id: wikidata
name: Wikidata
domain: query.wikidata.org
kind: dataset
mode: api
priority: 3
license: "CC0 1.0 (public domain) — Wikidata:Licensing: \"All structured data in the main, property and lexeme namespaces is made available under the Creative Commons CC0 License\""
attribution: "Data: Wikidata (CC0)"
homepage: https://www.wikidata.org/wiki/Wikidata:Licensing
notes: >-
  SPARQL endpoint (GET, Accept: application/sparql-results+json). Items with P31/P279* = Q671224 ("data center";
  NB: Q1063421 is NOT data center). robots.txt of query.wikidata.org disallows /sparql for generic crawlers; WDQS is a
  public query API governed by its own limits (60 s/query, 60 s processing per 60 s per client, 5 parallel, HTTP 429 +
  Retry-After) and the Wikimedia User-Agent policy — respectRobots is deliberately false for this API endpoint.
coverage: { global: true }
fetch:
  level: 1
  maxLevel: 1
  userAgent: bot
  rpm: 10
  concurrency: 1
  respectRobots: false
  timeoutMs: 90000
  maxCreditsPerRun: 0
schedule:
  dataset: weekly
implementation: wikidata
params:
  endpoint: https://query.wikidata.org/sparql
  classQid: Q671224
  pageSize: 2000
  labelLanguages: "en,fr,de,es,nl,it,pt,ja,zh,mul"
parserVersion: wikidata_v1