{ "openapi": "3.0.1", "info": { "title": "Lead List Cleaner: Dedupe & Tidy CRM CSVs", "description": "Clean a lead list you already have before CRM import: remove duplicates, trim whitespace, lowercase emails, optionally format US/Canada phones, and flag invalid, missing or personal-domain emails. Input an Apify dataset or CSV URL. No scraping, no enrichment.", "version": "0.2", "x-build-id": "8kHeyH5jiHDGQUoWt" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/silent_jubilance~lead-list-cleaner/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-silent_jubilance-lead-list-cleaner", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/silent_jubilance~lead-list-cleaner/runs": { "post": { "operationId": "runs-sync-silent_jubilance-lead-list-cleaner", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/silent_jubilance~lead-list-cleaner/run-sync": { "post": { "operationId": "run-sync-silent_jubilance-lead-list-cleaner", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "datasetId": { "title": "Source dataset", "type": "string", "description": "Apify dataset to clean (read-only access is requested). Use this OR CSV URL, not both." }, "csvUrl": { "title": "CSV URL", "pattern": "^https?://.+", "type": "string", "description": "Direct http(s) link to a CSV file, e.g. a Google Sheets 'Publish to web → CSV' link. Comma, semicolon, tab and pipe delimiters; UTF-8, cp1252 or latin-1. Max 50 MB / 100,000 rows. Use this OR Source dataset, not both." }, "dedupeKeys": { "title": "Dedupe keys", "type": "array", "description": "Columns that define a duplicate. Use an exact column name (case-insensitive) or a field type: email, phone, company, full_name, website, title, linkedin. Several keys = all must match. Comparison ignores case and surrounding spaces; rows where every key is blank are never treated as duplicates. Empty list = no de-duplication. The first occurrence is kept.", "default": [ "email" ], "items": { "type": "string" } }, "removeDuplicates": { "title": "Remove duplicates", "type": "boolean", "description": "On: later duplicates are dropped from the output. Off: they are kept and flagged duplicate_of_row_N.", "default": true }, "trimWhitespace": { "title": "Trim whitespace", "type": "boolean", "description": "Strip leading/trailing spaces and collapse repeated spaces in every cell.", "default": true }, "lowercaseEmails": { "title": "Lowercase emails", "type": "boolean", "description": "Lowercase every column detected as an email column.", "default": true }, "normalizePhones": { "title": "Format US/Canada phones", "type": "boolean", "description": "Rewrite 10-digit numbers (or 11 digits starting with 1) in phone columns as +1XXXXXXXXXX. Other numbers are left unchanged. Off by default.", "default": false }, "titleCaseNames": { "title": "Fix ALL-CAPS / lowercase names", "type": "boolean", "description": "In name columns, title-case words that are entirely upper- or lower-case (\"jane DOE\" → \"Jane Doe\"). Mixed-case words such as McDonald are left alone. Off by default.", "default": false }, "flagIssues": { "title": "Flag issues per row", "type": "boolean", "description": "Add per-row flags: missing_email, invalid_email (format check only, not a deliverability check), personal_domain, bad_phone, missing_company, ragged_row, duplicate_of_row_N.", "default": true }, "issuesColumnInCsv": { "title": "Add issues column to CLEANED_CSV", "type": "boolean", "description": "Append a preflight_issues column to CLEANED_CSV with the plain-English reason for each flag, e.g. \"Email 'sam@@x.example' is not a valid email format (not auto-fixed)\". Off by default, so the CSV keeps exactly your columns. The dataset always has the preflightIssues field.", "default": false } } }, "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 } } } } } } } } } }