{ "openapi": "3.0.1", "info": { "title": "Data.gov Dataset Catalog Crawler", "description": "Crawl 300K+ US government datasets from Data.gov. Extract titles, organizations, tags, formats, download URLs, API endpoints, temporal and spatial coverage, contacts, and resources. Filter by agency, format, category, and tags.", "version": "1.0", "x-build-id": "1AomDpW024f23zfeq" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/jungle_synthesizer~datagov-dataset-crawler/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-jungle_synthesizer-datagov-dataset-crawler", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/jungle_synthesizer~datagov-dataset-crawler/runs": { "post": { "operationId": "runs-sync-jungle_synthesizer-datagov-dataset-crawler", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/jungle_synthesizer~datagov-dataset-crawler/run-sync": { "post": { "operationId": "run-sync-jungle_synthesizer-datagov-dataset-crawler", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "sp_intended_usage", "sp_improvement_suggestions" ], "properties": { "sp_intended_usage": { "title": "What is the intended usage of this data?", "minLength": 1, "type": "string", "description": "Please describe how you plan to use the data extracted by this crawler." }, "sp_improvement_suggestions": { "title": "How can we improve this crawler for you?", "minLength": 1, "type": "string", "description": "Provide any feedback or suggestions for improvements." }, "sp_contact": { "title": "Contact Email", "minLength": 1, "type": "string", "description": "Provide your email address so we can get in touch with you." }, "searchQuery": { "title": "Search Query", "type": "string", "description": "Full-text search across dataset titles, descriptions, and tags. Leave empty to browse all datasets." }, "organization": { "title": "Organization", "enum": [ "", "department-of-health-and-human-services", "department-of-commerce", "department-of-agriculture", "environmental-protection-agency", "department-of-transportation", "department-of-energy", "department-of-defense", "department-of-the-interior", "department-of-labor", "national-aeronautics-and-space-administration", "department-of-education", "department-of-homeland-security", "department-of-justice", "department-of-housing-and-urban-development", "department-of-the-treasury", "department-of-veterans-affairs", "national-science-foundation", "small-business-administration", "general-services-administration", "census-bureau" ], "type": "string", "description": "Filter by publishing organization (federal agency)." }, "dataFormat": { "title": "Data Format", "enum": [ "", "CSV", "JSON", "XML", "API", "XLS", "PDF", "SHP", "GeoJSON", "KML", "RDF", "HTML" ], "type": "string", "description": "Filter by resource format. Finds datasets containing at least one resource in the selected format." }, "tags": { "title": "Tags", "type": "array", "description": "Filter by dataset tags (e.g., 'health', 'environment'). Datasets must match all specified tags.", "items": { "type": "string" } }, "category": { "title": "Category / Topic", "enum": [ "", "agriculture", "business", "climate", "consumer", "ecosystems", "education", "energy", "finance", "health", "local", "manufacturing", "maritime", "ocean", "public-safety", "science", "weather" ], "type": "string", "description": "Filter by Data.gov topic category." }, "includeResources": { "title": "Include Resource Details", "type": "boolean", "description": "When enabled, extracts individual resource (file/API) details within each dataset including download URLs, formats, and sizes.", "default": true }, "sortBy": { "title": "Sort By", "enum": [ "score desc", "metadata_modified desc", "metadata_created desc", "name asc" ], "type": "string", "description": "Sort results by relevance, most recently modified, or metadata creation date." }, "maxItems": { "title": "Max Items", "type": "integer", "description": "Maximum number of dataset records to return. Set to 0 for unlimited.", "default": 100 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Select proxies. The Data.gov CKAN API is a government service and typically does not require proxies." } } }, "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 } } } } } } } } } }