id: coltdcs
name: Colt Data Centre Services
domain: www.coltdatacentres.net
kind: operator
mode: hybrid
priority: 1
license: "Publicly accessible operator pages; factual data only; © Colt Data Centre Services"
attribution: "Colt DCS"
homepage: https://www.coltdatacentres.net/en-GB/our-locations
notes: "Site pages /en-GB/our-locations/data-centre-locations-<region>/<slug> carry animated counters as data-value attributes (MW of IT power, ㎡, Colt tier). Development sites (Frankfurt 3, London 4…) are recorded as pipeline with planned MW. JSON-LD address is the London HQ and is ignored."
coverage: { operators: ["Colt DCS"], countries: ["GB", "DE", "FR", "NL", "JP", "IN"] }
fetch: { level: 1, maxLevel: 2, rpm: 15, concurrency: 2, respectRobots: true, maxCreditsPerRun: 20 }
discovery:
  sitemap: ["https://www.coltdatacentres.net/en-GB/sitemap.xml"]
  include: ["/en-GB/our-locations/data-centre-locations-[a-z]+/[a-z0-9-]+$", "/en-GB/developments/[a-z-]+/[a-z0-9-]+$", "/en-GB/media-room/press-releases/"]
  exclude: ["\\?", "#", "/(health-and-safety|security|sustainability|construction-timeline|receipt[a-z-]*|get-a-quote|see-all)$"]
  classify:
    - { pattern: "/en-GB/(our-locations|developments)/[a-z-]+/[a-z0-9-]+$", group: facility_pages, pageType: facility_page, priority: 60 }
    - { pattern: "/press-releases/.", group: newsroom, pageType: press_release, priority: 50 }
schedule: { facility_pages: weekly, newsroom: daily, sitemap: weekly }
extractors:
  facility: { match: ["/en-GB/(our-locations|developments)/[a-z-]+/[a-z0-9-]+$"], kind: facility, parser: coltdcs_facility_v1 }
defaults: { operatorName: Colt DCS, facilityType: wholesale }