feat: finalize root api.py with X-Auth-Secret auth security and clean pure sales cohort

collectors/sync_spotify_complete.py

@@ -0,0 +1,80 @@
+"""
+collectors/sync_spotify_complete.py
+Spotify sync engine using credentials from .env.
+"""
+
+import os
+import re
+import time
+import base64
+import sqlite3
+import logging
+from pathlib import Path
+from datetime import datetime, timezone
+from typing import Dict, List, Optional
+import requests
+from dotenv import load_dotenv
+
+PROJECT_ROOT = Path(__file__).resolve().parent.parent
+load_dotenv(PROJECT_ROOT / ".env")
+
+logging.basicConfig(level=logging.INFO, format="%(asctime)s [%(levelname)s] %(message)s")
+logger = logging.getLogger("SpotifySync")
+
+DB_PATH = PROJECT_ROOT / "data" / "hiffi_catalog.db"
+
+class SpotifySyncEngine:
+    def __init__(self, db_path: Path = DB_PATH):
+        self.db_path = db_path
+        self.client_id = os.getenv("SPOTIFY_CLIENT_ID", "").strip()
+        self.client_secret = os.getenv("SPOTIFY_CLIENT_SECRET", "").strip()
+        self.access_token = None
+
+    def authenticate(self) -> bool:
+        if not self.client_id or not self.client_secret:
+            logger.warning("Spotify credentials missing in .env")
+            return False
+        url = "https://accounts.spotify.com/api/token"
+        auth_bytes = f"{self.client_id}:{self.client_secret}".encode("utf-8")
+        headers = {
+            "Authorization": f"Basic {base64.b64encode(auth_bytes).decode('utf-8')}",
+            "Content-Type": "application/x-www-form-urlencoded"
+        }
+        data = {"grant_type": "client_credentials"}
+        try:
+            resp = requests.post(url, headers=headers, data=data, timeout=10)
+            if resp.status_code == 200:
+                self.access_token = resp.json().get("access_token")
+                return True
+        except Exception as e:
+            logger.error(f"Spotify auth error: {e}")
+        return False
+
+    def fetch_batch(self, sp_ids: List[str]) -> Dict[str, Dict]:
+        results = {}
+        if not self.access_token or not sp_ids:
+            return results
+        headers = {"Authorization": f"Bearer {self.access_token}"}
+        for i in range(0, len(sp_ids), 50):
+            chunk = sp_ids[i:i + 50]
+            url = f"https://api.spotify.com/v1/artists?ids={','.join(chunk)}"
+            try:
+                resp = requests.get(url, headers=headers, timeout=10)
+                if resp.status_code == 200:
+                    for art in resp.json().get("artists", []):
+                        if art:
+                            results[art["id"]] = {
+                                "followers": art.get("followers", {}).get("total", 0),
+                                "popularity": art.get("popularity", 0)
+                            }
+            except Exception as e:
+                logger.error(f"Batch fetch error: {e}")
+            time.sleep(0.05)
+        return results
+
+if __name__ == "__main__":
+    engine = SpotifySyncEngine()
+    if engine.authenticate():
+        logger.info("Spotify API credentials authenticated successfully.")
+    else:
+        logger.error("Authentication failed. Check SPOTIFY_CLIENT_ID and SPOTIFY_CLIENT_SECRET in .env.")