# ══════════════════════════════════════════════════════════════
# PDFOnlineEditor.com — robots.txt
# Last Updated: June 2026
# Contact: support@pdfonlineeditor.com
# ══════════════════════════════════════════════════════════════

# ── SITEMAPS ──
Sitemap: https://pdfonlineeditor.com/sitemap.xml

# ── UNIVERSAL ACCESS — Allow all crawlers ──
User-agent: *
Allow: /
Crawl-delay: 1

# Block internal/admin paths
Disallow: /admin
Disallow: /api/
Disallow: /_internal/
Disallow: /dashboard/

# ══════════════════════════════════════════════════════════════
# GOOGLE BOTS
# ══════════════════════════════════════════════════════════════
User-agent: Googlebot
Allow: /
Crawl-delay: 0

User-agent: Googlebot-Image
Allow: /

User-agent: Googlebot-News
Allow: /blog/

User-agent: Googlebot-Video
Allow: /

User-agent: AdsBot-Google
Allow: /

User-agent: Mediapartners-Google
Allow: /

User-agent: APIs-Google
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: GoogleOther
Allow: /

# ══════════════════════════════════════════════════════════════
# BING / MICROSOFT BOTS
# ══════════════════════════════════════════════════════════════
User-agent: Bingbot
Allow: /
Crawl-delay: 1

User-agent: msnbot
Allow: /

User-agent: BingPreview
Allow: /

# ══════════════════════════════════════════════════════════════
# AI SEARCH ENGINES & LLM CRAWLERS
# ══════════════════════════════════════════════════════════════

# OpenAI / ChatGPT
User-agent: ChatGPT-User
Allow: /

User-agent: GPTBot
Allow: /

User-agent: OAI-SearchBot
Allow: /

# Anthropic / Claude
User-agent: ClaudeBot
Allow: /

User-agent: anthropic-ai
Allow: /

# Google Gemini / Bard
User-agent: Google-Extended
Allow: /

# Perplexity AI
User-agent: PerplexityBot
Allow: /

# Meta AI
User-agent: FacebookBot
Allow: /

User-agent: Meta-ExternalAgent
Allow: /

User-agent: meta-externalagent
Allow: /

# Cohere AI
User-agent: cohere-ai
Allow: /

# You.com
User-agent: YouBot
Allow: /

# Brave Search
User-agent: BraveBot
Allow: /

# Apple / Siri
User-agent: Applebot
Allow: /
Crawl-delay: 1

User-agent: AppleBot-Extended
Allow: /

# DuckDuckGo
User-agent: DuckDuckBot
Allow: /

# Yandex
User-agent: YandexBot
Allow: /
Crawl-delay: 2

# Baidu
User-agent: Baiduspider
Allow: /
Crawl-delay: 2

# Sogou
User-agent: Sogou
Allow: /

# Naver
User-agent: Yeti
Allow: /

# Qwant
User-agent: Qwantify
Allow: /

# Seznam
User-agent: SeznamBot
Allow: /

# Common Crawl (used by many AI training datasets)
User-agent: CCBot
Allow: /

# Internet Archive
User-agent: ia_archiver
Allow: /

# Diffbot (knowledge graph)
User-agent: Diffbot
Allow: /

# Amazon Alexa
User-agent: ia_archiver
Allow: /

# LinkedIn
User-agent: LinkedInBot
Allow: /

# Twitter/X
User-agent: Twitterbot
Allow: /

# Slack
User-agent: Slackbot
Allow: /

# Telegram
User-agent: TelegramBot
Allow: /

# WhatsApp
User-agent: WhatsApp
Allow: /

# Pinterest
User-agent: Pinterest
Allow: /

# Semrush (SEO tool)
User-agent: SemrushBot
Allow: /

# Ahrefs (SEO tool)
User-agent: AhrefsBot
Allow: /
Crawl-delay: 5

# Moz
User-agent: rogerbot
Allow: /
Crawl-delay: 5

# ══════════════════════════════════════════════════════════════
# AI-SPECIFIC CONTENT FILES
# ══════════════════════════════════════════════════════════════
# LLM-readable site description: https://pdfonlineeditor.com/llms.txt
# AI crawl policy: https://pdfonlineeditor.com/ai.txt
# Standard sitemap: https://pdfonlineeditor.com/sitemap.xml
# ══════════════════════════════════════════════════════════════