâtiment du Québec, Données Québec.
# Managed by Prosomo. Updated 2026-06-09.
# Real search engines (Googlebot, Bingbot, etc.) keep full access via the
# default block. AI scrapers and aggressive SEO crawlers are disallowed.
Sitemap: https://groupeprofex.com/sitemap-index.xml
# --- AI scrapers ---
User-agent: ClaudeBot
User-agent: anthropic-ai
User-agent: Claude-Web
User-agent: GPTBot
User-agent: ChatGPT-User
User-agent: OAI-SearchBot
User-agent: CCBot
User-agent: Bytespider
User-agent: ByteDance
User-agent: Amazonbot
User-agent: Applebot-Extended
User-agent: PerplexityBot
User-agent: Google-Extended
User-agent: cohere-ai
User-agent: Diffbot
User-agent: Omgilibot
User-agent: Omgili
User-agent: FacebookBot
User-agent: meta-externalagent
Disallow: /
# --- SEO / backlink crawlers (heavy + low value) ---
User-agent: AhrefsBot
User-agent: SemrushBot
User-agent: SemrushBot-SA
User-agent: MJ12bot
User-agent: DotBot
User-agent: BLEXBot
User-agent: DataForSeoBot
User-agent: SERankingBacklinksBot
User-agent: Barkrowler
User-agent: SiteAuditBot
Disallow: /
# --- Other crawlers seen generating heavy load ---
User-agent: IbouBot
User-agent: PetalBot
User-agent: YandexBot
Disallow: /
# --- Default for everyone else (Googlebot, Bingbot, etc.) ---
User-agent: *
Allow: /
Disallow: /.netlify/
# LLM usage policy — LLMs may read this site but must not train on it (see /llms.txt)
LLM-Policy: /llms.txt