extractStructuredData

From Page or Locator

export declare function extractStructuredData(options: {
  source: Page | Locator;
  dataSchema: JsonSchema | z.ZodSchema;
  prompt?: string;
  strategy?: "IMAGE" | "MARKDOWN" | "HTML";
  enableDomMatching?: boolean;
  enableCache?: boolean;
  maxRetries?: number;
  model?: SUPPORTED_MODELS;
  apiKey?: string;
}): Promise<any>;

Extract structured data from web pages using AI-powered content analysis.

Examples

Page source

import { extractStructuredData } from '@intuned/browser/ai';
export default async function handler(params, page, context){
await page.goto("https://books.toscrape.com/")
const product = await extractStructuredData({
  source: page,
  strategy: "HTML",
  model: "gpt-4o",
  dataSchema: {
    type: "object",
    properties: {
      name: { type: "string" },
      price: { type: "string" },
      description: { type: "string" },
      inStock: { type: "boolean" }
    },
    required: ["name", "price"]
  },
  prompt: "Extract product details from this e page"
});
console.log(`Found book: ${product.name} - ${product.price}`);
}

Arguments

options · Object · required

Configuration object containing extraction parameters

Show options

options.source · Page | Locator

Playwright Page object to extract data from the entire page or Locator object to extract data from a specific element

options.dataSchema · JsonSchema | z.ZodSchema

JsonSchema defining the structure of the data to extract. This can be a JsonSchema or ZodSchema

options.strategy · string

Type of extraction: “HTML”, “IMAGE”, or “MARKDOWN”. Defaults to “HTML”

options.prompt · string

Optional prompt to guide the extraction process and provide more context

options.enableDomMatching · boolean

Whether to enable DOM element matching during extraction. Defaults to false. When set to true, all types in the schema must be strings to match with the DOM elements. The extracted results will be matched with the DOM elements and returned, then cached in a smart fashion so that the next time the same data is extracted, the result will be returned from the cache even if the DOM has minor changes.

options.enableCache · boolean

Whether to enable caching of the extracted data. Defaults to true

options.maxRetries · number

Maximum number of retry attempts on failures. Failures can be validation errors, API errors, output errors, etc. Defaults to 3

options.model · SUPPORTED_MODELS

AI model to use for extraction. See SUPPORTED_MODELS for all supported models. Defaults to “claude-3-5-haiku-latest”

options.apiKey · string

Optional API key for AI extraction (if provided, will not be billed to your account)

Returns: any

Promise resolving to the extracted structured data matching the provided schema