# 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: /

# END Cloudflare Managed Content

# Crawlers Setup
User-agent: *
Disallow: /index.php/
Disallow: /checkout/
Disallow: /advisieportalbuilder/
Disallow: /stores/store/redirect/
Disallow: /catalogsearch/
Disallow: /catalogsearch/result/

# Directories
Disallow: /app/
Disallow: /bin/
Disallow: /catalog/
Disallow: /customer/
Disallow: /dev/
Disallow: /errors/
Disallow: /lib/
Disallow: /phpserver/
Disallow: /pkginfo/
Disallow: /report/
Disallow: /review/
Disallow: /sendfriend/
Disallow: /setup/
Disallow: /update/
Disallow: /var/
Disallow: /vendor/

# Files
Disallow: /cron.php
Disallow: /cron.sh
Disallow: /error_log
Disallow: /install.php
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

# Do not index pages that are sorted or filtered.
Disallow: /*?*product_list_mode=
Disallow: /*?*product_list_order=
Disallow: /*?*product_list_limit=
Disallow: /*?*product_list_dir=

# Do not index session ID
# Paths (no clean URLs)
Disallow: /*?
Disallow: /*?SID=
Disallow: /*.php$
Disallow: /*?limit=all
Disallow: /*?cPath=*
Disallow: /*&cPath=*
Disallow: /*?osCsid=*
Disallow: /*&osCsid=*
Disallow: /*?products_id=*
Disallow: /*&products_id=*
Disallow: /*?p
Disallow: /*?utm_source
Disallow: /*?pagina
Disallow: /*?site
Disallow: /*?channable
Disallow: /*?ae_
Disallow: /*?adv_

# CVS, SVN directory and dump files
Disallow: /*.CVS
Disallow: /*.Zip$
Disallow: /*.Svn$
Disallow: /*.Idea$
Disallow: /*.Sql$
Disallow: /*.Tgz$
Disallow: /*.bak$

# Parameters
Disallow: /*?*price=*
Disallow: /*&price=*
Disallow: /*?*limit=*
Disallow: /*?*&limit=*
Disallow: /*?*order=*
Disallow: /*&order=*
Disallow: /*?*dir=*
Disallow: /*&dir=*
Disallow: /*___store=*
Disallow: /*___from_store=*
Disallow: /*?*manufacturer=*
Disallow: /*brand=*
Disallow: /*price
Disallow: /*?*color=*
Disallow: /*&color=*
Disallow: /*?links=*
Disallow: /*&links=*
Disallow: /*?gclid=*
Disallow: /*&gclid=*
Disallow: /*?sqr=*
Disallow: /*&sqr=*
Disallow: /*?tax_display=*
Disallow: /*&tax_display=*
Disallow: /*?rating=*
Disallow: /*&rating=*
Disallow: /*?*limit=*
Disallow: /*&limit=*
Disallow: /*?*stock=*
Disallow: /*&stock=*
Disallow: /*?q=*
Disallow: /*?*adv_serie*
Disallow: /*?*adv_kleur*
Disallow: /*?*adv_product_type*
Disallow: /*?*esn_serie*
Disallow: /*?*esn_kleur*
Disallow: /*?*esn_product_type*
Disallow: /*?add-to-cart

User-agent: YoudaoBot
User-agent: sogou spider
User-agent: Baiduspider
User-agent: Baiduspider-video
User-agent: Baiduspider-image
User-agent: Exabot
User-agent: MJ12bot
User-agent: Dotbot
User-agent: Gigabot
User-agent: AhrefsBot
User-agent: BlackWidow
User-agent: Bot\ [EMAIL="craftbot@yahoo.com"]mailto:craftbot@yahoo.com[/EMAIL]
User-agent: ChinaClaw
User-agent: Custo
User-agent: DISCo
User-agent: ia_archiver
User-agent: Download\ Demon
User-agent: eCatch
User-agent: EirGrabber
User-agent: EmailSiphon
User-agent: EmailWolf
User-agent: Express\ WebPictures
User-agent: ExtractorPro
User-agent: EyeNetIE
User-agent: FlashGet
User-agent: GetRight
User-agent: GetWeb!
User-agent: Go!Zilla
User-agent: Go-Ahead-Got-It
User-agent: GrabNet
User-agent: Grafula
User-agent: HMView
User-agent: HTTrack
User-agent: Image\ Stripper
User-agent: Image\ Sucker
User-agent: Indy\ Library
User-agent: InterGET
User-agent: Internet\ Ninja
User-agent: JetCar
User-agent: JOC\ Web\ Spider
User-agent: larbin
User-agent: LeechFTP
User-agent: Mass\ Downloader
User-agent: MIDown\ tool
User-agent: Mister\ PiX
User-agent: Navroad
User-agent: NearSite
User-agent: NetAnts
User-agent: Slurp
User-agent: NetSpider
User-agent: Net\ Vampire
User-agent: NetZIP
User-agent: Octopus
User-agent: Offline\ Explorer
User-agent: Offline\ Navigator
User-agent: PageGrabber
User-agent: Papa\ Foto
User-agent: pavuk
User-agent: pcBrowser
User-agent: RealDownload
User-agent: ReGet
User-agent: SiteSnagger
User-agent: SmartDownload
User-agent: SuperBot
User-agent: SuperHTTP
User-agent: Surfbot
User-agent: tAkeOut
User-agent: Teleport\ Pro
User-agent: VoidEYE
User-agent: Web\ Image\ Collector
User-agent: Web\ Sucker
User-agent: WebAuto
User-agent: WebCopier
User-agent: WebFetch
User-agent: WebGo\ IS
User-agent: WebLeacher
User-agent: WebReaper
User-agent: WebSauger
User-agent: Website\ eXtractor
User-agent: Website\ Quester
User-agent: WebStripper
User-agent: WebWhacker
User-agent: WebZIP
User-agent: Wget
User-agent: Widow
User-agent: WWWOFFLE
User-agent: Xaldon\ WebSpider
User-agent: Zeus
User-agent: NaverBot
User-agent: Yeti
User-agent: moget
User-agent: ichiro
User-agent: Yandex
User-agent: ShopWiki
User-agent: duggmirror
User-agent: Vagabondo
User-agent: YisouSpider
User-agent: EasouSpider
User-agent: Indy Library
User-agent: SISTRIX Crawler
User-agent: YYSpider
User-agent: web-archive-net.com
User-agent: teleport
User-agent: teleportPro
User-agent: publiclibraryarchive.org
User-agent: CherryPicker
User-agent: EmailCollector
User-agent: Webbandit
User-agent: Telesoft
User-agent: WebZip/4.0
Disallow: /

# Allow AI search and agent use
User-agent: OAI-SearchBot
User-agent: ChatGPT-User
User-agent: PerplexityBot
User-agent: AndiBot
User-agent: PhindBot
User-agent: YouBot
Allow: /

# Disallow AI training data collection
User-agent: GPTBot
User-agent: CCBot
User-agent: Google-Extended
Disallow: /

User-agent: Googlebot-Image
Disallow: /
Allow: /media/
Allow: /skin/
Sitemap: https://glampere.nl/sitemap_glampere_nl/sitemap.xml