{ "openapi": "3.0.1", "info": { "title": "Csv Data Cleaning And Normalization", "description": "Operations teams need to validate and normalize recurring CSV and Excel imports without manually correcting rows, silently discarding failures, or losing an audit trail of changes.", "version": "0.0", "x-build-id": "zm4fwSG79XP4lWpu3" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/first_watch~csv-data-cleaning-and-normalization/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-first_watch-csv-data-cleaning-and-normalization", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/first_watch~csv-data-cleaning-and-normalization/runs": { "post": { "operationId": "runs-sync-first_watch-csv-data-cleaning-and-normalization", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/first_watch~csv-data-cleaning-and-normalization/run-sync": { "post": { "operationId": "run-sync-first_watch-csv-data-cleaning-and-normalization", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "source", "columns" ], "properties": { "source": { "title": "Tabular source", "maxProperties": 7, "type": "object", "description": "Use inlineCsv with csv, inlineRecords with records, inlineJson with json, base64Document with format and base64, url with format and url, or apifyDataset with a public datasetId. CSV/XLSX files: at most 3 MB. Optional delimiter: comma, semicolon, tab or pipe; worksheet: name or index 1-10. Remote hosts: apify.com and api.apify.com only. See README for examples." }, "columns": { "title": "Import specification", "minItems": 1, "maxItems": 100, "type": "array", "description": "1-100 objects with a safe lowercase snake_case target and type: string, email, phone, integer, number, boolean, date or datetime. Optional sources (up to 20), required, trim, case, emptyAsNull, default, allowedValues (up to 1000), dateFormats, outputDateFormat and numberFormat (auto, US or EU; number and integer columns only). Values such as 1,234 or 03/04/2026 are never guessed: numberFormat, a single day/month order in dateFormats, or unambiguous values in the same column must settle them. Runtime validation checks every nested option.", "items": { "type": "object" } }, "deduplicationKeys": { "title": "Duplicate key fields", "maxItems": 20, "uniqueItems": true, "type": "array", "description": "Up to 20 canonical targets forming a compound key. The first valid occurrence is accepted; subsequent matches are rejected.", "items": { "type": "string", "minLength": 1, "maxLength": 64 }, "default": [] }, "unknownColumns": { "title": "Unmapped columns", "enum": [ "drop", "preserve", "reject" ], "type": "string", "description": "Drop, reject, or preserve extra fields. Preserve converts extra field names to snake_case and nested values to stable JSON strings; name collisions reject that row.", "default": "drop" }, "maximumRows": { "title": "Maximum source rows", "minimum": 1, "maximum": 1000, "type": "integer", "description": "If the source has more rows than this, the run stops before any row is delivered, OUTPUT reports LIMIT_REACHED with a ROW_LIMIT error and the run fails. Hard maximum: 1000.", "default": 1000 }, "maskSensitiveInLogs": { "title": "Protect diagnostic values", "type": "boolean", "description": "Compatibility option. Raw values are never logged, even when false. Full values are retained only in outputs.", "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 }, "PROXY_UNBLOCKER_UNITS": { "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 }, "PROXY_UNBLOCKER_UNITS": { "type": "integer", "example": 0 } } } } } } } } } }