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%
1.3 KB · 24 lines yaml
Raw Blame History
1id: kaodata2name: Kao Data3domain: www.kaodata.com4kind: operator5mode: hybrid6priority: 27license: "Publicly accessible operator pages; factual data only; © Kao Data"8attribution: "Kao Data"9homepage: https://www.kaodata.com/locations/10notes: "Campus pages /locations/<campus>/ publish the campus address, full-build IT load, acreage and a list of buildings 'KLON-01 (8.8MW Operational)' → campus record + one record per building with its own MW and lifecycle status. Cookie-consent scripts trip the blocked heuristic → maxLevel 2."11coverage: { operators: ["Kao Data"], countries: ["GB"] }12fetch: { level: 1, maxLevel: 2, rpm: 15, concurrency: 2, respectRobots: true, maxCreditsPerRun: 20 }13discovery:14  sitemap: ["https://kaodata.com/wp-sitemap-posts-page-1.xml", "https://kaodata.com/wp-sitemap-posts-news-1.xml"]15  include: ["/locations/[a-z-]+/$", "/news/."]16  exclude: ["\\?", "#"]17  classify:18    - { pattern: "/locations/[a-z-]+/$", group: facility_pages, pageType: facility_page, priority: 60 }19    - { pattern: "/news/.", group: newsroom, pageType: press_release, priority: 50 }20schedule: { facility_pages: weekly, newsroom: daily, sitemap: weekly }21extractors:22  facility: { match: ["/locations/[a-z-]+/$"], kind: facility, parser: kaodata_facility_v1 }23defaults: { operatorName: Kao Data, facilityType: wholesale, countryIso2: GB }24