{ "openapi": "3.0.1", "info": { "title": "Website Contact & Tech Stack Scraper", "description": "Scrape any website for emails, phone numbers, social profiles, tech stack, ad pixels, chatbot, and a lead score. One clean record per domain. Bulk lead generation + MCP server for AI agents.", "version": "0.1", "x-build-id": "zgyGC7iu9yfOX9One" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/headply~website-intelligence-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-headply-website-intelligence-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/headply~website-intelligence-scraper/runs": { "post": { "operationId": "runs-sync-headply-website-intelligence-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/headply~website-intelligence-scraper/run-sync": { "post": { "operationId": "run-sync-headply-website-intelligence-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "Start URLs", "type": "array", "description": "List of websites to crawl, as a standard Apify request list. Each entry is an object with a `url`. Merged with the `websites` field.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "websites": { "title": "Websites (plain URLs)", "type": "array", "description": "Convenience list of plain website URLs, one per line. Merged with `startUrls`. At least one of `startUrls` or `websites` must be non-empty.", "default": [], "items": { "type": "string" } }, "maxPagesPerSite": { "title": "Max pages per site", "minimum": 1, "maximum": 200, "type": "integer", "description": "Hard cap on the number of pages crawled per domain. The default of 3 fetches the homepage plus the two highest-ranked contact pages (contact / about / team) and skips product/category sprawl — that's where the leads live. Raise for broader coverage; lower (e.g. 1) for homepage-only fastest mode.", "default": 3 }, "maxDepth": { "title": "Max crawl depth", "minimum": 0, "maximum": 10, "type": "integer", "description": "Maximum link depth from the start URL (homepage is depth 0).", "default": 2 }, "prioritizeContactPages": { "title": "Prioritize contact pages", "type": "boolean", "description": "Enqueue likely contact/about/team pages and footer links before generic internal links.", "default": true }, "renderJavaScript": { "title": "Render JavaScript", "enum": [ "auto", "always", "never" ], "type": "string", "description": "When to use a real browser. `auto` escalates to a browser only when a page looks JS-rendered; `always` renders every page; `never` uses HTTP only.", "default": "auto" }, "checkLiveAds": { "title": "Check live ads", "type": "boolean", "description": "Best-effort check of the Meta Ad Library and Google Ads Transparency Center for active ads. Slower and gated; may return null.", "default": false }, "captureScreenshot": { "title": "Capture homepage screenshot", "type": "boolean", "description": "Save a homepage screenshot to the key-value store and return its URL. Forces a browser render of the homepage.", "default": false }, "validateEmailMx": { "title": "Validate email MX records", "type": "boolean", "description": "DNS MX lookup for discovered email domains. No SMTP verification is ever performed.", "default": false }, "bypassProtection": { "title": "Bypass bot protection (slower, costs residential proxy)", "type": "boolean", "description": "When a site is blocked by Cloudflare's passive challenge, retry with a stealth browser over residential proxy. Off by default for speed/cost — most sites don't need it. Interactive CAPTCHAs (PerimeterX, DataDome, Akamai) are never attempted (unbeatable); those fail fast regardless of this flag.", "default": false }, "respectRobotsTxt": { "title": "Respect robots.txt", "type": "boolean", "description": "Honor each site's robots.txt rules while crawling.", "default": true }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Apify proxy settings. Datacenter proxy (the default) is fast and cost-effective and works for most sites. Switch to Residential only for sites that block datacenter IPs — it is far more expensive per GB and will increase your per-domain cost.", "default": { "useApifyProxy": true } }, "maxConcurrentDomains": { "title": "Max concurrent domains", "minimum": 1, "maximum": 20, "type": "integer", "description": "How many domains are crawled in parallel. Higher is faster for large lists; lower reduces memory pressure. Each domain still gets its own isolated crawl.", "default": 5 }, "maxConcurrency": { "title": "Max concurrency (pages per domain)", "minimum": 1, "maximum": 100, "type": "integer", "description": "Maximum number of pages fetched in parallel within each domain's crawl. Use 'Max concurrent domains' to control how many domains run at once.", "default": 10 }, "requestTimeoutSecs": { "title": "Request timeout (seconds)", "minimum": 5, "maximum": 300, "type": "integer", "description": "Per-request fetch/render budget in seconds. Higher values give slow or heavy JavaScript sites more time to render.", "default": 30 }, "maxRequestRetries": { "title": "Max request retries", "minimum": 0, "maximum": 10, "type": "integer", "description": "How many times to retry a failed request before giving up on that page.", "default": 1 }, "scoringWeights": { "title": "Lead scoring weights (advanced)", "type": "object", "description": "Optional override of the lead-score weights. Leave empty to use sensible defaults from scoring.py.", "default": {} } } }, "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 } } } } } } } } } }