{ "openapi": "3.0.1", "info": { "title": "Dataset Merge, Dedupe & Only New Items", "description": "Merge Apify datasets, remove duplicates on normalized fields (URLs, case, spaces) and output only items not seen in earlier runs. Works with limited permissions, schedules and integrations. CSV/Excel export.", "version": "1.0", "x-build-id": "SiNge2e8cBS4fHpp1" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/genesis.labs.co~dataset-merge-dedupe/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-genesis.labs.co-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/genesis.labs.co~dataset-merge-dedupe/runs": { "post": { "operationId": "runs-sync-genesis.labs.co-dataset-merge-dedupe", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/genesis.labs.co~dataset-merge-dedupe/run-sync": { "post": { "operationId": "run-sync-genesis.labs.co-dataset-merge-dedupe", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "Datasets to merge, in priority order (when two items share a key, the one from the earlier dataset is kept). Pick from your runs or paste dataset IDs." }, "datasetId": { "title": "Dataset from an integration", "type": "string", "description": "For integrations: set to {{resource.defaultDatasetId}} in \"Run another Actor when a run succeeds\" to process each finished scraper run. Merged after \"Datasets\"." }, "mode": { "title": "Mode", "enum": [ "dedupe", "onlyNew", "merge" ], "type": "string", "description": "Only new items: outputs items whose key was never output by an earlier run with the same Memory name. Great for scheduled scrapers and alerts.", "default": "dedupe" }, "dedupeFields": { "title": "Key fields", "type": "array", "description": "Fields that identify an item, e.g. url, or title + price. Dot paths work (e.g. location.city). Leave empty to compare whole items.", "items": { "type": "string" } }, "memoryName": { "title": "Memory name (only new items)", "pattern": "^[a-zA-Z0-9-]{0,40}$", "type": "string", "description": "Letters, digits and hyphens. Each name keeps its own list of seen keys in a key-value store in your account, so runs with the same name never output the same item twice." }, "resetMemory": { "title": "Reset memory", "type": "boolean", "description": "Forget all keys stored under this Memory name and start over.", "default": false }, "emptyKeyItems": { "title": "Items with an empty key", "enum": [ "keep", "drop" ], "type": "string", "description": "What to do when all key fields of an item are empty.", "default": "keep" }, "trim": { "title": "Trim spaces", "type": "boolean", "description": "Ignore leading and trailing spaces when comparing keys.", "default": true }, "collapseWhitespace": { "title": "Collapse inner whitespace", "type": "boolean", "description": "Treat runs of spaces, tabs and newlines as one space.", "default": true }, "caseInsensitive": { "title": "Ignore letter case", "type": "boolean", "description": "\"iPhone 15\" and \"IPHONE 15\" match.", "default": true }, "normalizeUrls": { "title": "Normalize URLs", "type": "boolean", "description": "http/https, www., trailing slashes, #fragments, parameter order and tracking parameters (utm_*, fbclid, gclid...) don't create duplicates.", "default": true }, "stripUrlQuery": { "title": "Ignore all URL parameters", "type": "boolean", "description": "Compare URLs without any ?query parameters.", "default": false }, "removeDiacritics": { "title": "Ignore accents", "type": "boolean", "description": "\"Café\" and \"Cafe\" match.", "default": false }, "pickFields": { "title": "Keep only these fields", "type": "array", "description": "Output only these fields (dot paths allowed). Leave empty to keep all.", "items": { "type": "string" } }, "omitFields": { "title": "Remove fields", "type": "array", "description": "Top-level fields to drop, e.g. #debug, html.", "items": { "type": "string" } }, "renameFields": { "title": "Rename fields", "type": "object", "description": "Map of old name to new name, e.g. {\"url\": \"productUrl\", \"price.value\": \"price\"}." }, "addSourceField": { "title": "Add source dataset ID", "type": "boolean", "description": "Adds _sourceDatasetId to every output item.", "default": false }, "maxItems": { "title": "Max output items", "minimum": 1, "type": "integer", "description": "Stop after this many output items." } } }, "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 } } } } } } } } } }