# As a condition of accessing this website, you agree to abide by the following
# content signals:

# (a)  If a Content-Signal = yes, you may collect content for the corresponding
#      use.
# (b)  If a Content-Signal = no, you may not collect content for the
#      corresponding use.
# (c)  If the website operator does not include a Content-Signal for a
#      corresponding use, the website operator neither grants nor restricts
#      permission via Content-Signal with respect to the corresponding use.

# The content signals and their meanings are:

# search:   building a search index and providing search results (e.g., returning
#           hyperlinks and short excerpts from your website's contents). Search does not
#           include providing AI-generated search summaries.
# ai-input: inputting content into one or more AI models (e.g., retrieval
#           augmented generation, grounding, or other real-time taking of content for
#           generative AI search answers).
# ai-train: training or fine-tuning AI models.

# ANY RESTRICTIONS EXPRESSED VIA CONTENT SIGNALS ARE EXPRESS RESERVATIONS OF
# RIGHTS UNDER ARTICLE 4 OF THE EUROPEAN UNION DIRECTIVE 2019/790 ON COPYRIGHT
# AND RELATED RIGHTS IN THE DIGITAL SINGLE MARKET.

# BEGIN Cloudflare Managed content

User-agent: *
Content-Signal: search=yes,ai-train=no
Allow: /

User-agent: Amazonbot
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: CloudflareBrowserRenderingCrawler
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: GPTBot
Disallow: /

User-agent: meta-externalagent
Disallow: /

# END Cloudflare Managed Content

# ==============================================================
# robots.txt — Saianand Commercial Limited
# Domain  : saianandcommerciallimited.co.in
# Updated : 2025-05-23
# Purpose : Crawl directives for search-engine and AI bots
# ==============================================================

# ── ALL COMPLIANT CRAWLERS ────────────────────────────────────
User-agent: *

# Allow the full public-facing site
Allow: /
Allow: /assets/css/
Allow: /assets/js/

# Disallow server-side / non-public paths
Disallow: /assets/php/
Disallow: /admin/
Disallow: /private/
Disallow: /tmp/
Disallow: /cache/
Disallow: /logs/
Disallow: /vendor/
Disallow: /node_modules/
Disallow: /.git/
Disallow: /.env
Disallow: /composer.json
Disallow: /composer.lock
Disallow: /package.json
Disallow: /package-lock.json

# Block query-string duplicates that could cause thin-content issues
Disallow: /*?*print=
Disallow: /*?*preview=
Disallow: /*?*session=
Disallow: /*?*utm_

# ── GOOGLEBOT ────────────────────────────────────────────────
User-agent: Googlebot
Allow: /
Crawl-delay: 5

# ── GOOGLEBOT IMAGE ──────────────────────────────────────────
User-agent: Googlebot-Image
Allow: /assets/
Disallow: /

# ── BINGBOT ──────────────────────────────────────────────────
User-agent: Bingbot
Allow: /
Crawl-delay: 10

# ── DUCKDUCKBOT ──────────────────────────────────────────────
User-agent: DuckDuckBot
Allow: /
Crawl-delay: 10

# ── SLURP (Yahoo) ────────────────────────────────────────────
User-agent: Slurp
Allow: /
Crawl-delay: 10

# ── BAIDUSPIDER ──────────────────────────────────────────────
User-agent: Baiduspider
Allow: /
Crawl-delay: 15

# ── AI / LLM TRAINING BOTS ───────────────────────────────────
# These bots crawl for AI model training.
# Disallowed by default; update if licensing changes.

User-agent: GPTBot
Disallow: /

User-agent: ChatGPT-User
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: anthropic-ai
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: cohere-ai
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: Omgilibot
Disallow: /

User-agent: FacebookBot
Disallow: /

# ── HIGH-VOLUME SEO SCRAPERS (block) ─────────────────────────
User-agent: AhrefsBot
Disallow: /

User-agent: SemrushBot
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: DotBot
Disallow: /

User-agent: BLEXBot
Disallow: /

User-agent: PetalBot
Disallow: /

User-agent: Bytespider
Disallow: /

# ── SITEMAPS ─────────────────────────────────────────────────
Sitemap: https://saianandcommerciallimited.co.in/sitemap.xml

# ── HOST DIRECTIVE ───────────────────────────────────────────
Host: saianandcommerciallimited.co.in