app.py

# src/run_scraper.py
from playwright.async_api import async_playwright
import asyncio
import os
import subprocess

async def scrape():
    """
    Scrapes the top 4 post titles and URLs from Hacker News
    and saves them to hn.txt.
    """
    # NOT OK, BUT NOW I DON'T HAVE ANOTHER SOLUTION. Dockerfile AND setup.sh DOESN'T HELP.
    # Check if the browser executable exists
    browser_path = os.path.expanduser('~/.cache/ms-playwright/chromium_headless_shell-1181/chrome-linux/headless_shell')
    if not os.path.exists(browser_path):
        print("Playwright browsers not found. Installing...")
        try:
            subprocess.run(["playwright", "install"], check=True)
            print("Playwright installation complete.")
        except FileNotFoundError:
            print("Playwright command not found. Please ensure it's in your PATH.")
            return
    # NOT OK, BUT NOW I DON'T HAVE ANOTHER SOLUTION. Dockerfile AND setup.sh DOESN'T HELP.
    
    # Use the async_playwright context manager to launch the browser
    async with async_playwright() as p:
        # Launch a browser instance (Chromium in this case)
        browser = await p.chromium.launch()
        page = await browser.new_page()
        await page.goto('https://news.ycombinator.com')

        # Use locators for a more robust way to select elements
        links_locator = page.locator('.titleline > a')
        
        results = []
        # Iterate through the first 4 located elements
        for i in range(4):
            locator = links_locator.nth(i)
            title = await locator.inner_text()
            url = await locator.get_attribute('href')
            
            # Handle relative URLs by prepending the base URL if necessary
            if url and not url.startswith('http'):
                url = f"https://news.ycombinator.com/{url}"
            
            results.append(f"{title} - {url}")

        # Write the results to the output file
        with open('hn.txt', 'w', encoding='utf-8') as file:
            for result in results:
                file.write(result + '\n')
        
        # Always remember to close the browser
        await browser.close()
        print("Scraping complete. 'hn.txt' has been created.")

if __name__ == "__main__":
    asyncio.run(scrape())