{
"openapi": "3.0.1",
"info": {
"title": "Website Contact Details Crawler",
"description": "Crawl any list of websites and extract every email address, phone number (E.164) and social media profile, deduplicated into one clean record per domain. Fast HTTP-only crawler with pay-per-result pricing.",
"version": "0.0",
"x-build-id": "10XJdVHZ9fepbzw7t"
},
"servers": [
{
"url": "https://api.apify.com/v2"
}
],
"paths": {
"/acts/yasaslive~website-contact-details-crawler/run-sync-get-dataset-items": {
"post": {
"operationId": "run-sync-get-dataset-items-yasaslive-website-contact-details-crawler",
"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": {
"$ref": "#/components/schemas/inputSchema"
}
}
}
},
"parameters": [
{
"name": "token",
"in": "query",
"required": true,
"schema": {
"type": "string"
},
"description": "Enter your Apify token here"
}
],
"responses": {
"200": {
"description": "OK"
}
}
}
},
"/acts/yasaslive~website-contact-details-crawler/runs": {
"post": {
"operationId": "runs-sync-yasaslive-website-contact-details-crawler",
"x-openai-isConsequential": false,
"summary": "Executes an Actor and returns information about the initiated run in response.",
"tags": [
"Run Actor"
],
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"$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": {
"$ref": "#/components/schemas/runsResponseSchema"
}
}
}
}
}
}
},
"/acts/yasaslive~website-contact-details-crawler/run-sync": {
"post": {
"operationId": "run-sync-yasaslive-website-contact-details-crawler",
"x-openai-isConsequential": false,
"summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.",
"tags": [
"Run Actor"
],
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"$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": "Websites to scan",
"type": "array",
"description": "Website addresses or plain domains (e.g. acme-bakery.com). You can also upload a text file or link a Google Sheet with one URL per line. Each website becomes one result row; duplicates of the same website are merged.",
"default": [
{
"url": "https://russanddaughters.com"
},
{
"url": "https://voodoodoughnut.com"
},
{
"url": "https://levainbakery.com"
}
],
"items": {
"type": "object",
"required": [
"url"
],
"properties": {
"url": {
"type": "string",
"title": "URL of a web page",
"format": "uri"
}
}
}
},
"maxPagesPerDomain": {
"title": "Max pages per website",
"minimum": 1,
"maximum": 1000,
"type": "integer",
"description": "The most pages scanned on any one website. Contact, about and team pages are scanned first, so 10–20 is usually enough. Each scanned page is billed as one page-crawled event.",
"default": 20
},
"maxDepth": {
"title": "Max link depth",
"minimum": 0,
"maximum": 10,
"type": "integer",
"description": "How many clicks away from the start page the crawler may go. 0 = only the start page, 1 = pages linked from it, 2 = one level further.",
"default": 2
},
"maxResults": {
"title": "Max websites",
"minimum": 1,
"maximum": 100000,
"type": "integer",
"description": "Stop after this many websites have been delivered. Useful to cap spend on large lists.",
"default": 50
},
"prioritizePaths": {
"title": "Pages to scan first",
"type": "array",
"description": "URL paths most likely to hold contact details. Links matching these (e.g. /en/contact-us/ matches /contact-us) are scanned before any other page.",
"default": [
"/contact",
"/contact-us",
"/about",
"/about-us",
"/team",
"/impressum",
"/kontakt"
],
"items": {
"type": "string"
}
},
"sameDomainOnly": {
"title": "Stay on the exact same domain",
"type": "boolean",
"description": "On: only pages on the website's own domain (www or not) are scanned. Off: subdomains such as shop.acme.com or blog.acme.com are scanned too. Other websites are never followed.",
"default": true
},
"extractPhones": {
"title": "Extract phone numbers",
"type": "boolean",
"description": "Find and validate phone numbers and return them in international E.164 format alongside the original text.",
"default": true
},
"extractSocials": {
"title": "Extract social media profiles",
"type": "boolean",
"description": "Find links to Facebook, Instagram, LinkedIn (company and personal), X/Twitter, YouTube, TikTok, Pinterest, GitHub, Threads and Bluesky profiles. Share buttons and individual posts are ignored.",
"default": true
},
"phoneCountryHint": {
"title": "Default phone country",
"pattern": "^[A-Za-z]{2}$",
"type": "string",
"description": "Two-letter country code (e.g. US, GB, DE, AU) used to understand phone numbers written without a +country prefix. Numbers written with a + prefix are recognised for every country.",
"default": "US"
},
"respectRobotsTxt": {
"title": "Respect robots.txt",
"type": "boolean",
"description": "On (recommended): pages a website asks crawlers not to visit are skipped. If you turn this off, you are responsible for making sure you are allowed to crawl the websites.",
"default": true
},
"maxRequestRetries": {
"title": "Retries per page",
"minimum": 0,
"maximum": 10,
"type": "integer",
"description": "How many times a failed or blocked page is retried (with a new IP and increasing wait) before giving up. Failed pages are never billed.",
"default": 3
},
"proxyConfiguration": {
"title": "Proxy",
"type": "object",
"description": "Apify Proxy (datacenter) works for almost all small-business websites. Switch to residential proxies only if many websites block the crawler.",
"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
},
"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
}
}
}
}
}
}
}
}
}
}