# Crawl a Docs Subtree into Markdown Chunks

**Use case:** 

Crawl an authorized public docs or help subtree into Markdown pages with nested chunks for RAG. Replace the sandbox URL with your /docs or /help section and declare the correct rights basis. The first run returns bounded PAGE rows; later runs create fresh snapshots for index refreshes.

## Input

```json
{
  "sources": [
    {
      "url": "https://books.toscrape.com/",
      "scope": "subtree",
      "rightsBasis": "permission",
      "rightsReference": "https://books.toscrape.com/",
      "attribution": "Scraping practice sandbox (books.toscrape.com)"
    }
  ],
  "sitemapUrls": [],
  "discoverSitemaps": false,
  "includeUrlGlobs": [],
  "excludeUrlGlobs": [],
  "maxPages": 10,
  "maxDepth": 2,
  "renderingMode": "http",
  "removeSelectors": [],
  "includeChunks": true,
  "chunkMaxChars": 6000,
  "chunkOverlapChars": 300,
  "maxDownloadMiB": 100
}
```

## Output

```json
{
  "source_url": {
    "label": "Final source URL",
    "format": "string"
  },
  "title": {
    "label": "Title",
    "format": "string"
  },
  "markdown": {
    "label": "Markdown",
    "format": "string"
  },
  "content_hash": {
    "label": "Content hash",
    "format": "string"
  },
  "fingerprint": {
    "label": "Semantic fingerprint",
    "format": "string"
  }
}
```

## About this Actor

This example demonstrates how to use [Website Content Crawler: Markdown for AI and RAG](https://apify.com/automa-flow/website-content-crawler.md) with a specific input configuration. Visit the [Actor detail page](https://apify.com/automa-flow/website-content-crawler.md) to learn more, explore other use cases, and run it yourself.


## How to integrate an Actor?

This Task's input is already configured above. Use it as-is rather than inventing a new one.

Do not guess an integration path. Every one of them is in the agent quickstart at https://apify.com/agents.md: the Apify MCP server, Agent Skills with the Apify CLI, the JavaScript and Python clients, the REST API, and the account-free path for an agent with no human to sign in. It also carries the rule on stating cost before the first paid run.

For full API examples (JavaScript, Python, CLI, MCP, OpenAPI), see this Task's Actor page: https://apify.com/automa-flow/website-content-crawler.md

Each client library has reference documentation the quickstart does not restate: [JavaScript/TypeScript](https://docs.apify.com/api/client/js/docs.md) (`npm install apify-client`) and [Python](https://docs.apify.com/api/client/python/docs.md) (`pip install apify-client`).