{ "openapi": "3.0.1", "info": { "title": "Dataset Transformer - Filter, Dedupe, Merge & Export CSV", "description": "Filter, deduplicate, merge, sort, rename and flatten Apify datasets from any scraper, then export clean rows to a dataset, CSV or JSON file.", "version": "1.0", "x-build-id": "ZCTpp5JBpTQoebTtJ" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/seemuapps~dataset-transformer/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-seemuapps-dataset-transformer", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/seemuapps~dataset-transformer/runs": { "post": { "operationId": "runs-sync-seemuapps-dataset-transformer", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/seemuapps~dataset-transformer/run-sync": { "post": { "operationId": "run-sync-seemuapps-dataset-transformer", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "datasetIds" ], "properties": { "datasetIds": { "title": "Datasets to transform", "type": "array", "description": "One or more dataset IDs, dataset names ('my-leads' or 'username~my-leads'), run IDs (the run's default dataset is used) or dataset/run URLs. Several datasets are merged in the order listed. When chaining from another actor via an integration, use {{resource.defaultDatasetId}}.", "items": { "type": "string" } }, "filters": { "title": "Filters", "type": "array", "description": "Keep only rows that match these rules. Each rule: {\"field\": \"dotted.path\", \"operator\": \"...\", \"value\": ...}. Operators: equals, notEquals, contains, notContains, regex, notRegex, gt, gte, lt, lte, exists, notExists, in, notIn. Text matching is case-insensitive unless the rule sets \"caseSensitive\": true. Numbers stored as text (\"1,234\", \"$19.99\", \"10.5K\") and ISO dates compare correctly. If a path points into a list (e.g. \"posts.likes\"), the rule matches when any item matches. Leave empty to keep every row.", "default": [] }, "filterLogic": { "title": "Combine filters with", "enum": [ "AND", "OR" ], "type": "string", "description": "AND keeps rows that match every rule; OR keeps rows that match at least one rule.", "default": "AND" }, "dedupeBy": { "title": "Remove duplicates by", "type": "array", "description": "Field(s) that identify a duplicate, e.g. 'phone', 'url' or 'username'. With several fields, rows are duplicates only when all of them match. Use '*' to remove rows that are identical in every field. The first occurrence is kept (after sorting, if a sort is set). Rows where all of these fields are empty are always kept. Leave empty to skip deduplication.", "default": [], "items": { "type": "string" } }, "dedupeNormalize": { "title": "Loose duplicate matching", "type": "boolean", "description": "Ignore case and extra spaces, treat '1,000' and 1000 as equal, and compare phone numbers by digits only ('(555) 123-4567' = '555.123.4567'). Turn off for exact matching.", "default": true }, "fields": { "title": "Keep only these fields", "type": "array", "description": "Output only these fields, in this order. Dotted paths reach into nested objects ('address.city'); a path through a list collects every item's value ('images.url'). Leave empty to keep all fields.", "default": [], "items": { "type": "string" } }, "omitFields": { "title": "Remove these fields", "type": "array", "description": "Drop these fields from the output. Dotted paths are supported ('address.geo').", "default": [], "items": { "type": "string" } }, "renameFields": { "title": "Rename fields", "type": "object", "description": "JSON object of old name to new name, e.g. {\"title\": \"businessName\", \"address.city\": \"city\"}. Renaming a dotted path moves that value to the new top-level name.", "default": {} }, "flatten": { "title": "Flatten nested objects", "type": "boolean", "description": "Turn nested objects into dotted columns ({\"address\": {\"city\": \"Austin\"}} becomes \"address.city\": \"Austin\") in the dataset output too. The CSV file is always flat.", "default": false }, "arrayMode": { "title": "Lists when flattening", "enum": [ "join", "index", "json" ], "type": "string", "description": "How lists become columns when flattening (and in the CSV file). Join: lists of text or numbers become 'a, b, c' and lists of objects become JSON text. Index: every item gets its own column (tags.0, tags.1, images.0.url). JSON: every list becomes JSON text.", "default": "join" }, "sortBy": { "title": "Sort by field", "type": "string", "description": "Sort the output by this field (dotted paths allowed). Numbers stored as text and ISO dates sort correctly; rows without the field go last. Leave empty to keep the input order." }, "sortOrder": { "title": "Sort order", "enum": [ "asc", "desc" ], "type": "string", "description": "Ascending (A to Z, smallest first) or descending (Z to A, largest first).", "default": "asc" }, "offset": { "title": "Skip first N rows", "minimum": 0, "type": "integer", "description": "Skip this many rows of the final result (after filtering, deduplication and sorting).", "default": 0 }, "maxItems": { "title": "Max rows", "minimum": 0, "type": "integer", "description": "Stop after this many output rows. 0 means no limit.", "default": 0 }, "addSourceField": { "title": "Add source dataset column", "type": "boolean", "description": "Add a '_sourceDataset' field with the name or ID of the dataset each row came from. Useful when merging several runs.", "default": false }, "pushToDataset": { "title": "Save rows to the output dataset", "type": "boolean", "description": "Write the transformed rows to this run's dataset, so you can export them in any format or chain another actor.", "default": true }, "exportCsv": { "title": "Save a CSV file", "type": "boolean", "description": "Also save all rows as OUTPUT.csv in the key-value store (always flat, with a header row).", "default": true }, "exportJson": { "title": "Save a JSON file", "type": "boolean", "description": "Also save all rows as a single OUTPUT.json array in the key-value store.", "default": false }, "csvDelimiter": { "title": "CSV delimiter", "enum": [ ",", ";", "tab", "|" ], "type": "string", "description": "Column separator for OUTPUT.csv. Use semicolon for Excel in locales that use a decimal comma.", "default": "," }, "csvBom": { "title": "Excel-friendly CSV (UTF-8 BOM)", "type": "boolean", "description": "Start OUTPUT.csv with a UTF-8 byte-order mark so Excel shows accents, emoji and non-Latin text correctly when the file is double-clicked.", "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 }, "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 } } } } } } } } } }