BitTorrent 种子文件生成与 Web Seed 技术详解：从理论到实践

#!/usr/bin/env python3
"""
纯 Python Bencode 编码实现
遵循 BitTorrent 规范：字典键按字典序排序
"""

def bencode(obj):
    """
    将 Python 对象编码为 Bencode 格式
    
    参数:
        obj: Python 对象（str/bytes/int/list/dict）
    
    返回:
        bytes: Bencode 编码后的字节序列
    """
    if isinstance(obj, str):
        obj = obj.encode('utf-8')
    
    if isinstance(obj, bytes):
        return str(len(obj)).encode('ascii') + b':' + obj
    
    elif isinstance(obj, int):
        return b'i' + str(obj).encode('ascii') + b'e'
    
    elif isinstance(obj, list):
        result = b'l'
        for item in obj:
            result += bencode(item)
        result += b'e'
        return result
    
    elif isinstance(obj, dict):
        result = b'd'
        # 键必须按字典序排序（BitTorrent 规范强制要求）
        for key in sorted(obj.keys()):
            if not isinstance(key, str):
                raise TypeError(f"字典键必须是字符串: {type(key)}")
            result += bencode(key)
            result += bencode(obj[key])
        result += b'e'
        return result
    
    else:
        raise TypeError(f"不支持的类型: {type(obj)}")

#!/usr/bin/env python3
"""
单文件 BitTorrent 种子生成器
支持 Web Seed 和 Tracker 配置
"""

import os
import sys
import hashlib
import time
from pathlib import Path

def calculate_piece_hashes(data, piece_length):
    """
    计算文件分块 SHA1 哈希
    
    参数:
        data: 文件二进制数据
        piece_length: 每块大小（字节）
    
    返回:
        bytes: 所有块哈希值的拼接（每块 20 字节）
    """
    pieces = []
    offset = 0
    
    while offset < len(data):
        chunk = data[offset:offset + piece_length]
        pieces.append(hashlib.sha1(chunk).digest())
        offset += piece_length
    
    return b''.join(pieces)

def generate_torrent(file_path, output_path, trackers=None, web_seeds=None, 
                     piece_length=16384, comment=None):
    """
    生成带 Web Seed 支持的种子文件
    
    参数:
        file_path: 要打包的文件路径
        output_path: 输出 .torrent 文件路径
        trackers: Tracker URL 列表
        web_seeds: Web Seed URL 列表
        piece_length: 分块大小（默认 16KB）
        comment: 注释信息
    
    返回:
        str: Info Hash（四十位十六进制字符串）
    """
    # 1. 读取文件内容
    with open(file_path, 'rb') as f:
        data = f.read()
    
    # 2. 计算分块哈希
    piece_hashes = calculate_piece_hashes(data, piece_length)
    
    # 3. 构造 Info 字典
    info = {
        'name': os.path.basename(file_path),
        'length': len(data),
        'piece length': piece_length,
        'pieces': piece_hashes
    }
    
    # 4. 构造完整的 torrent 元数据
    torrent = {
        'info': info,
        'creation date': int(time.time()),
        'created by': 'PythonTorrentGenerator/1.0'
    }
    
    # 添加 Tracker 配置
    if trackers:
        torrent['announce'] = trackers[0]
        if len(trackers) > 1:
            torrent['announce-list'] = [[t] for t in trackers]
    else:
        torrent['announce'] = 'http://127.0.0.1:6881/announce'
    
    # 添加 Web Seed 配置
    if web_seeds:
        torrent['url-list'] = web_seeds
    
    # 添加注释
    if comment:
        torrent['comment'] = comment
    
    # 5. Bencode 编码并写入文件
    with open(output_path, 'wb') as f:
        f.write(bencode(torrent))
    
    # 6. 计算 Info Hash
    info_encoded = bencode(info)
    info_hash = hashlib.sha1(info_encoded).hexdigest()
    
    return info_hash

def main():
    """命令行入口"""
    import argparse
    
    parser = argparse.ArgumentParser(description='BitTorrent 种子文件生成器')
    parser.add_argument('file', help='要打包的文件路径')
    parser.add_argument('-o', '--output', default='output.torrent', 
                        help='输出种子文件路径')
    parser.add_argument('-p', '--piece-size', type=int, default=16384,
                        help='分块大小（字节），默认 16384')
    parser.add_argument('-t', '--tracker', action='append',
                        help='Tracker URL（可多次使用）')
    parser.add_argument('-w', '--webseed', action='append',
                        help='Web Seed URL（可多次使用）')
    parser.add_argument('-c', '--comment', help='种子注释')
    
    args = parser.parse_args()
    
    if not os.path.exists(args.file):
        print(f"错误：文件不存在 - {args.file}")
        sys.exit(1)
    
    info_hash = generate_torrent(
        file_path=args.file,
        output_path=args.output,
        trackers=args.tracker,
        web_seeds=args.webseed,
        piece_length=args.piece_size,
        comment=args.comment
    )
    
    print(f"[✓] 种子生成成功")
    print(f"    输出: {args.output}")
    print(f"    Info Hash: {info_hash}")
    print(f"    分块大小: {args.piece_size} 字节")
    print(f"    文件大小: {os.path.getsize(args.file)} 字节")
    if args.tracker:
        print(f"    Tracker: {args.tracker}")
    if args.webseed:
        print(f"    Web Seed: {args.webseed}")

if __name__ == '__main__':
    main()

#!/usr/bin/env python3
"""
多文件 BitTorrent 种子生成器
支持整个目录打包，保持目录结构
"""

import os
import sys
import hashlib
import time
from pathlib import Path

def calculate_piece_hashes_multifile(dir_path, files, piece_length):
    """
    计算多文件目录的分块哈希
    所有文件按顺序拼接，统一分块
    """
    pieces = []
    current_piece = b''
    
    for file_info in files:
        file_path = dir_path / '/'.join(file_info['path'])
        
        with open(file_path, 'rb') as f:
            while True:
                chunk = f.read(piece_length - len(current_piece))
                if not chunk:
                    break
                
                current_piece += chunk
                
                if len(current_piece) == piece_length:
                    pieces.append(hashlib.sha1(current_piece).digest())
                    current_piece = b''
    
    # 处理最后一个不完整的块
    if current_piece:
        pieces.append(hashlib.sha1(current_piece).digest())
    
    return b''.join(pieces)

def generate_multi_file_torrent(dir_path, output_path, trackers=None, 
                                web_seeds=None, piece_length=16384, 
                                comment=None):
    """
    生成多文件种子
    """
    dir_path = Path(dir_path)
    
    if not dir_path.is_dir():
        raise ValueError(f"路径不是目录: {dir_path}")
    
    # 1. 收集所有文件
    files = []
    total_size = 0
    
    for file in sorted(dir_path.rglob('*')):
        if file.is_file():
            rel_path = str(file.relative_to(dir_path)).split(os.sep)
            file_size = file.stat().st_size
            files.append({
                'length': file_size,
                'path': rel_path
            })
            total_size += file_size
    
    if not files:
        raise ValueError(f"目录为空: {dir_path}")
    
    # 2. 计算分块哈希
    piece_hashes = calculate_piece_hashes_multifile(dir_path, files, piece_length)
    
    # 3. 构造 Info 字典（多文件模式）
    info = {
        'name': os.path.basename(dir_path),
        'piece length': piece_length,
        'pieces': piece_hashes,
        'files': files
    }
    
    # 4. 构造完整的 torrent
    torrent = {
        'info': info,
        'creation date': int(time.time()),
        'created by': 'PythonTorrentGenerator/1.0'
    }
    
    if trackers:
        torrent['announce'] = trackers[0]
        if len(trackers) > 1:
            torrent['announce-list'] = [[t] for t in trackers]
    else:
        torrent['announce'] = 'http://127.0.0.1:6881/announce'
    
    if web_seeds:
        torrent['url-list'] = web_seeds
    
    if comment:
        torrent['comment'] = comment
    
    # 5. 写入文件
    with open(output_path, 'wb') as f:
        f.write(bencode(torrent))
    
    # 6. 计算 Info Hash
    info_encoded = bencode(info)
    info_hash = hashlib.sha1(info_encoded).hexdigest()
    
    return info_hash, total_size, len(files)

# 1. 生成单文件种子，带 Web Seed 和 Tracker
python3 torrent_gen.py authorized_keys \
    -o public_key.torrent \
    -w http://192.168.56.6:8000/authorized_keys \
    -t http://tracker.opentrackr.org:1337/announce \
    -t udp://tracker.opentrackr.org:1337/announce \
    -c "Public key transfer test"

# 输出：
# [✓] 种子生成成功
#     输出: public_key.torrent
#     Info Hash: 8602f8bc5d459eec4890d586b1913ec6c20e846a
#     分块大小: 16384 字节
#     文件大小: 91 字节
#     Tracker: ['http://tracker.opentrackr.org:1337/announce', 'udp://tracker.opentrackr.org:1337/announce']
#     Web Seed: ['http://192.168.56.6:8000/authorized_keys']

# 2. 生成目录种子
python3 torrent_gen.py /path/to/project \
    -o project.torrent \
    -p 32768 \
    -t http://tracker.example.com/announce

import requests

def fetch_piece_from_webseed(base_url, start, end):
    """
    通过 Web Seed 下载指定字节范围
    
    参数:
        base_url: Web Seed 基础 URL
        start: 起始字节位置
        end: 结束字节位置（不包含）
    
    返回:
        bytes: 下载的数据
    """
    headers = {
        'Range': f'bytes={start}-{end-1}',
        'User-Agent': 'BitTorrent/7.0'
    }
    
    response = requests.get(base_url, headers=headers, timeout=30)
    
    if response.status_code in (200, 206):
        # 200 = OK（完整文件）
        # 206 = Partial Content（部分内容）
        return response.content
    elif response.status_code == 416:
        # Range Not Satisfiable
        raise ValueError("请求范围超出文件大小")
    else:
        raise RuntimeError(f"HTTP 错误: {response.status_code}")