# RAG-Markdown Extractor (`hachi-dev/rag-markdown-extractor`) Actor

The ultimate web-to-markdown tool for AI builders. Extracts clean content from any site, auto-dismisses cookie banners, and handles SPAs with Playwright. Optimized for LangChain, LlamaIndex, and RAG pipelines. Save token costs with 99% noise-free markdown.

- **URL**: https://apify.com/hachi-dev/rag-markdown-extractor.md
- **Developed by:** [JI JUN](https://apify.com/hachi-dev) (community)
- **Categories:** AI, Automation, Developer tools
- **Features:** Limited permissions
- **Stats:** 5 total users, 0 monthly users, 100.0% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

from $17.70 / 1,000 results

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

## RAG-Markdown Extractor

🧹 Extracts the **main content** from any web page and outputs it as clean, structured **Markdown** — optimized for Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), and vector databases.

### ✨ Why This Actor?

| Problem | Solution |
|---------|----------|
| Web pages are full of ads, navbars, cookie banners, and boilerplate | **50+ noise selectors** + text-based heuristics strip everything automatically |
| SPAs don't render with simple HTTP requests | **Playwright headless browser** waits for dynamic content to fully render |
| Cookie consent dialogs leak into scraped text | **Auto-dismiss** consent popups before extraction |
| You need structured metadata alongside content | Every output includes **title, source URL, date, category, keywords, author** |

### 🚀 Features

- **Deep Noise Removal** — 50+ CSS selectors + text-matching heuristics remove ads, navbars, footers, sidebars, cookie/GDPR banners, modals, and more.
- **Cookie Consent Auto-Dismiss** — Automatically clicks "Accept"/"Allow All" buttons so they don't pollute the output.
- **Smart Markdown Formatting** — Preserves headings, lists, code blocks, and links using [Turndown](https://github.com/mixmark-io/turndown).
- **SPA Support** — Uses Playwright to fully render JavaScript-heavy Single Page Applications before extraction.
- **Proxy Support** — Bypass anti-bot protections with Apify Proxy.
- **Metadata Enrichment** — Outputs word count, character count, description, and structured metadata header.
- **Empty Image Cleanup** — Strips decorative images with no alt text to reduce noise.

### 📦 Output Format

Each item in the output dataset contains:

| Field | Type | Description |
|-------|------|-------------|
| `url` | string | Source URL of the page |
| `title` | string | Page title |
| `description` | string | Meta description of the page |
| `wordCount` | number | Number of words in the extracted content |
| `charCount` | number | Number of characters in the extracted content |
| `markdown` | string | The cleaned Markdown with metadata header |

#### Example Output

```markdown
## Building RAG Pipelines

> **Source:** https://example.com/rag-pipelines
> **Extracted:** 2026-03-01
> **Category:** AI Engineering
> **Author:** Jane Doe

---

Retrieval-Augmented Generation (RAG) is a technique that...
```

### ⚙️ Input Parameters

| Parameter | Type | Default | Description |
|-----------|------|---------|-------------|
| `startUrls` | Array | *required* | List of URLs to extract Markdown from |
| `maxConcurrency` | Integer | `5` | Max pages processed in parallel |
| `waitForSPA` | Integer (ms) | `2000` | Extra wait time for SPA rendering |
| `proxyConfiguration` | Object | Apify Proxy | Proxy settings to bypass blocks |

### 🎯 Use Cases

- **RAG Pipeline Data Ingestion** — Feed clean Markdown directly into LangChain, LlamaIndex, or custom RAG systems.
- **Knowledge Base Building** — Bulk-extract documentation, articles, or blog posts into a structured format.
- **AI Training Data** — Collect clean text from the web for fine-tuning language models.
- **Content Monitoring** — Track changes in competitor content or news articles over time.
- **Research & Analysis** — Extract and analyze articles at scale without manual copy-pasting.

### 💻 Usage

Run on the Apify Platform via the UI, or locally:

```bash
apify run -p
```

# Actor input Schema

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

A list of URLs to extract Markdown from. Each URL will be visited by a headless browser and its main content will be converted to clean Markdown.

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

Maximum number of pages to process in parallel. Lower values use less memory; higher values finish faster.

## `waitForSPA` (type: `integer`):

Extra milliseconds to wait after DOM is loaded, giving Single Page Applications time to render dynamic content.

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

Select proxies to be used by your crawler. Recommended to bypass anti-bot protections.

## Actor input object example

```json
{
  "startUrls": [
    {
      "url": "https://apify.com/about"
    }
  ],
  "maxConcurrency": 5,
  "waitForSPA": 2000,
  "proxyConfiguration": {
    "useApifyProxy": 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 = {
    "startUrls": [
        {
            "url": "https://apify.com/about"
        }
    ],
    "proxyConfiguration": {
        "useApifyProxy": true
    }
};

// Run the Actor and wait for it to finish
const run = await client.actor("hachi-dev/rag-markdown-extractor").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://apify.com/about" }],
    "proxyConfiguration": { "useApifyProxy": True },
}

# Run the Actor and wait for it to finish
run = client.actor("hachi-dev/rag-markdown-extractor").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://apify.com/about"
    }
  ],
  "proxyConfiguration": {
    "useApifyProxy": true
  }
}' |
apify call hachi-dev/rag-markdown-extractor --silent --output-dataset

```

## MCP server setup

```json
{
    "mcpServers": {
        "apify": {
            "type": "http",
            "url": "https://mcp.apify.com/?tools=fetch-actor-details,hachi-dev/rag-markdown-extractor"
        }
    }
}
```

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/L9EyRm6dfOnw2Lja7/builds/1I6uD37ZVd3acnQ5m/openapi.json