hiffi-artist-intelligence/scripts/sync_platform_urls.py

"""
scripts/sync_platform_urls.py
Populates verified direct URLs for YouTube, Spotify, and Instagram,
and reports on profile image coverage for the 500 cohort.
"""
from pathlib import Path
import sys
import pandas as pd

ROOT_DIR = Path(__file__).resolve().parent.parent
if str(ROOT_DIR) not in sys.path:
    sys.path.insert(0, str(ROOT_DIR))

from core.database import get_connection

def main():
    print("=" * 65)
    print("HIFFI INTELLIGENCE: DIRECT SOCIAL URLS & IMAGE AUDIT")
    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 = pd.read_csv(csv_path)
    name_col = "name" if "name" in df.columns else "artist_name"

    conn = get_connection()
    cur = conn.cursor()

    updated = 0
    for _, row in df.iterrows():
        name = str(row[name_col]).strip()

        ch_id = str(row["channel_id"]).strip() if pd.notna(row.get("channel_id")) else ""
        yt_url = f"https://www.youtube.com/channel/{ch_id}" if ch_id and ch_id.lower() not in ["none", "nan"] else None

        sp_id = str(row["spotify_id"]).strip() if pd.notna(row.get("spotify_id")) else ""
        sp_url = f"https://open.spotify.com/artist/{sp_id}" if sp_id and sp_id.lower() not in ["none", "nan"] else None

        ig_raw = str(row["instagram_handle"]).strip().lstrip("@") if pd.notna(row.get("instagram_handle")) else ""
        ig_url = f"https://www.instagram.com/{ig_raw}/" if ig_raw and ig_raw.lower() not in ["none", "nan"] else None

        cur.execute("""
            UPDATE artists
            SET youtube_url = ?,
                spotify_url = ?,
                instagram_url = ?
            WHERE LOWER(artist_name) = LOWER(?)
        """, (yt_url, sp_url, ig_url, name))

        if cur.rowcount > 0:
            updated += 1

    conn.commit()
    print(f"Direct platform URLs successfully populated for {updated} artists.")

    # Image Audit across the 500 cohort
    cohort = [str(n).strip() for n in df[name_col].dropna()]
    placeholders = ",".join(["?"] * len(cohort))
    cur.execute(f"""
        SELECT 
            COUNT(*) as total,
            SUM(CASE WHEN image_url IS NOT NULL AND image_url != '' THEN 1 ELSE 0 END) as with_images,
            SUM(CASE WHEN image_url IS NULL OR image_url == '' THEN 1 ELSE 0 END) as missing_images,
            SUM(CASE WHEN image_verified_flag = 1 THEN 1 ELSE 0 END) as verified_images
        FROM artists
        WHERE artist_name IN ({placeholders})
    """, cohort)
    img_stats = cur.fetchone()

    print("\n--- COHORT PROFILE IMAGE STATUS ---")
    print(f"Total Cohort Artists : {img_stats[0]}")
    print(f"Artists with Images  : {img_stats[1]}")
    print(f"Missing Images       : {img_stats[2]}")
    print(f"Verified Images Flag : {img_stats[3]}")
    print("=" * 65)

    conn.close()

if __name__ == "__main__":
    main()