{ "openapi": "3.0.1", "info": { "title": "Website Contact Scraper – Emails, Phones, Socials", "description": "Scrape a business's contact details off its website: every email address and validated phone number, social and messaging profiles, postal address and contact form — one row per site. It reads the page you give plus the few pages likeliest to carry contacts, because a home page rarely does.", "version": "0.1", "x-build-id": "JVlaQQErX5cfN2xfL" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/simple.actors~website-contacts/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-simple.actors-website-contacts", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/simple.actors~website-contacts/runs": { "post": { "operationId": "runs-sync-simple.actors-website-contacts", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/simple.actors~website-contacts/run-sync": { "post": { "operationId": "run-sync-simple.actors-website-contacts", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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 (URL editor)", "type": "array", "description": "The websites to look up, one per entry. Give the home page — the actor finds the contact page itself. Each website produces exactly one row, however many of its pages had to be read.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "urls": { "title": "Websites (plain list, bare hosts OK)", "type": "array", "description": "The same thing as \"Websites\", as a plain list — easier to paste a column out of a spreadsheet, and it accepts a bare host such as example.com with no https:// in front. Both inputs are read; giving either one is enough.", "items": { "type": "string" } }, "maxPagesPerSite": { "title": "Pages to read per website (your cost ceiling)", "minimum": 1, "maximum": 20, "type": "integer", "description": "How many pages of each site may be read — and, because this Actor charges per page read, your ceiling on what each website costs. The first page is the address you gave; the rest are that site's own links, ranked by how likely each is to carry contact details — a contact page, an imprint, an about or team page. You are charged only for pages actually read, which averages 3.9 at the default of 5, because guessed addresses that turn out not to exist are never charged. Set it to 1 to read only the page you gave: the cheapest possible run, and it finds roughly half as many email addresses, because most sites do not publish one on the home page. Above about 6 there is little left to find.", "default": 5 }, "renderJs": { "title": "When to run the page's JavaScript", "enum": [ "auto", "always", "never" ], "type": "string", "description": "\"auto\" reads the served HTML and opens a browser only when that HTML turned out to hold nothing at all — no email, no phone, no social link and nowhere to go next — which is what a JavaScript-built shell looks like. It is the right setting for almost everyone and the cheapest. \"always\" renders every page: several times slower and dearer. \"never\" refuses the browser, so a site that needs one comes back as an error row.", "default": "auto" }, "countryHint": { "title": "Country for phone numbers without a country code", "type": "string", "description": "A two-letter country code, such as GB, US or DE. It is used only to read phone numbers written the local way, without a country code in front — \"020 7946 0958\" is a real number in the UK and not a number anywhere else, so a guess has to be made. Left empty, the actor takes the country from the site's own structured data, then from its domain ending, and falls back to US. Whichever was used is reported on every row as phoneCountry." }, "proxy": { "title": "Proxy (datacenter is usually enough)", "type": "object", "description": "Defaults to Apify's datacenter proxy, which is included in every plan and is enough for almost every site. Switch to residential if sites answer with challenge pages — every retry already lands on a different address, so a challenge that survives that is usually about the address pool rather than the request.", "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 } } } } } } } } } }