{ "openapi": "3.0.1", "info": { "title": "Website Contact & Tech Extractor — Emails, Phones, Stack", "description": "Give it company domains and it reads each company's own website for published emails, phone numbers, social profiles, VAT numbers and the technologies they run — respecting robots.txt, with no third-party database involved.", "version": "0.1", "x-build-id": "J3mGxizfI8WN4mk8K" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/dalbian~website-contact-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-dalbian-website-contact-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/dalbian~website-contact-extractor/runs": { "post": { "operationId": "runs-sync-dalbian-website-contact-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/dalbian~website-contact-extractor/run-sync": { "post": { "operationId": "run-sync-dalbian-website-contact-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "properties": { "domains": { "title": "Domains or URLs", "type": "array", "description": "Company domains or full URLs, one per line — apify.com, https://www.example.fr, example.co.uk. Each is visited on its own website only; nothing else is consulted.", "default": [ "apify.com" ], "items": { "type": "string" } }, "maxPagesPerSite": { "title": "Pages per site", "minimum": 1, "maximum": 100, "type": "integer", "description": "How many pages to read per site. Contact, about and legal-notice pages are always visited first, so 10 to 15 finds the details on most sites. Raise it for large sites that bury their contact page.", "default": 12 }, "concurrency": { "title": "Sites in parallel", "minimum": 1, "maximum": 20, "type": "integer", "description": "How many different sites to process at once. Pages within one site are always read one after another, so a single site is never hammered.", "default": 5 }, "respectRobotsTxt": { "title": "Respect robots.txt", "type": "boolean", "description": "Obey each site's robots.txt and skip what it disallows. Leave this on: it is what makes this Actor safe to run on a client list, and a site that forbids crawling is reported as such rather than silently skipped.", "default": true }, "extractEmails": { "title": "Extract emails", "type": "boolean", "description": "Collect published email addresses, with obvious placeholders and image filenames filtered out. A generic address such as contact@ is chosen as the primary one when present, because it is the one meant for inbound contact.", "default": true }, "extractPhones": { "title": "Extract phone numbers", "type": "boolean", "description": "Collect phone numbers, preferring those behind a tel: link since loose digit runs in page text are often dates or prices.", "default": true }, "extractSocialProfiles": { "title": "Extract social profiles", "type": "boolean", "description": "Collect LinkedIn, Facebook, Instagram, X, YouTube, TikTok, GitHub and WhatsApp links, ignoring share buttons.", "default": true }, "extractTechnologies": { "title": "Detect technologies", "type": "boolean", "description": "Detect the CMS, e-commerce platform, JavaScript framework, analytics, chat, payment and marketing tools in use — Shopify, WordPress, HubSpot, Stripe, Klaviyo and around forty more. This is how sales teams find everyone running a given stack.", "default": true }, "extractIdentifiers": { "title": "Extract legal identifiers", "type": "boolean", "description": "Pick up VAT numbers and French SIRET numbers from legal-notice pages, which lets you join a website to an official company record.", "default": true }, "maxSites": { "title": "Maximum sites", "minimum": 1, "maximum": 50000, "type": "integer", "description": "Hard stop on how many sites this run processes. Set it low for a trial before committing a full list.", "default": 500 } } }, "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 } } } } } } } } } }