{ "openapi": "3.0.1", "info": { "title": "Contact Details Scraper — Emails, Phones, Socials from Websites", "description": "Extract emails, phone numbers and social profiles (Facebook, Instagram, LinkedIn, X, YouTube, TikTok, WhatsApp...) from a list of websites or domains: one merged row per domain.", "version": "0.1", "x-build-id": "wIw3xwX9GDh4o3PTM" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/tortuga~contact-details-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-tortuga-contact-details-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/tortuga~contact-details-scraper/runs": { "post": { "operationId": "runs-sync-tortuga-contact-details-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/tortuga~contact-details-scraper/run-sync": { "post": { "operationId": "run-sync-tortuga-contact-details-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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 or domains to scan, e.g. https://acme.com or acme.co.uk. Each domain becomes one result row; several URLs of the same domain are crawled together. You can also upload a text/CSV file or link one (e.g. a Google Sheets CSV export).", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "urlsText": { "title": "Or paste a list of domains / URLs", "type": "string", "description": "Paste websites or domains: one per line, comma-separated, or a whole CSV export (every column holding a website or domain is used, other columns are ignored)." }, "maxPagesPerDomain": { "title": "Max pages per domain", "minimum": 1, "maximum": 50, "type": "integer", "description": "Pages read per website, start page included. Contact, Impressum/imprint, About, Team, support and legal pages are read first, then other pages. 5 finds most published contacts; pages beyond 5 are charged as 'extra page' (only for domains where contacts were found).", "default": 5 }, "maxDepth": { "title": "Crawl depth", "minimum": 0, "maximum": 5, "type": "integer", "description": "How many clicks away from the start page to go: 0 = start page only, 1 = the start page and the pages it links to (default), 2 = also pages linked from those.", "default": 1 }, "sameDomainEmailsOnly": { "title": "Only emails on the website's own domain", "type": "boolean", "description": "Keep only addresses on the site's own domain (info@acme.com for acme.com, also mail.acme.com). Drops web agency, partner and free-mail (gmail.com...) addresses that the site shows.", "default": false }, "includeSubdomains": { "title": "Include subdomains", "type": "boolean", "description": "Also crawl other subdomains of the site (shop.acme.com, support.acme.com) like the main one. Off: only the domain itself, with or without www.; contact, imprint, about and team pages on other subdomains are still read when the site links to them.", "default": false }, "respectRobotsTxt": { "title": "Respect robots.txt", "type": "boolean", "description": "Follow each site's robots.txt rules: pages it disallows are not visited. Recommended.", "default": true }, "includePageRows": { "title": "Also output one row per page", "type": "boolean", "description": "Besides the merged row per domain, output one row per visited page (type 'page') with what was found on that page: handy to see where an email was published. Page rows are free.", "default": false }, "maxItems": { "title": "Max domains", "minimum": 1, "type": "integer", "description": "Stop after this many domain rows. Leave empty to process the whole list." }, "maxConcurrency": { "title": "Websites at once", "minimum": 1, "maximum": 50, "type": "integer", "description": "Websites visited in parallel. Every site gets at most 3 requests at a time with pauses in between, so a higher value is still polite to each site.", "default": 10 }, "defaultCountry": { "title": "Country for local phone numbers", "type": "string", "description": "Two-letter country code used to read phone numbers written without +country code when the site does not reveal its country (domain ending like .de / .co.uk, address data, page language). Default: US." }, "onlyNewOrChanged": { "title": "Only new or changed domains", "type": "boolean", "description": "Remember what earlier runs of this list found and output only domains that are new or whose emails, phone numbers or social profiles changed. Use with a Schedule; unchanged domains are not output and not charged.", "default": false }, "monitoringKey": { "title": "Monitoring key", "type": "string", "description": "Name for this watch, so several schedules on the same list stay separate; defaults to a key derived from the input." }, "proxyConfiguration": { "title": "Proxy", "type": "object", "description": "Apify datacenter proxy (default) works for most websites. Pick the Residential group for lists of sites that block datacenter IPs (Apify bills residential traffic per GB).", "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 } } } } } } } } } }