Get HTML of iframes in Microsoft Playwright

Playwright is a powerful framework for web testing and automation. This article demonstrates how to extract the HTML content of child IFRAMEs within a webpage using Python and Playwright.

Installation

To use Playwright in your Python project, you'll need to install it using pip:

pip install playwright
playwright install

Python Code

Here's the Python code:

import asyncio
from playwright.async_api import async_playwright, Frame

async def main():
  """
  This function retrieves the HTML content of each child iframe on a webpage.
  """
  async with async_playwright() as p:
    browser = await p.chromium.launch(headless=False)
    page = await browser.new_page()
    url = "https://interactive-examples.mdn.mozilla.net/pages/tabbed/iframe.html"
    await page.goto(url)

    # Wait for page to load and iframes to be rendered
    await page.wait_for_load_state("networkidle")

    for frame in page.frames:
      if not frame.url.startswith("http"):
        # May start with "about:"
        print(f'{frame.url}: Not a valid URL')
        continue
      if frame.url == url:
        print(f'{frame.url}: Skipping parent')
        continue
      print(f'{frame.url}: content below')
      print('*' * 80)
      content = await frame.content()
      print(content)
      print('*' * 80)

    await browser.close()

asyncio.run(main())