{ "openapi": "3.0.1", "info": { "title": "Website Content Crawler", "description": "Deep crawl websites and extract clean text, Markdown, or HTML for LLMs, RAG, and AI apps. Removes navigation, ads, cookie banners. Supports headless browser & HTTP. Sitemap discovery, URL scoping, file downloads. Feed ChatGPT, LangChain, LlamaIndex, Pinecone. The cheapest content crawler on Apify.", "version": "1.0", "x-build-id": "wPAO3szFwejVv7rqF" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/worshipful_knife~website-content-crawler/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-worshipful_knife-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/worshipful_knife~website-content-crawler/runs": { "post": { "operationId": "runs-sync-worshipful_knife-website-content-crawler", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/worshipful_knife~website-content-crawler/run-sync": { "post": { "operationId": "run-sync-worshipful_knife-website-content-crawler", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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 to start crawling from. The crawler will follow links found on these pages.", "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" ], "type": "string", "description": "Select the crawler engine.", "default": "playwright:adaptive" }, "maxCrawlPages": { "title": "Max pages", "minimum": 1, "maximum": 1000000, "type": "integer", "description": "Maximum number of pages to crawl.", "default": 100 }, "maxCrawlDepth": { "title": "Max crawling depth", "minimum": 0, "maximum": 100, "type": "integer", "description": "Maximum link depth from start URLs. 0 = only start URLs.", "default": 20 }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "maximum": 200, "type": "integer", "description": "Maximum number of pages crawled in parallel.", "default": 10 }, "excludeUrlGlobs": { "title": "Exclude URLs (globs)", "type": "array", "description": "Glob patterns for URLs to skip. E.g. https://example.com/archive/**", "default": [], "items": { "type": "string" } }, "includeUrlGlobs": { "title": "Include URLs (globs)", "type": "array", "description": "If set, only URLs matching these globs will be crawled.", "default": [], "items": { "type": "string" } }, "outputFormat": { "title": "Output format", "enum": [ "text", "markdown", "html" ], "type": "string", "description": "Format of the extracted content.", "default": "markdown" }, "removeElementsCssSelector": { "title": "Additional elements to remove (CSS selector)", "type": "string", "description": "CSS selector for additional elements to remove. Nav, footer, header, ads, scripts, and iframes are always removed by default.", "default": "" }, "extractElementsCssSelector": { "title": "Extract HTML elements (CSS selector)", "type": "string", "description": "If set, only keep content from elements matching this selector. E.g. 'article, main, .content'", "default": "" }, "removeCookieWarnings": { "title": "Remove cookie warnings", "type": "boolean", "description": "Attempt to auto-dismiss cookie consent banners.", "default": true }, "waitForDynamicContent": { "title": "Wait for dynamic content (ms)", "minimum": 0, "maximum": 30000, "type": "integer", "description": "Time in ms to wait after page load for dynamic content. Only for browser crawler.", "default": 1000 }, "maxScrollHeight": { "title": "Maximum scroll height (px)", "minimum": 0, "maximum": 100000, "type": "integer", "description": "Scroll the page to this height to trigger lazy loading. 0 = no scroll.", "default": 0 }, "expandClickables": { "title": "Expand clickable elements", "type": "boolean", "description": "Click elements like accordions and tabs to expand their content.", "default": false }, "saveFiles": { "title": "Save files", "type": "boolean", "description": "Download linked document files (PDF, DOC, DOCX, XLS, XLSX, CSV).", "default": false }, "useSitemaps": { "title": "Use sitemaps", "type": "boolean", "description": "Discover additional URLs from sitemaps.", "default": true }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Proxy settings for the crawler.", "default": { "useApifyProxy": true } }, "requestTimeoutSecs": { "title": "Request timeout (seconds)", "minimum": 10, "maximum": 300, "type": "integer", "description": "Maximum time for loading a single page. Lower values help avoid hanging on blocked sites.", "default": 30 } } }, "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 } } } } } } } } } }