{ "openapi": "3.0.1", "info": { "title": "Merge & Deduplicate Datasets: Remove Duplicates, Only New Items", "description": "Merge Apify datasets, CSV and JSON files into one, remove duplicates by any field, output only new items since the last run, filter, rename and flatten. $0.10 per 1,000 rows.", "version": "0.2", "x-build-id": "w4BrHYI99pprmJITV" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/gmyri~dataset-merge-dedup/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-gmyri-dataset-merge-dedup", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/gmyri~dataset-merge-dedup/runs": { "post": { "operationId": "runs-sync-gmyri-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/gmyri~dataset-merge-dedup/run-sync": { "post": { "operationId": "run-sync-gmyri-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 (e.g. outputs of your scraper runs). Only the datasets you select here are readable by the Actor." }, "fileUrls": { "title": "CSV / JSON / JSONL file URLs", "type": "array", "description": "Direct links to CSV, TSV, JSON (array or {items:[...]}) or JSON Lines files. Google Sheets 'Publish to web → CSV' links work.", "items": { "type": "string" } }, "inlineItems": { "title": "Inline items (JSON array)", "type": "array", "description": "Rows passed directly, handy for AI agents and quick tests." }, "deduplicate": { "title": "Remove duplicates", "type": "boolean", "description": "Drop rows that share the same dedup key.", "default": true }, "dedupFields": { "title": "Dedup fields", "type": "array", "description": "Fields that define a duplicate, e.g. 'url' or 'title' + 'address.city' (dot paths supported). Empty = compare the whole row. Rows where all dedup fields are empty are always kept.", "items": { "type": "string" } }, "dedupCaseInsensitive": { "title": "Case-insensitive", "type": "boolean", "description": "'ACME Ltd' equals 'acme ltd'.", "default": true }, "dedupTrimWhitespace": { "title": "Ignore extra whitespace", "type": "boolean", "description": "Collapse and trim whitespace before comparing.", "default": true }, "keepOccurrence": { "title": "Which duplicate to keep", "enum": [ "first", "last" ], "type": "string", "description": "With 'last', later sources overwrite earlier ones.", "default": "first" }, "onlyNewItems": { "title": "Only output rows not seen in previous runs", "type": "boolean", "description": "Incremental mode for scheduled scrapes: remembers dedup keys in a named key-value store and skips rows already output before.", "default": false }, "stateStoreName": { "title": "State store name", "type": "string", "description": "Named key-value store that keeps the remembered keys. Use a different name per pipeline.", "default": "dataset-dedup-state" }, "filters": { "title": "Filters", "type": "array", "description": "All must match. Each filter: {\"field\": \"price\", \"op\": \"lt\", \"value\": 100}. Ops: eq, ne, contains, notContains, in, notIn, gt, gte, lt, lte, exists, notExists, regex." }, "pickFields": { "title": "Keep only these fields", "type": "array", "description": "Output only these fields (dot paths allowed). Empty = keep all.", "items": { "type": "string" } }, "omitFields": { "title": "Remove fields", "type": "array", "description": "Fields to drop.", "items": { "type": "string" } }, "renameFields": { "title": "Rename fields", "type": "object", "description": "Map of old name to new name, e.g. {\"address.city\": \"city\"}." }, "flattenNested": { "title": "Flatten nested objects", "type": "boolean", "description": "Turn {\"a\":{\"b\":1}} into {\"a.b\":1}. Useful before CSV export.", "default": false }, "trimStrings": { "title": "Trim strings", "type": "boolean", "description": "Collapse whitespace in all string values.", "default": false }, "dropEmptyFields": { "title": "Drop empty fields", "type": "boolean", "description": "Remove null, empty-string and empty list/object values.", "default": false }, "addSourceField": { "title": "Add _source field", "type": "boolean", "description": "Record which dataset or file each row came from.", "default": false }, "inferCsvTypes": { "title": "Infer numbers/booleans in CSV", "type": "boolean", "description": "Convert '12', '3.5', 'true' in CSV cells to numbers/booleans.", "default": true }, "maxOutputItems": { "title": "Max output rows", "minimum": 0, "type": "integer", "description": "Stop after this many output rows (0 = no limit).", "default": 0 }, "saveCsvFile": { "title": "Also save OUTPUT.csv", "type": "boolean", "description": "Save the result as a CSV file in the key-value store (flattened).", "default": false }, "saveJsonFile": { "title": "Also save OUTPUT.json", "type": "boolean", "description": "Save the result as one JSON file in the key-value store.", "default": false }, "maxFileSizeMb": { "title": "Max file size (MB)", "minimum": 1, "maximum": 2000, "type": "integer", "description": "Larger files are skipped.", "default": 200 }, "requestTimeoutSecs": { "title": "Download timeout (s)", "minimum": 5, "maximum": 900, "type": "integer", "description": "Timeout per file download.", "default": 120 } } }, "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 } } } } } } } } } }