{ "openapi": "3.0.1", "info": { "title": "Stealth Website Crawler", "description": "Crawl websites protected by Cloudflare, DataDome, and other anti-bot systems. Extract clean text or markdown for AI/LLM pipelines. Like Website Content Crawler, but for sites that block you.", "version": "0.1", "x-build-id": "jVSNajeaEKVb1jOTf" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/nocturne~stealth-website-crawler/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-nocturne-stealth-website-crawler", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/nocturne~stealth-website-crawler/runs": { "post": { "operationId": "runs-sync-nocturne-stealth-website-crawler", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/nocturne~stealth-website-crawler/run-sync": { "post": { "operationId": "run-sync-nocturne-stealth-website-crawler", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "URLs", "type": "array", "description": "URLs to process.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "actions": { "title": "Actions (interactive mode)", "type": "array", "description": "Sequence of actions to perform on each page. If provided, runs in interactive mode. Types: click, fill, type, scroll, hover, select, wait, screenshot, javascript, extractHtml, extractContent, captureNetwork, humanActivity, mouseMove." }, "captureNetwork": { "title": "Capture network responses", "type": "boolean", "description": "Record JSON/API responses made by the page. Useful for intercepting data APIs.", "default": false }, "maxCrawlPages": { "title": "Max pages to crawl", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Maximum pages to crawl (crawl mode only).", "default": 10 }, "maxCrawlDepth": { "title": "Max crawl depth", "minimum": 0, "maximum": 100, "type": "integer", "description": "How many links deep to follow from start URLs. 0 = start URLs only.", "default": 20 }, "outputFormat": { "title": "Content output format", "enum": [ "markdown", "html", "text" ], "type": "string", "description": "Format for extracted content.", "default": "markdown" }, "followLinks": { "title": "Follow links", "type": "boolean", "description": "Follow same-domain links to discover more pages (crawl mode).", "default": true }, "includeUrlGlobs": { "title": "Include URL patterns", "type": "array", "description": "Only crawl URLs matching these glob patterns. Example: https://example.com/blog/*", "items": { "type": "string" } }, "excludeUrlGlobs": { "title": "Exclude URL patterns", "type": "array", "description": "Skip URLs matching these glob patterns. Example: **/login**", "items": { "type": "string" } }, "waitForSelector": { "title": "Wait for selector", "type": "string", "description": "CSS selector to wait for before processing each page. Useful for JS-heavy sites." }, "takeScreenshots": { "title": "Take screenshots", "type": "boolean", "description": "Capture a screenshot of each page. Stored in key-value store.", "default": false }, "blockResources": { "title": "Block images, fonts, CSS", "type": "boolean", "description": "Block images, media, fonts, and stylesheets to reduce proxy bandwidth and speed up crawling.", "default": false }, "initialCookies": { "title": "Initial cookies", "type": "array", "description": "Cookies to set before crawling. Format: [{name, value, domain, path}]" }, "maxConcurrency": { "title": "Max concurrent pages", "minimum": 1, "maximum": 10, "type": "integer", "description": "Number of pages to load simultaneously. Lower = safer stealth, higher = faster.", "default": 3 }, "requestTimeoutSecs": { "title": "Request timeout (seconds)", "minimum": 5, "maximum": 120, "type": "integer", "description": "Max time to wait for a page to load.", "default": 30 }, "maxRetries": { "title": "Max retries per page", "minimum": 0, "maximum": 5, "type": "integer", "description": "Number of retry attempts for failed pages. Failed pages are not charged.", "default": 1 }, "proxyConfig": { "title": "Proxy configuration", "type": "object", "description": "Residential proxies strongly recommended for anti-bot sites.", "default": { "useApifyProxy": true, "apifyProxyGroups": [ "RESIDENTIAL" ] } } } }, "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 } } } } } } } } } }