# NTT Global Data Centers (NTT DATA) — facility pages + newsroom on services.global.ntt
id: ntt
name: NTT Global Data Centers
domain: services.global.ntt
kind: operator
mode: hybrid
priority: 1
license: "Publicly accessible operator pages; factual data only; © NTT DATA, Inc."
attribution: "NTT Global Data Centers"
homepage: https://services.global.ntt/en-us/services-and-products/global-data-centers/global-locations
notes: >
  Sitecore site, open to plain HTTP. Facility pages live under
  /en-us/services-and-products/global-data-centers/global-locations/<region>/<slug>; slugs ending in "-data-centers"
  are metro indexes. Pages publish the street address, "N MW of critical IT load" and spec blocks; no coordinates.
  No RSS feed; the newsroom (/en-us/newsroom/<slug>) is classified from the English sitemap.
  robots.txt disallows Sitecore system paths and /-/media/ntt/global/documents/ (not crawled).
coverage: { global: true, operators: ["NTT Global Data Centers", "NTT DATA", "NTT Ltd."] }
fetch:
  level: 1
  maxLevel: 4
  rpm: 20
  concurrency: 2
  respectRobots: true
  maxCreditsPerRun: 40
  maxCreditsPerDay: 120   # premium credits per UTC day for this connector (all runs, all workers)
discovery:
  sitemap: ["https://services.global.ntt/en-us/sitemap.xml"]
  include:
    - "/en-us/services-and-products/global-data-centers/global-locations/"
    - "/en-us/newsroom/[a-z0-9-]+$"
  exclude: ["\\?", "/virtual-tour", "sitecore", "/-/media/", "/global-locations/community/"]   # /community/ pages duplicate the emea/apac facility pages (same slugs)
  classify:
    - { pattern: "/global-locations/[a-z-]+/[a-z0-9-]+-data-centers$", group: index, pageType: facility_index, priority: 20 }
    - { pattern: "/global-locations/[a-z-]+/[a-z0-9-]+$", group: facility_pages, pageType: facility_page, priority: 60 }
    - { pattern: "/global-locations/[a-z-]+$", group: index, pageType: facility_index, priority: 10 }
    - { pattern: "/global-locations/?$", group: index, pageType: facility_index, priority: 10 }
    - { pattern: "/en-us/newsroom/[a-z0-9-]+$", group: newsroom, pageType: press_release, priority: 70 }
  maxUrlsPerRun: 2000
schedule:
  facility_pages: weekly
  newsroom: daily
  index: monthly
  sitemap: weekly
extractors:
  facility:
    # selected by URL only (classifyPage() may mislabel deep facility URLs; the URL is authoritative)
    match: ["/global-locations/[a-z-]+/[a-z0-9-]+$"]
    kind: facility
    parser: ntt_facility_v1
defaults:
  operatorName: NTT Global Data Centers
  operatorKind: colocation
  facilityType: colocation
parserVersion: v1