{ "openapi": "3.0.1", "info": { "title": "Website Lead Enricher", "description": "Extract emails, phones, social profiles, and company data from any website. CRM-ready B2B lead enrichment with HubSpot, Salesforce, and Pipedrive export modes. Quality score, WHOIS lookup, and E.164 phone normalization included.", "version": "0.0", "x-build-id": "iojJsmueZgBrGRj4y" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/operational_zirconia~website-lead-enricher/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-operational_zirconia-website-lead-enricher", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/operational_zirconia~website-lead-enricher/runs": { "post": { "operationId": "runs-sync-operational_zirconia-website-lead-enricher", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/operational_zirconia~website-lead-enricher/run-sync": { "post": { "operationId": "run-sync-operational_zirconia-website-lead-enricher", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "urls" ], "properties": { "urls": { "title": "URLs to scrape", "type": "array", "description": "List of URLs or domains to enrich. Each entry is fetched, parsed, and analysed for contact data (emails, phones, social links). Bare domains automatically get 'https://' prepended. Example: ['https://acme.com', 'stripe.com', 'www.example.org/contact']. Total runtime scales with the list size; processing runs in parallel up to 'maxConcurrency'.", "items": { "type": "string" } }, "maxConcurrency": { "title": "Max Concurrency", "minimum": 1, "maximum": 10, "type": "integer", "description": "Maximum number of URLs processed in parallel. Example: with 20 URLs and concurrency 5, the actor handles 5 at a time and queues the remaining 15. Higher values finish faster but may trigger rate limits or get your IP blocked by target sites; lower values are slower but safer. Recommended: 3-5 for small batches (< 50 URLs), 1-2 for large batches (50+ URLs).", "default": 5 }, "includeWhois": { "title": "Include WHOIS", "type": "boolean", "description": "When true, each output row includes a 'whois' object with domain registration data: registrar name, creation/expiration dates, and registrant organization (when public per GDPR redaction). When false, only scraped page data is returned and no WHOIS lookup is performed. Example: enabling this for 'acme.com' adds {registrar: 'GoDaddy', createdAt: '2010-03-15', registrantOrg: 'ACME Corp'} to that row; disabling it skips the lookup entirely and saves ~1 second per URL. Default is false to minimize per-domain cost — enable explicitly when you need registrant data.", "default": false }, "skipEmailPatternFinder": { "title": "Skip email pattern finder", "type": "boolean", "description": "Skip Step 2 (email pattern detection) — when true, the pipeline emits a synthetic 'pattern' step with status 'skipped' and no DNS lookups are performed. When false (default), Step 2 runs and adds emailPattern, patternConfidence, generatedEmails[], patternAnalysis, alternateEmailPatterns, and dataQuality to every record. See docs/NextSteps/EmailPatternFinder.md.", "default": false }, "searchWhois": { "title": "Search WHOIS for registrant email", "type": "boolean", "description": "Mine the WHOIS registrant email (when includeWhois is true and the registry exposes it) and add it to generatedEmails[] with source 'whois-registrant'. No-op when skipEmailPatternFinder is true. Default false.", "default": false }, "goal": { "title": "Outreach goal", "enum": [ "quick-outreach", "high-deliverability", "max-coverage" ], "type": "string", "description": "Tunes patternAnalysis.bounceRiskBucket thresholds and sequenceStrategy per outreach intent. 'quick-outreach' is strict — only the safest ~20% of generated patterns ship (sequenceStrategy: 'single-shot'). 'high-deliverability' (default) is medium — top ~60% ship (sequenceStrategy: 'fallback'). 'max-coverage' is loose — top ~95% ship (sequenceStrategy: 'progressive'). See docs/NextSteps/EmailPatternFinder.md §goal semantics.", "default": "high-deliverability" }, "hunterApiKey": { "title": "Hunter.io API key (optional)", "type": "string", "description": "Optional Hunter.io API key — when set, the Step 2 pipeline additionally pulls emails from Hunter.io's domain-search API and adds them to generatedEmails[] with source 'hunter-api'. Failures (401, 429, network) populate patternAnalysis.hunterError without failing the step. Free tier is fine for low-volume runs. Leave empty to skip. See docs/NextSteps/EmailPatternFinder.md." }, "csvMode": { "title": "CSV Export Mode", "enum": [ "standard", "hubspot", "salesforce", "pipedrive" ], "type": "string", "description": "Format of the generated CSV. 'standard' (generic - 18 columns, booleans true/false), 'hubspot' (First Name, Last Name, Email, Company, Phone, LinkedIn Profile URL - booleans true/false), 'salesforce' (FirstName, LastName, Email, Company, Phone, LeadSource - booleans TRUE/FALSE), 'pipedrive' (name, email, phone, org_name, linkedin - booleans 1/0). Default: 'standard'. Use the mode matching your CRM to import the CSV directly without mapping columns. In Apify cloud, the CRM-ready CSV is written to the Key-value store tab as OUTPUT__CSV. Locally, it is written to LOCAL_OUTPUT_DIR with the mode included in the file name.", "default": "standard" }, "companyTypes": { "title": "Company Types Filter", "type": "array", "description": "Allow-list filter for company types. Each input website is heuristically classified as one of the supported verticals (saas, saas_b2b, agency, ecommerce, legal, medical, consulting, manufacturing, media, nonprofit, education, realestate, finance, or 'other' when no rule matches). When this list is non-empty, only records whose inferred companyType appears in the list are kept in the output; the rest are marked with passedCompanyTypeFilter=false in the dataset and dropped from the local CSV / JSON export. When this list is empty (default), every record is kept regardless of companyType. Note: 'other' is intentionally not in the enum — it is the fallback label when no rule matches, so filtering on it is meaningless.", "items": { "type": "string", "enum": [ "saas", "saas_b2b", "agency", "ecommerce", "legal", "medical", "consulting", "manufacturing", "media", "nonprofit", "education", "realestate", "finance" ], "enumTitles": [ "SaaS", "SaaS B2B", "Agency", "E-commerce", "Legal", "Medical", "Consulting", "Manufacturing", "Media", "Nonprofit", "Education", "Real estate", "Finance" ] }, "default": [] }, "proxyConfiguration": { "title": "Proxy Configuration", "type": "object", "description": "Apify proxy passthrough. **Default is OFF (no proxy)** — the actor makes direct HTTP requests when this section is left untouched. Flip 'Use Apify Proxy' on to route through the Apify-managed pool. Tier matters: **DATACENTER** is US-only and ~$2.50/GB (cheap US scrapes, blocked by Cloudflare/Akamai); **RESIDENTIAL** supports 200+ countries (DE, FR, UK, JP, BR, etc.) and is ~$12/GB (bypasses most anti-bot, required for non-US geo-targeting). Use 'apifyProxyCountry' to pin exit-node geography. For BYO proxies, set 'useApifyProxy' off and provide 'proxyUrls' in 'scheme://user:pass@host:port' form." } } }, "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 } } } } } } } } } }