{ "openapi": "3.0.1", "info": { "title": "Contact Scraper BR — Email, WhatsApp + Receita Federal (CNPJ)", "description": "Bulk website contact scraper for Brazilian B2B lead enrichment. Finds emails, phones, WhatsApp links, contact pages, forms, and social profiles — then exports a CRM-ready CSV (one row per company, 26 columns) that imports directly into Google Sheets, Excel, Pipedrive, HubSpot, or RD Station.", "version": "0.2", "x-build-id": "1gefKZaFUPlsaaSgo" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/joaosbp~website-contact-finder-br/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-joaosbp-website-contact-finder-br", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/joaosbp~website-contact-finder-br/runs": { "post": { "operationId": "runs-sync-joaosbp-website-contact-finder-br", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/joaosbp~website-contact-finder-br/run-sync": { "post": { "operationId": "run-sync-joaosbp-website-contact-finder-br", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "Business websites", "type": "array", "description": "Public business website URLs to scan for contact channels.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "maxItems": { "title": "Maximum websites", "minimum": 1, "maximum": 5000, "type": "integer", "description": "Maximum number of websites processed in one run.", "default": 10 }, "maxConcurrency": { "title": "Concurrent websites", "minimum": 1, "maximum": 10, "type": "integer", "description": "Number of websites processed concurrently. Use a lower value with browser rendering.", "default": 3 }, "useBrowser": { "title": "Render JavaScript pages", "type": "boolean", "description": "Use Playwright for JavaScript-heavy websites. Keep disabled for faster and cheaper HTTP processing.", "default": false }, "followContactPages": { "title": "Follow contact pages", "type": "boolean", "description": "Follow same-domain contact/support links discovered on each homepage and merge their contact channels into one result.", "default": false }, "maxSecondaryPages": { "title": "Maximum secondary pages per website", "minimum": 0, "maximum": 5, "type": "integer", "description": "Strict per-domain budget for discovered contact pages. Only used when contact-page following is enabled.", "default": 2 }, "maxRetries": { "title": "Maximum retries", "minimum": 0, "maximum": 5, "type": "integer", "description": "Retry attempts for transient network, timeout, 429, or server errors.", "default": 2 }, "requestTimeoutSecs": { "title": "Request timeout seconds", "minimum": 5, "maximum": 120, "type": "integer", "description": "Maximum time to wait for each website request or browser navigation.", "default": 20 }, "maxContentBytes": { "title": "Maximum response size", "minimum": 50000, "maximum": 5000000, "type": "integer", "description": "Maximum bytes read from each website to protect memory and control cost.", "default": 2000000 }, "proxy": { "title": "Proxy configuration", "type": "object", "description": "Optional Apify Proxy configuration. Most public business websites do not require a proxy.", "default": { "useApifyProxy": false } }, "enrichCnpj": { "title": "Enrich with Receita Federal (CNPJ)", "type": "boolean", "description": "Detect CNPJ on each website and enrich with public Receita Federal data (razão social, porte, situação cadastral, CNAE, município/UF) via BrasilAPI. Adds a lead score boost. Free, no auth required.", "default": true }, "googleSheets": { "title": "Google Sheets export (optional)", "type": "object", "description": "Export results directly to Google Sheets without downloading CSV. Requires spreadsheet ID and auth (service account JSON or API key).", "properties": { "spreadsheetId": { "title": "Spreadsheet ID", "type": "string", "description": "The ID from the Google Sheets URL (between /d/ and /edit)" }, "sheetName": { "title": "Sheet/tab name", "type": "string", "description": "Name of the sheet tab to write to", "default": "Leads" }, "apiKey": { "title": "Google API key", "type": "string", "description": "Google Cloud API key with Sheets API enabled (simpler, requires shared/public sheet)" }, "serviceAccountJson": { "title": "Service account JSON", "type": "string", "description": "Full service account JSON key for full automation (no user interaction)" }, "mode": { "title": "Write mode", "type": "string", "enum": [ "append", "overwrite" ], "description": "append: add rows to existing data; overwrite: replace all data", "default": "append" } } }, "webhookUrl": { "title": "Webhook URL (optional)", "type": "string", "description": "URL to receive run completion notification with top leads (Slack, Discord, Make, n8n, Zapier, custom endpoint)." }, "webhookSecret": { "title": "Webhook secret (optional)", "type": "string", "description": "Bearer token for webhook authentication." } } }, "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 } } } } } } } } } }