{ "openapi": "3.0.1", "info": { "title": "Website to Markdown for LLMs & RAG — Content Extractor", "description": "Turn any URL or whole site into clean, LLM-ready Markdown, text, or JSON. Strips nav/ads/boilerplate; keeps headings, links, tables, code. Sitemap-aware concurrent crawl, URL filters, robots.txt respected, rich metadata. Charged only per page extracted — no startup fee.", "version": "0.1", "x-build-id": "01NkHOmISRezFghaO" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/runlayer~website-to-markdown/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-runlayer-website-to-markdown", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/runlayer~website-to-markdown/runs": { "post": { "operationId": "runs-sync-runlayer-website-to-markdown", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/runlayer~website-to-markdown/run-sync": { "post": { "operationId": "run-sync-runlayer-website-to-markdown", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "urls" ], "properties": { "urls": { "title": "URLs", "type": "array", "description": "One or more URLs to convert. Each extracted page produces one dataset item and one billable event. You may omit the https:// prefix.", "items": { "type": "string" } }, "outputFormat": { "title": "Output format", "enum": [ "markdown", "text", "html", "json" ], "type": "string", "description": "markdown (best for LLMs/RAG), text (plain), html (cleaned main-content HTML), or json (everything: markdown + text + metadata + links).", "default": "markdown" }, "onlyMainContent": { "title": "Extract main content only", "type": "boolean", "description": "Use readability to keep only the main article and strip navigation, sidebars, ads, footers and boilerplate. Turn off to convert the whole page body.", "default": true }, "jsRendering": { "title": "Render JavaScript", "type": "boolean", "description": "Load the page in a real browser so JS-rendered content (SPAs, React/Vue sites) is captured. Turn off for a much faster fetch on static/server-rendered pages.", "default": true }, "includeLinks": { "title": "Include links", "type": "boolean", "description": "Include the list of links found on each page in the output (also used as crawl targets when crawling is on).", "default": true }, "crawl": { "title": "Crawl the site (follow links)", "type": "boolean", "description": "Beyond the URLs you provide, follow links to discover and convert more pages, up to the limits below.", "default": false }, "maxPages": { "title": "Max pages", "minimum": 1, "maximum": 5000, "type": "integer", "description": "Hard cap on the total number of pages converted (across all seeds). Protects you from runaway crawls and cost.", "default": 10 }, "maxDepth": { "title": "Max crawl depth", "minimum": 0, "maximum": 10, "type": "integer", "description": "How many link-hops away from your seed URLs to follow. 0 = only the URLs you gave. 1 = them plus pages they link to, etc.", "default": 1 }, "sameDomainOnly": { "title": "Stay on the same domain", "type": "boolean", "description": "Only follow links that stay on the seed page's domain.", "default": true }, "respectRobotsTxt": { "title": "Respect robots.txt", "type": "boolean", "description": "Skip pages disallowed by the site's robots.txt. Recommended — polite crawling.", "default": true }, "useSitemap": { "title": "Discover URLs from sitemap.xml", "type": "boolean", "description": "When crawling, also seed from the site's own sitemap.xml (and any Sitemap: entries in robots.txt) — the fastest, most complete way to reach every page. Subject to the URL filters below.", "default": false }, "includeUrlPatterns": { "title": "Include URL patterns", "type": "array", "description": "Only crawl/keep discovered URLs matching these glob patterns (* = wildcard), e.g. https://site.com/blog/* or */docs/*. Empty = allow all. Does not filter the URLs you explicitly provide.", "default": [], "items": { "type": "string" } }, "excludeUrlPatterns": { "title": "Exclude URL patterns", "type": "array", "description": "Skip discovered URLs matching these glob patterns (* = wildcard), e.g. */tag/*, */login*, *.pdf.", "default": [], "items": { "type": "string" } }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "maximum": 15, "type": "integer", "description": "How many pages to fetch in parallel. Higher = faster crawls, but uses more memory — be considerate of the target site.", "default": 5 }, "removeSelectors": { "title": "Remove elements (CSS selectors)", "type": "array", "description": "Extra CSS selectors to delete before extraction, e.g. '.related-articles' or '#comments'.", "default": [], "items": { "type": "string" } }, "waitUntil": { "title": "Wait until", "enum": [ "load", "domcontentloaded", "networkidle" ], "type": "string", "description": "When to consider a page loaded (only applies when Render JavaScript is on).", "default": "load" }, "timeoutMs": { "title": "Timeout per page (ms)", "minimum": 5000, "maximum": 120000, "type": "integer", "description": "Max time to wait for a page before giving up on it.", "default": 45000 }, "proxyConfiguration": { "title": "Proxy", "type": "object", "description": "Off by default (fast, works on most sites). Enable Apify Proxy — including residential — for bot-protected sites that block datacenter IPs.", "default": { "useApifyProxy": 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 } } } } } } } } } }