{ "openapi": "3.0.1", "info": { "title": "Lead List Deduplicator & Merger", "description": "Merge and deduplicate lead lists from multiple Apify datasets, CSV files and inline JSON into one clean, outreach-ready list. Pure data processor — no scraping, no proxies, no external APIs.", "version": "0.1", "x-build-id": "22dYRvQqgkvenIUow" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/jurassic_jove~lead-deduplicator-merger/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-jurassic_jove-lead-deduplicator-merger", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/jurassic_jove~lead-deduplicator-merger/runs": { "post": { "operationId": "runs-sync-jurassic_jove-lead-deduplicator-merger", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/jurassic_jove~lead-deduplicator-merger/run-sync": { "post": { "operationId": "run-sync-jurassic_jove-lead-deduplicator-merger", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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 dataset IDs", "type": "array", "description": "IDs of Apify datasets produced by previous scraper runs (e.g. Google Maps, Instagram, TikTok). All items are fetched with pagination. Invalid IDs are skipped with a warning.", "items": { "type": "string" } }, "csvUrls": { "title": "CSV file URLs", "type": "array", "description": "Public URLs to CSV files (for example key-value store download links). The parser tolerates a BOM, comma/semicolon/tab/pipe delimiters and quoted fields. Malformed rows are skipped and counted, never crashing the run.", "items": { "type": "string" } }, "inlineRecords": { "title": "Inline JSON records", "type": "array", "description": "Raw lead records pasted directly as a JSON array of objects. Useful for quick tests or merging a small hand-built list. The example below is prefilled to show the format and how duplicates merge — replace it with your own records or clear it." }, "dedupeKeys": { "title": "Deduplication keys", "type": "array", "description": "Which fields identify a duplicate. Records are merged if ANY selected key matches (e.g. same email OR same domain). Email is the primary, safest key. Add others to catch more duplicates.", "items": { "type": "string", "enum": [ "email", "domain", "phone", "name+city" ], "enumTitles": [ "Email (recommended)", "Website domain", "Phone number", "Name + City" ] }, "default": [ "email" ] }, "mergeStrategy": { "title": "Merge strategy", "enum": [ "most_complete", "first_seen", "last_seen" ], "type": "string", "description": "How to combine the records inside a duplicate group. 'Most complete' keeps the record with the most filled-in fields and fills any gaps from its duplicates. 'First seen' / 'Last seen' prefer the earliest / latest record per field.", "default": "most_complete" }, "normalizePhones": { "title": "Normalize phone numbers", "type": "boolean", "description": "Format output phone numbers as E.164 (e.g. +14155552671) when the number is plausible for the default country. Phones are always compared digits-only regardless of this setting.", "default": true }, "defaultCountry": { "title": "Default country (ISO 3166-1 alpha-2)", "type": "string", "description": "Two-letter country code used to interpret phone numbers that have no country prefix. Defaults to US.", "default": "US" }, "stripPlusAliases": { "title": "Strip + aliases from emails (for matching)", "type": "boolean", "description": "When ON, john+news@gmail.com and john@gmail.com are treated as the SAME lead for deduplication. The original deliverable email is always preserved in the output. Default OFF (safer for B2B).", "default": false }, "keepSourceInfo": { "title": "Keep source info", "type": "boolean", "description": "Include a _sources array on every output record showing which dataset(s) / CSV file(s) it was merged from.", "default": true } } }, "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 } } }, "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 } } } } } } } } } }