{ "openapi": "3.0.1", "info": { "title": "Contact Details Extractor", "description": "The cheapest contact scraper on Apify. Extract emails, phone numbers, company names, addresses & 25+ social profiles at $0.001/page - 50% less than competitors. Smart crawling auto-finds contact pages, bypasses Cloudflare protection, browser mode for JS sites, sitemap discovery.", "version": "1.0", "x-build-id": "XlOlbhSTPnZBZd5GP" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/worshipful_knife~contact-details-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-worshipful_knife-contact-details-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/worshipful_knife~contact-details-extractor/runs": { "post": { "operationId": "runs-sync-worshipful_knife-contact-details-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/worshipful_knife~contact-details-extractor/run-sync": { "post": { "operationId": "run-sync-worshipful_knife-contact-details-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": "Start URLs", "type": "array", "description": "List of websites to extract contact details from. Plain domains (example.com) and full URLs (https://example.com/about) both work.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "maxPagesPerStartUrl": { "title": "Max pages per website", "minimum": 1, "maximum": 500, "type": "integer", "description": "Maximum number of pages to crawl per start URL. Lower = cheaper, faster. Higher = more thorough.", "default": 20 }, "maxDepth": { "title": "Max link depth", "minimum": 0, "maximum": 5, "type": "integer", "description": "How many clicks away from the start URL to follow. Depth 1 = only the homepage; depth 2 = homepage + linked pages.", "default": 2 }, "sameDomain": { "title": "Stay on same domain", "type": "boolean", "description": "Only follow links that stay on the same registered domain as the start URL.", "default": true }, "useSitemap": { "title": "Use sitemap.xml", "type": "boolean", "description": "Discover pages via /sitemap.xml. When enabled, the crawler prioritises pages with /contact, /about, /team, /imprint in the URL.", "default": false }, "browserMode": { "title": "Browser rendering mode", "enum": [ "off", "auto", "on" ], "type": "string", "description": "off = fast HTTP only. on = always render with a real browser (Playwright). auto = HTTP first, fall back to browser if the page looks empty (best balance).", "default": "auto" }, "mergeContacts": { "title": "Merge contacts per domain", "type": "boolean", "description": "Combine all data found across pages of the same domain into a single record. Disable to get one record per page.", "default": true }, "extractAddresses": { "title": "Extract physical addresses", "type": "boolean", "description": "Parse postal addresses from schema.org markup, footers, and contact pages.", "default": true }, "extractCompanyInfo": { "title": "Extract company info", "type": "boolean", "description": "Detect company name, description, and logo via og:site_name, schema.org Organization, and title heuristics.", "default": true }, "decodeCloudflareEmails": { "title": "Decode Cloudflare-protected emails", "type": "boolean", "description": "Decode emails hidden behind Cloudflare's email obfuscation (data-cfemail attribute).", "default": true }, "phoneCountryHint": { "title": "Phone country hint", "type": "string", "description": "Default ISO country code (US, GB, FR, DE, etc.) for parsing phone numbers without an international prefix. Leave empty for auto-detection from the page." }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "maximum": 50, "type": "integer", "description": "How many pages to crawl in parallel. Higher = faster but more likely to be rate-limited.", "default": 10 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Proxy settings. Datacenter proxy is the default and works for most sites. Switch to RESIDENTIAL for sites that block datacenter IPs.", "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 } } } } } } } } } }