chm2epub/eccode.py

import os
from chardet import detect

def detect_file_encoding(file_path):
    """
    自动检测文件编码。
    :param file_path: 文件路径
    :return: 检测到的编码
    """
    with open(file_path, 'rb') as f:
        raw_data = f.read(1024)  # 读取部分数据进行检测
    result = detect(raw_data)
    return result.get('encoding', 'utf-8')  # 默认返回 utf-8

def convert_encoding_in_dir(directory, dest_encoding):
    """
    转换指定目录下所有文件的编码。
    :param directory: 目录路径
    :param dest_encoding: 目标编码
    """
    for root, dirs, files in os.walk(directory):
        for file in files:
            file_path = os.path.join(root, file)
            try:
                # 自动检测文件编码
                src_encoding = detect_file_encoding(file_path)

                # 读取并转换文件内容
                with open(file_path, 'r', encoding=src_encoding, errors='ignore') as f:
                    content = f.read()

                # 写入目标编码
                with open(file_path, 'w', encoding=dest_encoding) as f:
                    f.write(content)

                print(f"已成功转换文件编码: {file_path} (从 {src_encoding} 转到 {dest_encoding})")
            except Exception as e:
                print(f"无法处理文件 {file_path}: {e}")

# 示例调用
directory = "./全书"
dest_encoding = "utf-8"
convert_encoding_in_dir(directory, dest_encoding)