{ "openapi": "3.0.1", "info": { "title": "Wikibase Entity Extractor", "description": "Point at ANY Wikibase instance (Wikidata, MaRDI, self-hosted) and extract items & properties via the modern REST v1 API: full typed entities, per-statement rows, or labels + descriptions. One runner for every install. Pay per entity.", "version": "0.1", "x-build-id": "tXGgOMb4bPOP6xhru" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/datamule~wikibase-entity-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-datamule-wikibase-entity-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/datamule~wikibase-entity-extractor/runs": { "post": { "operationId": "runs-sync-datamule-wikibase-entity-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/datamule~wikibase-entity-extractor/run-sync": { "post": { "operationId": "run-sync-datamule-wikibase-entity-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } } }, "components": { "schemas": { "inputSchema": { "type": "object", "required": [ "entityIds" ], "properties": { "instanceUrls": { "title": "Wikibase instance URLs", "type": "array", "description": "One or more Wikibase base URLs to query, e.g. https://www.wikidata.org (the central hub), https://portal.mardi4nfdi.de (MaRDI, a self-hosted math knowledge graph), https://commons.wikimedia.org, or any self-hosted Wikibase + MediaWiki install. The actor appends the REST v1 path (/w/rest.php/wikibase/v1/…) itself — give the site root. Every bare entity ID is fetched from each instance listed here. NOT required if every entityIds value is already a full URL. Note: the *.wikibase.cloud hosted fleet bot-gates the REST path and will be skipped with a warning.", "items": { "type": "string" } }, "entityIds": { "title": "Entity IDs", "type": "array", "description": "The Wikibase entities to fetch: items (Q…) and/or properties (P…), e.g. Q42, P31. Each value may instead be a full URL — a REST URL (https://www.wikidata.org/w/rest.php/wikibase/v1/entities/items/Q42) or a human entity page (https://www.wikidata.org/wiki/Q42) — from which the instance and ID are parsed (then instanceUrls is optional for that value). Q… → item, P… → property.", "items": { "type": "string" } }, "mode": { "title": "Mode", "enum": [ "entity", "statements", "labels" ], "type": "string", "description": "What to extract per entity. entity = the full typed entity as one flat row (labels, descriptions, aliases, a statements summary, sitelink count). statements = one row per statement (property, rank, value type + content, qualifiers, references) — flattens the knowledge graph's claims into a table. labels = only the lightweight labels + descriptions sub-resources, one row per entity (cheapest way to translate/label thousands of IDs).", "default": "entity" }, "languages": { "title": "Language filter", "type": "array", "description": "Optionally restrict labels, descriptions and aliases to these language codes (e.g. en, de, fr). Leave empty to return every language the entity has. Applies to entity and labels modes.", "items": { "type": "string" } }, "maxEntities": { "title": "Max entities", "minimum": 1, "type": "integer", "description": "Maximum number of entities to process across all instances. Each entity successfully returned is one billable event. Default 1000.", "default": 1000 }, "bearer": { "title": "Bearer token (optional)", "type": "string", "description": "Optional bearer token for a private / access-gated Wikibase. Sent as Authorization: Bearer *** — NOT required for public instances (Wikidata, MaRDI, Commons) — leave empty. Never logged." }, "extraHeaders": { "title": "Extra request headers", "type": "object", "description": "Optional extra HTTP headers to send with every request, as a JSON object, e.g. {\"x-api-key\": \"...\"} for an instance behind an API gateway. Leave empty for public instances." } } }, "runsResponseSchema": { "type": "object", "properties": { "data": { "type": "object", "properties": { "id": { "type": "string" }, "actId": { "type": "string" }, "userId": { "type": "string" }, "startedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "finishedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "status": { "type": "string", "example": "READY" }, "meta": { "type": "object", "properties": { "origin": { "type": "string", "example": "API" }, "userAgent": { "type": "string" } } }, "stats": { "type": "object", "properties": { "inputBodyLen": { "type": "integer", "example": 2000 }, "rebootCount": { "type": "integer", "example": 0 }, "restartCount": { "type": "integer", "example": 0 }, "resurrectCount": { "type": "integer", "example": 0 }, "computeUnits": { "type": "integer", "example": 0 } } }, "options": { "type": "object", "properties": { "build": { "type": "string", "example": "latest" }, "timeoutSecs": { "type": "integer", "example": 300 }, "memoryMbytes": { "type": "integer", "example": 1024 }, "diskMbytes": { "type": "integer", "example": 2048 } } }, "buildId": { "type": "string" }, "defaultKeyValueStoreId": { "type": "string" }, "defaultDatasetId": { "type": "string" }, "defaultRequestQueueId": { "type": "string" }, "buildNumber": { "type": "string", "example": "1.0.0" }, "containerUrl": { "type": "string" }, "usage": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "integer", "example": 1 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } }, "usageTotalUsd": { "type": "number", "example": 0.00005 }, "usageUsd": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "number", "example": 0.00005 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } } } } } } } } }