# Scrape Documentation into Markdown for RAG

**Use case:** 

Turn any documentation site into a clean Markdown corpus for retrieval-augmented generation and knowledge bases.

## Input

```json
{
  "startUrls": [
    {
      "url": "https://docs.python.org/3/"
    }
  ],
  "maxRequestsPerCrawl": 100,
  "maxDepth": 3,
  "globs": [],
  "includeMetadata": true
}
```

## Output

```json
{
  "url": {
    "label": "Source URL",
    "format": "link"
  },
  "title": {
    "label": "Page Title",
    "format": "text"
  },
  "markdown": {
    "label": "Markdown (Snippet)",
    "format": "text"
  },
  "author": {
    "label": "Author",
    "format": "text"
  },
  "wordCount": {
    "label": "Word Count",
    "format": "number"
  }
}
```

## About this Actor

This example demonstrates how to use [LLM Markdown Crawler](https://apify.com/sleek_waveform/llm-markdown-crawler) with a specific input configuration. Visit the [Actor detail page](https://apify.com/sleek_waveform/llm-markdown-crawler) to learn more, explore other use cases, and run it yourself.