# Any fields you define, from pages without markup

**Use case:** 

Pages with no structured data, extracted with AI into a custom JSON Schema (title, developer, price, currency, category, stock). Every value must quote the page or it is rejected, and readings such as true/false are kept separate from values found on the page. AI mode: model tokens are billed to the account running the Actor, bounded by maxLlmCostUsd.

## Input

```json
{
  "sourceMode": "urls",
  "urls": [
    "https://sandbox.oxylabs.io/products/1",
    "https://sandbox.oxylabs.io/products/12"
  ],
  "datasetOffset": 0,
  "schemaPreset": "custom",
  "extractionSchema": {
    "type": "object",
    "required": [
      "title",
      "price",
      "currency"
    ],
    "properties": {
      "title": {
        "type": "string",
        "description": "Title of the main product on the page, not related products"
      },
      "developer": {
        "type": "string"
      },
      "price": {
        "type": "number",
        "description": "Price of the main product as written"
      },
      "currency": {
        "type": "string",
        "description": "Currency exactly as written next to the price"
      },
      "gameType": {
        "type": "string",
        "enum": [
          "singleplayer",
          "multiplayer"
        ]
      },
      "inStock": {
        "type": "boolean",
        "description": "Whether the product is in stock"
      }
    }
  },
  "mode": "llm",
  "llmProvider": "apify-openrouter",
  "llmModel": "openai/gpt-4.1-mini",
  "maxLlmCostUsd": 0.05,
  "maxInputChars": 20000,
  "maxOutputTokens": 1500,
  "interpretedValues": "separate",
  "recordTimeoutSecs": 120,
  "maxRecords": 50,
  "concurrency": 4,
  "requestTimeoutSecs": 30,
  "maxPageBytes": 2000000,
  "respectRobotsTxt": true,
  "saveSourceRecords": false,
  "readerUrlsField": "urls",
  "readerMaxTotalChargeUsd": 1
}
```

## Output

```json
{
  "inputId": {
    "label": "Input ID",
    "format": "string"
  },
  "status": {
    "label": "Status",
    "format": "string"
  },
  "evidence": {
    "label": "Evidence",
    "format": "object"
  },
  "conflicts": {
    "label": "Conflicts",
    "format": "array"
  },
  "rejected": {
    "label": "Rejected values",
    "format": "array"
  },
  "transformations": {
    "label": "Transformations",
    "format": "array"
  },
  "model": {
    "label": "Model",
    "format": "object"
  }
}
```

## How it works

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

The AI Web Scraper - Structured Data to Your JSON Schema Actor is ready to run with the inputs already set for "Any fields you define, from pages without markup". [Sign up or log in](https://console.apify.com/create-task-from-example/2korKkXBTaX4tD5o7) and you'll land in Apify Console with a copy of this exact task.

### 2. Start the "Any fields you define, from pages without markup" task

The AI Web Scraper - Structured Data to Your JSON Schema Actor will start running based on the input automatically. You can also change all the input fields, like source, page urls, and more, to match your specific use case.

### 3. Receive the "Any fields you define, from pages without markup" 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 input id, status, evidence, 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 "Any fields you define, from pages without markup" task via API](https://apify.com/leadproof/structured-web-extractor.md).

## About this Actor

This example demonstrates how to use [AI Web Scraper - Structured Data to Your JSON Schema](https://apify.com/leadproof/structured-web-extractor.md) with a specific input configuration. Visit the [Actor detail page](https://apify.com/leadproof/structured-web-extractor.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/leadproof/structured-web-extractor.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`).