# RAG-Ready Website Crawler — Clean Content for LLMs & Vector DBs (`yourwingman/rag-ready-crawler`) Actor

Crawl websites and output clean, chunked content optimized for RAG pipelines, LLM training data, and vector databases. Built for AI knowledge bases and semantic search.

- **URL**: https://apify.com/yourwingman/rag-ready-crawler.md
- **Developed by:** [Wingman](https://apify.com/yourwingman) (community)
- **Categories:** Lead generation
- **Stats:** 2 total users, 1 monthly users, 100.0% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

Pay per event + usage

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

## Actor: RAG-Ready Website Crawler

Crawl any website and output clean, chunked content optimized for Retrieval-Augmented Generation (RAG) pipelines, LLM training data, and vector databases.

### Features

- **Clean content extraction**: Removes navigation, ads, sidebars, footers
- **Semantic chunking**: Smart split by headings and paragraphs
- **Markdown output**: Clean markdown format ideal for LLM consumption
- **Metadata extraction**: Title, description, headings, word count, publish date
- **Token counting**: Track approximate token counts per chunk
- **Same-domain crawling**: Respect site boundaries by default
- **Flexible crawling**: Configurable page limits and depth

### Use Cases

- Build RAG knowledge bases from documentation sites
- Collect training data for LLM fine-tuning
- Create vector database entries from web content
- Archive important web content in clean format
- Build AI-ready datasets from blogs and documentation

### Input

```json
{
  "startUrls": ["https://docs.example.com"],
  "maxPages": 50,
  "chunkSize": 2000,
  "chunkOverlap": 200,
  "includeMetadata": true,
  "outputFormat": "markdown",
  "excludeSelectors": ["nav", "footer", ".sidebar", ".advertisement"]
}
```

### Output

```json
{
  "url": "https://docs.example.com/getting-started",
  "title": "Getting Started",
  "chunkIndex": 0,
  "content": "# Getting Started\n\nWelcome to the documentation...",
  "tokenCount": 450,
  "charCount": 1850,
  "headings": ["Getting Started", "Installation", "Quick Start"],
  "metadata": {
    "description": "Learn how to get started with Example",
    "author": "Example Team",
    "publishDate": "2026-01-15"
  }
}
```

### Changelog

#### v1.0.0 (2026-07-09)

- Initial release
- Clean HTML-to-markdown content extraction
- Semantic chunking with configurable size/overlap
- Full metadata extraction
- Token counting for LLM context estimation
- Apify Dataset output with chunked entries

# Actor input Schema

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

URLs to start crawling from. Can be a single page or an entire site.

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

Maximum number of pages to crawl.

## `sameDomain` (type: `boolean`):

Only crawl pages on the same domain as start URLs.

## `chunkSize` (type: `integer`):

Target size for each content chunk. Used for RAG splitting.

## `chunkOverlap` (type: `integer`):

Overlap between consecutive chunks to maintain context.

## `includeMetadata` (type: `boolean`):

Include page metadata: description, keywords, author, publish date, etc.

## `excludeSelectors` (type: `array`):

CSS selectors to exclude from content (e.g., 'nav, footer, .sidebar').

## `outputFormat` (type: `string`):

Format for the extracted content.

## Actor input object example

```json
{
  "startUrls": [
    "https://docs.example.com"
  ],
  "maxPages": 50,
  "sameDomain": true,
  "chunkSize": 2000,
  "chunkOverlap": 200,
  "includeMetadata": true,
  "excludeSelectors": [
    "nav",
    "footer",
    ".sidebar",
    ".advertisement"
  ],
  "outputFormat": "markdown"
}
```

# Actor output Schema

## `url` (type: `string`):

URL of the crawled page

## `title` (type: `string`):

HTML title of the page

## `chunkIndex` (type: `string`):

Position of this chunk within the page content (0-based)

## `content` (type: `string`):

Cleaned formatted content (markdown, text, or HTML)

## `tokenCount` (type: `string`):

Estimated number of tokens (~4 chars/token)

## `charCount` (type: `string`):

Length of the content in characters

## `headings` (type: `string`):

Comma-separated list of h1/h2/h3 headings from the page

## `metadata_description` (type: `string`):

HTML meta description

## `metadata_keywords` (type: `string`):

HTML meta keywords

## `metadata_author` (type: `string`):

HTML meta author

## `metadata_publishDate` (type: `string`):

Article publication date

## `metadata_ogImage` (type: `string`):

Open Graph image URL

## `metadata_ogType` (type: `string`):

Open Graph content type

## `format` (type: `string`):

Content format (markdown, text, or html)

## `crawlTimestamp` (type: `string`):

ISO timestamp when the page was crawled

# 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": [
        "https://docs.example.com"
    ],
    "excludeSelectors": [
        "nav",
        "footer",
        ".sidebar",
        ".advertisement"
    ]
};

// Run the Actor and wait for it to finish
const run = await client.actor("yourwingman/rag-ready-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": ["https://docs.example.com"],
    "excludeSelectors": [
        "nav",
        "footer",
        ".sidebar",
        ".advertisement",
    ],
}

# Run the Actor and wait for it to finish
run = client.actor("yourwingman/rag-ready-crawler").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 '{
  "startUrls": [
    "https://docs.example.com"
  ],
  "excludeSelectors": [
    "nav",
    "footer",
    ".sidebar",
    ".advertisement"
  ]
}' |
apify call yourwingman/rag-ready-crawler --silent --output-dataset

```

## MCP server setup

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

```

## OpenAPI specification

Download the OpenAPI definition: https://api.apify.com/v2/acts/qwfQTTHl3X8dPg8Zl/builds/Xh8bTr2VYbCuCcMd5/openapi.json