# HKTVmall robots.txt
# Last reviewed: 2026-06-04
# Note: malicious bots ignore robots.txt. This file declares intent.
#       Use WAF / rate limiting for actual enforcement.

Sitemap: https://www.hktvmall.com/sitemap.xml

# --------------------------------------------------
# Welcome crawlers: AI training, AI search, web search
# Same path restrictions as everyone else.
# Rules omit the trailing slash so each path does prefix
# matching: e.g. "/cart" blocks /cart, /cart/, /cart/items,
# and any other URL beginning with "/cart". Tradeoff:
# unrelated URLs like /cartoon or /avenuestore would also
# be blocked if they ever existed.
# --------------------------------------------------
User-agent: GPTBot
User-agent: ChatGPT-User
User-agent: OAI-SearchBot
User-agent: anthropic-ai
User-agent: ClaudeBot
User-agent: Claude-SearchBot
User-agent: Google-Extended
User-agent: Googlebot
User-agent: Applebot-Extended
User-agent: Bingbot
User-agent: PerplexityBot
User-agent: Perplexity-User
User-agent: MetaExternalAgent
User-agent: FacebookBot
User-agent: CCBot
User-agent: cohere-ai
User-agent: Amazonbot
User-agent: Diffbot
User-agent: Bytespider
User-agent: ImagesiftBot
User-agent: Omgilibot
User-agent: YouBot
Disallow: /hktv/zh/cart
Disallow: /hktv/zh/checkout
Disallow: /hktv/zh/checkout/single
Disallow: /hktv/zh/wishlist
Disallow: /hktv/zh/avenue
Disallow: /hktv/zh/citibank
Disallow: /hktv/en/cart
Disallow: /hktv/en/checkout
Disallow: /hktv/en/checkout/single
Disallow: /hktv/en/wishlist
Disallow: /hktv/en/avenue
Disallow: /hktv/en/citibank

# --------------------------------------------------
# Default: all other crawlers
# --------------------------------------------------
User-agent: *
Disallow: /hktv/zh/cart
Disallow: /hktv/zh/checkout
Disallow: /hktv/zh/checkout/single
Disallow: /hktv/zh/wishlist
Disallow: /hktv/zh/avenue
Disallow: /hktv/zh/citibank
Disallow: /hktv/en/cart
Disallow: /hktv/en/checkout
Disallow: /hktv/en/checkout/single
Disallow: /hktv/en/wishlist
Disallow: /hktv/en/avenue
Disallow: /hktv/en/citibank

# --------------------------------------------------
# Blocked: search engines we don't want indexing us
# (verify these business decisions periodically)
# Note: RFC 9309 requires exact product-token match,
# so each Yandex crawler is listed explicitly.
# --------------------------------------------------
User-agent: Baiduspider
User-agent: YandexBot
User-agent: YandexImages
User-agent: YandexMedia
User-agent: YandexNews
User-agent: YandexFavicons
User-agent: NaverBot
User-agent: PetalBot
User-agent: SeznamBot
Disallow: /

# --------------------------------------------------
# Blocked: SEO/marketing scrapers (high volume, low value to us)
# --------------------------------------------------
User-agent: MJ12bot
User-agent: SemrushBot
User-agent: DotBot
User-agent: BLEXBot
User-agent: DataForSeoBot
User-agent: MauiBot
User-agent: SerpstatBot
User-agent: rogerbot
User-agent: linkdexbot
Disallow: /

# --------------------------------------------------
# Blocked: site rippers / offline downloaders
# --------------------------------------------------
User-agent: HTTrack
User-agent: Wget
User-agent: WebCopier
User-agent: Webzip
User-agent: WebStripper
User-agent: WebSauger
User-agent: WebReaper
User-agent: Offline Explorer
User-agent: Teleport
User-agent: SiteSnagger
User-agent: Xenu
User-agent: GetRight
User-agent: NetAnts
Disallow: /

# --------------------------------------------------
# Blocked: email / contact harvesters
# --------------------------------------------------
User-agent: EmailCollector
User-agent: EmailSiphon
User-agent: EmailWolf
User-agent: ExtractorPro
User-agent: CherryPicker
User-agent: NICErsPRO
Disallow: /

# --------------------------------------------------
# Blocked: misc nuisance / abusive
# --------------------------------------------------
User-agent: CazoodleBot
User-agent: Heritrix
User-agent: Nutch
User-agent: psbot
User-agent: BackDoorBot
User-agent: BotALot
User-agent: BuiltBotTough
User-agent: BunnySlippers
User-agent: CopyRightCheck
User-agent: DittoSpyder
User-agent: LinkScan
User-agent: LinkWalker
User-agent: MIIxpc
User-agent: ProPowerBot
User-agent: RepoMonkey
User-agent: SpankBot
User-agent: Zeus
Disallow: /

# --------------------------------------------------
# Blocked: legacy bots (carried over from original file)
# --------------------------------------------------
User-agent: AboutUsBot
User-agent: Amfibibot
User-agent: antibot
User-agent: appie
User-agent: Aqua_Products
User-agent: asterias
User-agent: b2w/0.1
User-agent: BackDoorBot/1.0
User-agent: BecomeBot
User-agent: BlowFish
User-agent: BlowFish/1.0
User-agent: Bookmark search tool
User-agent: Browsershots
User-agent: BruinBot
User-agent: btbot
User-agent: Bullseye
User-agent: Bullseye/1.0
User-agent: cfetch
User-agent: CheeseBot
User-agent: CherryPickerElite/1.0
User-agent: CherryPickerSE/1.0
User-agent: CoolBot
User-agent: cosmos
User-agent: Cowbot
User-agent: Crescent
User-agent: Crescent Internet ToolPak HTTP OLE Control v.1.0
User-agent: CydralSpider
User-agent: dcbspider
User-agent: Download Ninja
User-agent: Dumbot
User-agent: EroCrawler
User-agent: Euripbot
User-agent: Exabot
User-agent: FairAd Client
User-agent: FAST Enterprise Crawler
User-agent: Fetch
User-agent: FindLinks
User-agent: Flaming AttackBot
User-agent: Foobot
User-agent: Gaisbot
User-agent: Generic
User-agent: Georgios
User-agent: GetRight/4.2
User-agent: Gigabot
User-agent: GoForIt
User-agent: gonzo
User-agent: gridBOT
User-agent: grub
User-agent: grub-client
User-agent: Harvest
User-agent: Harvest/1.5
User-agent: Haste
User-agent: HenryTheMiragoRobot
User-agent: hloader
User-agent: HooWWWer
User-agent: httplib
User-agent: humanlinks
User-agent: iCCrawler
User-agent: IconSurf
User-agent: InfoNaviRobot
User-agent: IRLbot
User-agent: Iron33
User-agent: Iron33/1.0.2
User-agent: IXE Crawler
User-agent: JemmaTheTourist
User-agent: JennyBot
User-agent: Jetbot
User-agent: Jetbot/1.0
User-agent: Kenjin Spider
User-agent: Keyword Density
User-agent: Keyword Density/0.9
User-agent: KFSW-Bot
User-agent: KnowItAll
User-agent: Lachesis
User-agent: larbin
User-agent: LexiBot
User-agent: libWeb/clsHTTP
User-agent: libwww
User-agent: LinkextractorPro
User-agent: linko
User-agent: LinkScan/8.1a Unix
User-agent: LNSpiderguy
User-agent: LocalcomBot
User-agent: looksmart
User-agent: lwp-trivial
User-agent: lwp-trivial/1.34
User-agent: Mata Hari
User-agent: MentorMate Spider
User-agent: Microsoft URL Control
User-agent: Microsoft URL Control - 5.01.4511
User-agent: Microsoft URL Control - 6.00.8169
User-agent: MIIxpc/4.2
User-agent: mirago
User-agent: Mister PiX
User-agent: MMCrawler
User-agent: moget
User-agent: moget*
User-agent: moget/2.1
User-agent: Molbsy
User-agent: Moni
User-agent: Mozilla/4.0 (compatible; BullsEye; Windows 95)
User-agent: Mozilla/4.0 (compatible; Netcraft Web Server Survey)
User-agent: MSIECrawler
User-agent: Muscat Ferret
User-agent: MyEngines-Bot
User-agent: Net Attache
User-agent: NetMechanic
User-agent: NetResearchServer
User-agent: NimbleCrawler
User-agent: NPBot
User-agent: NPT
User-agent: ObjectsSearch
User-agent: Openbot
User-agent: Openfind
User-agent: Openfind data gathere
User-agent: Oracle Ultra Search
User-agent: penthesilea*
User-agent: PerMan
User-agent: PhpDig*
User-agent: ProPowerBot/2.14
User-agent: ProWebWalker
User-agent: Python-urllib
User-agent: QuepasaCreep
User-agent: QueryN Metasearch
User-agent: Radiation Retriever
User-agent: Radiation Retriever 1.1
User-agent: RepoMonkey Bait & Tackle/v1.01
User-agent: RepoMonkey*
User-agent: RMA
User-agent: RPT-HTTPClient
User-agent: SBIder
User-agent: searchpreview
User-agent: Searchspider
User-agent: Shim-Crawler
User-agent: sitecheck.internetseer.com
User-agent: Slurp
User-agent: sna
User-agent: sohu-search
User-agent: spanner
User-agent: Speedy
User-agent: Spider_ Monkey
User-agent: SpiderJack
User-agent: Spinne
User-agent: stalker
User-agent: Steeler
User-agent: SuperGet
User-agent: suzuran
User-agent: Szukacz
User-agent: Szukacz/1.4
User-agent: TAMU_CS_IRL_CRAWLER
User-agent: Telesoft
User-agent: The Intraformant
User-agent: TheNomad
User-agent: thesubot
User-agent: thumbshots-de-bot
User-agent: toCrawl/UrlDispatcher
User-agent: True_Robot
User-agent: True_Robot/1.0
User-agent: turingos
User-agent: TutorGig
User-agent: twiceler
User-agent: Ultraseek
User-agent: URL Control
User-agent: URL_Spider_Pro
User-agent: URLy Warning
User-agent: USyd-NLP-Spider
User-agent: VCI
User-agent: VCI WebViewer VCI WebViewer Win32
User-agent: vilainrobot
User-agent: VIREL
User-agent: vscooter
User-agent: VSE/1.0
User-agent: Web Image Collector
User-agent: WebAuto
User-agent: WebBandit
User-agent: WebBandit/3.50
User-agent: WebCapture
User-agent: WebEnhancer
User-agent: WebmasterWorldForumBot
User-agent: Website Quester
User-agent: Webster Pro
User-agent: Webwhacker
User-agent: Wget/1.5.3
User-agent: Wget/1.6
User-agent: WWW-Collector-E
User-agent: Xenu's
User-agent: Xenu's Link Sleuth 1.1c
User-agent: Yahoo-MMAudVid
User-agent: Yahoo-MMCrawler
User-agent: Zao
User-agent: Zeus 32297 Webster Pro V2.9 Win32
User-agent: Zeus Link Scout
User-agent: ZipppBo
Disallow: /