{ "openapi": "3.0.1", "info": { "title": "Website Content Crawler for AI — Markdown, RAG Chunks & PDFs", "description": "Crawl any website into clean Markdown or text for AI, RAG and LLMs. Fast HTTP with automatic stealth-browser fallback, sitemaps and llms.txt, PDF/DOCX/PPTX/XLSX parsing, heading-aware chunks with token counts, incremental re-crawls.", "version": "0.1", "x-build-id": "ehORIcqEN3RmA9L6q" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/he_work~ai-website-crawler/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-he_work-ai-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/he_work~ai-website-crawler/runs": { "post": { "operationId": "runs-sync-he_work-ai-website-crawler", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/he_work~ai-website-crawler/run-sync": { "post": { "operationId": "run-sync-he_work-ai-website-crawler", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "properties": { "startUrls": { "title": "Start URLs", "type": "array", "description": "Pages to start from. Links are followed within the crawl scope. Direct links to PDF / DOCX / PPTX / XLSX files work too.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "crawlScope": { "title": "Crawl scope", "enum": [ "path", "host", "domain", "single" ], "type": "string", "description": "Which links to follow. Include / exclude globs refine it.", "default": "path" }, "maxPages": { "title": "Max pages", "minimum": 1, "type": "integer", "description": "Pages (and documents) to process per run, including ones that fail.", "default": 100 }, "maxDepth": { "title": "Max link depth", "minimum": 0, "type": "integer", "description": "Clicks away from a start URL. 0 = start URLs only (plus sitemap / llms.txt pages).", "default": 20 }, "includeGlobs": { "title": "Include URL globs", "type": "array", "description": "Only crawl URLs matching one of these, e.g. https://example.com/docs/** (* = one path segment, ** = anything).", "items": { "type": "string" } }, "excludeGlobs": { "title": "Exclude URL globs", "type": "array", "description": "Never crawl URLs matching these, e.g. **/tag/**, **?page=*", "items": { "type": "string" } }, "useSitemaps": { "title": "Use sitemaps", "type": "boolean", "description": "Read robots.txt / sitemap.xml (incl. sitemap indexes and .gz) to find pages that links don't reach.", "default": true }, "useLlmsTxt": { "title": "Use llms.txt", "type": "boolean", "description": "If the site publishes /llms.txt, crawl the pages it lists.", "default": true }, "respectRobotsTxt": { "title": "Respect robots.txt", "type": "boolean", "description": "Skip URLs disallowed for crawlers.", "default": true }, "renderingMode": { "title": "Rendering", "enum": [ "auto", "http", "browser" ], "type": "string", "description": "Auto re-renders a page in a stealth browser when it is empty without JavaScript or behind a bot check.", "default": "auto" }, "contentMode": { "title": "Content", "enum": [ "article", "full" ], "type": "string", "description": "How much of each page to keep.", "default": "article" }, "outputFormats": { "title": "Output formats", "type": "array", "description": "Markdown keeps headings, lists, tables and links. HTML = the raw page.", "items": { "type": "string", "enum": [ "markdown", "text", "html" ] }, "default": [ "markdown" ] }, "markdownLinks": { "title": "Keep links in Markdown", "type": "boolean", "description": "Off = plain link text (smaller, better for embeddings).", "default": true }, "markdownImages": { "title": "Keep images in Markdown", "type": "boolean", "description": "Include ![alt](src) image references.", "default": false }, "removeSelectors": { "title": "Remove CSS selectors", "type": "string", "description": "Extra elements to drop before extraction, e.g. .newsletter, #comments, .related-posts" }, "chunkSize": { "title": "RAG chunk size", "minimum": 0, "maximum": 8000, "type": "integer", "description": "0 = off. Splits each page's Markdown into heading-aware chunks of up to this many LLM tokens (OpenAI cl100k tokenizer, not characters), each with its heading path. Typical: 500–1000.", "default": 0 }, "chunkOverlap": { "title": "Chunk overlap", "minimum": 0, "maximum": 1000, "type": "integer", "description": "How many LLM tokens of the previous chunk are repeated at the start of the next one.", "default": 100 }, "parseDocuments": { "title": "Parse documents", "type": "boolean", "description": "Download linked PDF, DOCX, PPTX, XLSX, TXT, MD and CSV files on the site and convert them to Markdown.", "default": true }, "incrementalName": { "title": "Incremental crawl name", "type": "string", "description": "Any name, e.g. 'my-docs'. Runs with the same name remember page fingerprints: each page gets change_status new / changed / unchanged, and pages that disappeared are listed in the run report." }, "skipUnchanged": { "title": "Skip unchanged pages", "type": "boolean", "description": "With an incremental crawl name: don't output (or charge for) pages whose content didn't change since the last run.", "default": true }, "includeLinkLists": { "title": "Include link lists", "type": "boolean", "description": "Add every internal, external and document link found on the page.", "default": false }, "includeJsonLd": { "title": "Include JSON-LD", "type": "boolean", "description": "Add the page's schema.org structured data.", "default": false }, "saveCombinedFiles": { "title": "Save combined files", "type": "boolean", "description": "Also save site.md (all pages in one Markdown file), llms.txt (page index) and chunks.jsonl (vector-DB ready) in the run's key-value store.", "default": true }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "maximum": 50, "type": "integer", "description": "Parallel HTTP requests.", "default": 10 }, "browserConcurrency": { "title": "Browser tabs", "minimum": 1, "maximum": 6, "type": "integer", "description": "Parallel browser pages (when a browser is needed).", "default": 2 }, "browserWaitSecs": { "title": "Browser wait (seconds)", "minimum": 0, "maximum": 30, "type": "integer", "description": "Extra time for JavaScript content to appear.", "default": 2 }, "requestDelayMs": { "title": "Delay between requests to a site (ms)", "minimum": 0, "type": "integer", "description": "Politeness delay per host.", "default": 0 }, "proxyConfiguration": { "title": "Proxy", "type": "object", "description": "Optional. By default the crawler connects directly and moves a site to Apify datacenter, then residential proxies only if it gets blocked (included in the price)." } } }, "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 }, "PROXY_UNBLOCKER_UNITS": { "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 }, "PROXY_UNBLOCKER_UNITS": { "type": "integer", "example": 0 } } } } } } } } } }