# Turn Any Web Page Into Structured JSON With Plain English

**Use case:** 

Describe the data you want in plain English, add a link, and get clean JSON that matches your schema. The example reads the first page of a book store and returns the first 5 books with their title and price. Replace the link and the instruction with your own. No login, no API key, and fields that are not on the page come back empty instead of invented.

## Input

```json
{
  "startUrls": [
    {
      "url": "https://books.toscrape.com/"
    }
  ],
  "instructions": "List the first 5 books on the page with their title, price in GBP and star rating from 1 to 5.",
  "outputSchema": {
    "includePersonalData": false,
    "instructions": "List the first 5 books on the page with their title and price in GBP.",
    "maxPages": 1,
    "startUrls": [
      {
        "url": "https://books.toscrape.com/"
      }
    ],
    "useBrowserFallback": false,
    "outputSchema": {
      "type": "object",
      "properties": {
        "books": {
          "type": "array",
          "items": {
            "type": "object",
            "properties": {
              "title": {
                "type": "string"
              },
              "priceGbp": {
                "type": [
                  "number",
                  "null"
                ]
              }
            },
            "required": [
              "title"
            ]
          }
        }
      },
      "required": [
        "books"
      ]
    }
  },
  "maxPages": 1,
  "model": "google/gemini-2.5-flash-lite",
  "useBrowserFallback": false,
  "includePersonalData": false
}
```

## Output

```json
{
  "url": {
    "label": "Page",
    "format": "string"
  },
  "status": {
    "label": "Status",
    "format": "string"
  },
  "title": {
    "label": "Title",
    "format": "string"
  },
  "data": {
    "label": "Extracted data",
    "format": "object"
  },
  "error": {
    "label": "Error",
    "format": "string"
  },
  "fetchedVia": {
    "label": "Fetched via",
    "format": "string"
  },
  "scrapedAt": {
    "label": "Scraped at",
    "format": "string"
  }
}
```

## How it works

### 1. Sign up on Apify or log in

The AI Web Scraper: Any Page to Validated JSON, Plain English Actor is ready to run with the inputs already set for "Turn Any Web Page Into Structured JSON With Plain English". [Sign up or log in](https://console.apify.com/create-task-from-example/fuiCaTfowdqrCo4HQ) and you'll land in Apify Console with a copy of this exact task.

### 2. Start the "Turn Any Web Page Into Structured JSON With Plain English" task

The AI Web Scraper: Any Page to Validated JSON, Plain English Actor will start running based on the input automatically. You can also change all the input fields, like start urls, extraction request, and more, to match your specific use case.

### 3. Receive the "Turn Any Web Page Into Structured JSON With Plain English" output

Monitor the progress in real time. You will be notified as soon as your dataset is complete and ready for review. Each result includes data such as page, status, title, and more.

### 4. Integrate into your workflow

The final output is delivered in JSON, CSV, or Excel format, ready to be plugged into your workflow. You can also [run the "Turn Any Web Page Into Structured JSON With Plain English" task via API](https://apify.com/conserving_celerytop/ai-web-scraper.md).

## About this Actor

This example demonstrates how to use [AI Web Scraper: Any Page to Validated JSON, Plain English](https://apify.com/conserving_celerytop/ai-web-scraper.md) with a specific input configuration. Visit the [Actor detail page](https://apify.com/conserving_celerytop/ai-web-scraper.md) to learn more, explore other use cases, and run it yourself.


## How to integrate an Actor?

This Task's input is already configured above. Use it as-is rather than inventing a new one.

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 full API examples (JavaScript, Python, CLI, MCP, OpenAPI), see this Task's Actor page: https://apify.com/conserving_celerytop/ai-web-scraper.md

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`).