# AI Web Scraper: Extract Any Data From Any Page in Plain English (`lanky_quantifier/ai-web-scraper`) Actor

- **URL**: https://apify.com/lanky\_quantifier/ai-web-scraper.md
- **Developed by:** [Vhub Systems](https://apify.com/lanky_quantifier) (community)
- **Categories:** Developer tools, AI, E-commerce
- **Stats:** 2 total users, 1 monthly users, 100.0% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

Pay per usage

This Actor is paid per platform usage. The Actor is free to use, and you only pay for the Apify platform usage, which gets cheaper the higher subscription plan you have.

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

## 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

## AI Web Scraper — Extract Any Data From Any Page in Plain English

**Stop writing CSS selectors.** Point this actor at any URL, describe the fields you
want in plain English, and get clean structured JSON back. Powered by an LLM, so it
keeps working even when the site changes its layout.

### Why this over a normal scraper

| Normal scraper | AI Web Scraper |
|----------------|----------------|
| You write & maintain CSS/XPath selectors | You write one sentence |
| Breaks on every redesign | Survives redesigns (reads the page like a human) |
| One scraper per site | One actor for **any** site |
| Needs a developer | Anyone can use it |

### How to use

1. **URLs to scrape** — paste one or more page URLs.
2. **What to extract** — describe it: *"For each product: name, price, rating, in\_stock"*.
3. **List mode** — ON for repeated items (products, posts, rows), OFF for one object per page.
4. Run. Results land in the dataset as clean JSON, ready for Excel/Sheets/API.

### Example

**Input**

```json
{
  "startUrls": [{ "url": "https://news.ycombinator.com/" }],
  "extractionPrompt": "For each story: title, points, author, number_of_comments, url",
  "listMode": true
}
```

**Output** (verified live)

```json
[
  { "title": "SearXNG: A free internet metasearch engine", "points": 101, "author": "theanonymousone", "number_of_comments": 24 },
  { "title": "Giant trees have no trouble pumping water to top branches", "points": 29, "author": "hhs", "number_of_comments": 11 }
]
```

### Use cases

- **E-commerce** — product name, price, rating, availability across any shop.
- **Lead-gen** — names, titles, emails, companies from directory pages.
- **Real estate / jobs / listings** — structured rows from any listing site.
- **News / research** — headlines, authors, dates, summaries.
- **Anything with repeated items** — no selector, just describe it.

### Pricing

**Pay per result.** You're charged per extracted item — no monthly fee, no charge for
empty pages. Cheap on small jobs, scales linearly on big ones.

### Notes

- Reads visible page text (not raw HTML), so it's robust to markup changes.
- Returns `null` for fields it can't find — it never invents data.
- Large pages are trimmed before extraction to keep runs fast and cheap.
- Each item includes `_sourceUrl` so you always know where it came from.

Built by **Vhub Systems**.

# Actor input Schema

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

One or more page URLs to extract data from.

## `extractionPrompt` (type: `string`):

Describe the fields you want, e.g. 'For each story: title, points, author, number of comments, url'.

## `listMode` (type: `boolean`):

ON = return an array of repeated items (products, posts, rows). OFF = return a single object for the whole page.

## `maxItems` (type: `integer`):

Cap on items returned per page (list mode).

## `maxCharsToLLM` (type: `integer`):

Trims the cleaned page text before sending to the LLM to control cost/latency.

## Actor input object example

```json
{
  "startUrls": [
    {
      "url": "https://news.ycombinator.com/"
    }
  ],
  "extractionPrompt": "For each story on the page: title, points, author, number_of_comments, url",
  "listMode": true,
  "maxItems": 50,
  "maxCharsToLLM": 24000
}
```

# 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://news.ycombinator.com/"
        }
    ],
    "extractionPrompt": "For each story on the page: title, points, author, number_of_comments, url"
};

// Run the Actor and wait for it to finish
const run = await client.actor("lanky_quantifier/ai-web-scraper").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://news.ycombinator.com/" }],
    "extractionPrompt": "For each story on the page: title, points, author, number_of_comments, url",
}

# Run the Actor and wait for it to finish
run = client.actor("lanky_quantifier/ai-web-scraper").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": [
    {
      "url": "https://news.ycombinator.com/"
    }
  ],
  "extractionPrompt": "For each story on the page: title, points, author, number_of_comments, url"
}' |
apify call lanky_quantifier/ai-web-scraper --silent --output-dataset

```

## MCP server setup

```json
{
    "mcpServers": {
        "apify": {
            "command": "npx",
            "args": [
                "mcp-remote",
                "https://mcp.apify.com/?tools=lanky_quantifier/ai-web-scraper",
                "--header",
                "Authorization: Bearer <YOUR_API_TOKEN>"
            ]
        }
    }
}

```

## OpenAPI specification

Download the OpenAPI definition: https://api.apify.com/v2/actors/icjkLFtOmTI5R6qcZ/builds/9ydJnFRbYIKBprsQ7/openapi.json