AI 학습 데이터 수집용 동적 모바일 프록시

from playwright.sync_api import sync_playwright
import requests
import time

# Target crawler params
PROXY_IP = "192.168.1.100:10001"
ROTATION_URL = "http://192.168.1.100:8000/api/rotate?port=10001"

def fetch_unblocked_text(url):
    with sync_playwright() as p:
        # Connect browser through physical SIM proxy port
        browser = p.chromium.launch(
            proxy={"server": f"socks5://{PROXY_IP}"}
        )
        context = browser.new_context()
        page = context.new_page()
        
        try:
            page.goto(url, timeout=15000)
            if "blocked" in page.title().lower():
                print("Encountered block! Triggering XProxy cellular tower rotation...")
                requests.get(ROTATION_URL)
                time.sleep(5)
                # Retry page load
                page.goto(url)
            
            content = page.content()
            print("Page content scraped successfully.")
            return content
        except Exception as e:
            print(f"Scraper error: {e}")
        finally:
            browser.close()