# Web Page to Markdown & Clean Text for AI (`datasetworks/web-to-text`) Actor

Turn any web page into clean Markdown or plain text for LLMs, RAG and AI agents. Strips menus, ads and boilerplate. Fast, cheap at $1 per 1,000 pages, respects robots.txt.

- **URL**: https://apify.com/datasetworks/web-to-text.md
- **Developed by:** [Dataset Works](https://apify.com/datasetworks) (community)
- **Categories:** AI, Developer tools
- **Features:** Limited permissions
- **Stats:** 2 total users, 1 monthly users, 100.0% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

$1.00 / 1,000 page converteds

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

## Web Page to Markdown & Clean Text for AI

**Turn any web page into clean Markdown or plain text, ready for an LLM, a RAG pipeline or an AI agent.**

Give it URLs. It fetches each page, strips menus, cookie banners, sidebars and footers, and returns the main content as tidy Markdown (headings, lists, links and tables kept) and/or plain text. Fast and lightweight: no browser, results in seconds.

### Sample output

| url | title | wordCount | markdown (start) |
| --- | --- | --- | --- |
| https://en.wikipedia.org/wiki/Web_scraping | Web scraping | 4083 | `**Web scraping**, **web harvesting**, or **web data extraction** is [data scraping](...) used for...` |
| https://www.bbc.co.uk/news | Home - BBC News | 3136 | `## Top stories ...` |

Each result also has `status`, `httpStatus`, `description`, `language`, `truncated`, `depth`, `fetchedAt` and, if you ask for it, `links`.

### How to use

1. Paste one or more URLs into **URLs**.
2. Choose **Markdown**, **Plain text** or both.
3. Optional: **Follow links** to also convert linked pages in the same site section (depth 1, 2...), **Max pages**, and **Max characters per page** to fit a model's context window.
4. Run, then export as JSON, CSV or Excel, or read results via the API.

Pages that can't be converted are listed with `status: "failed"` or `"skipped"` and a reason, and are not charged.

### Pricing

**$1 per 1,000 pages converted** ($0.001 per page). Failed and skipped pages are free. Platform usage is included.

### For AI agents

Call it through the Apify API or the Apify MCP server with `{"startUrls": [{"url": "https://example.com/article"}], "maxCharsPerPage": 20000}` and read `markdown` from the result. Every result has the same fields, and errors come back as data rather than crashes, so agents can handle them.

### Limits

This tool reads the HTML a site sends. Pages that only show content after JavaScript runs, or that need a login, will return little or no text. Sites whose robots.txt disallows automated access are skipped.

### Data and responsibility

The tool fetches only public pages, identifies itself honestly as DatasetWorksBot, follows robots.txt and crawl delays, and never logs in or gets around captchas or blocks. You are responsible for how you use the content you convert, including copyright and any personal data on the pages you choose.

### Support

Found a bug or need a feature? Open an issue on this page and we'll reply within one working day.

Built and maintained by **Dataset Works**.

# Actor input Schema

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

Pages to convert. Each one becomes one result.

## `outputFormats` (type: `array`):

Markdown keeps headings, lists, links and tables. Text is plain text with line breaks.

## `mainContentOnly` (type: `boolean`):

Removes menus, footers, cookie banners and sidebars, keeping the article or main body.

## `crawlDepth` (type: `integer`):

0 converts only the URLs you give. 1 also converts pages they link to on the same site and section, and so on.

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

Upper limit on pages converted in this run.

## `maxCharsPerPage` (type: `integer`):

Cut each page's output to this length, to fit an AI model's context. Leave empty for no limit.

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

Adds a list of all links on each page.

## Actor input object example

```json
{
  "startUrls": [
    {
      "url": "https://docs.apify.com/academy/web-scraping-for-beginners"
    }
  ],
  "outputFormats": [
    "markdown"
  ],
  "mainContentOnly": true,
  "crawlDepth": 0,
  "maxPages": 50,
  "includeLinks": false
}
```

# Actor output Schema

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

No description

# 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("datasetworks/web-to-text").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("datasetworks/web-to-text").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 datasetworks/web-to-text --silent --output-dataset

```

## MCP server setup

```json
{
    "mcpServers": {
        "apify": {
            "type": "http",
            "url": "https://mcp.apify.com/?tools=fetch-actor-details,datasetworks/web-to-text"
        }
    }
}
```

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/aGY8gMSlpOUWXqiKH/builds/ozqmTNoRRvbl33dYq/openapi.json
