{ "openapi": "3.0.1", "info": { "title": "Merge Datasets & Remove Duplicates: CSV, JSON, Apify", "description": "Merge Apify datasets and CSV/JSON/JSONL files into one dataset and remove duplicates. Use to combine scraper outputs or exports. Input: datasetIds and/or fileUrls, dedupFields, optional renameFields, filters, keepFields. Output: merged deduplicated rows (optional _source field) plus a SUMMARY.", "version": "0.1", "x-build-id": "PSOmegFQesOQiJIhS" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/phaux~dataset-merge-dedup/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-phaux-dataset-merge-dedup", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/phaux~dataset-merge-dedup/runs": { "post": { "operationId": "runs-sync-phaux-dataset-merge-dedup", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/phaux~dataset-merge-dedup/run-sync": { "post": { "operationId": "run-sync-phaux-dataset-merge-dedup", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "Apify datasets", "type": "array", "description": "Datasets to merge, in order. In Console pick them with the dataset picker; via API pass dataset IDs (or 'username~dataset-name'). Only these datasets can be read by the run (read-only access). Example: [\"\"]." }, "fileUrls": { "title": "CSV, JSON or JSONL file URLs", "type": "array", "description": "Public URLs of CSV (any delimiter), JSON (array, or object with an items/data list) or JSON Lines files. Each is downloaded once, up to maxFileSizeMb. Example: [\"https://raw.githubusercontent.com/datasets/country-list/main/data.csv\", \"https://raw.githubusercontent.com/datasets/country-codes/main/data/country-codes.csv\"].", "items": { "type": "string" } }, "dedupFields": { "title": "Deduplicate by fields", "type": "array", "description": "Rows with the same values in all these fields count as duplicates; the first one is kept. Dot paths work for nested fields (e.g. 'address.city'). Rows where all of these fields are empty are always kept. Leave empty for no field-based dedup.", "items": { "type": "string" } }, "dedupWholeItem": { "title": "Deduplicate identical rows", "type": "boolean", "description": "When no dedup fields are set: drop rows that are identical in every field. Default: false.", "default": false }, "caseInsensitive": { "title": "Case-insensitive matching", "type": "boolean", "description": "Ignore letter case (and surrounding spaces) when comparing dedup keys and text filters. Default: false.", "default": false }, "renameFields": { "title": "Rename fields", "type": "object", "description": "Map of old top-level field name to new name, e.g. {\"Company Name\": \"company\"}. Applied first. Map several source names to one new name to align differently named columns." }, "filters": { "title": "Filters", "type": "array", "description": "Keep only rows matching these conditions, e.g. [{\"field\": \"price\", \"op\": \"gt\", \"value\": 10}, {\"field\": \"email\", \"op\": \"notEmpty\"}]. Ops: eq, neq, gt, gte, lt, lte, contains, notContains, startsWith, endsWith, regex, in, notIn, exists, notExists, empty, notEmpty. Numbers in text are compared as numbers." }, "filterMode": { "title": "Filter mode", "enum": [ "all", "any" ], "type": "string", "description": "all = a row must match every filter; any = at least one. Default: \"all\".", "default": "all" }, "keepFields": { "title": "Keep only these fields", "type": "array", "description": "Output only these fields, in this order (dot paths allowed; missing values become null). Leave empty to keep all fields. Example: [\"url\", \"title\", \"price\"].", "items": { "type": "string" } }, "omitFields": { "title": "Drop these fields", "type": "array", "description": "Top-level fields to remove (ignored when keepFields is set). Example: [\"html\", \"debug\"].", "items": { "type": "string" } }, "addSourceField": { "title": "Add source field", "type": "boolean", "description": "Add the dataset ID or file URL each row came from. Default: false.", "default": false }, "sourceFieldName": { "title": "Source field name", "type": "string", "description": "Name of the source field. Example: \"_source\". Default: \"_source\".", "default": "_source" }, "maxItems": { "title": "Max output rows", "minimum": 0, "type": "integer", "description": "Stop after this many rows are saved (0 = no limit). Also caps the cost of a run. Default: 0.", "default": 0 }, "skipHiddenFields": { "title": "Skip hidden fields", "type": "boolean", "description": "Drop fields starting with # from dataset rows (Apify's hidden-field convention). Default: false.", "default": false }, "csvDelimiter": { "title": "CSV delimiter", "type": "string", "description": "auto detects , ; tab or |. Or give one character (use 'tab' for tab). Example: \",\" or \";\". Default: \"auto\".", "default": "auto" }, "maxFileSizeMb": { "title": "Max file size (MB)", "minimum": 1, "maximum": 500, "type": "integer", "description": "Per file URL (1–500). Large JSON arrays need about 10x their size in memory; JSON Lines and CSV need less. Raise the run memory for big files. Default: 100.", "default": 100 }, "failOnSourceError": { "title": "Fail if any source fails", "type": "boolean", "description": "Off: a missing dataset or broken file is reported in SOURCE_ERRORS and the other sources are still merged. On: the run fails at the first broken source. Default: false.", "default": false }, "timeBudgetSecs": { "title": "Time budget (seconds)", "minimum": 0, "type": "integer", "description": "Stop reading after this many seconds and keep the rows saved so far (0 = only the run timeout guard). Default: 0.", "default": 0 } } }, "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 } } } } } } } } } }