id: ovhcloud
name: OVHcloud
domain: www.ovhcloud.com
kind: operator
mode: hybrid
priority: 1
license: "Publicly accessible operator pages; factual data only; © OVHcloud"
attribution: "OVHcloud"
homepage: https://www.ovhcloud.com/en/datacenter/
notes: "Index page embeds a `datacenters` JSON map (city, country, lat/lng per datacenter location) → one record per location (geo precision approximate). Only depth-6 city pages (continent/country/region/city) are parsed for name/description/region; depth-5 pages are ambiguous (region vs city) and are skipped. OVHcloud does not publish per-site MW."
coverage: { operators: ["OVHcloud"], countries: ["FR", "CA", "US", "DE", "GB", "PL", "AU", "SG", "IN", "IT", "ES", "MA"] }
fetch: { level: 1, maxLevel: 2, rpm: 15, concurrency: 2, respectRobots: true, maxCreditsPerRun: 20, maxBytes: 6000000 }
discovery:
  sitemap: ["https://www.ovhcloud.com/en/www.ovhcloud.com_en_sitemap.xml"]
  seeds: [{ url: "/en/datacenter/", group: facility_index, pageType: facility_index }]
  include: ["/en/datacenter/"]
  exclude: ["\\?", "#"]
  classify:
    - { pattern: "/en/datacenter/$", group: facility_index, pageType: facility_index, priority: 90 }
    - { pattern: "/en/datacenter/[a-z-]+/[a-z-]+/[a-z-]+(/[a-z-]+)?/$", group: facility_pages, pageType: facility_page, priority: 60 }
schedule: { facility_index: weekly, facility_pages: monthly, sitemap: weekly }
extractors:
  locations: { match: ["/en/datacenter/$"], kind: facility, parser: ovhcloud_locations_v1 }
  facility: { match: ["/en/datacenter/[a-z-]+/[a-z-]+/[a-z-]+"], kind: facility, parser: ovhcloud_facility_v1 }
defaults: { operatorName: OVHcloud, facilityType: hyperscale, isHyperscale: true }