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: airtrunk2name: AirTrunk3domain: airtrunk.com4kind: operator5mode: hybrid6priority: 17license: "Publicly accessible operator pages; factual data only; © AirTrunk Operating Pty Ltd"8attribution: "AirTrunk"9homepage: https://airtrunk.com/locations/10notes: "Facility pages /location/<code>-<city>/ publish key features (total capacity MW, site ha, built-up m², design PUE). Country resolved from the city named on the page (deterministic metro lookup)."11coverage: { operators: ["AirTrunk"], countries: ["AU", "SG", "HK", "JP", "MY", "IN"] }12fetch: { level: 1, maxLevel: 2, rpm: 15, concurrency: 2, respectRobots: true, maxCreditsPerRun: 20 }13discovery:14  sitemap: ["https://airtrunk.com/location-sitemap.xml", "https://airtrunk.com/post-sitemap.xml"]15  include: ["/location/[a-z]{3}\\d-[a-z-]+/$", "airtrunk\\.com/airtrunk-[a-z0-9-]+/$"]16  exclude: ["\\?", "#", "/customer-notification/", "airtrunk\\.com/(zh-hans|zh|ja|ko)/"]17  classify:18    - { pattern: "/location/[a-z]{3}\\d-[a-z-]+/$", group: facility_pages, pageType: facility_page, priority: 60 }19    - { pattern: "airtrunk\\.com/airtrunk-[a-z0-9-]+/$", group: newsroom, pageType: press_release, priority: 50 }20schedule: { facility_pages: weekly, newsroom: daily, sitemap: weekly }21extractors:22  facility: { match: ["/location/[a-z]{3}\\d-[a-z-]+/$"], kind: facility, parser: airtrunk_facility_v1 }23defaults: { operatorName: AirTrunk, facilityType: hyperscale, isHyperscale: true }24