Realtime query selector evaluation for Playwright

README.sh

python scripts/playwright_playground.py \
  "https://www.google.com/search?q=cloudflare+stock+price" \
  "h3" \
  --timeout 1 \
  --content-type text

# Output allows quick iteration
Cloudflare, Inc. (NET) Stock Price, News, Quote & History

Try new selector (q to quit): div[data-attrid="Price"]
78.66 USD +0.14 (0.18%)todaypast 5 dayspast monthpast 6 monthsyear to datepast yearpast 5 yearsall timeClosed: Jul 19, 7:12 PM EDT • DisclaimerPre-marketAfter hours 78.50 −0.16 (0.20%)

Try new selector (q to quit): div[data-attrid="Price"] > span > span > span
78.66

Try new selector (q to quit): q

playwright_evaluator.py

import argparse

from playwright.sync_api import sync_playwright


def main(
    url: str, selector: str, timeout: float, content_type: str, headless: bool
) -> None:
    """Allows users to interactively evaluate query selectors when using Playwright against a given URL"""
    with sync_playwright() as p:
        browser = p.chromium.launch(headless=headless)
        page = browser.new_page()
        page.goto(url)

        while True:
            try:
                element = page.wait_for_selector(selector, timeout=timeout * 1000)
                if element:
                    if content_type == "text":
                        print(element.text_content())
                    elif content_type == "html":
                        print(element.inner_html())
                    else:
                        print("Invalid content type. Please choose 'text' or 'html'.")
                else:
                    print("Selector found no content")

                selector = input("\nTry new selector (q to quit): ")
                if selector.lower() == "q":
                    break
            except Exception as e:
                print(f"Error: {str(e)}")
                selector = input("\nTry new selector (q to quit): ")
                if selector.lower() == "q":
                    break
        browser.close()


def parse_args() -> argparse.Namespace:
    parser = argparse.ArgumentParser(
        description="Test a selector on a webpage using Playwright."
    )
    parser.add_argument("url", type=str, help="The URL of the webpage to test.")
    parser.add_argument("selector", type=str, help="The selector to test.")
    parser.add_argument(
        "--timeout",
        type=float,
        default=3,
        help="The timeout (in seconds) for the selector to appear.",
    )
    parser.add_argument(
        "--content-type",
        type=str,
        default="text",
        choices=["text", "html"],
        help="The type of content to display (text or html).",
    )
    parser.add_argument(
        "--headless",
        type=bool,
        default=True,
        choices=[True, False],
        help="Whether or not the browser runs in headless mode or not",
    )
    return parser.parse_args()


if __name__ == "__main__":
    args = parse_args()
    main(args.url, args.selector, args.timeout, args.content_type, args.headless)