{ "openapi": "3.0.1", "info": { "title": "Advanced Website Crawling Actor", "description": "A fast and reliable scraper for any website that extracts clean HTML, Markdown, and text content. Provides clean, structured data with support for dynamic rendering, recursive sitemap discovery, SSL bypass, and easy API integration for your applications.", "version": "1.0", "x-build-id": "i0dcGkQ05Rujw2Dag" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/techforce.global~advanced-website-crawling-actor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-techforce.global-advanced-website-crawling-actor", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/techforce.global~advanced-website-crawling-actor/runs": { "post": { "operationId": "runs-sync-techforce.global-advanced-website-crawling-actor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/techforce.global~advanced-website-crawling-actor/run-sync": { "post": { "operationId": "run-sync-techforce.global-advanced-website-crawling-actor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "startUrl" ], "properties": { "startUrl": { "title": "Start URL", "type": "string", "description": "Target URL to crawl", "default": "https://www.apify.com" }, "maxPages": { "title": "Max Pages", "maximum": 200, "type": "integer", "description": "Maximum number of pages to crawl.", "default": 20 }, "maxDepth": { "title": "Max Crawl Depth", "type": "integer", "description": "Maximum depth from start URLs.", "default": 5 }, "concurrency": { "title": "Concurrency", "type": "integer", "description": "Number of concurrent crawler workers.", "default": 20 }, "batchSize": { "title": "Dataset Batch Size", "type": "integer", "description": "Number of records pushed to dataset per batch.", "default": 20 }, "outputFormat": { "title": "Output Format", "type": "string", "description": "Content format to store.", "default": "text" }, "includePatterns": { "title": "Include URL Patterns", "type": "array", "description": "Glob patterns for URLs to include.", "items": { "type": "string" }, "default": [ "*" ] }, "excludePatterns": { "title": "Exclude URL Patterns", "type": "array", "description": "Glob patterns for URLs to exclude.", "items": { "type": "string" }, "default": [] }, "maxRequestsPerCrawl": { "title": "Max Requests Per Crawl", "type": "integer", "description": "Hard cap on total requests per run.", "default": 1000 }, "maxRetries": { "title": "Max Retries", "type": "integer", "description": "Maximum retries per request.", "default": 2 }, "browserConcurrency": { "title": "Browser Concurrency", "type": "integer", "description": "Maximum concurrent Playwright browser pages (applies only to JS-heavy pages that fail static fetch).", "default": 8 }, "deduplicateContent": { "title": "Deduplicate Content", "type": "boolean", "description": "Skip duplicate content using SHA-256 hashing.", "default": true }, "respectRobotsTxt": { "title": "Respect robots.txt", "type": "boolean", "description": "Whether to respect robots.txt rules.", "default": true }, "proxy": { "title": "Apify Proxy Configuration", "type": "object", "description": "Apify Proxy settings.", "properties": { "apifyProxyGroups": { "title": "Proxy Groups", "type": "array", "description": "List of Apify Proxy groups (e.g., RESIDENTIAL).", "items": { "type": "string" } }, "apifyProxyCountry": { "title": "Proxy Country", "type": "string", "description": "Two-letter country code for proxy routing (e.g., IN, US)." } } } } }, "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 } } } } } } } } } }