# robots.txt for Viralance
# https://viralance.com/robots.txt

# Global rules - Allow all good bots
User-agent: *
Allow: /
Allow: /*.css$
Allow: /*.js$
Allow: /*.webp$
Allow: /*.png$
Allow: /*.jpg$
Allow: /*.svg$

# Block authentication, API routes, and user areas
Disallow: /api/
Disallow: /login
Disallow: /register
Disallow: /forgot-password
Disallow: /verify-email
Disallow: /dashboard/

# Sitemap locations
Sitemap: https://viralance.com/sitemap.xml
Sitemap: https://viralance.com/video-sitemap.xml

# Specific rules for major search engines

# Google (primary target)
User-agent: Googlebot
Allow: /
Disallow: /api/
Disallow: /dashboard/

# Google Images - allow all images
User-agent: Googlebot-Image
Allow: /

# Google Video - allow video content (important for AI video tool)
User-agent: Googlebot-Video
Allow: /

# Bing
User-agent: Bingbot
Allow: /
Disallow: /api/
Disallow: /dashboard/

# Yandex
User-agent: Yandex
Allow: /
Disallow: /api/
Disallow: /dashboard/

# ChatGPT & AI Crawlers (2026)
# OpenAI live search bot — CRITICAL: blocking this hides Viralance from ChatGPT Search answers
User-agent: OAI-SearchBot
Allow: /
Disallow: /dashboard/

User-agent: GPTBot
Allow: /
Disallow: /api/
Disallow: /dashboard/

User-agent: ChatGPT-User
Allow: /
Disallow: /dashboard/

# Training crawlers are allowed since 2026-10-02 (GPTBot, ClaudeBot, Meta,
# Cohere, Mistral): a product site benefits from being known to the models.
# The Cloudflare AI-bot setting must agree with this file.
User-agent: Claude-SearchBot
Allow: /
Disallow: /api/
Disallow: /dashboard/

User-agent: Claude-User
Allow: /
Disallow: /api/
Disallow: /dashboard/

# Claude training crawler + legacy
User-agent: ClaudeBot
Allow: /
Disallow: /api/
Disallow: /dashboard/

User-agent: anthropic-ai
Allow: /
Disallow: /api/
Disallow: /dashboard/

# Perplexity AI (crawler + live answer fetcher)
User-agent: PerplexityBot
Allow: /
Disallow: /dashboard/

User-agent: Perplexity-User
Allow: /
Disallow: /dashboard/

# Google general-purpose crawler (AI Overviews use Googlebot)
User-agent: GoogleOther
Allow: /
Disallow: /dashboard/

# Google Gemini / Vertex AI grounding (Google-Extended is a control token, not
# a crawler; allowing it lets Gemini cite and ground answers on public pages)
User-agent: Google-Extended
Allow: /
Disallow: /api/
Disallow: /dashboard/

# Meta AI (2026)
User-agent: Meta-ExternalAgent
Allow: /
Disallow: /api/
Disallow: /dashboard/

User-agent: Meta-ExternalFetcher
Allow: /
Disallow: /dashboard/
Disallow: /api/

# Cohere AI (2026)
User-agent: cohere-ai
Allow: /
Disallow: /api/
Disallow: /dashboard/

# Mistral AI (2026)
User-agent: MistralBot
Allow: /
Disallow: /api/
Disallow: /dashboard/

# Block bad bots
User-agent: SemrushBot
Disallow: /

User-agent: AhrefsBot
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: DotBot
Disallow: /