chm2epub/eccode.py

from tqdm import tqdm
import os
from chardet import detect

# 定义日志文件路径
log_file_path = "conversion_log.txt"


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 log_message_to_file(log_file_path, message):
    """
    将日志信息写入日志文件
    :param log_file_path: 日志文件路径
    :param message: 要记录的日志信息
    """
    try:
        with open(log_file_path, 'a', encoding='utf-8') as log_file:
            log_file.write(message + '\n')
    except Exception as e:
        print(f"无法写入日志文件：{e}")


def convert_encoding_in_dir(directory, dest_encoding, extensions):
    """
    转换指定目录下所有指定格式的文件的编码，并显示进度条。
    :param directory: 目录路径
    :param dest_encoding: 目标编码
    :param extensions: 需要处理的文件扩展名列表（如 ['.txt', '.html']）
    """
    # 获取所有指定格式的文件路径
    files_to_process = []
    for root, _, files in os.walk(directory):
        for file in files:
            if any(file.lower().endswith(ext) for ext in extensions):  # 检查文件扩展名
                files_to_process.append(os.path.join(root, file))

    # 遍历文件并转换编码
    for file_path in tqdm(files_to_process, desc="转换文件编码进度", unit="文件"):
        try:
            # 自动检测文件编码
            # src_encoding = detect_file_encoding(file_path)
            src_encoding = "GB2312"
            # if src_encoding == 'MacRoman' or src_encoding == 'ascii':
            #     src_encoding = "GB2312"

            # 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)

            # 构建日志信息
            log_message = f"已成功转换文件编码: {file_path} (从 {src_encoding} 转到 {dest_encoding})"
            log_message_to_file(log_file_path, log_message)
        except Exception as e:
            error_message = f"无法处理文件 {file_path}: {e}"
            log_message_to_file(log_file_path, error_message)


# 示例调用
directory = "./全书"  # 替换为你的目标文件夹路径
dest_encoding = "utf-8"
extensions = ['.txt', '.html', '.htm', '.js', '.css']  # 需要处理的文件扩展名
convert_encoding_in_dir(directory, dest_encoding, extensions)