> ## Documentation Index
> Fetch the complete documentation index at: https://intunedhq.com/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# extractMarkdown

Converts HTML content from a Playwright Page or Locator to semantic markdown format.

```typescript theme={null}
export declare function extractMarkdown(input: {
  source: Page | Locator;
}): Promise<string>;
```

## Examples

<CodeGroup>
  ```typescript Extract Markdown from Locator theme={null}
  import { extractMarkdown } from "@intuned/browser";
  import { BrowserContext, Page } from "playwright";

  interface Params {}

  export default async function handler(
    params: Params,
    page: Page,
    context: BrowserContext
  ) {
    await page.goto("https://books.toscrape.com/");
    const headerLocator = page.locator("h1").first(); // First title on the page
    const markdown = await extractMarkdown({ source: headerLocator }); // Extract markdown from the first title
    console.log(markdown);
    return markdown;
  }
  ```

  ```typescript Extract Markdown from Page theme={null}
  import { extractMarkdown } from "@intuned/browser";
  import { BrowserContext, Page } from "playwright";

  interface Params {}

  export default async function handler(
    params: Params,
    page: Page,
    context: BrowserContext
  ) {
    await page.goto("https://sandbox.intuned.dev/pdfs");
    const markdown = await extractMarkdown({ source: page });
    console.log(markdown);
    return markdown;
  }
  ```
</CodeGroup>

## Arguments

<ResponseField name="input" type="Object" required>
  The input object containing the source of the HTML content

  <Expandable title="properties" defaultOpen>
    <ResponseField name="input.source" type="Page | Locator" required>
      The source of the HTML content. When a Page is provided, extracts from the entire page. When a Locator is provided, extracts from that specific element.
    </ResponseField>
  </Expandable>
</ResponseField>

## Returns: `Promise<string>`

Promise that resolves to the markdown representation of the HTML content