# robots.txt for PracHub
# https://prachub.com

User-agent: *
Allow: /

# Disallow low-value pages
Disallow: /login
Disallow: /register
Disallow: /logout
Disallow: /forgot-password
Disallow: /activate
Disallow: /invite/
Disallow: /api/
# /careers was deprecated; removed the Disallow so Google can crawl, see the
# 404, and deindex over time. Previously the Disallow blocked discovery of
# the gone status, leaving phantom index entries with no snippet (14k imps,
# 0.7% CTR at avg position 1.2 in 3-month GSC, May 2026).

# Allow AI crawlers
User-agent: GPTBot
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: anthropic-ai
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

User-agent: Applebot-Extended
Allow: /

User-agent: cohere-ai
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: Bytespider
Allow: /

User-agent: meta-externalagent
Allow: /

User-agent: CCBot
Allow: /

User-agent: Amazonbot
Allow: /

User-agent: Diffbot
Allow: /

# Allow Google to crawl everything important
User-agent: Googlebot
Allow: /


# Junk SEO scrapers — no search or AI-answer value, heavy crawl volume across
# ~18k URLs. Deliberately NOT blocked: AhrefsBot (our own Ahrefs dashboards
# depend on it crawling prachub.com), SemrushBot, and every AI/search crawler
# allowed above.
User-agent: MJ12bot
Disallow: /

User-agent: DotBot
Disallow: /

User-agent: DataForSeoBot
Disallow: /

User-agent: BLEXBot
Disallow: /

User-agent: PetalBot
Disallow: /

User-agent: serpstatbot
Disallow: /

User-agent: Barkrowler
Disallow: /

User-agent: MegaIndex.ru
Disallow: /

User-agent: ZoominfoBot
Disallow: /

User-agent: SeekportBot
Disallow: /

# Sitemaps
Sitemap: https://prachub.com/sitemap.xml

# LLM discovery
LLMs-Txt: https://prachub.com/llms.txt