id: involta
name: Ark Data Centers (Involta)
domain: www.arkdna.com
kind: operator
mode: hybrid
priority: 2
license: "Publicly accessible operator pages; factual data only; © Ark Data Centers"
attribution: "Ark Data Centers (formerly Involta)"
homepage: https://www.arkdna.com/data-centers/
notes: "Involta rebranded as Ark Data Centers (arkdna.com; involta.com redirects). Metro pages /data-centers/<state>/<city>/ describe 1–2 facilities per metro with total square feet, Tier and certifications; recorded as one metro-level record."
coverage: { operators: ["Ark Data Centers", "Involta"], countries: ["US"] }
fetch: { level: 1, maxLevel: 2, rpm: 15, concurrency: 2, respectRobots: true, maxCreditsPerRun: 20 }
discovery:
  sitemap: ["https://www.arkdna.com/sitemap_index.xml"]
  include: ["/data-centers/[a-z-]+/[a-z-]+/$", "/news/", "/press-releases?/"]
  exclude: ["\\?", "#", "/data-centers/(data-center-locations|data-center-services)/"]
  classify:
    - { pattern: "/data-centers/[a-z-]+/[a-z-]+/$", group: facility_pages, pageType: facility_page, priority: 60 }
    - { pattern: "/(news|press-releases?)/.", group: newsroom, pageType: press_release, priority: 50 }
schedule: { facility_pages: weekly, newsroom: daily, sitemap: weekly }
extractors:
  facility: { match: ["/data-centers/[a-z-]+/[a-z-]+/$"], kind: facility, parser: arkdna_facility_v1 }
defaults: { operatorName: Ark Data Centers, facilityType: colocation, countryIso2: US }