{ "openapi": "3.0.1", "info": { "title": "Sitemap to Markdown Crawler — Website to Markdown for LLM & RAG", "description": "Website to markdown crawler: give a domain, it finds the sitemap, fetches pages over plain HTTP and returns clean Markdown, headings, links, lastmod and content hash. Incremental re-crawls. Export JSON/CSV/Excel.", "version": "0.1", "x-build-id": "55FjjhyrOb7EAlujT" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/leadsbrary~sitemap-to-markdown-crawler/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-leadsbrary-sitemap-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/leadsbrary~sitemap-to-markdown-crawler/runs": { "post": { "operationId": "runs-sync-leadsbrary-sitemap-to-markdown-crawler", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/leadsbrary~sitemap-to-markdown-crawler/run-sync": { "post": { "operationId": "run-sync-leadsbrary-sitemap-to-markdown-crawler", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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 pages to convert. A homepage or bare domain triggers robots.txt/sitemap discovery; a sitemap URL is used directly; other URLs are crawl seeds.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "maxResults": { "title": "Maximum pages", "minimum": 1, "maximum": 100000, "type": "integer", "description": "Maximum number of pages delivered (and billed) in this run.", "default": 50 }, "discoveryMode": { "title": "Discovery mode", "enum": [ "sitemap_then_links", "sitemap_only", "links_only" ], "type": "string", "description": "Sitemap first with link-following fallback, sitemap only, or link-following only.", "default": "sitemap_then_links" }, "includeUrlPatterns": { "title": "Include URL patterns", "type": "array", "description": "Glob patterns (e.g. https://crawlee.dev/js/docs/**). When set, only matching URLs are converted.", "default": [], "items": { "type": "string" } }, "excludeUrlPatterns": { "title": "Exclude URL patterns", "type": "array", "description": "Glob patterns of URLs to skip (e.g. **/tags/**, **/*.pdf).", "default": [], "items": { "type": "string" } }, "maxCrawlDepth": { "title": "Max link depth", "minimum": 0, "maximum": 10, "type": "integer", "description": "Link depth from start URLs when following links (not used for sitemap URLs).", "default": 3 }, "changedSince": { "title": "Changed since (date)", "type": "string", "description": "ISO date (e.g. 2026-09-01). Only sitemap URLs with lastmod on/after this date are crawled; URLs without lastmod are kept." }, "skipUnchanged": { "title": "Skip unchanged pages (incremental)", "type": "boolean", "description": "Store a content hash per URL and skip (not output, not billed) pages unchanged since the previous run with the same state key.", "default": false }, "stateKey": { "title": "State key", "type": "string", "description": "Name of the incremental state. Defaults to the first start URL hostname." }, "contentSelector": { "title": "Content CSS selector", "type": "string", "description": "Optional CSS selector of the main content. Otherwise main/article/[role=main] heuristics are used." }, "removeSelectors": { "title": "Remove CSS selectors", "type": "array", "description": "Extra CSS selectors removed before conversion (e.g. .cookie-banner).", "default": [], "items": { "type": "string" } }, "includeHtml": { "title": "Include cleaned HTML", "type": "boolean", "description": "Also output the cleaned HTML of the main content.", "default": false }, "respectRobotsTxt": { "title": "Respect robots.txt", "type": "boolean", "description": "Skip URLs disallowed by robots.txt.", "default": true }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "maximum": 50, "type": "integer", "description": "Parallel requests.", "default": 10 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Only needed if the target blocks direct requests (datacenter proxy is usually enough).", "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 }, "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 } } } } } } } } } }