# Website to Markdown Crawler for LLM & RAG (`anatolia-data/website-to-markdown-crawler`) Actor

Crawl any website or docs and get clean Markdown for LLMs, RAG and AI agents. Strips menus, footers and cookie banners, keeps headings, lists, tables, code and links. Follows links or the sitemap. Pay per page.

- **URL**: https://apify.com/anatolia-data/website-to-markdown-crawler.md
- **Developed by:** [Oğulcan Katmer](https://apify.com/anatolia-data) (community)
- **Security:** Limited permissions
- **Stats:** 2 total users, 1 monthly users, 100.0% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

from $1.00 / 1,000 pages

This Actor is paid per event. You are not charged for the Apify platform usage, but only a fixed price for specific events.

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

## What's an Apify Actor?

An Actor is a serverless cloud program that runs on the Apify platform. It has two run modes.
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.

Apify vocabulary and the platform model are defined once, in the agent quickstart at https://apify.com/agents.md.

## 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.

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 examples already wired to this Actor's own input schema, see the [API](#api) section below.

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`).

# README

## Website to Markdown Crawler for LLM & RAG

Turn any website, documentation or blog into **clean Markdown** ready for ChatGPT, Claude, RAG pipelines, vector databases and AI agents.

The crawler removes menus, headers, footers, cookie banners and ads, and keeps what matters: headings, paragraphs, lists, tables, code blocks, links and image alt text. One row per page.

No browser, so it is fast and cheap. Pay only for pages saved.

### Use cases

- **RAG / knowledge bases:** load docs or help centers into a vector database
- **Custom GPTs and AI agents:** give an assistant a company's website as context
- **LLM fine-tuning datasets:** collect clean text from many pages
- **Content audits and migration:** export a whole site as Markdown

### Input

| Field | What it does |
|---|---|
| Start URLs | Sites, docs sections or single pages, e.g. `https://docs.example.com/guide/` |
| Max pages | Total pages to save (default 20) |
| Max link depth | How many clicks from the start URL to follow (0 = only the start pages) |
| Also use sitemap.xml | Discover pages from the sitemap too |
| Stay under the start path | Crawl only `/guide/...` when you start at `/guide/` |
| Only / Skip URLs matching | Glob filters like `**/blog/**` |
| Minimum words per page | Thin pages are skipped and not charged |

### Output

| Field | Description |
|---|---|
| `url`, `canonicalUrl` | Page address |
| `title`, `description`, `language` | From the page head |
| `markdown` | Clean Markdown of the main content |
| `wordCount`, `depth` | Size and distance from the start URL |
| `text`, `links` | Optional plain text and link list |

#### Example

```json
{
  "url": "https://docs.example.com/guide/install",
  "title": "Install – Example Docs",
  "wordCount": 412,
  "markdown": "# Install\n\nRun the installer...\n\n## Requirements\n\n- Node.js 20+\n- 2 GB RAM"
}
```

### Pricing

**$1.00 per 1,000 pages** saved. Pages under the minimum word count, failed pages and sitemap files are free.

### Limits

- It reads the HTML the server sends. Pages that only render text with JavaScript in the browser may come back empty.
- Sites that block bots or need a login are not supported.

### Related

- [Website Contact Finder – Emails, Phones & Socials](https://apify.com/anatolia-data/website-contact-finder)
- [Website Tech Stack Detector](https://apify.com/anatolia-data/website-tech-stack-detector)

# Actor input Schema

## `startUrls` (type: `array`):

Websites, docs sections or single pages to convert. The crawler stays on the same site and (by default) under the same path.

## `maxPages` (type: `integer`):

Maximum number of pages saved in total.

## `maxDepth` (type: `integer`):

How many clicks away from the start URL to follow links. 0 = only the start URLs.

## `useSitemap` (type: `boolean`):

Find pages from the site's sitemap.xml as well as by following links.

## `stayOnPath` (type: `boolean`):

Only crawl pages whose path starts with the start URL's folder (e.g. /docs/).

## `includeUrlGlobs` (type: `array`):

Optional glob patterns, e.g. https://example.com/blog/\*\*

## `excludeUrlGlobs` (type: `array`):

Optional glob patterns to skip, e.g. **/tag/**

## `minWords` (type: `integer`):

Pages with less text are skipped and not charged.

## `keepNavigation` (type: `boolean`):

Off: only the main content is converted.

## `includeText` (type: `boolean`):

Adds a plain-text version of the main content.

## `includeLinks` (type: `boolean`):

Adds the list of links found on the page.

## `proxyConfiguration` (type: `object`):

Apify Proxy is used by default.

## `maxConcurrency` (type: `integer`):

Pages fetched in parallel.

## Actor input object example

```json
{
  "startUrls": [
    {
      "url": "https://docs.apify.com/academy/web-scraping-for-beginners"
    }
  ],
  "maxPages": 20,
  "maxDepth": 2,
  "useSitemap": false,
  "stayOnPath": true,
  "includeUrlGlobs": [],
  "excludeUrlGlobs": [],
  "minWords": 20,
  "keepNavigation": false,
  "includeText": false,
  "includeLinks": false,
  "proxyConfiguration": {
    "useApifyProxy": true
  },
  "maxConcurrency": 10
}
```

# Actor output Schema

## `results` (type: `string`):

All pages as JSON.

## `overview` (type: `string`):

Open the dataset in a table view.

# 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 = {
    "startUrls": [
        {
            "url": "https://docs.apify.com/academy/web-scraping-for-beginners"
        }
    ]
};

// Run the Actor and wait for it to finish
const run = await client.actor("anatolia-data/website-to-markdown-crawler").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 = { "startUrls": [{ "url": "https://docs.apify.com/academy/web-scraping-for-beginners" }] }

# Run the Actor and wait for it to finish
run = client.actor("anatolia-data/website-to-markdown-crawler").call(run_input=run_input)

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

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

```

## CLI example

```bash
echo '{
  "startUrls": [
    {
      "url": "https://docs.apify.com/academy/web-scraping-for-beginners"
    }
  ]
}' |
apify call anatolia-data/website-to-markdown-crawler --silent --output-dataset

```

## MCP server setup

```json
{
    "mcpServers": {
        "apify": {
            "type": "http",
            "url": "https://mcp.apify.com/?tools=fetch-actor-details,anatolia-data/website-to-markdown-crawler"
        }
    }
}
```

The hosted server signs you in with OAuth on first connect, so no API token belongs in this config. Clients without OAuth support can send an `Authorization: Bearer <APIFY_API_TOKEN>` header instead, using a token from API & Integrations in Apify Console (https://console.apify.com/settings/integrations).

## OpenAPI specification

Download the OpenAPI definition: https://api.apify.com/v2/actors/jht8ntXgwl1EccTRO/builds/H8GZZBHWBxSuBXi6E/openapi.json