app.py

from flask import Flask, request, Response
import httpx

app = Flask(__name__)

# Replace 'socio_secret_2026' with a strong, random password
SECRET_KEY = "socio_secret_2026"

@app.route('/api/proxy')
def proxy():
    target_url = request.args.get('url')
    key = request.args.get('key')
    
    # 1. Security Check
    if key != SECRET_KEY:
        return "Unauthorized", 401
        
    if not target_url:
        return "Missing URL", 400

    # 2. Browser-like Headers to minimize block probability
    headers = {
        'User-Agent': 'Mozilla/5.0 (Linux; Android 6.0; Nexus 5 Build/MRA58N) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/139.0.0.0 Mobile Safari/537.36',
        'Accept-Language': 'en-US,en;q=0.5',
        'Upgrade-Insecure-Requests': '1',
        'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
    }
    
    try:
        # 3. Fetch with http2=True and follow_redirects=True
        with httpx.Client(headers=headers, http2=True, follow_redirects=True, timeout=None) as client:
            resp = client.get(target_url)
            
        # 4. Return the content back to your Airflow scraper
        return Response(
            resp.text, 
            status=resp.status_code, 
            content_type=resp.headers.get('content-type', 'text/html')
        )
    except Exception as e:
        return str(e), 500

if __name__ == '__main__':
    app.run()