{ "openapi": "3.0.1", "info": { "title": "Website Email & Contact Scraper", "description": "Crawl any list of websites and get their emails, phone numbers and social profiles, sorted by inbox type (editorial, general, person, support) with the page each one was found on.", "version": "0.1", "x-build-id": "FIcAn8h6Zmfd3eZFK" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/avoca_code~website-email-contact-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-avoca_code-website-email-contact-scraper", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/avoca_code~website-email-contact-scraper/runs": { "post": { "operationId": "runs-sync-avoca_code-website-email-contact-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/avoca_code~website-email-contact-scraper/run-sync": { "post": { "operationId": "run-sync-avoca_code-website-email-contact-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "startUrls": { "title": "Websites", "type": "array", "description": "Websites to scrape. A homepage URL or a bare domain both work (example.com). The crawl stays on each site's own domain.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "domains": { "title": "Domains (plain list)", "type": "array", "description": "Optional: paste domains one per line instead of using the Websites field. Duplicates across both fields are removed.", "items": { "type": "string" } }, "emailFilter": { "title": "Which emails to return", "enum": [ "all", "outreach" ], "type": "string", "description": "'All emails' returns every address found. 'Outreach inboxes only' keeps editorial / partnership / advertising inboxes, info@ / contact@, named people and support@, and drops things like jobs@, noreply-style and team@ addresses.", "default": "all" }, "includeOffDomainEmails": { "title": "Include emails on other domains", "type": "boolean", "description": "Keep emails whose domain differs from the website (e.g. a parent company or agency address shown on the contact page). Each email is flagged with sameDomain either way.", "default": true }, "includePhones": { "title": "Phone numbers", "type": "boolean", "description": "Extract phone numbers, validated with Google's libphonenumber.", "default": true }, "includeSocials": { "title": "Social profiles", "type": "boolean", "description": "Extract LinkedIn, X/Twitter, Facebook, Instagram, YouTube, TikTok and other profile links.", "default": true }, "includeTechnologies": { "title": "Tech stack", "type": "boolean", "description": "Detect the homepage's technologies (CMS, analytics, CDN...).", "default": false }, "maxPagesPerWebsite": { "title": "Max pages per website", "minimum": 1, "maximum": 50, "type": "integer", "description": "Contact, about, team, press, advertise and partner pages are crawled first, so 10-20 pages finds most inboxes.", "default": 20 }, "maxSecondsPerWebsite": { "title": "Time limit per website (seconds)", "minimum": 20, "maximum": 600, "type": "integer", "description": "Hard time budget for one website, so a slow site can't stall the run.", "default": 120 }, "useBrowserFallback": { "title": "Use a real browser when needed", "type": "boolean", "description": "Switch to Chrome for sites that render with JavaScript or show a bot check. Turn off for a faster, cheaper run on simple sites.", "default": true }, "maxConcurrency": { "title": "Websites in parallel", "minimum": 1, "maximum": 10, "type": "integer", "description": "How many websites to crawl at the same time.", "default": 5 }, "proxyConfiguration": { "title": "Proxy", "type": "object", "description": "Most sites work without a proxy. For sites behind Cloudflare or other bot checks (they come back with error 'blocked by bot protection'), use Apify Proxy with the RESIDENTIAL group.", "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 } } } } } } } } } }