{ "openapi": "3.0.1", "info": { "title": "Scraped Dataset QA Preflight", "description": "A quick QA pass for scraper output before client handoff, CRM import, or scheduled pipeline use. Checks sampled rows for field gaps, duplicates, type shifts, and sensitive-pattern counts.", "version": "0.1", "x-build-id": "Te0WsDz4YvZeQYW5l" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/checksmithcats~scraped-dataset-qa-preflight/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-checksmithcats-scraped-dataset-qa-preflight", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/checksmithcats~scraped-dataset-qa-preflight/runs": { "post": { "operationId": "runs-sync-checksmithcats-scraped-dataset-qa-preflight", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/checksmithcats~scraped-dataset-qa-preflight/run-sync": { "post": { "operationId": "run-sync-checksmithcats-scraped-dataset-qa-preflight", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "datasetId": { "title": "Apify dataset ID", "type": "string", "description": "Dataset ID to read via the Apify API." }, "runId": { "title": "Apify run ID", "type": "string", "description": "Actor run ID. The preflight resolves its default dataset ID." }, "apiToken": { "title": "Apify API token", "type": "string", "description": "Optional token for private datasets or runs. Sent in the Authorization header only and not stored in reports." }, "items": { "title": "Submitted JSON items", "type": "array", "description": "Optional inline array of item objects. Use this when not reading from Apify API.", "items": { "type": "object" } }, "dataJson": { "title": "Submitted JSON text", "type": "string", "description": "Optional JSON array, or an object with an items array." }, "csvText": { "title": "Submitted CSV text", "type": "string", "description": "Optional CSV with a header row. Values are summarized as aggregate QA signals." }, "preset": { "title": "Preset", "enum": [ "googleMaps", "leadList", "socialProfile", "generic" ], "type": "string", "description": "Source-specific field expectations and default duplicate keys.", "default": "generic" }, "keyFields": { "title": "Duplicate key fields", "maxItems": 12, "type": "array", "description": "Optional fields used to count duplicate row groups. Preset defaults are used when empty.", "items": { "type": "string" } }, "schemaContractJson": { "title": "Schema contract JSON", "type": "string", "description": "Optional lightweight JSON Schema object. The preflight checks required fields and simple property types." }, "sampleLimit": { "title": "Sample limit", "minimum": 1, "maximum": 5000, "type": "integer", "description": "Maximum number of rows to sample from the current dataset. Keep the default small for scheduled or exploratory runs.", "default": 200 }, "missingRateWarning": { "title": "Missing-rate warning threshold", "minimum": 0.01, "maximum": 1, "type": "number", "description": "Warn when an observed field is empty or missing in at least this share of sampled rows.", "default": 0.3 } } }, "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 } } } } } } } } } }