{ "openapi": "3.0.1", "info": { "title": "ESGF Search Harvester — CMIP6 / CORDEX Climate Data", "description": "Point at ANY ESGF federation node (LLNL, DKRZ, IPSL...) and harvest climate-model dataset/file records via the Search API. Facet-filter by project, model, experiment, variable, frequency. Modes: search, facets, wget file listing.", "version": "0.1", "x-build-id": "v9OWA2frRuKHXV8MQ" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/datamule~esgf-search-harvester/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-datamule-esgf-search-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/datamule~esgf-search-harvester/runs": { "post": { "operationId": "runs-sync-datamule-esgf-search-harvester", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/datamule~esgf-search-harvester/run-sync": { "post": { "operationId": "run-sync-datamule-esgf-search-harvester", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "nodes": { "title": "ESGF federation node(s)", "type": "array", "description": "One or more ESGF index nodes to query. Accepts a bare host or a full base URL; the '/esg-search' mount is assumed if omitted. Leave empty to query the default federation trio (LLNL, DKRZ, IPSL).", "default": [], "items": { "type": "string" } }, "mode": { "title": "Mode", "enum": [ "search", "facets", "wget" ], "type": "string", "description": "search = facet-filtered dataset/file query (paginated). facets = the controlled-vocabulary index (facet_counts) for the node. wget = the ESGF download script parsed into one row per file.", "default": "search" }, "type": { "title": "Record type", "enum": [ "Dataset", "File", "Any" ], "type": "string", "description": "Dataset = one row per dataset (aggregate). File = one row per .nc file (carries url + checksum). Any = do not constrain.", "default": "Dataset" }, "project": { "title": "Project", "type": "array", "description": "e.g. CMIP6, CMIP5, CORDEX, obs4MIPs, input4MIPs, PMIP4. Empty = all projects on the node.", "default": [], "items": { "type": "string" } }, "experiment_id": { "title": "Experiment id", "type": "array", "description": "e.g. historical, ssp585, piControl, amip. CMIP experiment identifier(s).", "default": [], "items": { "type": "string" } }, "variable": { "title": "Variable", "type": "array", "description": "CMOR variable short name(s), e.g. tas, pr, psl, tos, siconc.", "default": [], "items": { "type": "string" } }, "frequency": { "title": "Frequency", "type": "array", "description": "e.g. mon, day, 6hr, yr, fx.", "default": [], "items": { "type": "string" } }, "source_id": { "title": "Source id (model)", "type": "array", "description": "Climate model identifier(s), e.g. EC-Earth3, CESM2, GFDL-ESM4, MPI-ESM1-2-HR.", "default": [], "items": { "type": "string" } }, "model": { "title": "Model (CMIP5 legacy)", "type": "array", "description": "Legacy CMIP5 model facet (use source_id for CMIP6).", "default": [], "items": { "type": "string" } }, "institution_id": { "title": "Institution id", "type": "array", "description": "Modelling-centre identifier(s), e.g. NCAR, MPI-M, EC-Earth-Consortium.", "default": [], "items": { "type": "string" } }, "activity_id": { "title": "Activity id", "type": "array", "description": "CMIP6 activity, e.g. CMIP, ScenarioMIP, DCPP, HighResMIP.", "default": [], "items": { "type": "string" } }, "variant_label": { "title": "Variant label", "type": "array", "description": "Ensemble member, e.g. r1i1p1f1.", "default": [], "items": { "type": "string" } }, "grid_label": { "title": "Grid label", "type": "array", "description": "e.g. gn, gr, gr1.", "default": [], "items": { "type": "string" } }, "realm": { "title": "Realm", "type": "array", "description": "e.g. atmos, ocean, land, seaIce.", "default": [], "items": { "type": "string" } }, "table_id": { "title": "Table id", "type": "array", "description": "CMOR table, e.g. Amon, day, Omon, fx.", "default": [], "items": { "type": "string" } }, "data_node": { "title": "Data node", "type": "array", "description": "Constrain to dataset(s) hosted on specific data node(s), e.g. esgf-data1.llnl.gov.", "default": [], "items": { "type": "string" } }, "query": { "title": "Free-text query", "type": "string", "description": "Optional Solr free-text query applied on top of the facet filters.", "default": "" }, "extraFacets": { "title": "Extra facet filters", "type": "object", "description": "Any additional facet constraints as {facet: [values]}, e.g. {\"nominal_resolution\": [\"100 km\"]}. Merged with the dedicated facet inputs above.", "default": {} }, "facetFields": { "title": "Facet fields (facets mode)", "type": "array", "description": "Which facet fields to index when mode=facets.", "default": [ "project", "experiment_id", "source_id", "variable", "frequency" ], "items": { "type": "string" } }, "distrib": { "title": "Distributed (federated) search", "type": "boolean", "description": "If true, the node fans the query out across the whole federation (slower, can partially fail). Default false = query only the target node.", "default": false }, "latestOnly": { "title": "Latest versions only", "type": "boolean", "description": "Restrict to the latest dataset version (latest=true). Recommended.", "default": true }, "replica": { "title": "Replica handling", "enum": [ "exclude", "include", "only" ], "type": "string", "description": "exclude = primary copies only (replica=false). include = both. only = replicas only.", "default": "exclude" }, "maxRecords": { "title": "Max records (total)", "minimum": 0, "type": "integer", "description": "Cap on total records across all nodes. 0 = no cap (harvest to completion — can be very large).", "default": 200 }, "pageSize": { "title": "Page size", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Records per request page (1-1000).", "default": 100 } } }, "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 } } } } } } } } } }