# 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.
# use:      how AI systems may consume the content (immediate, reference, or full).

# 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,use=reference
Allow: /

# Training crawlers
User-agent: Amazonbot
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: GPTBot
Disallow: /

User-agent: omgili
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: Claude-Web
Disallow: /

User-agent: cohere-ai
Disallow: /

User-agent: MistralAI-Training
Disallow: /

User-agent: meta-externalagent
Disallow: /

User-agent: GoogleOther
Disallow: /

User-agent: Baiduspider
Disallow: /

User-agent: PetalBot
Disallow: /

User-agent: AwarioSmartBot
User-agent: AwarioRssBot
Disallow: /

User-agent: Google-CloudVertexBot
Disallow: /

User-agent: QualifiedBot
Disallow: /

User-agent: Cotoyogi
Disallow: /

User-agent: ICC-Crawler
Disallow: /

User-agent: atlassian-bot
Disallow: /

User-agent: FishBot
Disallow: /

User-agent: BorderxBot
Disallow: /

User-agent: NavuBot
Disallow: /

User-agent: SemrushBot-SWA
Disallow: /

User-agent: WARDBot
Disallow: /

User-agent: magpie-crawler
Disallow: /

User-agent: KimiBot
Disallow: /

User-agent: CitibotSiteCrawler
Disallow: /

# AI Search crawlers
User-agent: PerplexityBot
Disallow: /

User-agent: YouBot
Disallow: /

User-agent: OAI-SearchBot
Disallow: /

User-agent: Claude-SearchBot
Disallow: /

User-agent: Applebot
Disallow: /

User-agent: Amzn-SearchBot
Disallow: /

User-agent: MistralAI-Index
Disallow: /

User-agent: Kimi-SearchBot
Disallow: /

User-agent: ShapBot
Disallow: /

User-agent: Bravebot
Disallow: /

User-agent: Anomura
Disallow: /

User-agent: Element451Bot
Disallow: /

User-agent: alphalens-bot
Disallow: /

# AI Agents
User-agent: Perplexity-User
Disallow: /

User-agent: FireCrawl
Disallow: /

User-agent: FirecrawlAgent
Disallow: /

User-agent: Claude-User
Disallow: /

User-agent: ChatGPT-User
Disallow: /

User-agent: Google-Agent
Disallow: /

User-agent: Google-GeminiNotebook
User-agent: Google-NotebookLM
Disallow: /

User-agent: MistralAI-User
Disallow: /

User-agent: Kimi-User
Disallow: /

User-agent: Amzn-User
Disallow: /

User-agent: meta-externalfetcher
Disallow: /

User-agent: Retool
Disallow: /

User-agent: Instapaper
Disallow: /

User-agent: ChathiveCrawler
Disallow: /

# END Cloudflare Managed Content

# robots.txt for www.vitacom.ro, b2b.vitacom.ro and export.vitacom.ro. The
# three hosts run on one Magento install, so they share this file. b2b and
# export answer NOINDEX,NOFOLLOW.
#
# Google and every crawler without its own group below follow the one
# "User-agent: *" group. Google obeys only the most specific group that names
# it, so a "User-agent: Googlebot" or "Googlebot-Image" group, even an empty
# one, makes Google skip every rule here. Put Google's rules in this group.
#
# Category URLs with filter, sort, page or SID= parameters are not disallowed
# in this group on purpose. Filtered pages name their canonical URL, and with
# Liquidlab Meta Tags 1.5.0 or later filtered and sorted listings answer
# NOINDEX,FOLLOW. Google has to crawl them to see that and drop the variants
# it has indexed: a Disallow would hide it. Once Search Console's indexed
# count is back near the catalog's size, the filter and sort parameters can
# be disallowed here. Keep p= crawlable.
#
# CSS and JS are not disallowed either: Google renders pages with them.
# Groups contain no blank lines, so parsers that end a group at a blank line
# still see every rule.

User-agent: *
Crawl-delay: 10
# Directories
Disallow: /app/
Disallow: /bin/
Disallow: /dev/
Disallow: /lib/
Disallow: /phpserver/
Disallow: /pub/
Disallow: /setup/
Disallow: /update/
Disallow: /var/
Disallow: /vendor/
Disallow: /admin/
Disallow: /directory/
Disallow: /.well-known/
# Paths (clean URLs)
Disallow: /index.php/
Disallow: /catalog/product_compare/
Disallow: /catalog/category/view/
Disallow: /catalog/product/view/
Disallow: /catalogsearch/
Disallow: /checkout/
Disallow: /control/
Disallow: /contacts/
Disallow: /customer/
Disallow: /customize/
Disallow: /newsletter/
Disallow: /wishlist/
Disallow: /customer/account/
Disallow: /customer/account/login/
Disallow: /sales/order/history
Disallow: /default/algemene-voorwaarden
Disallow: /algemene-voorwaarden
Disallow: /default/privacy-policy-cookie-restriction-mode
Disallow: /privacy-policy-cookie-restriction-mode
# General technical directories and files on a server
Disallow: /cgi-bin/
# Files
Disallow: /composer.json
Disallow: /composer.lock
Disallow: /CONTRIBUTING.md
Disallow: /CONTRIBUTOR_LICENSE_AGREEMENT.html
Disallow: /COPYING.txt
Disallow: /Gruntfile.js
Disallow: /LICENSE.txt
Disallow: /LICENSE_AFL.txt
Disallow: /nginx.conf.sample
Disallow: /package.json
Disallow: /php.ini.sample
Disallow: /RELEASE_NOTES.txt
# Paths (no clean URLs)
Disallow: /*.php$
Disallow: /*.CVS
Disallow: /*.Zip$
Disallow: /*.Svn$
Disallow: /*.Idea$
Disallow: /*.Sql$
Disallow: /*.Tgz$

# Bingbot (VIT-244): public pages allowed, faceted/sorted/search/cart/account URLs blocked, rate-limited.
# Bingbot obeys ONLY this group once it exists (it ignores "User-agent: *"), so every rule it needs is here.
# Path rules come before query rules so first-match and longest-match parsers agree.
User-agent: bingbot
Crawl-delay: 10
Disallow: /catalogsearch/
Disallow: /search/
Disallow: /checkout/
Disallow: /amasty_quote/
Disallow: /customer/
Disallow: /wishlist/
Disallow: /sales/
Disallow: /newsletter/
Disallow: /review/
Disallow: /catalog/product_compare/
Disallow: /catalog/product/view/
Disallow: /catalog/category/view/
Disallow: /stores/store/
Disallow: /index.php/
Disallow: /*?p=*&
Allow: /*?p=
Disallow: /*?

# SEO tools, archives and scrapers: they bring no shoppers, only load.
# Never list a search engine or an AI assistant here: they are how shoppers
# find the store. Yandex, Baidu, Petal and Amazon were taken off this list on
# 2026-10-12 and follow the "User-agent: *" group.
User-agent: CazoodleBot
User-agent: Fasterfox
User-agent: clark-crawler2/Nutch-1.19-SNAPSHOT
User-agent: clark-crawler2
User-agent: SemrushBot-SA
User-agent: serpstatbot
User-agent: MJ12bot
User-agent: SemrushBot
User-agent: ia_archiver
Disallow: /

# Sitemaps
Sitemap: https://www.vitacom.ro/media/sitemap/b2c_ro_sitemap.xml
Sitemap: https://www.vitacom.ro/media/sitemap/b2c_en_sitemap.xml
Sitemap: https://www.vitacom.ro/media/sitemap/b2c_hu_sitemap.xml