{ "openapi": "3.0.1", "info": { "title": "Stealth Website Scraper", "description": "Extract text, links, metadata, HTML, markdown, and structured page data with HTTP-first crawling and stealth-aware browser fallback.", "version": "0.1", "x-build-id": "AtczkowNlCWfsPENd" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/solutionssmart~stealth-website-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-solutionssmart-stealth-website-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/solutionssmart~stealth-website-scraper/runs": { "post": { "operationId": "runs-sync-solutionssmart-stealth-website-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/solutionssmart~stealth-website-scraper/run-sync": { "post": { "operationId": "run-sync-solutionssmart-stealth-website-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "startUrls" ], "properties": { "startUrls": { "title": "Start URLs", "type": "array", "description": "One or more URLs to scrape. Supports strings and request objects.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "maxPages": { "title": "Max pages", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Maximum number of pages to process across the crawl.", "default": 100 }, "maxDepth": { "title": "Max depth", "minimum": 0, "maximum": 20, "type": "integer", "description": "Maximum crawl depth from the start URLs.", "default": 2 }, "sameDomainOnly": { "title": "Same domain only", "type": "boolean", "description": "Restrict crawling to the same root domain as each start URL.", "default": true }, "scrapeInternalLinks": { "title": "Crawl internal links", "type": "boolean", "description": "Follow internal links discovered on scraped pages.", "default": true }, "extractionMode": { "title": "Extraction mode", "enum": [ "text", "markdown", "html", "links", "all" ], "type": "string", "description": "Choose the primary content extraction output.", "default": "all" }, "crawlingMode": { "title": "Crawling mode", "enum": [ "http-first", "browser-only" ], "type": "string", "description": "Choose HTTP-first crawling or full browser-only crawling.", "default": "http-first" }, "stealthBrowser": { "title": "Browser engine", "enum": [ "playwright", "cloak" ], "type": "string", "description": "Playwright is the default browser engine. CloakBrowser is attempted when selected.", "default": "cloak" }, "fallbackOnStatusCodes": { "title": "Fallback HTTP status codes", "type": "array", "description": "Trigger browser fallback when these HTTP response codes appear.", "items": { "type": "integer", "minimum": 100, "maximum": 599 }, "default": [ 403, 429, 503 ] }, "minTextLengthForSuccess": { "title": "Min text length for success", "minimum": 0, "maximum": 100000, "type": "integer", "description": "Trigger browser fallback when extracted text is shorter than this threshold.", "default": 300 }, "waitUntil": { "title": "Browser waitUntil", "enum": [ "domcontentloaded", "load", "networkidle" ], "type": "string", "description": "Navigation readiness state for browser scraping.", "default": "domcontentloaded" }, "blockResources": { "title": "Block heavy browser resources", "type": "boolean", "description": "Abort images, fonts, media, and stylesheets in browser mode to reduce cost.", "default": true }, "includeHtml": { "title": "Include HTML in output", "type": "boolean", "description": "Include the page HTML in the dataset output.", "default": false }, "includeLinks": { "title": "Include internal links", "type": "boolean", "description": "Include normalized internal links in output.", "default": true }, "includeExternalLinks": { "title": "Include external links", "type": "boolean", "description": "Include normalized external links in output.", "default": false }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "maximum": 100, "type": "integer", "description": "Maximum parallel requests or pages.", "default": 5 }, "requestTimeoutSecs": { "title": "Request timeout seconds", "minimum": 5, "maximum": 300, "type": "integer", "description": "Timeout for HTTP requests and browser navigation.", "default": 30 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Apify proxy configuration." }, "customUserAgent": { "title": "Custom user agent", "type": "string", "description": "Optional user agent applied to HTTP requests and browser contexts." } } }, "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 } } } } } } } } } }