{ "openapi": "3.0.1", "info": { "title": "Docs Site to Markdown Corpus", "description": "Turn any documentation site into a clean Markdown corpus: one file per page with front matter (title, URL, breadcrumbs), headings, code blocks with languages, tables and absolute links, plus an INDEX.json. Built for LLM wikis, RAG and offline docs. Pay per page.", "version": "0.2", "x-build-id": "JrpL3xTsLGbxeg8YW" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/vellumlabs~docs-to-markdown-corpus/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-vellumlabs-docs-to-markdown-corpus", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/vellumlabs~docs-to-markdown-corpus/runs": { "post": { "operationId": "runs-sync-vellumlabs-docs-to-markdown-corpus", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/vellumlabs~docs-to-markdown-corpus/run-sync": { "post": { "operationId": "run-sync-vellumlabs-docs-to-markdown-corpus", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "Documentation pages to start from. By default the crawler stays on the same host and under the same path prefix as each start URL (e.g. `https://docs.example.com/guide/` only crawls `/guide/**`). Use **Include URL globs** to widen or narrow the scope.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "maxPages": { "title": "Max pages", "minimum": 1, "maximum": 100000, "type": "integer", "description": "Hard cap on the number of pages crawled in one run. Each stored page is one `page-scraped` billing event, so this also caps your cost.", "default": 200 }, "maxCrawlDepth": { "title": "Max crawl depth", "minimum": 0, "maximum": 100, "type": "integer", "description": "How many link hops away from the start URLs the crawler may go. `0` = only the start URLs.", "default": 20 }, "stateKey": { "title": "Watch mode: state key (only new and changed pages since the last run)", "type": "string", "description": "Name of a key-value store that remembers the content hash of every page already exported, e.g. `apify-docs-watch`. With a state key, each run re-crawls the site but returns and bills **only pages that are new or whose content changed** since the previous run with the same key; unchanged pages are skipped for free. Pages that disappeared are listed in `CHANGES.json` (only after a complete crawl, i.e. not cut by Max pages or the budget). Leave empty for a normal one-off export. Use one key per site / per scope, and set Max pages above the site's size.", "default": "" }, "includeUrlGlobs": { "title": "Include URL globs", "type": "array", "description": "Only follow links matching at least one of these globs (e.g. `https://docs.example.com/guide/**`). Leave empty to derive one glob per start URL automatically (same host, same path prefix).", "default": [], "items": { "type": "string" } }, "excludeUrlGlobs": { "title": "Exclude URL globs", "type": "array", "description": "Never follow links matching these globs. Binary files, feeds, search and edit pages are always excluded.", "default": [], "items": { "type": "string" } }, "contentSelector": { "title": "Content CSS selector", "type": "string", "description": "CSS selector of the main content element. Leave empty to auto-detect (`article`, `main`, `[role=main]`, common docs-framework wrappers such as Docusaurus, MkDocs, GitBook, ReadTheDocs, VitePress, Mintlify, Sphinx, Nextra).", "default": "" }, "removeSelectors": { "title": "Remove elements (CSS selectors)", "type": "array", "description": "Elements removed from the content before conversion. Added on top of the built-in list (navigation, sidebars, footers, edit links, copy buttons, cookie banners, table-of-contents, breadcrumbs, scripts, styles).", "default": [], "items": { "type": "string" } }, "saveMarkdownFiles": { "title": "Also save one .md file per page to the key-value store", "type": "boolean", "description": "When enabled, each page is additionally written to the run's key-value store as `page-.md` with YAML front matter, and an `INDEX.json` manifest is written at the end. Handy for dropping straight into Obsidian, Claude Code or an LLM wiki.", "default": true }, "includeHtml": { "title": "Include cleaned HTML in output", "type": "boolean", "description": "Adds the cleaned content HTML to each dataset item. Increases dataset size.", "default": false }, "respectRobotsTxt": { "title": "Respect robots.txt", "type": "boolean", "description": "Skip URLs disallowed by the target site's robots.txt. Strongly recommended; leave on unless you own the site.", "default": true }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "maximum": 50, "type": "integer", "description": "Maximum parallel requests. Lower it for small or rate-limited sites.", "default": 8 }, "maxRequestsPerMinute": { "title": "Max requests per minute", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Politeness throttle per run.", "default": 240 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Proxy settings. Most public docs sites need no proxy; enable Apify Proxy only if you get blocked.", "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 } } } } } } } } } }