# Sitemap to RAG Dataset (`ghostgrid/sitemap-to-rag-dataset`) Actor

Convert any website sitemap into an LLM-ready dataset for RAG pipelines.

- **URL**: https://apify.com/ghostgrid/sitemap-to-rag-dataset.md
- **Developed by:** [GhostGrid](https://apify.com/ghostgrid) (community)
- **Categories:** AI, Developer tools, Automation
- **Stats:** 2 total users, 0 monthly users, 100.0% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

from $0.80 / 1,000 page extracteds

This Actor is paid per event and usage. You are charged both the fixed price for specific events and for Apify platform usage.

Learn more: https://docs.apify.com/platform/actors/running/actors-in-store#pay-per-event

## What's an Apify Actor?

Actors are web data automations that power AI and operations. They run on the Apify platform to scrape websites, process data, connect APIs, and automate workflows.
In Batch mode, an Actor accepts a well-defined JSON input, performs an action which can take anything from a few seconds to a few hours,
and optionally produces a well-defined JSON output, datasets with results, or files in key-value store.
In Standby mode, an Actor provides a web server which can be used as a website, API, or an MCP server.
Actors are written with capital "A".

## How to integrate an Actor?

If asked about integration, you help developers integrate Actors into their projects.
You adapt to their stack and deliver integrations that are safe, well-documented, and production-ready.
The best way to integrate Actors is as follows.

- **AI agents and MCP clients** — the [Apify MCP server](https://docs.apify.com/integrations/mcp.md) at `https://mcp.apify.com` (remote, streamable HTTP, OAuth on first use).
- **Agentic workflows and local Actor development** — [Agent Skills](https://apify.com/.well-known/agent-skills/index.json) with the [Apify CLI](https://docs.apify.com/cli/docs.md): `npm install -g apify-cli`, then `apify login`.
- **JavaScript/TypeScript projects** — the official [JS/TS client](https://docs.apify.com/api/client/js/docs.md): `npm install apify-client`.
- **Python projects** — the official [Python client](https://docs.apify.com/api/client/python/docs.md): `pip install apify-client`.
- **Any other language** — the [REST API](https://docs.apify.com/api/v2.md).

For usage examples, see the [API](#api) section below.

For more details, see Apify documentation as [Markdown index](https://docs.apify.com/llms.txt) and [Markdown full-text](https://docs.apify.com/llms-full.txt).

# README

## Sitemap to RAG Dataset

Feed it a sitemap URL (or just a homepage), get back clean text content from every page, formatted for RAG pipelines and LLM training.

### What it does

- Parses sitemap.xml files (including sitemap indexes, gzipped sitemaps, and auto-discovery from robots.txt)
- Crawls each page and strips out navigation, footers, sidebars, ads, and other boilerplate
- Outputs clean text and markdown versions of the main content
- Extracts metadata (title, description, keywords, Open Graph image)
- Detects page language and counts words
- Splits content into RAG-ready chunks with stable chunk IDs (UUID5 based on URL + index)
- Estimates token counts per chunk (len/4 heuristic)
- Computes SHA-256 content hashes for pages and chunks
- Supports diff mode to detect new, changed, and removed pages between crawls

### Input

| Parameter | Type | Default | Description |
|---|---|---|---|
| `sitemap_url` | string | *required* | URL to a sitemap.xml or a website homepage (auto-detects sitemap) |
| `max_pages` | integer | 100 | Max pages to crawl (1 - 10,000) |
| `include_linked_pages` | boolean | false | Also crawl pages linked from sitemap pages |
| `chunk_strategy` | string | fixed\_size | How to split text: `fixed_size`, `sentence`, or `paragraph` |
| `chunk_token_limit` | integer | 512 | Max tokens per chunk (100 - 4,096) |
| `diff_mode` | boolean | false | Compare with previous crawl, report new/changed/removed pages |
| `include_chunks` | boolean | true | Output RAG chunks as separate dataset items |

### Output

The dataset contains two types of records:

#### Page records (`type: "page"`)

One per crawled page:

| Field | Type | Description |
|---|---|---|
| `type` | string | Always `"page"` |
| `url` | string | Page URL |
| `title` | string | Page title |
| `text` | string | Clean main content as plain text |
| `markdown` | string | Content formatted as markdown |
| `content_hash` | string | SHA-256 hex digest of the page text |
| `metadata` | object | Description, keywords, OG image, canonical URL |
| `crawled_at` | string | ISO 8601 timestamp |
| `word_count` | integer | Word count of the extracted text |
| `language` | string | Detected language code (e.g. en) |

#### Chunk records (`type: "chunk"`)

One per RAG chunk (when `include_chunks` is true):

| Field | Type | Description |
|---|---|---|
| `type` | string | Always `"chunk"` |
| `url` | string | Source page URL |
| `title` | string | Source page title |
| `chunk_id` | string | Stable UUID5 (based on url:chunk\_index) |
| `chunk_index` | integer | 0-based index within the page |
| `total_chunks` | integer | Total chunks for this page |
| `text` | string | The chunk text |
| `start_char` | integer | Character offset in full page text |
| `end_char` | integer | End character offset |
| `token_estimate` | integer | Estimated tokens (len/4) |
| `content_hash` | string | SHA-256 of the chunk text |
| `page_content_hash` | string | SHA-256 of the full page text |
| `language` | string | Page language code |

#### Diff records (`type: "diff"`)

One per run when `diff_mode` is true:

| Field | Type | Description |
|---|---|---|
| `type` | string | Always `"diff"` |
| `new` | list | URLs found in this crawl but not the previous one |
| `changed` | list | URLs present in both but with different content hash |
| `removed` | list | URLs in the previous crawl but not this one |
| `crawl_time` | string | ISO 8601 timestamp of this crawl |
| `previous_crawl_time` | string | ISO 8601 timestamp of the previous crawl |
| `total_new` | integer | Count of new URLs |
| `total_changed` | integer | Count of changed URLs |
| `total_removed` | integer | Count of removed URLs |

### How to use

Run locally:

```bash
apify run --input '{"sitemap_url": "https://example.com/sitemap.xml"}'
```

With chunking and diff mode:

```bash
apify run --input '{"sitemap_url": "https://example.com/sitemap.xml", "max_pages": 50, "chunk_strategy": "paragraph", "chunk_token_limit": 256, "diff_mode": true}'
```

Deploy to Apify:

```bash
apify push
```

### Pricing

This actor uses pay-per-event (PPE) pricing. You are charged 1 event per page successfully crawled and extracted. Chunk records and diff records do not incur additional charges.

# Actor input Schema

## `sitemap_url` (type: `string`):

URL to a sitemap.xml file or a website homepage (we will auto-detect the sitemap).

## `max_pages` (type: `integer`):

Maximum number of pages to crawl from the sitemap.

## `include_linked_pages` (type: `boolean`):

Also crawl pages linked from sitemap pages.

## `chunk_strategy` (type: `string`):

How to split page text into RAG chunks.

## `chunk_token_limit` (type: `integer`):

Maximum tokens per chunk (tokens estimated as characters / 4).

## `diff_mode` (type: `boolean`):

Compare with previous crawl and report new/changed/removed pages.

## `include_chunks` (type: `boolean`):

Output RAG chunks as separate dataset items alongside raw pages.

## Actor input object example

```json
{
  "sitemap_url": "https://apify.com/sitemap.xml",
  "max_pages": 100,
  "include_linked_pages": false,
  "chunk_strategy": "fixed_size",
  "chunk_token_limit": 512,
  "diff_mode": false,
  "include_chunks": true
}
```

# API

You can run this Actor programmatically using our API. Below are code examples in JavaScript, Python, and CLI, as well as the OpenAPI specification and MCP server setup.

## JavaScript example

```javascript
import { ApifyClient } from 'apify-client';

// Initialize the ApifyClient with your Apify API token
// Replace the '<YOUR_API_TOKEN>' with your token
const client = new ApifyClient({
    token: '<YOUR_API_TOKEN>',
});

// Prepare Actor input
const input = {
    "sitemap_url": "https://apify.com/sitemap.xml"
};

// Run the Actor and wait for it to finish
const run = await client.actor("ghostgrid/sitemap-to-rag-dataset").call(input);

// Fetch and print Actor results from the run's dataset (if any)
console.log('Results from dataset');
console.log(`💾 Check your data here: https://console.apify.com/storage/datasets/${run.defaultDatasetId}`);
const { items } = await client.dataset(run.defaultDatasetId).listItems();
items.forEach((item) => {
    console.dir(item);
});

// 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/js/docs

```

## Python example

```python
from apify_client import ApifyClient

# Initialize the ApifyClient with your Apify API token
# Replace '<YOUR_API_TOKEN>' with your token.
client = ApifyClient("<YOUR_API_TOKEN>")

# Prepare the Actor input
run_input = { "sitemap_url": "https://apify.com/sitemap.xml" }

# Run the Actor and wait for it to finish
run = client.actor("ghostgrid/sitemap-to-rag-dataset").call(run_input=run_input)

# Fetch and print Actor results from the run's dataset (if there are any)
print("💾 Check your data here: https://console.apify.com/storage/datasets/" + run["defaultDatasetId"])
for item in client.dataset(run["defaultDatasetId"]).iterate_items():
    print(item)

# 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start

```

## CLI example

```bash
echo '{
  "sitemap_url": "https://apify.com/sitemap.xml"
}' |
apify call ghostgrid/sitemap-to-rag-dataset --silent --output-dataset

```

## MCP server setup

```json
{
    "mcpServers": {
        "apify": {
            "command": "npx",
            "args": [
                "mcp-remote",
                "https://mcp.apify.com/?tools=ghostgrid/sitemap-to-rag-dataset",
                "--header",
                "Authorization: Bearer <YOUR_API_TOKEN>"
            ]
        }
    }
}

```

## OpenAPI specification

Download the OpenAPI definition: https://api.apify.com/v2/actors/0LknHMphYQEKZozLW/builds/e3FLWo1AFZpjsB5hm/openapi.json