{ "openapi": "3.0.1", "info": { "title": "Website Contact Finder – Emails, Phones & Social Links", "description": "Find emails, phone numbers and social media profiles (LinkedIn, X/Twitter, Facebook, Instagram, YouTube, TikTok) on any list of company websites. Crawls contact, about, impressum and legal pages, one clean row per domain. Pay only for domains where contacts are found.", "version": "0.1", "x-build-id": "N4zQKXiEVq6pVcrdF" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/gazidev~website-contact-finder/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-gazidev-website-contact-finder", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/gazidev~website-contact-finder/runs": { "post": { "operationId": "runs-sync-gazidev-website-contact-finder", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/gazidev~website-contact-finder/run-sync": { "post": { "operationId": "run-sync-gazidev-website-contact-finder", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "urls": { "title": "Websites (domains or URLs)", "type": "array", "description": "Company websites to scan, e.g. `acme.com` or `https://www.acme.de/en/`. `https://` is added automatically. Each domain is processed once and returns one row.", "default": [ "hawksheadrelish.com", "puccinibomboni.com", "fairmountbagel.com" ], "items": { "type": "string" } }, "bulkText": { "title": "Bulk list (paste text or CSV)", "type": "string", "description": "Paste a big list: one domain per line, comma/semicolon separated, or a whole CSV export (the first cell that looks like a domain/URL in each row is used)." }, "sourceFileUrl": { "title": "Bulk list file URL (TXT/CSV)", "type": "string", "description": "Public URL of a .txt or .csv file with domains/URLs (e.g. a Google Sheets 'publish to web' CSV link)." }, "maxPagesPerSite": { "title": "Max pages per website", "minimum": 1, "maximum": 50, "type": "integer", "description": "Homepage + the most promising pages (contact, about, impressum/imprint, team, legal, footer links). 10 is enough for most small business sites. The price per domain is the same whatever you choose.", "default": 10 }, "maxDepth": { "title": "Max link depth", "minimum": 0, "maximum": 3, "type": "integer", "description": "0 = homepage only, 1 = homepage + contact-like pages linked from it, 2 = also contact-like pages linked from those (e.g. Contact → Locations).", "default": 2 }, "extractEmails": { "title": "Emails", "type": "boolean", "description": "Find email addresses (mailto links, text, obfuscated `name [at] domain [dot] com`, Cloudflare-protected emails, schema.org). Junk (image names, Sentry/Wix tracking addresses, placeholders) is filtered out.", "default": true }, "extractPhones": { "title": "Phone numbers", "type": "boolean", "description": "Find phone numbers (tel: links, schema.org, text) and normalize them with Google's libphonenumber (international + E.164 format, country, mobile/landline, fax flagged).", "default": true }, "extractSocials": { "title": "Social media profiles", "type": "boolean", "description": "LinkedIn, X/Twitter, Facebook, Instagram, YouTube, TikTok, GitHub and Pinterest profile links (share buttons and post links are ignored).", "default": true }, "verifyEmailDomains": { "title": "Check email domains (DNS MX)", "type": "boolean", "description": "Check that each email's domain can receive mail (MX record). Emails on dead domains are moved out of `emails` (still listed in `emailDetails` with `mxValid: false`).", "default": true }, "phoneCountry": { "title": "Default phone country (ISO code)", "type": "string", "description": "Two-letter country code used to read local-format numbers like `030 1234567`, e.g. `DE`, `GB`, `US`. Leave empty to detect it per site from the country domain (.de, .co.uk...) and page language." }, "includePageDetails": { "title": "Include per-page details", "type": "boolean", "description": "Add a `pages` array to every row: each crawled URL with the emails, phones and social links found on it.", "default": false }, "maxSites": { "title": "Max websites", "minimum": 0, "type": "integer", "description": "Stop after this many websites (0 = no limit). Useful to test a big list cheaply.", "default": 0 }, "respectRobotsTxt": { "title": "Respect robots.txt", "type": "boolean", "description": "Skip pages disallowed by the site's robots.txt and honor Crawl-delay (max 5 s). Recommended.", "default": true }, "maxConcurrency": { "title": "Websites in parallel", "minimum": 1, "maximum": 50, "type": "integer", "description": "How many websites are crawled at the same time. Each website gets at most 2 parallel requests, so crawling stays polite.", "default": 10 }, "requestTimeoutSecs": { "title": "Request timeout (seconds)", "minimum": 3, "maximum": 120, "type": "integer", "description": "Per-request timeout. Failed requests are retried.", "default": 20 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Optional. Not needed for most sites.", "default": { "useApifyProxy": 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 } } } } } } } } } }