{ "openapi": "3.0.1", "info": { "title": "Website Contact Scraper — Bulk Email, Phone & Social Finder", "description": "Turn a list of domains into one clean row per website: emails, phone numbers, 18 social profiles, postal address, contact-page URL and mail provider (MX/SPF/DMARC), read from the homepage plus its contact, about and imprint pages. You only pay for domains where a contact is actually found.", "version": "0.1", "x-build-id": "WFt4CLWxQDC7t2PLJ" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/scrapersdelight~website-contact-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-scrapersdelight-website-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/scrapersdelight~website-contact-scraper/runs": { "post": { "operationId": "runs-sync-scrapersdelight-website-contact-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/scrapersdelight~website-contact-scraper/run-sync": { "post": { "operationId": "run-sync-scrapersdelight-website-contact-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "domains": { "title": "Company domains or website URLs", "type": "array", "description": "One company website per line — `acme.com`, `www.acme.com` or `https://acme.com/anything` all work, and duplicates are collapsed by host. Each domain returns exactly ONE row. Leave this empty and the actor runs a small built-in demo list so you can see the output shape before spending anything.", "default": [], "items": { "type": "string" } }, "maxPagesPerDomain": { "title": "Max pages per domain", "minimum": 1, "maximum": 10, "type": "integer", "description": "Total pages fetched per website, INCLUDING the homepage. The default of 3 is the homepage plus the two best contact-ish hops (contact → imprint → privacy → about → support → locations), which is where essentially all of the extra email yield sits. Raising it finds a little more on big sites and costs you nothing extra — the price is per domain, not per page.", "default": 3 }, "useSitemapFallback": { "title": "Use sitemap.xml to find the contact page", "type": "boolean", "description": "When the homepage navigation exposes no contact/about/imprint link at all (common on JS-heavy sites with a rendered footer), fetch `/sitemap.xml` and pick the contact page out of it. In recon this recovered a `/contact` page on 2 of the 3 domains where nav discovery found nothing. One extra request, only on domains that need it.", "default": true }, "includeDnsSignals": { "title": "Include mail-provider signals (MX / SPF / DMARC)", "type": "boolean", "description": "Resolve the domain's MX, SPF and DMARC records and name the mail provider (Google Workspace, Microsoft 365, …). This is DOMAIN-level deliverability signal — it tells you the domain accepts mail and who runs it. It is NOT mailbox verification; see the README's honest-limits section.", "default": true }, "respectRobotsTxt": { "title": "Respect robots.txt", "type": "boolean", "description": "Fetch each site's robots.txt and skip any page its `User-agent: *` rules disallow. Off by default because most sites' robots.txt is written for search crawlers and blocking a `/contact` page is rare; turn it on if your own policy requires it. Skipped pages are named in the row's `notes`.", "default": false }, "requestConcurrency": { "title": "Concurrent domains", "minimum": 1, "maximum": 30, "type": "integer", "description": "How many websites to work on at once. 12 is the tested sweet spot: pushing much higher causes footer/contact-page misses through connection contention, which read as false 'no email found'.", "default": 12 }, "requestTimeoutSecs": { "title": "Request timeout (seconds)", "minimum": 5, "maximum": 60, "type": "integer", "description": "Per-request timeout. Each page gets up to 3 attempts with a freshly rotated proxy session, so a slow site still gets a fair chance before it is recorded as `timeout`.", "default": 15 }, "maxDomains": { "title": "Max domains", "minimum": 0, "type": "integer", "description": "Stop after this many domains from your list. 0 = no limit. Useful for a cheap first pass over the top of a big list.", "default": 0 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Defaults to Apify Proxy's automatic (datacenter) pool — 20/20 test domains returned 200 through it, and it keeps the run cheap. Switch to RESIDENTIAL only for targets that block datacenter IPs: it is slower, and in testing only 7 of 12 domains succeeded on the FIRST attempt (the actor retries with a rotated session, so they all still returned data). You can also supply your own proxies here.", "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 } } } } } } } } } }