{ "openapi": "3.0.1", "info": { "title": "Merge & Deduplicate Datasets: Remove Duplicates", "description": "Merge any number of Apify datasets into one and remove duplicate items by one or more fields (url, id, product.id + shop). Only-new-items mode makes scheduled scrapers output new results only. Streams large datasets, limited permissions. Duplicates are never charged.", "version": "0.1", "x-build-id": "OfoKn04n4kSvY2woR" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/grace_hartwell~dataset-merge-dedup/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-grace_hartwell-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/grace_hartwell~dataset-merge-dedup/runs": { "post": { "operationId": "runs-sync-grace_hartwell-dataset-merge-dedup", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/grace_hartwell~dataset-merge-dedup/run-sync": { "post": { "operationId": "run-sync-grace_hartwell-dataset-merge-dedup", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "Datasets to merge", "type": "array", "description": "Pick one or more datasets. The picker grants this run READ access to exactly these datasets (limited permissions) – nothing else in your account is touched. Required for real use; if you leave it empty, the Actor runs a small demo on \"Demo items\" instead." }, "dedupFields": { "title": "Deduplicate by fields", "type": "array", "description": "Fields whose combined value must be unique, e.g. [\"url\"] or [\"product.id\", \"shop\"]. Dot paths for nested fields. Leave empty to remove only fully identical items.", "items": { "type": "string" } }, "caseInsensitive": { "title": "Case-insensitive comparison", "type": "boolean", "description": "Treat \"ABC\" and \"abc\" as equal.", "default": false }, "trimStrings": { "title": "Trim whitespace", "type": "boolean", "description": "Ignore leading/trailing whitespace when comparing strings.", "default": true }, "missingFieldMode": { "title": "Items missing all dedup fields", "enum": [ "keep-all", "as-empty", "drop" ], "type": "string", "description": "keep-all: output them (never treated as duplicates). as-empty: treat missing as an empty value (all such items collapse into one). drop: skip them.", "default": "keep-all" }, "onlyNewItems": { "title": "Only output items not seen in previous runs", "type": "boolean", "description": "Remembers item keys in a key-value store created by this Actor (named dedup-state-) and skips items already output in earlier runs. Great for scheduled scrapers.", "default": false }, "stateKey": { "title": "State key", "type": "string", "description": "Name of the remembered state. Use different keys for unrelated pipelines.", "default": "default" }, "updateState": { "title": "Update state after run", "type": "boolean", "description": "Turn off for a dry run that compares against the state without changing it.", "default": true }, "referenceDatasetIds": { "title": "Reference datasets (filter only)", "type": "array", "description": "Optional: items whose key appears in these datasets are treated as already seen and not output. READ access only." }, "outputFields": { "title": "Output only these fields", "type": "array", "description": "Optional projection, e.g. [\"url\", \"title\", \"price.value\"]. Empty = full items.", "items": { "type": "string" } }, "addSourceDatasetId": { "title": "Add _sourceDatasetId", "type": "boolean", "description": "Add the ID of the dataset each item came from.", "default": false }, "maxOutputItems": { "title": "Max output items", "minimum": 0, "type": "integer", "description": "0 = unlimited. Output is also capped by your 'Max total charge' budget.", "default": 0 }, "pageSize": { "title": "Read page size", "minimum": 100, "maximum": 50000, "type": "integer", "description": "Items read per API call (streaming). Lower it for very large items.", "default": 5000 }, "pushBatchSize": { "title": "Write batch size", "minimum": 1, "maximum": 5000, "type": "integer", "description": "Items written per API call.", "default": 1000 }, "demoItems": { "title": "Demo items (used only when no dataset is selected)", "type": "array", "description": "A tiny built-in example so a run without datasets still shows how deduplication works (e.g. Apify's default-input test). Ignored as soon as you select at least one dataset above. Max 100 items. Output items are charged like normal output items.", "default": [ { "url": "https://example.com/product/1", "title": "Blue mug", "price": 12.9 }, { "url": "https://example.com/product/2", "title": "Red mug", "price": 11.5 }, { "url": "https://example.com/product/1", "title": "Blue mug (duplicate)", "price": 12.9 }, { "url": " https://example.com/product/3 ", "title": "Green mug", "price": 13 }, { "url": "https://example.com/product/2", "title": "Red mug (duplicate)", "price": 11.5 } ] } } }, "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 } } } } } } } } } }