apps/backend/python/test_scribd_cookie.py

#!/usr/bin/env python3
"""
Quick Scribd Test - Direct cookie usage
"""
import requests
from bs4 import BeautifulSoup

SESSION_COOKIE = "dWY2a0xyM05wbUhCaGNpNThUbGxiK08wM2ZHamVSL1Z1RHNEQmhLVjdJaXh1U2h3SzNHK2pxZ3kwNWVVN0s0cmpQWk9zZVVlSVVuWDdTQlZ0QktPbnpORktMOXg1dUdWMjBkMDc0NmtZbVpuWXEwZEwzaTdVUjZrOW1oaDlGN3l6SXA0S1QweElEQjVtK3R1MVpocXlVTTBvTDd1aVFIY01td25FQ3RmQ2xkdUVsSndZeHpvNG9ySlMrZFkrdlV0em1ucHoyZEpJemFCcDVBVllzbkROWjFMc1hTOXBlWWJ2YnkxRENEK3EwQ3BwMTRtNEduQU9sSnNFTjBxNk9DakZ3bGRBT3l3YzUyNUxPRmRWN2pTUVp4bWxzZ0xhUTZ3ODZlcFFGbllpSlV3a05EZjM2V1EvWTdmM1JlOUk1NUI1c2FrbHVzR3gvUzB3cGo5dVpsYWEyNDRMNnlXWG1oNytYZEJOa2paRzZyKy96Zk5NWHQ1SFpvT3NJZm4vNlN2WUtERkhuZURiNXVua29qNms5SFJPWDJZN1htdnVoRG5RalVIOUZuZnVTbUthZUtyU1hpeUozZ3JXYU5iekhLYkt3eUNGUkl2dzNnL2xpdTY4RTVrQWc9PS0tbXYvN0pSK0Y1MHNtMjFZVlErMS9rQT09--1e9fed463dd32fe74209f0b7785597c16ba7fcb2"

session = requests.Session()
session.headers.update({
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36",
    "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8",
    "Accept-Language": "en-US,en;q=0.9,da;q=0.8",
})

# Set cookie
session.cookies.set("_scribd_session", SESSION_COOKIE, domain=".scribd.com")

print("🔍 Testing Scribd Authentication...")
print("=" * 50)

# Test various endpoints
endpoints = [
    ("Account", "https://www.scribd.com/account"),
    ("Saved", "https://www.scribd.com/saved"),
    ("Library", "https://www.scribd.com/library"),
    ("Home", "https://www.scribd.com/"),
]

for name, url in endpoints:
    try:
        resp = session.get(url, allow_redirects=True)
        soup = BeautifulSoup(resp.text, 'html.parser')
        
        # Check for login indicators
        has_logout = bool(soup.find('a', href=lambda x: x and 'logout' in x.lower() if x else False))
        has_signin = bool(soup.find('a', href=lambda x: x and 'sign' in x.lower() if x else False))
        title = soup.find('title')
        title_text = title.get_text()[:50] if title else "No title"
        
        print(f"\n📍 {name}: {resp.status_code}")
        print(f"   URL: {resp.url[:60]}...")
        print(f"   Title: {title_text}")
        print(f"   Logout link: {'✅' if has_logout else '❌'}")
        print(f"   Signin link: {'⚠️' if has_signin else '✅'}")
        
        # Check for user-specific content
        if 'saved' in url.lower():
            # Look for document items
            items = soup.select('.cell_wrapper, .document_row, [data-document-id]')
            print(f"   Documents found: {len(items)}")
            
    except Exception as e:
        print(f"\n📍 {name}: ❌ Error - {e}")

print("\n" + "=" * 50)
print("🍪 Cookie test complete")