{ "openapi": "3.0.1", "info": { "title": "Website Lead Extractor: Emails, Phones & Addresses", "description": "Turn a list of company websites into a clean B2B lead list. Extracts emails, phone numbers in E.164, postal addresses, PO boxes, VAT and company registration numbers and social profiles, verifies every email against DNS, and returns one row per company. Pay per company, never per page.", "version": "0.1", "x-build-id": "5ichlfal4HLsdf3av" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/f0rty7even~website-lead-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-f0rty7even-website-lead-extractor", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/f0rty7even~website-lead-extractor/runs": { "post": { "operationId": "runs-sync-f0rty7even-website-lead-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/f0rty7even~website-lead-extractor/run-sync": { "post": { "operationId": "run-sync-f0rty7even-website-lead-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "required": [ "startUrls" ], "properties": { "startUrls": { "title": "Websites to extract leads from", "type": "array", "description": "One or more company websites. Paste bare domains (northwind.co), full URLs (https://northwind.co/contact) or a whole spreadsheet column separated by commas or new lines. Every form of the same domain is merged, so a company is crawled and charged only once.", "items": { "type": "string" } }, "maxPagesPerDomain": { "title": "Max pages per website", "minimum": 1, "maximum": 25, "type": "integer", "description": "How many pages to read on each site. The homepage is always read, then the highest-value contact pages (contact, about, imprint, team, locations). Five is enough for almost every site: raising it finds slightly more on large sites and costs you nothing extra, because you are billed per company, not per page.", "default": 5 }, "verifyEmails": { "title": "Verify emails against DNS", "type": "boolean", "description": "Check every email's domain for MX records, flag disposable and free-mailbox addresses, and detect the mail provider (Google Workspace, Microsoft 365 and so on). Adds a second or two per site and removes the addresses that would bounce.", "default": true }, "enableBrowserFallback": { "title": "Retry with a browser when a site renders in JavaScript", "type": "boolean", "description": "If a site loads fine but publishes no contact details in its HTML, open it in a real browser and try again. Only fires on sites that need it. Turn it off for the fastest possible run on plain HTML sites.", "default": true }, "maxWebsites": { "title": "Max websites (spend cap)", "minimum": 1, "maximum": 100000, "type": "integer", "description": "Hard stop after this many websites, as a safety net on large inputs. Leave empty to process everything you supplied." }, "maxConcurrency": { "title": "Websites in parallel", "minimum": 1, "maximum": 30, "type": "integer", "description": "How many sites to work on at once. Raise it to finish large lists faster; lower it if you are being polite to a set of small servers.", "default": 10 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Proxy used to reach the websites. The default rotating datacenter proxy is included on every plan and works for most sites. If a site behind Cloudflare or a WordPress security plugin blocks it, switch to Residential.", "default": { "useApifyProxy": 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 } } } } } } } } } }