SPB Git forge
38commits 1branches 0releases
338.7 MBsize
maindefault branch
3 h agolast push
HTML 53.9% TypeScript 44.5% JavaScript 0.6% SQL 0.5%
1.4 KB · 24 lines yaml
Raw Blame History
1id: involta2name: Ark Data Centers (Involta)3domain: www.arkdna.com4kind: operator5mode: hybrid6priority: 27license: "Publicly accessible operator pages; factual data only; © Ark Data Centers"8attribution: "Ark Data Centers (formerly Involta)"9homepage: https://www.arkdna.com/data-centers/10notes: "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."11coverage: { operators: ["Ark Data Centers", "Involta"], countries: ["US"] }12fetch: { level: 1, maxLevel: 2, rpm: 15, concurrency: 2, respectRobots: true, maxCreditsPerRun: 20 }13discovery:14  sitemap: ["https://www.arkdna.com/sitemap_index.xml"]15  include: ["/data-centers/[a-z-]+/[a-z-]+/$", "/news/", "/press-releases?/"]16  exclude: ["\\?", "#", "/data-centers/(data-center-locations|data-center-services)/"]17  classify:18    - { pattern: "/data-centers/[a-z-]+/[a-z-]+/$", group: facility_pages, pageType: facility_page, priority: 60 }19    - { pattern: "/(news|press-releases?)/.", group: newsroom, pageType: press_release, priority: 50 }20schedule: { facility_pages: weekly, newsroom: daily, sitemap: weekly }21extractors:22  facility: { match: ["/data-centers/[a-z-]+/[a-z-]+/$"], kind: facility, parser: arkdna_facility_v1 }23defaults: { operatorName: Ark Data Centers, facilityType: colocation, countryIso2: US }24