#!/usr/bin/env python3
"""
数据集下载脚本
从SCIDB下载红外电力设备数据集
"""

import argparse
import sys
import time
from pathlib import Path
from urllib.parse import urlparse, parse_qs

import requests
from tqdm import tqdm


def parse_urls_file(file_path: Path) -> list:
    """解析URL文件，返回URL和类别信息"""
    with open(file_path, 'r', encoding='utf-8') as f:
        lines = f.readlines()

    items = []
    for line in lines:
        line = line.strip()
        if not line:
            continue

        # 解析URL获取类别和文件名
        parsed = urlparse(line)
        query = parse_qs(parsed.query)

        path = query.get('path', [''])[0]
        filename = query.get('fileName', ['unknown.jpg'])[0]

        # 从路径提取类别
        parts = path.split('/')
        if len(parts) >= 3:
            category = parts[-2]  # 如 "Wave Traps"
        else:
            category = "Unknown"

        items.append({
            'url': line,
            'filename': filename,
            'category': category
        })

    return items


def create_directories(base_dir: Path, categories: set) -> dict:
    """创建类别目录"""
    dirs = {}
    for cat in categories:
        cat_dir = base_dir / cat
        cat_dir.mkdir(parents=True, exist_ok=True)
        dirs[cat] = cat_dir
    return dirs


def download_file(url: str, output_path: Path, session: requests.Session) -> bool:
    """下载单个文件"""
    try:
        response = session.get(url, timeout=30, stream=True)
        response.raise_for_status()

        with open(output_path, 'wb') as f:
            for chunk in response.iter_content(chunk_size=8192):
                f.write(chunk)

        return True
    except Exception as e:
        print(f"Error downloading {output_path.name}: {e}")
        return False


def download_dataset(urls_file: Path, output_dir: Path, max_workers: int = 4) -> None:
    """下载整个数据集"""
    print("=" * 50)
    print("开始下载红外电力设备数据集")
    print("=" * 50)

    # 解析URL
    print("解析URL文件...")
    items = parse_urls_file(urls_file)
    print(f"共找到 {len(items)} 个文件")

    # 创建目录
    categories = set(item['category'] for item in items)
    print(f"发现 {len(categories)} 个类别: {categories}")
    dirs = create_directories(output_dir, categories)

    # 创建session
    session = requests.Session()
    session.headers.update({
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36'
    })

    # 统计
    success_count = 0
    fail_count = 0

    # 下载文件
    print("\n开始下载...")
    for item in tqdm(items, desc="下载进度"):
        category_dir = dirs[item['category']]
        output_path = category_dir / item['filename']

        # 跳过已存在的文件
        if output_path.exists():
            success_count += 1
            continue

        if download_file(item['url'], output_path, session):
            success_count += 1
        else:
            fail_count += 1

        # 避免请求过快
        time.sleep(0.1)

    print("\n" + "=" * 50)
    print(f"下载完成!")
    print(f"成功: {success_count}")
    print(f"失败: {fail_count}")
    print(f"数据目录: {output_dir}")
    print("=" * 50)


def main():
    parser = argparse.ArgumentParser(description="下载红外电力设备数据集")
    parser.add_argument("--urls-file", type=str,
                       default="data/dataurls.txt",
                       help="URL列表文件")
    parser.add_argument("--output-dir", type=str,
                       default="data/raw/images",
                       help="输出目录")

    args = parser.parse_args()

    urls_file = Path(args.urls_file)
    output_dir = Path(args.output_dir)

    if not urls_file.exists():
        print(f"错误: URL文件不存在: {urls_file}")
        sys.exit(1)

    download_dataset(urls_file, output_dir)


if __name__ == "__main__":
    main()