{ "openapi": "3.0.1", "info": { "title": "Website to Markdown Crawler for AI & RAG (with PDFs)", "description": "Crawl a website and save every page as clean Markdown for LLMs, RAG and AI chatbots: main content only, no menus or cookie banners. Linked PDF, Word, PowerPoint and Excel files are converted too. Optional chunking.", "version": "1.0", "x-build-id": "bsfL1ojM8SVwFtaaG" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/prometheus-maker~website-to-markdown-crawler/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-prometheus-maker-website-to-markdown-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/prometheus-maker~website-to-markdown-crawler/runs": { "post": { "operationId": "runs-sync-prometheus-maker-website-to-markdown-crawler", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/prometheus-maker~website-to-markdown-crawler/run-sync": { "post": { "operationId": "run-sync-prometheus-maker-website-to-markdown-crawler", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "Websites or sections to crawl, one per line. With the default scope, only pages whose URL starts with the start URL are crawled: https://example.com/docs crawls /docs and /docs/... only.", "items": { "type": "string" } }, "maxPages": { "title": "Max pages per site", "minimum": 1, "maximum": 100000, "type": "integer", "description": "Upper limit of web pages saved per site. You pay per saved page, so this also caps the cost.", "default": 100 }, "crawlScope": { "title": "Crawl scope", "enum": [ "path", "host", "subdomains" ], "type": "string", "description": "Which links to follow: only pages under the start URL's folder, the whole host, or the host and its subdomains.", "default": "path" }, "crawlLinks": { "title": "Follow links", "type": "boolean", "description": "Turn off to save only the start URLs themselves.", "default": true }, "maxDepth": { "title": "Max link depth", "minimum": 0, "maximum": 50, "type": "integer", "description": "How many clicks away from a start URL to go. Empty = no limit (up to 50)." }, "includeUrlPatterns": { "title": "Only URLs containing", "type": "array", "description": "If set, only pages whose URL contains one of these texts are saved and followed. Wrap in slashes for a regular expression: /\\/blog\\/\\d{4}\\//", "default": [], "items": { "type": "string" } }, "excludeUrlPatterns": { "title": "Skip URLs containing", "type": "array", "description": "Pages and files whose URL contains one of these texts are skipped, e.g. /tag/ or ?page=. Wrap in slashes for a regular expression.", "default": [], "items": { "type": "string" } }, "useSitemap": { "title": "Also use the XML sitemap", "type": "boolean", "description": "Add pages listed in the site's sitemap (found via robots.txt or /sitemap.xml), within the crawl scope.", "default": false }, "includeDocuments": { "title": "Convert linked documents", "type": "boolean", "description": "Convert PDF, Word (.docx), PowerPoint (.pptx) and Excel (.xlsx) files linked from crawled pages to Markdown too.", "default": true }, "maxDocuments": { "title": "Max documents per site", "minimum": 0, "maximum": 10000, "type": "integer", "description": "Upper limit of linked documents converted per site.", "default": 20 }, "maxDocumentPages": { "title": "Max pages per document", "minimum": 1, "maximum": 2000, "type": "integer", "description": "Only the first N pages of long PDFs are converted.", "default": 200 }, "documentsFromOtherSites": { "title": "Documents hosted elsewhere", "type": "boolean", "description": "Also convert documents that crawled pages link to on other hosts (common for files on a CDN).", "default": true }, "keepLinks": { "title": "Keep links in Markdown", "type": "boolean", "description": "Keep [text](url) links, made absolute. Turn off for plain text with no URLs, which uses fewer LLM tokens.", "default": true }, "keepImages": { "title": "Keep images", "type": "boolean", "description": "Keep ![alt](url) image references in the Markdown.", "default": false }, "chunkSize": { "title": "Chunk size (characters)", "minimum": 0, "maximum": 100000, "type": "integer", "description": "If above 0, each item also gets 'chunks': pieces of at most this many characters, split at paragraph boundaries, each with its heading path. Ready for embeddings. 0 = off.", "default": 0 }, "chunkOverlap": { "title": "Chunk overlap (characters)", "minimum": 0, "maximum": 50000, "type": "integer", "description": "Characters repeated from the end of one chunk at the start of the next (at most half the chunk size).", "default": 0 }, "respectRobotsTxt": { "title": "Respect robots.txt", "type": "boolean", "description": "Skip pages the site's robots.txt asks crawlers not to visit. Leave on unless it is your own site.", "default": true }, "maxConcurrency": { "title": "Pages in parallel", "minimum": 1, "maximum": 20, "type": "integer", "description": "Pages fetched at the same time per site.", "default": 5 }, "maxRequestsPerHost": { "title": "Max requests per host at once", "minimum": 1, "maximum": 10, "type": "integer", "description": "Politeness limit per server. Lower it for small or slow sites.", "default": 4 } } }, "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 } } } } } } } } } }