metadata.py

from huggingface_hub import HfApi
import csv
import os

HF_TOKEN = os.getenv("HF_TOKEN") or ""
repo_id = "Segizu/facial-recognition"

api = HfApi()
files = api.list_repo_files(repo_id=repo_id, repo_type="dataset", token=HF_TOKEN)

# Generar URLs completas
base_url = f"https://huggingface.co/datasets/{repo_id}/resolve/main/"
image_urls = [base_url + f for f in files if f.lower().endswith(".jpg")]

# Escribir nuevo metadata.csv
with open("metadata.csv", "w", newline="") as f:
    writer = csv.writer(f)
    writer.writerow(["image"])
    for url in image_urls:
        writer.writerow([url])

print(f"✅ metadata.csv regenerado con URLs absolutas ({len(image_urls)} imágenes)")