hiffi-artist-intelligence/scripts/resolve_youtube_handles.py

import os
from pathlib import Path
import sqlite3
import time
import requests
from requests.adapters import HTTPAdapter
from urllib3.util.retry import Retry
from dotenv import load_dotenv

PROJECT_ROOT = Path(__file__).resolve().parent.parent
load_dotenv(PROJECT_ROOT / ".env")

YOUTUBE_API_KEY = os.getenv("YOUTUBE_API_KEY", "").strip()
DB_PATH = PROJECT_ROOT / "data" / "hiffi_catalog.db"

if not YOUTUBE_API_KEY:
    print("Error: YOUTUBE_API_KEY not found in .env")
    exit(1)

# Configure resilient HTTP session with automatic retries for WinError 10054
session = requests.Session()
retry_strategy = Retry(
    total=4,
    backoff_factor=1,
    status_forcelist=[429, 500, 502, 503, 504],
)
adapter = HTTPAdapter(max_retries=retry_strategy)
session.mount("https://", adapter)
session.mount("http://", adapter)

# Verified official YouTube handles
VERIFIED_HANDLES = {
    # Mismatches
    "Young Thug": "YoungThug",
    "Bas": "bas",
    "Cardi B": "iamcardib",
    "Stormzy": "StormzyTV",
    "Chingy": "Chingy",
    "Cassidy": "CassidyLarsiny",
    "Madlib": "MadlibInvazion",
    "EARTHGANG": "EARTHGANG",
    "Juvenile": "Juvenile",
    "UGK": "UGKMusic",
    "Conway the Machine": "WhoIsConway",
    "Smoke DZA": "SmokeDZA",
    "Open Mike Eagle": "mikeeagletv",
    
    # Remaining unlinked cohort
    "Key Glock": "KeyGlock",
    "Deante' Hitchcock": "DeanteHitchcock",
    "Veeze": "veeze__",
    "Fredo Santana": "FredoSantana",
    "Dizzee Rascal": "dizzeerascal",
    "Aitch": "AitchOfficial",
    "Digga D": "DiggaD",
    "K-Trap": "ktrap_official",
    "Nines": "Nines",
    "Potter Payper": "PotterPayper",
    "MoStack": "MoStack",
    "Stefflon Don": "stefflondon",
    "Merkules": "Merkules",
    "Night Lovell": "NightLovell",
    "Yung Lean": "yunglean",
    "Bladee": "bladee",
    "Ecco2k": "ecco2k",
    "Thaiboy Digital": "thaiboydigital",
    "BBNO$": "bbnomula",
    "Jhené Aiko": "JheneAiko",
    "Fredo": "Fredo",
    "Mick Jenkins": "MickJenkins",
    "Kirk Knight": "KirkKnight",
    "Cozz": "Cozz",
    "Masta Killa": "MastaKilla",
    "Mannie Fresh": "MannieFresh",
    "Grip": "Grip_SS",
    "Yung Miami": "YungMiami",
    "Oshun": "OSHUniverse",
    "Goonew": "Goonew64",
    "Big Pokey": "BigPokey",
    "Q Da Fool": "QDaFool",
    "100k Track": "100kTrack",
    "Hak": "haknyc",
    "Sporting Life": "sportinglife",
    "KrispyLife Kidd": "krispylife_kidd",
    "K-os": "kosinfluence",
    "Dom Genesis": "DomsGenesis",
    "BabySmoove": "babysmoove"
}

def resolve_by_handle(handle: str):
    clean_handle = handle.lstrip("@")
    url = "https://www.googleapis.com/youtube/v3/channels"
    params = {
        "part": "snippet,statistics",
        "forHandle": clean_handle,
        "key": YOUTUBE_API_KEY
    }
    try:
        resp = session.get(url, params=params, timeout=12)
        if resp.status_code == 200:
            items = resp.json().get("items", [])
            if items:
                channel_id = items[0]["id"]
                stats = items[0].get("statistics", {})
                subs = int(stats.get("subscriberCount", 0))
                title = items[0]["snippet"].get("title", "")
                return channel_id, subs, title
    except Exception as e:
        print(f"  [WARN: handle query failed for {handle}]: {e}")
    return None, 0, None

conn = sqlite3.connect(DB_PATH)
cur = conn.cursor()

print(f"Resolving {len(VERIFIED_HANDLES)} artists via official YouTube handles...\n")
success = 0

for artist_name, handle in VERIFIED_HANDLES.items():
    channel_id, subs, title = resolve_by_handle(handle)
    
    if not channel_id:
        # Fallback to search if handle query is empty
        try:
            s_resp = session.get(
                "https://www.googleapis.com/youtube/v3/search",
                params={"part": "snippet", "q": f"{artist_name} Official", "type": "channel", "maxResults": 1, "key": YOUTUBE_API_KEY},
                timeout=12
            )
            if s_resp.status_code == 200 and s_resp.json().get("items"):
                channel_id = s_resp.json()["items"][0]["snippet"]["channelId"]
                title = s_resp.json()["items"][0]["snippet"]["title"]
                stat_resp = session.get(
                    "https://www.googleapis.com/youtube/v3/channels",
                    params={"part": "statistics", "id": channel_id, "key": YOUTUBE_API_KEY},
                    timeout=12
                )
                if stat_resp.status_code == 200 and stat_resp.json().get("items"):
                    subs = int(stat_resp.json()["items"][0]["statistics"].get("subscriberCount", 0))
        except Exception as e:
            print(f"  [WARN: search query failed for {artist_name}]: {e}")

    if channel_id:
        canonical_url = f"https://www.youtube.com/channel/{channel_id}"
        cur.execute("SELECT artist_id FROM artists WHERE LOWER(artist_name) = ?", (artist_name.lower(),))
        row = cur.fetchone()
        if row:
            a_id = row[0]
            cur.execute("UPDATE artists SET youtube_url = ? WHERE artist_id = ?", (canonical_url, a_id))
            if subs > 0:
                cur.execute("UPDATE telemetry_metrics SET subscribers_count = ? WHERE artist_id = ?", (subs, a_id))
            conn.commit()
            success += 1
            print(f"[{success:02d}/{len(VERIFIED_HANDLES)}] {artist_name:<20} -> {title} (Subs: {subs:,}) [{channel_id}]")
        else:
            print(f"[NOT IN DB] {artist_name}")
    else:
        print(f"[FAILED] {artist_name}")

    time.sleep(0.3)

conn.close()
print(f"\nCompleted: {success}/{len(VERIFIED_HANDLES)} channels patched in hiffi_catalog.db.")