id: google-datacenters
name: Google data center locations
domain: www.google.com
kind: cloud_provider
mode: html
priority: 1
license: "Publicly published operator page (Google data center locations); facts only"
attribution: "Google — google.com/about/datacenters"
homepage: https://www.google.com/about/datacenters/locations/
coverage: { global: true, operators: ["Google"] }
implementation: cloud_regions
fetch:
  level: 1
  maxLevel: 2
  rpm: 10
  concurrency: 1
  respectRobots: true
  maxCreditsPerRun: 0
discovery:
  seeds:
    - { url: "https://www.google.com/about/datacenters/locations/", group: facility_pages, pageType: facility_index }
schedule:
  facility_pages: weekly
extractors:
  sites:
    match: ["/about/datacenters/locations/?$"]
    kind: facility
    parser: cloud_google_datacenters_v1
defaults:
  operatorName: Google
  operatorKind: hyperscaler
  facilityType: hyperscale
  isHyperscale: true
notes: >
  67 Google-owned sites embedded server-side (<div id="data-centers-data">): town/county + state/country,
  inDevelopment flag (→ status announced), sometimes a site-area lat/lng (used as "approximate" only when the
  curated city table has no entry). Per-location detail pages return 404 without a trailing path and are not crawled.