# robots.txt for https://tapvoter.com
# Last updated: 2026-08-23

# Google advertising crawlers — must reach every ad-bearing page to serve
# relevant creatives. AdsBot-Google ignores the wildcard group, so it needs its
# own. Neither is given the private areas, which carry no ads.
#
# The legacy app routes (/dashboard, /elections/*, /vote, /super-admin) were
# removed on 2026-08-23 and now 301 to app.tapvoter.com. They are deliberately
# NOT disallowed: a blocked URL is never fetched, so the crawler would never
# see the redirect and the old URLs would linger in the index unconsolidated.
User-agent: Mediapartners-Google
User-agent: AdsBot-Google
User-agent: AdsBot-Google-Mobile
Allow: /
Disallow: /admin/
Allow: /_next/static/
Disallow: /_next/

# Search engines — allow all public pages, block private/admin areas
User-agent: Googlebot
User-agent: Googlebot-Image
User-agent: Bingbot
Allow: /
Allow: /llms.txt
Disallow: /admin/
Allow: /_next/static/
Disallow: /_next/

# Social media crawlers — allow all public pages for OG previews
User-agent: facebookexternalhit
User-agent: Twitterbot
User-agent: LinkedInBot
User-agent: Slackbot
User-agent: WhatsApp
User-agent: Discordbot
Allow: /
Disallow: /admin/
Allow: /_next/static/
Disallow: /_next/

# AI/LLM crawlers — allow public pages + llms.txt for discovery & training
User-agent: GPTBot
User-agent: ChatGPT-User
User-agent: OAI-SearchBot
User-agent: anthropic-ai
User-agent: ClaudeBot
User-agent: Claude-User
User-agent: Claude-SearchBot
User-agent: CCBot
User-agent: PerplexityBot
User-agent: Perplexity-User
User-agent: Bytespider
User-agent: YouBot
User-agent: Applebot
User-agent: Applebot-Extended
User-agent: DuckAssistBot
User-agent: Amazonbot
User-agent: cohere-ai
User-agent: cohere-training-data-crawler
User-agent: MistralAI-User
User-agent: Google-CloudVertexBot
User-agent: Google-Extended
User-agent: Gemini-Deep-Research
User-agent: Meta-ExternalAgent
User-agent: Meta-ExternalFetcher
User-agent: Meta-WebIndexer
User-agent: AI2Bot
User-agent: AI2Bot-Dolma
User-agent: Diffbot
User-agent: img2dataset
User-agent: Timpibot
User-agent: TikTokSpider
User-agent: ExaBot
Allow: /llms.txt
Allow: /
Disallow: /admin/
Allow: /_next/static/
Disallow: /_next/

# SEO research crawlers — allowed (we want competitive visibility in Ahrefs/Semrush).
# Block low-signal, high-load bots that routinely ignore crawl budget.
User-agent: DotBot
User-agent: MJ12bot
User-agent: PetalBot
User-agent: BLEXBot
Disallow: /

# Default: allow all crawlers on public pages
User-agent: *
Allow: /
Disallow: /admin/
Allow: /_next/static/
Disallow: /_next/
Disallow: /404/

Sitemap: https://tapvoter.com/sitemap.xml