# ==============================================================
# robots.txt for Mectech Process Engineers Pvt. Ltd.
# https://www.mectech.co.in
# ==============================================================

# --------------------------------------------------------------
# General Rule: Allow all well-behaved crawlers
# Block only internal/dev directories
# --------------------------------------------------------------
User-agent: *
Disallow: /mectech_version_2.0/
Disallow: /admin/
Disallow: /private/
Disallow: /cgi-bin/
Allow: /

# --------------------------------------------------------------
# Google Search (Web + Images + News + Video)
# --------------------------------------------------------------
User-agent: Googlebot
Allow: /
Disallow: /mectech_version_2.0/

User-agent: Googlebot-Image
Allow: /public/f/images/

User-agent: Googlebot-Video
Allow: /

# --------------------------------------------------------------
# Bing / Microsoft Search
# --------------------------------------------------------------
User-agent: Bingbot
Allow: /
Disallow: /mectech_version_2.0/

User-agent: MSNBot
Allow: /

# --------------------------------------------------------------
# Apple Search
# --------------------------------------------------------------
User-agent: Applebot
Allow: /

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

# --------------------------------------------------------------
# Yandex (Russia / CIS markets)
# --------------------------------------------------------------
User-agent: YandexBot
Allow: /
Disallow: /mectech_version_2.0/

# --------------------------------------------------------------
# Baidu (China / Chinese language site)
# --------------------------------------------------------------
User-agent: Baiduspider
Allow: /

# --------------------------------------------------------------
# LinkedIn (important for B2B discovery)
# --------------------------------------------------------------
User-agent: LinkedInBot
Allow: /

# --------------------------------------------------------------
# Facebook / Meta (Open Graph previews)
# --------------------------------------------------------------
User-agent: facebookexternalhit
Allow: /

User-agent: Facebot
Allow: /

# --------------------------------------------------------------
# Twitter / X (link previews)
# --------------------------------------------------------------
User-agent: Twitterbot
Allow: /

# --------------------------------------------------------------
# WhatsApp (link previews — important for B2B enquiries)
# --------------------------------------------------------------
User-agent: WhatsApp
Allow: /

# ==============================================================
# LLM & AI CRAWLERS
# Allow all AI/LLM bots to crawl for knowledge indexing
# ==============================================================

# OpenAI (ChatGPT / GPT-4 / SearchGPT)
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: /

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

# Meta AI (Llama)
User-agent: Meta-ExternalAgent
Allow: /

User-agent: Meta-ExternalFetcher
Allow: /

# Perplexity AI
User-agent: PerplexityBot
Allow: /

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

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

# Amazon Alexa / Rufus (AI shopping assistant)
User-agent: Amazonbot
Allow: /

# Apple (AI / Siri Knowledge)
User-agent: Applebot-Extended
Allow: /

# Common Crawl (used to train many LLMs)
User-agent: CCBot
Allow: /

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

# Screaming Frog / Technical SEO (allow for audits)
User-agent: Screaming Frog SEO Spider
Allow: /

# ==============================================================
# Sitemaps
# ==============================================================
Sitemap: https://www.mectech.co.in/sitemap.xml

# ==============================================================
# LLMs.txt Reference (AI knowledge file)
# ==============================================================
# AI crawlers: see https://www.mectech.co.in/llms.txt
# for a structured summary of Mectech's products and services.