{ "openapi": "3.0.1", "info": { "title": "Lead List Cleaner — Dedupe, Phones, Addresses, Websites, Emails", "description": "Clean any business lead list (CSV, Google Sheet, JSON or an Apify dataset such as Google Maps results): remove duplicates, format phones (E.164) and addresses, check websites are live and email domains have MX, drop personal emails, add a quality score. $1.50 per 1,000 rows.", "version": "0.1", "x-build-id": "8x8g0aLnUc38Sm8gC" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/signalloom~lead-list-cleaner/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-signalloom-lead-list-cleaner", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/signalloom~lead-list-cleaner/runs": { "post": { "operationId": "runs-sync-signalloom-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/signalloom~lead-list-cleaner/run-sync": { "post": { "operationId": "run-sync-signalloom-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": "Apify dataset ID", "type": "string", "description": "Clean the results of another Actor run: pick the dataset or paste its ID (Run → Storage → Dataset ID). Works with Google Maps, store-leads or any other dataset in your account; the Actor gets read-only access to that dataset only. Leave all three sources empty to try the built-in sample. Example: \"aBcD1234eFgH5678\"." }, "sourceUrl": { "title": "CSV or JSON file URL", "type": "string", "description": "A link to a CSV or JSON file (comma, semicolon or tab separated). Google Sheets links work if the sheet is shared as \"Anyone with the link\". Example: \"https://example.com/leads.csv\"." }, "rows": { "title": "Rows (JSON)", "type": "array", "description": "Rows pasted as a JSON array of objects, e.g. [{\"name\": \"Joe's Pizza\", \"phone\": \"(512) 555 0100\", \"website\": \"joespizza.com\"}]. Rows from all sources you fill in are cleaned together." }, "fieldMapping": { "title": "Field mapping (optional)", "type": "object", "description": "Columns are detected automatically (name/title, phone, website/url/domain, email/emails, address or street/city/state/postalCode/country). Override any of them with your column name, e.g. {\"phone\": \"Main Phone\", \"name\": \"Company\"}. Keys: name, phone, website, email, address, street, city, state, postalCode, country." }, "defaultCountry": { "title": "Default country", "type": "string", "description": "Two-letter country code used for phone numbers without a +country code when the row has no country, e.g. US, GB, CA, AU, DE. Example: \"GB\".", "default": "US" }, "duplicates": { "title": "Duplicates", "enum": [ "flag", "remove" ], "type": "string", "description": "Flag: keep every row and mark duplicates (clean_is_duplicate, clean_duplicate_of_row). Remove: output only one row per business. Duplicate rows are never charged either way. API values: \"flag\", \"remove\".", "default": "flag" }, "mergeStrategy": { "title": "Which row to keep", "enum": [ "merge", "keepMostComplete", "keepFirst" ], "type": "string", "description": "Merge (recommended): keep the most complete row and fill its missing phone, website, email or address from its duplicates. Most complete: keep the most complete row as is. First: keep the first row as is. API values: \"merge\", \"keepMostComplete\", \"keepFirst\".", "default": "merge" }, "dedupeBy": { "title": "Match duplicates by", "type": "array", "description": "Rows are the same business when they share any of these. Website domain ignores social and platform pages (Facebook, Yelp…).", "items": { "type": "string", "enum": [ "domain", "phone", "nameAddress" ], "enumTitles": [ "Website domain", "Phone number", "Name + street address" ] }, "default": [ "domain", "phone", "nameAddress" ] }, "mergeLocations": { "title": "Merge branches of the same company", "type": "boolean", "description": "Off (default): rows with the same website or phone but different street addresses are kept as separate locations (chains, franchises). On: one row per company.", "default": false }, "checkWebsites": { "title": "Check websites are live", "type": "boolean", "description": "One request to each unique website's homepage: HTTP status, redirect target, HTTPS, parked domains. Page content is not read or stored.", "default": true }, "checkEmailDns": { "title": "Check email domains (MX)", "type": "boolean", "description": "Looks up each email domain's mail server (MX record) in DNS. No email is sent and no mail server is contacted.", "default": true }, "dropPersonEmails": { "title": "Drop person-looking emails", "type": "boolean", "description": "On (default): only company mailboxes are kept (info@, sales@, reservations@, the brand's own name). Addresses that look like a person's (jane@, j.smith@) are removed from the output, including from your original columns, and counted in clean_emails_dropped. Turn off only if you have a lawful basis to process personal emails.", "default": true }, "tidyOriginalFields": { "title": "Tidy original text fields", "type": "boolean", "description": "Trim spaces, collapse double spaces, remove invisible characters and decode HTML entities in your original columns too. The cleaned values are always in the clean_* columns.", "default": true }, "maxRows": { "title": "Maximum rows", "minimum": 1, "maximum": 100000, "type": "integer", "description": "Stop after this many input rows. Example: 1000.", "default": 10000 }, "maxConcurrency": { "title": "Websites checked in parallel", "minimum": 1, "maximum": 20, "type": "integer", "description": "How many different websites are checked at the same time. Each site gets at most one request per redirect.", "default": 10 } } }, "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 } } } } } } } } } }