PokemonCardSearch/code/modules/image_downloader.py

"""
图片下载模块
- 卡牌标准图：从 cards_master_v2 的 img_url (腾讯云COS) 下载，HTTP 直接访问
- 交易图：从 MinIO 下载（需配置账号密码），或从本地目录读取
"""
import os
import hashlib
import requests
import cv2
import numpy as np


def _url_to_filename(url):
    """URL 转本地文件名（md5 防冲突）"""
    return hashlib.md5(url.encode("utf-8")).hexdigest() + ".jpg"


def download_card_image(url, save_dir, timeout=15, retries=2):
    """
    下载卡牌标准图（COS，HTTP 公开访问）。
    已存在则直接返回路径（断点续传）。
    Returns: 本地路径；失败返回 None
    """
    fname = _url_to_filename(url)
    path = os.path.join(save_dir, fname)
    if os.path.exists(path) and os.path.getsize(path) > 0:
        return path

    for attempt in range(retries + 1):
        try:
            resp = requests.get(url, timeout=timeout)
            if resp.status_code == 200 and len(resp.content) > 0:
                with open(path, "wb") as f:
                    f.write(resp.content)
                return path
        except Exception:
            if attempt == retries:
                return None
    return None


def download_card_images_batch(urls, save_dir, workers=8):
    """批量下载卡牌图，返回 {url: local_path or None}"""
    from concurrent.futures import ThreadPoolExecutor, as_completed
    results = {}
    with ThreadPoolExecutor(max_workers=workers) as pool:
        futures = {pool.submit(download_card_image, url, save_dir): url for url in urls}
        for fut in as_completed(futures):
            url = futures[fut]
            try:
                results[url] = fut.result()
            except Exception:
                results[url] = None
    return results


def load_image_rgb(path):
    """读取图片为 RGB numpy 数组"""
    if path is None or not os.path.exists(path):
        return None
    img = cv2.imread(path)
    if img is None:
        return None
    return cv2.cvtColor(img, cv2.COLOR_BGR2RGB)


# ============ 交易图获取（MinIO / 本地） ============

def get_minio_client(minio_config):
    """创建 MinIO 客户端"""
    from minio import Minio
    return Minio(
        minio_config["endpoint"],
        access_key=minio_config["access_key"],
        secret_key=minio_config["secret_key"],
        secure=minio_config.get("secure", False),
    )


def download_transaction_image_minio(image_uri, save_dir, minio_config, bucket=None):
    """
    从 MinIO 下载交易图。
    image_uri 形如 'ebay102/2026-03-25-11-2/xxx.jpg'
    bucket 为 None 时，取 image_uri 第一段作为 bucket 名
    Returns: 本地路径；失败返回 None
    """
    if not minio_config.get("access_key"):
        return None  # 未配置账号密码

    parts = image_uri.split("/", 1)
    if bucket is None:
        bkt, obj = parts[0], parts[1] if len(parts) > 1 else ""
    else:
        bkt, obj = bucket, image_uri

    fname = _url_to_filename(image_uri)
    path = os.path.join(save_dir, fname)
    if os.path.exists(path) and os.path.getsize(path) > 0:
        return path

    try:
        client = get_minio_client(minio_config)
        client.fget_object(bkt, obj, path)
        return path if os.path.exists(path) else None
    except Exception:
        return None


def get_transaction_image_local(image_uri, local_root):
    """
    从本地目录读取交易图（若图片已下载到本地）。
    local_root: 本地根目录，image_uri 拼接其后
    Returns: 本地路径或 None
    """
    path = os.path.join(local_root, image_uri)
    return path if os.path.exists(path) else None