{ "openapi": "3.0.1", "info": { "title": "Dataset Filter & Transform: Filter, Pick, Rename, Flatten", "description": "Clean any Apify dataset without code: filter rows (equals, contains, regex, greater than, empty…), keep or drop columns, rename fields, flatten nested JSON, split list fields into rows, add tags. Chain it between a scraper and Google Sheets, CSV export or alerts.", "version": "0.0", "x-build-id": "hxJj94y0O4CTmaFa4" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/charlesmarkette~dataset-filter-transform-rename-flatten-fields/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-charlesmarkette-dataset-filter-transform-rename-flatten-fields", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/charlesmarkette~dataset-filter-transform-rename-flatten-fields/runs": { "post": { "operationId": "runs-sync-charlesmarkette-dataset-filter-transform-rename-flatten-fields", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/charlesmarkette~dataset-filter-transform-rename-flatten-fields/run-sync": { "post": { "operationId": "run-sync-charlesmarkette-dataset-filter-transform-rename-flatten-fields", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "datasetIds": { "title": "Datasets", "type": "array", "description": "One or more datasets to clean up, read in order (usually a scraper run's output). In an integration, use [\"{{resource.defaultDatasetId}}\"]. Leave empty to use 'Items' below instead." }, "datasetIdList": { "title": "Dataset IDs (typed)", "type": "array", "description": "Optional. Dataset IDs (or username~dataset-name) typed by hand, one per line. Read after the picked datasets.", "items": { "type": "string" } }, "items": { "title": "Items (instead of datasets)", "type": "array", "description": "Optional. A JSON list of objects to filter and transform, used only when no dataset is given above. Handy for quick tests and for calling this Actor from code." }, "filters": { "title": "Filters", "type": "array", "description": "Keep only rows that match these conditions. Each condition is {\"field\", \"op\", \"value\"}. Ops: equals, notEquals, contains, notContains, startsWith, endsWith, regex, greaterThan, lessThan, greaterOrEqual, lessOrEqual, in, notIn (value: a list or \"a, b, c\"), and exists, notExists, isEmpty, isNotEmpty (no value). Dots reach nested fields (address.city); on a list, a condition matches if any element matches. Numbers and ISO dates compare as numbers and dates. Leave empty to keep every row." }, "filterMode": { "title": "Filter mode", "enum": [ "all", "any" ], "type": "string", "description": "How the filter conditions combine: all of them must match (AND), or at least one (OR).", "default": "all" }, "caseSensitive": { "title": "Case-sensitive text matching", "type": "boolean", "description": "Off: 'ACME' equals 'acme'. A single condition can override this with \"caseSensitive\": true.", "default": false }, "unwindField": { "title": "Split a list field into rows", "type": "string", "description": "Optional. A field holding a list (e.g. emails). Each element becomes its own row, with the other fields copied. Dots for nested fields." }, "pickFields": { "title": "Keep only these fields", "type": "array", "description": "Optional. Output only these fields, in this order (handy for spreadsheet columns). Dots for nested fields; the column is then named 'address.city'. Empty = keep all.", "items": { "type": "string" } }, "omitFields": { "title": "Remove these fields", "type": "array", "description": "Optional. Fields to drop. Dots for nested fields (images.thumbnail removes it from every image).", "items": { "type": "string" } }, "renameFields": { "title": "Rename fields", "type": "object", "description": "Optional. {\"old name\": \"New Name\"}, applied in order. Renamed columns keep their position. Example: {\"title\": \"Company Name\", \"phone\": \"Phone Number\"}." }, "flatten": { "title": "Flatten nested fields", "type": "boolean", "description": "Nested objects become columns like 'address.city'. Lists stay lists unless you join them below.", "default": false }, "joinArrays": { "title": "Join lists into text", "type": "boolean", "description": "Lists of plain values (text, numbers) become one text value, e.g. [\"a\", \"b\"] → \"a, b\". Lists of objects are kept.", "default": false }, "arrayJoiner": { "title": "List separator", "type": "string", "description": "Text placed between joined list elements.", "default": ", " }, "addFields": { "title": "Add fields", "type": "object", "description": "Optional. Fixed values added to every row (overwriting a field with the same name), e.g. {\"source\": \"google-maps\", \"campaign\": \"october\"}." }, "trimStrings": { "title": "Trim spaces", "type": "boolean", "description": "Remove leading and trailing whitespace from every text value.", "default": false }, "emptyToNull": { "title": "Empty values to null", "type": "boolean", "description": "Empty text, empty lists and empty objects become null.", "default": false }, "lowercaseFields": { "title": "Lowercase these fields", "type": "array", "description": "Optional. Output fields whose text is lowercased, e.g. email. Use the output name (after renaming).", "items": { "type": "string" } }, "sortBy": { "title": "Sort by field", "type": "string", "description": "Optional. An output field name (after renaming). Numbers, dates and text sort naturally; empty values go last. Without 'Max results', sorting is limited to 200,000 rows." }, "sortDesc": { "title": "Sort descending", "type": "boolean", "description": "Largest, latest or Z first.", "default": false }, "maxResults": { "title": "Max results", "minimum": 1, "type": "integer", "description": "Optional cap on output rows." }, "offset": { "title": "Skip first rows", "minimum": 0, "type": "integer", "description": "Optional. Skip this many output rows (after filtering and sorting) before writing. Skipped rows are free." } } }, "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 } } } } } } } } } }