Function getCleanTextWithStripping

browse/src/content-security.ts:170–186

(page: Page | Frame)

 * Uses clone + remove approach: clones body, removes marked elements, returns innerText.
 */
export async function getCleanTextWithStripping(page: Page | Frame): Promise<string> {
  const raw = await page.evaluate(() => {
    const body = document.body;
    if (!body) return '';
    const clone = body.cloneNode(true) as HTMLElement;
    // Remove standard noise elements
    clone.querySelectorAll('script, style, noscript, svg').forEach(el => el.remove());
    // Remove hidden-marked elements
    clone.querySelectorAll('[data-gstack-hidden]').forEach(el => el.remove());
    return clone.innerText
      .split('\n')
      .map(line => line.trim())
      .filter(line => line.length > 0)
      .join('\n');
  });
  return stripLoneSurrogates(raw);
}

/**
 * Clean up data-gstack-hidden attributes from the page.