"""
scripts/test_spotify_extract.py
Tests parsing of Spotify's base64 hydration payload for monthly listeners.
"""

import base64
import re
import requests

url = "https://open.spotify.com/artist/2YZyLoL8N0Wb9xBt1NhZWg"  # Kendrick Lamar
headers = {
    "User-Agent": (
        "Mozilla/5.0 (Windows NT 10.0; Win64; x64) "
        "AppleWebKit/537.36 (KHTML, like Gecko) "
        "Chrome/124.0.0.0 Safari/537.36"
    )
}

r = requests.get(url, headers=headers, timeout=12)
print("HTTP Status:", r.status_code)

# 1. Search for embedded base64 state tag
match = re.search(r'<script id="initial-state"[^>]*>(.*?)</script>', r.text, re.DOTALL)
if match:
    encoded_data = match.group(1).strip()
    try:
        decoded = base64.b64decode(encoded_data).decode("utf-8", errors="ignore")
        hits = re.findall(r'"monthlyListeners":\s*(\d+)', decoded)
        print("Found via initial-state tag:")
        print("Monthly listeners hits:", hits)
    except Exception as e:
        print("Base64 decode error:", e)
else:
    print("Could not find <script id='initial-state'> tag.")

# 2. Raw fallback check on full body
raw_hits = re.findall(r'"monthlyListeners":\s*(\d+)', r.text)
print("Direct HTML body hits:", raw_hits)