# robots.txt for goodleapfinancingloans.com
# Updated: 2026-10-24
# Policy: open to all legitimate search engines and AI/LLM crawlers.
# Blocks only form submission endpoints and the APIdiamond partner URL.

# ===== Default: allow all crawlers =====
User-agent: *
Allow: /
Disallow: /cgi-bin/
Disallow: /tmp/
Disallow: /*.json$
Crawl-delay: 1

# ===== Google =====
User-agent: Googlebot
Allow: /
User-agent: Googlebot-Image
Allow: /
User-agent: Googlebot-News
Allow: /
User-agent: Googlebot-Video
Allow: /
User-agent: AdsBot-Google
Allow: /
User-agent: Mediapartners-Google
Allow: /

# ===== Google AI (Bard, Gemini, AI Overviews) =====
User-agent: Google-Extended
Allow: /

# ===== Bing =====
User-agent: Bingbot
Allow: /
User-agent: BingPreview
Allow: /
User-agent: msnbot
Allow: /
User-agent: msnbot-media
Allow: /

# ===== Bing / Copilot AI =====
User-agent: msnbot-UDiscovery
Allow: /

# ===== Yandex =====
User-agent: Yandex
Allow: /
User-agent: YandexBot
Allow: /

# ===== DuckDuckGo =====
User-agent: DuckDuckBot
Allow: /
User-agent: DuckAssistBot
Allow: /

# ===== Apple =====
User-agent: Applebot
Allow: /
User-agent: Applebot-Extended
Allow: /

# ===== OpenAI (ChatGPT) =====
User-agent: GPTBot
Allow: /
User-agent: ChatGPT-User
Allow: /
User-agent: OAI-SearchBot
Allow: /

# ===== Anthropic (Claude) =====
User-agent: ClaudeBot
Allow: /
User-agent: Claude-Web
Allow: /
User-agent: anthropic-ai
Allow: /

# ===== Perplexity =====
User-agent: PerplexityBot
Allow: /
User-agent: Perplexity-User
Allow: /

# ===== Meta AI =====
User-agent: Meta-ExternalAgent
Allow: /
User-agent: FacebookBot
Allow: /
User-agent: facebookexternalhit
Allow: /

# ===== Common Crawl (used by many LLMs for training data) =====
User-agent: CCBot
Allow: /

# ===== Other AI/research crawlers =====
User-agent: cohere-ai
Allow: /
User-agent: Diffbot
Allow: /
User-agent: Omgilibot
Allow: /
User-agent: Omgili
Allow: /
User-agent: Amazonbot
Allow: /
User-agent: Bytespider
Allow: /
User-agent: YouBot
Allow: /

# ===== Social crawlers (OG previews) =====
User-agent: Twitterbot
Allow: /
User-agent: LinkedInBot
Allow: /
User-agent: Pinterestbot
Allow: /
User-agent: Slackbot
Allow: /
User-agent: WhatsApp
Allow: /
User-agent: TelegramBot
Allow: /

# ===== Explicit block: aggressive scrapers that ignore crawl-delay =====
User-agent: SemrushBot
Disallow: /
User-agent: AhrefsBot
Disallow: /
User-agent: MJ12bot
Disallow: /
User-agent: DotBot
Disallow: /
User-agent: PetalBot
Disallow: /

# ===== Sitemaps =====
Sitemap: https://goodleapfinancingloans.com/sitemap-index.xml
Sitemap: https://goodleapfinancingloans.com/sitemap.xml
Sitemap: https://goodleapfinancingloans.com/sitemap-images.xml

# ===== LLM/AI content discovery =====
# llms.txt is a structured content map for AI assistants.
# llms-full.txt contains the full-content version.
# These are informational pointers; a proper crawler fetches them directly.