{ "openapi": "3.0.1", "info": { "title": "Merge & Deduplicate Datasets - Only New Items, Join, CSV/XLSX", "description": "Merge Apify datasets, CSV, JSON, JSONL or Excel files and pasted rows into one clean dataset: remove duplicates by any fields (case and whitespace normalised), keep only items new since your last run, left/inner join on a key, flatten nested JSON. $0.05 per 1,000 rows out.", "version": "0.1", "x-build-id": "m6V5yTnJ7EbBRLedP" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/actor-forge~dataset-merge-dedupe/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-actor-forge-dataset-merge-dedupe", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/actor-forge~dataset-merge-dedupe/runs": { "post": { "operationId": "runs-sync-actor-forge-dataset-merge-dedupe", "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/actor-forge~dataset-merge-dedupe/run-sync": { "post": { "operationId": "run-sync-actor-forge-dataset-merge-dedupe", "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": "Apify datasets to merge (pick them, or pass dataset IDs via the API). Picking a dataset here gives this run read access to it; nothing else on your account is readable. Read in the order given, after any pasted rows." }, "fileUrls": { "title": "File URLs (CSV, JSON, JSONL, Excel)", "type": "array", "description": "Public URLs of CSV/TSV (delimiter auto-detected, first row = column names), JSON (an array, or an object with an items/data/results array), JSON Lines or XLSX (first visible sheet) files, up to 100 MB each. Read after the datasets.", "items": { "type": "string" } }, "rows": { "title": "Rows (JSON)", "type": "array", "description": "Rows pasted as a JSON array of objects. Read first." }, "dedupeFields": { "title": "Deduplicate on fields", "type": "array", "description": "Rows with the same values in all of these fields are duplicates; the first one is kept. Dot paths reach nested values (e.g. address.postcode). Leave empty to compare whole rows. Rows where all these fields are empty are always kept.", "items": { "type": "string" } }, "normalizeValues": { "title": "Normalise values before comparing", "type": "boolean", "description": "Compare text case-insensitively with leading/trailing and repeated whitespace ignored (\" ACME Ltd\" = \"acme ltd\"), and a number equal to its text form (42 = \"42\"). The rows themselves are not changed.", "default": true }, "onlyNewItems": { "title": "Only new items since the last run", "type": "boolean", "description": "Remember the dedupe keys of every delivered row (in a key-value store on your own account) and skip rows already delivered by an earlier run with the same history name. Ideal for scheduled scrapes: each run outputs only what is new.", "default": false }, "historyKey": { "title": "History name", "type": "string", "description": "Separate 'only new items' memories for different pipelines, e.g. jobs-london or competitor-prices. Letters, digits, - and _.", "default": "default" }, "joinDatasetId": { "title": "Join: lookup dataset", "type": "string", "description": "Optional. A dataset whose rows are joined onto the merged rows (e.g. company details by domain). Up to 500,000 lookup rows; the first row per key is used." }, "joinFileUrl": { "title": "Join: lookup file URL", "type": "string", "description": "Optional, instead of a lookup dataset: a CSV, JSON, JSONL or XLSX file URL with the lookup rows." }, "joinOn": { "title": "Join on field", "type": "string", "description": "Field of the merged rows to match on (dot paths allowed). Required for a join." }, "joinLookupField": { "title": "Lookup key field", "type": "string", "description": "Field of the lookup rows to match on. Defaults to the same name as 'Join on field'." }, "joinPrefix": { "title": "Prefix for joined fields", "type": "string", "description": "Optional prefix for the fields copied from the lookup row, e.g. company_. Lookup fields only fill fields that are missing or empty in the row, so use a prefix to keep both versions.", "default": "" }, "joinType": { "title": "Join type", "enum": [ "left", "inner" ], "type": "string", "description": "Left: keep every row (unmatched rows unchanged). Inner: keep only rows that matched a lookup row.", "default": "left" }, "flatten": { "title": "Flatten nested JSON", "type": "boolean", "description": "Turn nested objects and arrays into flat columns (address.city, tags.0), handy for spreadsheets and CRMs.", "default": false }, "fields": { "title": "Keep only these fields", "type": "array", "description": "Optional. Output only these fields, in this order (dot paths allowed; the path becomes the column name).", "items": { "type": "string" } }, "omitFields": { "title": "Remove these fields", "type": "array", "description": "Optional. Drop these fields from every row (after flattening, use the flat names).", "items": { "type": "string" } }, "addSourceField": { "title": "Add a _source field", "type": "boolean", "description": "Tag each row with where it came from (input:rows, dataset: or file:).", "default": false }, "maxItems": { "title": "Max rows out", "minimum": 1, "maximum": 10000000, "type": "integer", "description": "Stop after delivering this many rows.", "default": 1000000 } } }, "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 } } } } } } } } } }