{ "openapi": "3.0.1", "info": { "title": "Email Scraper - Extract Emails from Websites", "description": "Powerful actor to crawl websites and extract email addresses using advanced detection. It bypasses Cloudflare protection, RTL obfuscation, and text patterns to deliver structured data. Features include configurable crawl depth, proxy support, and anti-detection measures.", "version": "1.0", "x-build-id": "5Z2dYDTUtcyrMIcn9" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/dominic-quaiser~email-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-dominic-quaiser-email-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/dominic-quaiser~email-scraper/runs": { "post": { "operationId": "runs-sync-dominic-quaiser-email-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/dominic-quaiser~email-scraper/run-sync": { "post": { "operationId": "run-sync-dominic-quaiser-email-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "required": [ "start_urls" ], "properties": { "start_urls": { "title": "Start URLs", "type": "array", "description": "URLs to start crawling from. The scraper will extract emails from these pages and follow links up to the specified depth.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "max_depth": { "title": "Maximum Crawl Depth", "minimum": 0, "maximum": 10, "type": "integer", "description": "Maximum depth of links to follow from start URLs. 0 = only start URLs, 1 = start URLs + one level of links, etc.", "default": 1 }, "stay_on_domain": { "title": "Stay on Same Domain", "type": "boolean", "description": "Only follow links that stay on the same domain as each start URL. When enabled, the crawler won't visit external sites.", "default": true }, "max_concurrent_pages": { "title": "Max Concurrent Pages", "minimum": 1, "maximum": 100, "type": "integer", "description": "Maximum number of pages to process simultaneously. Leave empty for auto-tuning (recommended: 50). Lower values use less memory.", "default": 50 }, "max_pages_per_domain": { "title": "Maximum Pages per Domain", "minimum": 1, "type": "integer", "description": "Maximum number of pages to crawl from each individual domain. Leave empty for unlimited. This limit applies separately to each domain.", "default": 200 }, "max_requests_per_run": { "title": "Maximum Requests", "minimum": 1, "type": "integer", "description": "Maximum number of pages to crawl globally across all domains. Leave empty for unlimited." }, "request_delay_min": { "title": "Minimum Request Delay (seconds)", "minimum": 0, "maximum": 60, "type": "number", "description": "Minimum delay between requests to avoid detection. Recommended: 1-2 seconds.", "default": 1 }, "request_delay_max": { "title": "Maximum Request Delay (seconds)", "minimum": 0, "maximum": 60, "type": "number", "description": "Maximum delay between requests. A random delay between min and max will be used.", "default": 3 }, "respect_robots_txt": { "title": "Respect robots.txt", "type": "boolean", "description": "Honor robots.txt directives including crawl delays and disallowed paths.", "default": false }, "rotate_user_agents": { "title": "Rotate User Agents", "type": "boolean", "description": "Use a pool of realistic user agents to appear as different users.", "default": true }, "proxy_configuration": { "title": "Proxy Configuration", "type": "object", "description": "Proxy settings to avoid being blocked. Recommended for large crawls." } } }, "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 } } } } } } } } } }