117 lines
4.0 KiB
Python
117 lines
4.0 KiB
Python
"""
|
|
scripts/force_replace_silhouettes.py
|
|
Direct local portrait generator for $uicideboy$, 100k Track, and Aminé.
|
|
Uses Wikimedia REST endpoints and guaranteed local binary writing.
|
|
Zero network dependencies on blocked CDNs.
|
|
"""
|
|
|
|
import sqlite3
|
|
import base64
|
|
import requests
|
|
import re
|
|
from pathlib import Path
|
|
|
|
BASE_DIR = Path(__file__).resolve().parent.parent
|
|
DB_PATH = BASE_DIR / "data" / "hiffi_catalog.db"
|
|
AVATAR_DIR = BASE_DIR / "data" / "artist_avatars"
|
|
AVATAR_DIR.mkdir(parents=True, exist_ok=True)
|
|
|
|
# Wikimedia REST API lead image endpoints (official, completely unblocked)
|
|
TARGET_CONFIG = {
|
|
"$uicideboy$": {
|
|
"wiki_title": "Suicideboys",
|
|
"fallback_deezer_id": "8482488"
|
|
},
|
|
"100k Track": {
|
|
"wiki_title": "100k_Track",
|
|
"fallback_deezer_id": "131441852"
|
|
},
|
|
"Aminé": {
|
|
"wiki_title": "Aminé_(rapper)",
|
|
"fallback_deezer_id": "10486256"
|
|
}
|
|
}
|
|
|
|
HEADERS = {
|
|
"User-Agent": "HIFFIArtistApp/1.0 (contact@hiffi.ai)",
|
|
"Accept": "application/json,image/*"
|
|
}
|
|
|
|
def clean_file_slug(name: str) -> str:
|
|
cleaned = re.sub(r'[^a-zA-Z0-9_-]', '_', name.strip().lower())
|
|
return re.sub(r'_+', '_', cleaned).strip('_')
|
|
|
|
def get_verified_image_bytes(artist_name: str, cfg: dict):
|
|
"""Fetches real image bytes using unblocked Wikipedia REST API or Deezer direct entity."""
|
|
# 1. Try Wikipedia REST summary API
|
|
title = cfg["wiki_title"]
|
|
wiki_url = f"https://en.wikipedia.org/api/rest_v1/page/summary/{title}"
|
|
try:
|
|
r = requests.get(wiki_url, headers=HEADERS, timeout=10)
|
|
if r.status_code == 200:
|
|
data = r.json()
|
|
if "thumbnail" in data and "source" in data["thumbnail"]:
|
|
img_url = data["thumbnail"]["source"]
|
|
img_res = requests.get(img_url, headers=HEADERS, timeout=10)
|
|
if img_res.status_code == 200 and len(img_res.content) > 3000:
|
|
return img_res.content, img_url
|
|
except Exception:
|
|
pass
|
|
|
|
# 2. Try Deezer public API entity endpoint
|
|
deezer_id = cfg["fallback_deezer_id"]
|
|
dz_url = f"https://api.deezer.com/artist/{deezer_id}"
|
|
try:
|
|
r = requests.get(dz_url, headers=HEADERS, timeout=10)
|
|
if r.status_code == 200:
|
|
data = r.json()
|
|
img_url = data.get("picture_xl") or data.get("picture_big") or data.get("picture_medium")
|
|
if img_url and "artist//500x500" not in img_url:
|
|
img_res = requests.get(img_url, headers=HEADERS, timeout=10)
|
|
if img_res.status_code == 200 and len(img_res.content) > 3000:
|
|
return img_res.content, img_url
|
|
except Exception:
|
|
pass
|
|
|
|
return None, None
|
|
|
|
def main():
|
|
if not DB_PATH.exists():
|
|
print(f"[-] Database not found at {DB_PATH}")
|
|
return
|
|
|
|
conn = sqlite3.connect(DB_PATH)
|
|
cursor = conn.cursor()
|
|
|
|
print("[*] Fetching verified unblocked face portraits...\n")
|
|
|
|
for artist_name, cfg in TARGET_CONFIG.items():
|
|
cursor.execute("SELECT artist_id FROM artists WHERE artist_name = ? COLLATE NOCASE", (artist_name,))
|
|
row = cursor.fetchone()
|
|
artist_id = str(row[0]) if row else "0"
|
|
|
|
slug = clean_file_slug(artist_name)
|
|
target_file = AVATAR_DIR / f"{slug}_{artist_id}.jpg"
|
|
|
|
print(f" [>] Processing {artist_name} (ID: {artist_id})...", flush=True)
|
|
img_bytes, img_url = get_verified_image_bytes(artist_name, cfg)
|
|
|
|
if img_bytes:
|
|
with open(target_file, "wb") as f:
|
|
f.write(img_bytes)
|
|
size_kb = len(img_bytes) / 1024
|
|
print(f" [+] Successfully written: {target_file.name} ({size_kb:.1f} KB)", flush=True)
|
|
|
|
cursor.execute(
|
|
"UPDATE artists SET image_url = ?, image_verified_flag = 1 WHERE artist_id = ?",
|
|
(img_url, artist_id)
|
|
)
|
|
conn.commit()
|
|
else:
|
|
print(f" [-] Failed to retrieve image for {artist_name}", flush=True)
|
|
|
|
conn.close()
|
|
print("\n[+] Direct write complete.")
|
|
|
|
if __name__ == "__main__":
|
|
main() |