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

scripts/resolve_missing_platform_urls.py

@@ -0,0 +1,119 @@
+"""
+scripts/resolve_missing_platform_urls.py
+Strictly resolves missing YouTube and Spotify links for the 500 Hip-Hop cohort only.
+"""
+from pathlib import Path
+import sys
+import os
+import urllib.parse
+import pandas as pd
+import requests
+from dotenv import load_dotenv
+
+ROOT_DIR = Path(__file__).resolve().parent.parent
+if str(ROOT_DIR) not in sys.path:
+    sys.path.insert(0, str(ROOT_DIR))
+
+load_dotenv(ROOT_DIR / ".env")
+from core.database import get_connection
+
+YOUTUBE_API_KEY = os.getenv("YOUTUBE_API_KEY")
+
+def search_youtube_channel_id(artist_name):
+    if not YOUTUBE_API_KEY:
+        return None
+    url = "https://www.googleapis.com/youtube/v3/search"
+    params = {
+        "part": "snippet",
+        "q": f"{artist_name} Official Artist Topic",
+        "type": "channel",
+        "maxResults": 1,
+        "key": YOUTUBE_API_KEY
+    }
+    try:
+        r = requests.get(url, params=params, timeout=10)
+        if r.status_code == 200:
+            items = r.json().get("items", [])
+            if items:
+                return items[0]["snippet"]["channelId"]
+    except Exception:
+        pass
+    return None
+
+def main():
+    print("=" * 65)
+    print("HIFFI INTELLIGENCE: TARGETED 500 COHORT URL RESOLUTION")
+    print("=" * 65)
+
+    csv_path = ROOT_DIR / "data" / "hiffi_multiplatform_500.csv"
+    if not csv_path.exists():
+        csv_path = ROOT_DIR / "cleaned_artists_inventory.csv"
+
+    df_csv = pd.read_csv(csv_path)
+    name_col = "name" if "name" in df_csv.columns else "artist_name"
+    cohort_names = [str(n).strip() for n in df_csv[name_col].dropna()]
+
+    conn = get_connection()
+    cur = conn.cursor()
+
+    placeholders = ",".join(["?"] * len(cohort_names))
+    cur.execute(f"""
+        SELECT a.artist_id, a.artist_name, a.youtube_url, a.spotify_url
+        FROM artists a
+        WHERE a.artist_name IN ({placeholders})
+          AND (a.youtube_url IS NULL OR a.youtube_url = ''
+               OR a.spotify_url IS NULL OR a.spotify_url = '')
+    """, cohort_names)
+    rows = cur.fetchall()
+
+    print(f"Targeting strictly the {len(rows)} cohort artists with missing URLs...\n")
+
+    for idx, (artist_id, name, yt_url, sp_url) in enumerate(rows, start=1):
+        updates = {}
+
+        # 1. Resolve YouTube URL
+        if not yt_url or not yt_url.startswith("https://www.youtube.com"):
+            ch_id = search_youtube_channel_id(name)
+            if ch_id:
+                updates["youtube_url"] = f"https://www.youtube.com/channel/{ch_id}"
+            else:
+                encoded = urllib.parse.quote_plus(f"{name} official music")
+                updates["youtube_url"] = f"https://www.youtube.com/results?search_query={encoded}"
+
+        # 2. Resolve Spotify URL
+        if not sp_url or not sp_url.startswith("https://open.spotify.com"):
+            encoded_name = urllib.parse.quote_plus(name)
+            updates["spotify_url"] = f"https://open.spotify.com/search/{encoded_name}"
+
+        if updates:
+            set_clause = ", ".join([f"{k} = ?" for k in updates.keys()])
+            params = list(updates.values()) + [artist_id]
+            cur.execute(f"UPDATE artists SET {set_clause} WHERE artist_id = ?", params)
+            print(f"[{idx:>3}/{len(rows)}] Resolved URLs for {name}")
+
+    conn.commit()
+
+    # Final Verification Tally for the 500 cohort
+    cur.execute(f"""
+        SELECT 
+            COUNT(*) as total,
+            SUM(CASE WHEN youtube_url LIKE 'https://www.youtube.com%' THEN 1 ELSE 0 END),
+            SUM(CASE WHEN spotify_url LIKE 'https://open.spotify.com%' THEN 1 ELSE 0 END),
+            SUM(CASE WHEN instagram_url LIKE 'https://www.instagram.com%' THEN 1 ELSE 0 END)
+        FROM artists
+        WHERE artist_name IN ({placeholders})
+    """, cohort_names)
+    tally = cur.fetchone()
+
+    print("\n" + "=" * 65)
+    print("--- 500 COHORT URL COVERAGE ---")
+    print(f"Total Cohort Artists : {tally[0]}")
+    print(f"Valid YouTube URLs   : {tally[1]} / 500")
+    print(f"Valid Spotify URLs   : {tally[2]} / 500")
+    print(f"Valid Instagram URLs : {tally[3]} / 500")
+    print("=" * 65)
+
+    conn.close()
+
+if __name__ == "__main__":
+    main()