Cloudflare Zero Trust Access & Cloudflared

import asyncio
from playwright.async_api import async_playwright
import random

async def scrape_protected_target(url: str, proxy_url: str):
    async with async_playwright() as p:
        # Launch Chromium with stealth arguments
        browser = await p.chromium.launch(
            headless=True,
            args=[
                "--disable-blink-features=AutomationControlled",
                "--no-sandbox",
                "--disable-infobars",
                "--disable-dev-shm-usage",
            ],
            proxy={"server": proxy_url}
        )

        context = await browser.new_context(
            viewport={"width": 1440, "height": 900},
            user_agent="Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/128.0.0.0 Safari/537.36",
            locale="en-US",
            timezone_id="America/New_York",
        )

        # Evade navigator.webdriver detection
        await context.add_init_script("""
            Object.defineProperty(navigator, 'webdriver', { get: () => undefined });
            window.chrome = { runtime: {} };
            Object.defineProperty(navigator, 'plugins', { get: () => [1, 2, 3] });
        """)

        page = await context.new_page()
        try:
            response = await page.goto(url, wait_until="domcontentloaded", timeout=30000)
            
            # Natural human scroll jitter
            await page.mouse.wheel(0, random.randint(300, 700))
            await asyncio.sleep(random.uniform(1.2, 2.5))

            if "Just a moment" in await page.title():
                # Cloudflare challenge detected - wait for turnstile token solve
                await page.wait_for_selector("iframe[src*='turnstile']", timeout=10000)
                await asyncio.sleep(3.0)

            html = await page.content()
            return html
        finally:
            await browser.close()