{ "openapi": "3.0.1", "info": { "title": "IIIF Presentation Harvester", "description": "Point at ANY IIIF manifest or collection (Wellcome, Bodleian, Harvard, Library of Congress and thousands more) and get flat metadata rows: label, description, metadata pairs, rights, thumbnail, canvas count, plus per-canvas image info. Handles IIIF Presentation API 2.x and 3.x. Pay per manifest.", "version": "0.1", "x-build-id": "1cpXYPdYL3lHNPgV6" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/datamule~iiif-presentation-harvester/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-datamule-iiif-presentation-harvester", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/datamule~iiif-presentation-harvester/runs": { "post": { "operationId": "runs-sync-datamule-iiif-presentation-harvester", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/datamule~iiif-presentation-harvester/run-sync": { "post": { "operationId": "run-sync-datamule-iiif-presentation-harvester", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "properties": { "manifestUrl": { "title": "IIIF manifest or collection URL", "type": "string", "description": "The URL of any IIIF Presentation API manifest OR collection — the metadata standard served by galleries, libraries, archives and museums worldwide. Manifest examples: https://iiif.wellcomecollection.org/presentation/v2/b18035723 (Wellcome), https://iiif.bodleian.ox.ac.uk/iiif/manifest/e32a277e-91e2-4a6d-8ba6-cc4bad230410.json (Bodleian). A collection URL is walked to harvest every manifest it lists. Both IIIF Presentation API 2.x and 3.x are handled automatically. One actor works against thousands of institutions." }, "collectionUrl": { "title": "IIIF collection URL (alias)", "type": "string", "description": "Optional alias for the URL field when pointing at a IIIF collection (a document that lists manifests and/or sub-collections). If both are set, manifestUrl takes precedence. A collection is walked breadth-first over its sub-collections, harvesting each manifest up to the Max records cap." }, "includeImageInfo": { "title": "Include per-canvas image info", "type": "boolean", "description": "When enabled, emit one extra row per canvas (page/image) in each manifest — canvas id, label, width, height, the IIIF Image API service base (used to build tile/region/full-size image URLs) and the direct image URL and format. Canvas rows are bundled with their manifest at no extra charge. Leave off for one metadata row per manifest.", "default": false }, "maxRecords": { "title": "Max records (manifests)", "minimum": 1, "type": "integer", "description": "A GLOBAL cap on the number of manifests to harvest when a collection URL is given (each harvested manifest is one billable event). Default 100. Ignored for a single manifest (which is always one manifest). Per-canvas rows do not count against this cap.", "default": 100 }, "bearer": { "title": "Bearer token", "type": "string", "description": "Optional bearer token for gated IIIF deployments (sent as Authorization: Bearer ***). Not required for public GLAM manifests. Never logged." }, "extraHeaders": { "title": "Extra request headers", "type": "object", "description": "Optional extra HTTP headers as a JSON object, e.g. {\"x-api-key\": \"...\"} for gated servers. Not required for public servers. Header values are never logged." } } }, "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 } } } } } } } } } }