# WebCoffee Robots.txt
# Updated: 2025-11-25

# Allow all robots full access by default
User-agent: *
Allow: /

# Block sensitive areas and duplicate content
Disallow: /api/
Disallow: /cgi-bin/
Disallow: /tmp/
Disallow: /private/
Disallow: /includes/
Disallow: /*?preview=true

# Block duplicate filter/sort URLs (keep clean canonical URLs only)
Disallow: /*?*sort=
Disallow: /*?*filter=
Disallow: /*?*search=
Disallow: /*?*details=
Disallow: /*?*price=

# Brand filter pages (e.g. /cafea-capsule?brand=["Lavazza"]) are deliberately crawlable: a category
# plus a single brand matches real search demand. Only single-brand URLs are indexable, and only
# where the filter holds at least 10 products — the page itself decides via meta robots, which is
# why this must NOT be disallowed here. A Disallow would hide that noindex/index signal entirely.
# Brand combined with any other filter still carries noindex from the page.

# Blog tag pages carry meta robots noindex as of 2026-09-01. Leave them crawlable for now so
# Google can see the noindex and drop them. From 2026-12-01, once they are out of the index,
# uncomment the line below to stop spending crawl budget on them entirely.
# Disallow: */etichete/*

# Block Next.js technical URLs (image optimization, build artifacts)
# But ALLOW JavaScript and CSS so Google can render the site properly
Disallow: /_next/image
Disallow: /_next/static/
Disallow: /_next/data/

# IMPORTANT: Allow JS and CSS files so Google can execute and render the site
Allow: /_next/static/*.js
Allow: /_next/static/*.css
Allow: /*.js$
Allow: /*.css$

# Specific rules for major search engines
# No crawl-delay needed - site is fast (287ms load time)
User-agent: Googlebot
Allow: /

User-agent: Bingbot
Allow: /

# Host directive (helps with canonical domain)
Host: www.webcoffee.ro

# Sitemaps
# The index at /sitemap.xml already lists the blog, product, category and brand
# sitemaps — no separate blog entry needed.
Sitemap: https://www.webcoffee.ro/sitemap.xml