{ "openapi": "3.0.1", "info": { "title": "Darwin Core Archive Extractor", "description": "Point at ANY GBIF IPT host (ipt.gbif.org, VertNet, iDigBio, Canadensys, INBO...) and extract biodiversity data. Lists the dataset catalog, or streams a Darwin Core Archive into flat occurrence/taxon/event rows. Parses meta.xml authoritatively. Per-IPT runner, not the GBIF central API.", "version": "0.1", "x-build-id": "lX26HlpdtLczN1zju" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/datamule~darwin-core-archive-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-datamule-darwin-core-archive-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/datamule~darwin-core-archive-extractor/runs": { "post": { "operationId": "runs-sync-datamule-darwin-core-archive-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/datamule~darwin-core-archive-extractor/run-sync": { "post": { "operationId": "run-sync-datamule-darwin-core-archive-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "iptHost" ], "properties": { "iptHost": { "title": "IPT host URL", "type": "string", "description": "Base URL of any GBIF IPT (Integrated Publishing Toolkit) installation. You can paste the bare host, the host + path, or a full rss.do/archive.do URL — it is normalized automatically. Examples: https://ipt.gbif.org, https://ipt.gbif.es, https://data.canadensys.net/ipt, https://ipt.inbo.be, https://ipt.idigbio.org" }, "mode": { "title": "Mode", "enum": [ "resources", "archive" ], "type": "string", "description": "resources = list every published dataset in the IPT catalog (cheap; one row per resource with its DwC-A archive URL, EML URL, publisher, guid, last-published date). archive = download one resource's Darwin Core Archive and stream its core file into one flat row per occurrence / taxon / event record.", "default": "resources" }, "resource": { "title": "Resource key (archive mode)", "type": "string", "description": "The IPT resource identifier to download in archive mode (the ?r= value, e.g. 'quercus_parc_test'). Leave empty to auto-select the first published resource (optionally narrowed by the filter below)." }, "resourceFilter": { "title": "Resource filter", "type": "string", "description": "Case-insensitive substring matched against each resource's title and key. In resources mode it filters the catalog; in archive mode it picks the first matching resource to download." }, "maxRecords": { "title": "Max records (archive mode)", "minimum": 1, "maximum": 500000, "type": "integer", "description": "Maximum number of records to extract in archive mode. The archive is streamed, so large datasets are capped without loading everything into memory. Ignored in resources mode.", "default": 1000 }, "publishedOnly": { "title": "Published resources only", "type": "boolean", "description": "In resources mode, skip catalog items that are registered but have no DwC-A archive yet (no download URL).", "default": true }, "keepRawTerms": { "title": "Keep raw Darwin Core term URIs", "type": "boolean", "description": "In archive mode, attach a 'termUris' object mapping each short field name to its full Darwin Core / Dublin Core term URI (e.g. scientificName -> http://rs.tdwg.org/dwc/terms/scientificName).", "default": false } } }, "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 } } } } } } } } } }