{ "openapi": "3.0.1", "info": { "title": "Kaggle Datasets Scraper", "description": "Search the public Kaggle dataset catalogue with one phrase. Save source-linked metadata for matching datasets, with optional full descriptions and version history.", "version": "0.0", "x-build-id": "A5UPG6Lteq0sMVDA8" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/maximedupre~kaggle-datasets/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-maximedupre-kaggle-datasets", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/maximedupre~kaggle-datasets/runs": { "post": { "operationId": "runs-sync-maximedupre-kaggle-datasets", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/maximedupre~kaggle-datasets/run-sync": { "post": { "operationId": "run-sync-maximedupre-kaggle-datasets", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "searchQuery" ], "properties": { "searchQuery": { "title": "Search phrase", "pattern": ".*\\S.*", "type": "string", "description": "Enter one phrase to find matching public Kaggle datasets." }, "sortBy": { "title": "Sort matching datasets by", "enum": [ "relevance", "popularity", "activity", "recency" ], "type": "string", "description": "Choose how to order matching Kaggle datasets." }, "fileType": { "title": "File format", "enum": [ "csv", "json", "sql" ], "type": "string", "description": "Keep datasets with one Kaggle file format. Leave this empty to include every format." }, "license": { "title": "License", "enum": [ "cc0", "cc-by", "cc-by-sa", "other" ], "type": "string", "description": "Keep datasets in one Kaggle license group. Leave this empty to include every license." }, "categoryIds": { "title": "Kaggle topic tag IDs", "type": "array", "description": "Add one or more Kaggle topic tag IDs to narrow the search. Leave this list empty to include every topic.", "items": { "type": "string", "pattern": "^[0-9]+$" } }, "minSize": { "title": "Minimum dataset size (bytes)", "minimum": 0, "type": "integer", "description": "Return only datasets at least this large. Leave this empty to use no minimum size." }, "maxSize": { "title": "Maximum dataset size (bytes)", "minimum": 0, "type": "integer", "description": "Return only datasets no larger than this size. Leave this empty to use no maximum size." }, "minDownloadCount": { "title": "Minimum download count", "minimum": 0, "type": "integer", "description": "After Kaggle finds matches, keep only datasets with at least this many downloads. Leave this empty to allow any count." }, "maxItems": { "title": "Maximum datasets to return", "minimum": 1, "type": "integer", "description": "Set how many matching datasets to return. Leave this empty to return all available results until the source is exhausted." }, "includeDetails": { "title": "Include full descriptions and version history", "type": "boolean", "description": "Add each dataset's full description and version history.", "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 } } } } } } } } } }