{ "openapi": "3.0.1", "info": { "title": "Website Content Crawler", "description": "Deep-crawl websites to extract clean text, Markdown, or HTML for AI/LLM apps, RAG pipelines, and vector databases. Supports adaptive crawling, HTML cleaning, file downloads, and structured dataset output. Easily integrates with LangChain, LlamaIndex, and other LLM tools.", "version": "0.0", "x-build-id": "niMVhlqRsmWuNmVJI" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/mikolabs~website-content-crawler/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-mikolabs-website-content-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/mikolabs~website-content-crawler/runs": { "post": { "operationId": "runs-sync-mikolabs-website-content-crawler", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/mikolabs~website-content-crawler/run-sync": { "post": { "operationId": "run-sync-mikolabs-website-content-crawler", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "Start URLs", "type": "array", "description": "One or more URLs of pages where the crawler will start. The Actor crawls sub-pages of these URLs by default.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "crawlerType": { "title": "Crawler type", "enum": [ "playwright:adaptive", "playwright:firefox", "cheerio", "jsdom", "playwright:chrome" ], "type": "string", "description": "How pages are fetched. Adaptive auto-switches between raw HTTP and Firefox. Cheerio is fastest. Firefox/Chrome handle JS-rendered sites.", "default": "playwright:adaptive" }, "includeUrlGlobs": { "title": "Include URLs (globs)", "type": "array", "description": "Glob patterns for URLs to crawl. If set, overrides the default start-URL-based scoping. Affects links only, not Start URLs.", "default": [], "items": { "type": "object", "required": [ "glob" ], "properties": { "glob": { "type": "string", "title": "Glob of a web page" } } } }, "excludeUrlGlobs": { "title": "Exclude URLs (globs)", "type": "array", "description": "Glob patterns for URLs to skip. Affects links only, not Start URLs.", "default": [], "items": { "type": "object", "required": [ "glob" ], "properties": { "glob": { "type": "string", "title": "Glob of a web page" } } } }, "maxCrawlDepth": { "title": "Max crawling depth", "minimum": 0, "type": "integer", "description": "Maximum link-following depth from start URLs. 0 = start URLs only.", "default": 20 }, "maxCrawlPages": { "title": "Max pages", "minimum": 0, "type": "integer", "description": "Maximum total pages to crawl, including start URLs. 0 = unlimited.", "default": 20 }, "maxResults": { "title": "Max results", "minimum": 0, "type": "integer", "description": "Maximum number of results (items) to save to the dataset. Unlike maxCrawlPages, this only counts pages with saved content.", "default": 20 }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "maximum": 20, "type": "integer", "description": "Maximum number of parallel page loads.", "default": 16 }, "initialConcurrency": { "title": "Initial concurrency", "minimum": 1, "maximum": 20, "type": "integer", "description": "Initial number of parallel page loads at crawl start. Gradually increases up to maxConcurrency. Useful to warm up without overloading the target.", "default": 1 }, "maxRequestRetries": { "title": "Max request retries", "minimum": 0, "type": "integer", "description": "Maximum number of retry attempts for failed requests.", "default": 3 }, "useSitemaps": { "title": "Load URLs from Sitemaps", "type": "boolean", "description": "If enabled, fetches sitemap.xml at each domain's root and enqueues matching URLs.", "default": false }, "useLlmsTxt": { "title": "Crawl /llms.txt and Markdown files", "type": "boolean", "description": "If enabled, the crawler looks for /llms.txt at domain roots and crawls those URLs. Also enables crawling .md files.", "default": false }, "respectRobotsTxtFile": { "title": "Respect robots.txt", "type": "boolean", "description": "Obey robots.txt exclusion rules.", "default": false }, "keepUrlFragments": { "title": "URL #fragments identify unique pages", "type": "boolean", "description": "Include URL fragments when checking for already-visited pages. Useful for single-page apps.", "default": false }, "ignoreCanonicalUrl": { "title": "Ignore canonical URLs", "type": "boolean", "description": "If enabled, ignores the canonical URL reported by the page and uses the actual URL for deduplication.", "default": false }, "dynamicContentWaitSecs": { "title": "Dynamic content wait (seconds)", "minimum": 0, "type": "number", "description": "Wait this many seconds after page load for dynamic content to appear. Only applies to browser crawlers.", "default": 0 }, "maxScrollPagePercent": { "title": "Max scroll page percent", "minimum": 0, "maximum": 100, "type": "integer", "description": "How much of the page to scroll before extraction. 100 = scroll through the full page to the last section, 0 disables scrolling. Ignored for raw HTTP crawlers.", "default": 100 }, "waitForSelector": { "title": "Wait for CSS selector", "type": "string", "description": "Wait for this CSS selector to appear before extracting content. Only for browser crawlers.", "default": "" }, "clickElementsCssSelector": { "title": "Click elements (CSS selector)", "type": "string", "description": "Click DOM elements matching this selector to expand collapsed content (e.g. [aria-expanded='false']). Browser only.", "default": "" }, "expandIframes": { "title": "Expand iframes", "type": "boolean", "description": "Include text content from iframes in the output. Browser crawler only.", "default": true }, "htmlTransformer": { "title": "HTML transformer", "enum": [ "readableText", "none" ], "type": "string", "description": "Controls how the page HTML is cleaned before text extraction.", "default": "readableText" }, "readableTextCharThreshold": { "title": "Readable text char threshold", "minimum": 0, "type": "integer", "description": "Minimum character count for readability extraction to be considered successful. Falls back to full-page extraction if below threshold.", "default": 100 }, "aggressivePrune": { "title": "Aggressive prune", "type": "boolean", "description": "Apply more aggressive HTML pruning to remove low-value content. May remove some relevant content.", "default": false }, "removeElementsCssSelector": { "title": "Remove HTML elements (CSS selector)", "type": "string", "description": "CSS selector for elements to remove before extraction. Defaults to nav, header, footer, ads, scripts, etc.", "default": "" }, "keepElementsCssSelector": { "title": "Keep elements (CSS selector)", "type": "string", "description": "If set, only content matching this CSS selector is kept; everything else is removed.", "default": "" }, "removeCookieWarnings": { "title": "Remove cookie warnings", "type": "boolean", "description": "Attempt to remove cookie consent banners.", "default": true }, "saveMarkdown": { "title": "Save Markdown", "type": "boolean", "description": "Convert page content to Markdown and include in output.", "default": true }, "saveHtml": { "title": "Save HTML snippet", "type": "boolean", "description": "Include the cleaned HTML snippet in the output record.", "default": false }, "saveHtmlAsFile": { "title": "Save raw HTML as file", "type": "boolean", "description": "Save full raw page HTML to the Key-Value Store and add a link in the output record.", "default": false }, "saveScreenshots": { "title": "Save screenshots", "type": "boolean", "description": "Capture a screenshot of each page (Playwright crawlers only) and store in the Key-Value Store.", "default": false }, "saveFiles": { "title": "Download linked files", "type": "boolean", "description": "Download PDF, DOC, DOCX, XLS, XLSX, CSV files linked from crawled pages.", "default": false }, "minFileDownloadSpeedKBps": { "title": "Min file download speed (KB/s)", "minimum": 0, "type": "number", "description": "Abort file downloads that stay below this speed for more than 10 seconds.", "default": 64 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Configure proxy for crawling. Set useApifyProxy: true to use Apify Proxy.", "default": { "useApifyProxy": true } }, "initialCookies": { "title": "Initial cookies", "type": "array", "description": "Cookies injected on every request (for pages behind login). JSON array of {name, value, domain?, path?}.", "default": [] }, "customHttpHeaders": { "title": "Custom HTTP headers", "type": "object", "description": "Extra HTTP headers added to all requests, e.g. {\"Authorization\": \"Bearer token\"}.", "default": {} }, "debugMode": { "title": "Debug mode", "type": "boolean", "description": "Include extra debug fields in output (raw HTML, response headers).", "default": false }, "debugLog": { "title": "Debug log", "type": "boolean", "description": "Enable verbose DEBUG-level logging.", "default": false }, "signHttpRequests": { "title": "Sign HTTP requests (experimental)", "type": "boolean", "description": "If enabled, HTTP requests will be cryptographically signed using the actor credentials. This is a platform-side feature.", "default": false } } }, "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 } } } } } } } } } }