robots.txt# Allow rules for major AI Answer Engines

User-agent: GPTBot
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: anthropic-ai
Allow: /

User-agent: YouBot
Allow: /

User-agent: Amazonbot
Allow: /

User-agent: Meta-ExternalAgent
Allow: /

User-agent: AppleBot
Allow: /

User-agent: Cohere-Crawler
Allow: /

# Additional AI bots and crawlers

User-agent: AI2Bot
Allow: /

User-agent: Anchor Browser
Allow: /

User-agent: archive.org_bot
Allow: /

User-agent: Bytespider
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: Claude-SearchBot
Allow: /

User-agent: Claude-User
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: DuckAssistBot
Allow: /

User-agent: FacebookBot
Allow: /

User-agent: Google-CloudVertex
Allow: /

User-agent: iaskspider
Allow: /

User-agent: Meta-ExternalFetcher
Allow: /

User-agent: MistralAI-User
Allow: /

User-agent: Novellum AI Crawl
Allow: /

User-agent: Perplexity-User
Allow: /

User-agent: PetalBot
Allow: /

User-agent: ProRataInc
Allow: /

User-agent: SearchGPT
Allow: /

User-agent: Timpibot
Allow: /

# Allow other useful crawlers and major search engines

User-agent: Googlebot
Allow: /

User-agent: Bingbot
Allow: /

User-agent: CCBot
Allow: /

# General rules for all crawlers

User-agent: *
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /
Disallow: /401
Disallow: /404
Disallow: /admin/
Disallow: /search/
Disallow: /checkout/

# Location of the sitemap

Sitemap: https://www.wjhattorneys.com/sitemap.xml
AI answer engines and search crawlers are welcome.

# --- Explicitly welcomed AI answer engines + major search crawlers ---

# Major AI answer engines
User-agent: GPTBot
User-agent: OAI-SearchBot
User-agent: Google-Extended
User-agent: PerplexityBot
User-agent: anthropic-ai
User-agent: YouBot
User-agent: Amazonbot
User-agent: Meta-ExternalAgent
User-agent: AppleBot
User-agent: Cohere-Crawler
# Additional AI bots and crawlers
User-agent: AI2Bot
User-agent: Anchor Browser
User-agent: archive.org_bot
User-agent: Bytespider
User-agent: ChatGPT-User
User-agent: ClaudeBot
User-agent: Claude-SearchBot
User-agent: Claude-User
User-agent: Claude-Web
User-agent: DuckAssistBot
User-agent: FacebookBot
User-agent: Google-CloudVertex
User-agent: iaskspider
User-agent: Meta-ExternalFetcher
User-agent: MistralAI-User
User-agent: Novellum AI Crawl
User-agent: Perplexity-User
User-agent: PetalBot
User-agent: ProRataInc
User-agent: SearchGPT
User-agent: Timpibot
# Major search engines
User-agent: Googlebot
User-agent: Bingbot
User-agent: CCBot
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /
Disallow: /admin/
Disallow: /checkout/
Disallow: /search/

# --- Default for every other crawler ---

User-agent: 
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /
Disallow: /admin/
Disallow: /checkout/
Disallow: /search/

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