{ "openapi": "3.0.1", "info": { "title": "USA Data.gov Dataset Scraper", "description": "Search Data.gov's current v4 Catalog API for U.S. government dataset metadata.", "version": "0.2", "x-build-id": "2togUUGspgYJXfZbf" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/muhammadafzal~usa-data-gov-datasets-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-muhammadafzal-usa-data-gov-datasets-scraper", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/muhammadafzal~usa-data-gov-datasets-scraper/runs": { "post": { "operationId": "runs-sync-muhammadafzal-usa-data-gov-datasets-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/muhammadafzal~usa-data-gov-datasets-scraper/run-sync": { "post": { "operationId": "run-sync-muhammadafzal-usa-data-gov-datasets-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "searchQuery": { "title": "Dataset search query", "maxLength": 200, "type": "string", "description": "Use this when you want Data.gov to search dataset titles, descriptions, tags, and publishers. Enter a phrase such as 'climate change' or 'public health'; the default is 'climate'. Leave blank to search the full catalog. This is not a direct dataset URL or a request to download the underlying data file.", "default": "climate" }, "organization": { "title": "Organization slug", "maxLength": 120, "type": "string", "description": "Use this when you want to restrict results to one Data.gov publisher organization. Enter its CKAN organization slug, for example 'epa' or 'department-of-energy'; leave blank for all organizations. This is a catalog filter, not a free-text organization name search.", "default": "" }, "tags": { "title": "Dataset tags", "maxItems": 10, "type": "array", "description": "Use this when results must include one or more Data.gov tags. Enter tag values such as ['api', 'environment']; tags are combined as required filters. Leave empty to keep the search query broad; this is not a list of URLs.", "items": { "type": "string", "maxLength": 80 }, "default": [] }, "maxResults": { "title": "Maximum datasets", "minimum": 1, "maximum": 100, "type": "integer", "description": "Use this when you need to cap the number of dataset records returned. Set an integer from 1 to 100; the default is 25. This controls catalog metadata records, not the number of rows inside each linked resource.", "default": 25 }, "pageSize": { "title": "API page size", "minimum": 1, "maximum": 100, "type": "integer", "description": "Use this when you want to control Data.gov API pagination. Set an integer from 1 to 100; the default is 50. Smaller pages reduce each request payload, while maxResults still controls the total output.", "default": 50 }, "after": { "title": "Pagination cursor", "maxLength": 1000, "type": "string", "description": "Use this when continuing a previous Data.gov v4 search from its OUTPUT nextAfter value. Paste the opaque cursor exactly as returned; leave blank for the first page. This is cursor pagination, not a numeric dataset-resource row offset.", "default": "" }, "sortBy": { "title": "Sort results by", "enum": [ "relevance", "popularity", "distance", "last_harvested_date" ], "type": "string", "description": "Use this when result order matters. Choose relevance, popularity, distance, or last_harvested_date; the default is relevance. This changes ordering only and does not filter datasets.", "default": "relevance" }, "includeResources": { "title": "Include resource links", "type": "boolean", "description": "Use this when you need the downloadable or API resource links published with each dataset. The default is true and returns up to 20 resources per dataset; set false for a lighter metadata-only response. This does not download resource contents.", "default": true }, "maxResourcesPerDataset": { "title": "Resources per dataset", "minimum": 0, "maximum": 50, "type": "integer", "description": "Use this when a dataset has many distributions and you want to cap links per output record. Set an integer from 0 to 50; the default is 20. This only limits returned metadata links and never fetches the linked files.", "default": 20 } } }, "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 } } } } } } } } } }