多线程文件下载工具 - 支持 HTTP、FTP 和磁力链接 - 常规

这是一个使用 Python 编写的命令行工具，支持多线程下载 HTTP、FTP 和磁力链接文件。

特性

支持使用多线程下载，提高下载速度。
支持下载 HTTP、FTP 和磁力链接文件。
可自定义线程数、输出文件名和目录。
使用 tqdm 库显示下载进度。

使用方法

将该脚本打包为可执行文件，例如命名为 downloader。
将该可执行文件移动到系统 PATH 环境变量包含的目录中，例如 /usr/local/bin。
打开终端，进入需要下载文件的目录。
运行命令 downloader -u <url> -o <filename>，其中 <url> 为下载链接，<filename> 为保存的文件名。
可选参数包括 -t <num_threads> 指定下载时使用的线程数，-d <directory> 指定保存文件的目录。
根据下载链接的类型，该工具会自动选择使用普通下载还是 BitTorrent 下载方式，下载完成后会保存到指定的目录中。

示例

下载 HTTP 文件：

downloader -u https://example.com/file.zip -o file.zip

下载 FTP 文件：

downloader -u ftp://example.com/file.txt -o file.txt

下载磁力链接文件：

downloader -u magnet:?xt=urn:btih:XXXXXXXXXXXXXXXXXXXXXXXX -o file.torrent

代码

import os
import argparse
import requests
import logging
import re
import transmissionrpc
from concurrent.futures import ThreadPoolExecutor, as_completed
from tqdm import tqdm


def check_dir(path):
    if not os.path.exists(path):
        os.makedirs(path)
    elif not os.path.isdir(path):
        raise argparse.ArgumentTypeError(f'{path} is not a directory')
    return path


def check_url(url):
    pattern = r'^https?://|^ftp://|^magnet:'
    if not re.match(pattern, url):
        raise argparse.ArgumentTypeError(f'{url} is not a valid url')
    return url


def download_file(url, filename, num_threads=4):
    response = requests.head(url)
    size = int(response.headers.get('Content-Length'))
    chunk_size = int(size / num_threads) + 1

    with open(filename, 'wb') as f:
        with tqdm(total=size, unit='B', unit_scale=True, desc=os.path.basename(filename), ncols=80, position=0) as bar:
            futures = []
            for i in range(num_threads):
                start = i * chunk_size
                end = min(start + chunk_size, size)
                futures.append((url, start, end, f))

            with ThreadPoolExecutor(max_workers=num_threads) as executor:
                for future in as_completed(executor.submit(download_range, *future, bar) for future in futures):
                    try:
                        future.result()
                    except Exception as e:
                        logging.error(f'Download failed: {e}')

    logging.info(f'Download completed: {filename}')


def download_range(url, start, end, fileobj, bar):
    headers = {'Range': f'bytes={start}-{end-1}'}
    with requests.get(url, headers=headers, stream=True) as response:
        for chunk in response.iter_content(chunk_size=1024):
            if chunk:
                fileobj.write(chunk)
                bar.update(len(chunk))


def download_ftp(url, filename, num_threads=4):
    with requests.get(url, stream=True) as response:
        total_size = response.headers.get('Content-Length')
        if total_size:
            total_size = int(total_size.strip())
            with tqdm(total=total_size, unit='B', unit_scale=True, desc=os.path.basename(filename), ncols=80, position=0) as bar:
                with open(filename, 'wb') as f:
                    chunk_size = int(total_size / num_threads) + 1
                    futures = []
                    for i in range(num_threads):
                        start = i * chunk_size
                        end = min(start + chunk_size, total_size)
                        futures.append((url, start, end, f, bar))

                    with ThreadPoolExecutor(max_workers=num_threads) as executor:
                        for future in as_completed(executor.submit(download_range_ftp, *future) for future in futures):
                            try:
                                future.result()
                            except Exception as e:
                                logging.error(f'Download failed: {e}')
            logging.info(f'Download completed: {filename}')
        else:
            with open(filename, 'wb') as f:
                f.write(response.content)
            logging.info(f'Download completed: {filename}')


def download_range_ftp(url, start, end, fileobj, bar):
    headers = {'Range': f'bytes={start}-{end-1}'}
    with requests.get(url, headers=headers, stream=True) as response:
        for chunk in response.iter_content(chunk_size=1024):
            if chunk:
                fileobj.write(chunk)
                bar.update(len(chunk))


def download_torrent(magnet, filename):
    tc = transmissionrpc.Client('localhost', port=9091)
    tc.add_torrent(magnet, download_dir=os.path.dirname(filename))
    logging.info(f'Download started: {filename}')


def main():
    parser = argparse.ArgumentParser(description='A command-line tool for downloading files.')
    parser.add_argument('-u', '--url', metavar='<URL>', type=check_url, required=True, help='download url')
    parser.add_argument('-o', '--output', metavar='<FILENAME>', type=str, required=True, help='output filename')
    parser.add_argument('-t', '--threads', metavar='<NUM_THREADS>', type=int, default=4, help='number of threads for downloading')
    parser.add_argument('-d', '--dir', metavar='<DIRECTORY>', type=check_dir, default='.', help='output directory')
    args = parser.parse_args()
    url, filename, num_threads, output_dir = args.url, args.output, args.threads, args.dir

    filename = os.path.join(output_dir, filename)
    if os.path.isfile(filename):
        i = 1
        while True:
            new_filename = f'{os.path.splitext(filename)[0]}_{i}{os.path.splitext(filename)[1]}'
            if not os.path.isfile(new_filename):
                filename = new_filename
                break
            i += 1

    if url.startswith('http'):
        download_file(url, filename, num_threads)
    elif url.startswith('ftp'):
        download_ftp(url, filename, num_threads)
    elif url.startswith('magnet'):
        download_torrent(url, filename)
    else:
        logging.error(f'The url {url} does not start with http, ftp or magnet.')


if __name__ == '__main__':
    logging.basicConfig(level=logging.INFO, format='%(asctime)s %(levelname)s: %(message)s', datefmt='%Y-%m-%d %H:%M:%S')
    main()

注意

使用磁力链接下载时，需要安装 transmission-cli 或其他 BitTorrent 客户端并配置好。
该脚本仅供学习和研究使用，请勿用于任何非法目的。