{ "openapi": "3.0.1", "info": { "title": "Kaggle Datasets Scraper", "description": "Scrapes Kaggle dataset listings by search term, tag, file type, license, or size. Returns one flat row per dataset with title, URL, size, votes, and optional full description and version history.", "version": "0.1", "x-build-id": "QAF2vNeJST6DO4GLf" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/parseforge~kaggle-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-parseforge-kaggle-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/parseforge~kaggle-scraper/runs": { "post": { "operationId": "runs-sync-parseforge-kaggle-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/parseforge~kaggle-scraper/run-sync": { "post": { "operationId": "run-sync-parseforge-kaggle-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "search": { "title": "Search term for datasets", "type": "string", "description": "Free-text query against dataset titles, descriptions, and tags. Leave blank to browse without a keyword (use sortBy / fileType to control discovery)." }, "maxItems": { "title": "Maximum datasets", "minimum": 1, "maximum": 1000000, "type": "integer", "description": "How many datasets to collect per run." }, "sortBy": { "title": "Sort by", "enum": [ "hottest", "votes", "updated", "active", "published" ], "type": "string", "description": "Order results by Kaggle's built-in sort orders.", "default": "hottest" }, "fileType": { "title": "File type", "enum": [ "all", "csv", "json", "sqlite", "bigQuery" ], "type": "string", "description": "Restrict results to datasets containing the chosen file format. 'all' returns every format.", "default": "all" }, "license": { "title": "License", "enum": [ "all", "cc", "gpl", "odb", "other" ], "type": "string", "description": "Restrict results to datasets shared under the chosen license. 'all' returns every license.", "default": "all" }, "tag": { "title": "Tag", "type": "string", "description": "Filter by a Kaggle tag slug (for example: 'classification', 'finance', 'computer vision', 'nlp', 'health'). Leave blank for no tag filter. See https://www.kaggle.com/datasets for valid tag slugs." }, "minSize": { "title": "Min size (bytes)", "minimum": 0, "type": "integer", "description": "Lower bound on the dataset's total uncompressed size in bytes." }, "maxSize": { "title": "Max size (bytes)", "minimum": 0, "type": "integer", "description": "Upper bound on the dataset's total uncompressed size in bytes." }, "includeDescription": { "title": "Include full description", "type": "boolean", "description": "Fetch the dataset detail endpoint for each record to populate description, tags, and versions. When false, those fields stay null and the run is faster.", "default": true } } }, "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 } } } } } } } } } }