有道翻译“批处理脚本”高级应用：利用命令行工具实现文件夹批量翻译与格式转换

# -*- coding: utf-8 -*-
import os
import hashlib
import json
import time
from pathlib import Path
import requests
from docx import Document
import chardet
# 导入其他必要的库...

class YoudaoBatchTranslator:
    def __init__(self, app_key, app_secret, from_lang='zh-CHS', to_lang='en'):
        self.app_key = app_key
        self.app_secret = app_secret
        self.from_lang = from_lang
        self.to_lang = to_lang
        self.api_url = 'https://openapi.youdao.com/api'
        # 简单的缓存字典，避免重复翻译相同内容
        self.translation_cache = {}
        # 支持的文件扩展名
        self.supported_extensions = {'.txt', '.md', '.csv', '.json', '.xml', '.html', '.htm'}

    def _sign(self, text):
        """生成API签名。"""
        salt = str(time.time())[:10]
        sign_str = self.app_key + text + salt + self.app_secret
        sign = hashlib.md5(sign_str.encode('utf-8')).hexdigest()
        return sign, salt

    def translate_text(self, text):
        """调用有道API翻译单段文本。"""
        if not text.strip():
            return ""
        # 检查缓存
        cache_key = f"{self.from_lang}_{self.to_lang}_{text}"
        if cache_key in self.translation_cache:
            return self.translation_cache[cache_key]

        sign, salt = self._sign(text)
        # API要求文本长度限制，此处简单处理，实际应对长文本进行拆分
        if len(text) > 5000:
            # 实现长文本拆分逻辑（此处省略）
            pass

        payload = {
            'q': text,
            'from': self.from_lang,
            'to': self.to_lang,
            'appKey': self.app_key,
            'salt': salt,
            'sign': sign,
            'signType': 'v3'
        }
        try:
            response = requests.post(self.api_url, data=payload, timeout=30)
            result = response.json()
            if result.get('errorCode') == '0':
                translation = result.get('translation', [''])[0]
                self.translation_cache[cache_key] = translation
                return translation
            else:
                print(f"API错误: {result.get('errorCode')}, {result.get('msg')}")
                return f"[翻译失败: {text}]"
        except Exception as e:
            print(f"网络或请求错误: {e}")
            return f"[翻译错误: {text}]"

    def read_file(self, file_path):
        """读取不同格式文件的文本内容。返回一个结构化的数据，例如段落列表。"""
        file_ext = Path(file_path).suffix.lower()
        content = []
        try:
            if file_ext == '.txt' or file_ext == '.md':
                with open(file_path, 'rb') as f:
                    raw_data = f.read()
                    encoding = chardet.detect(raw_data)['encoding'] or 'utf-8'
                text = raw_data.decode(encoding, errors='ignore')
                # 按行或段落分割
                content = [para for para in text.splitlines() if para.strip()]
            elif file_ext == '.docx':
                doc = Document(file_path)
                content = [para.text for para in doc.paragraphs if para.text.strip()]
            # 此处可扩展添加PDF、Excel等读取逻辑...
            else:
                print(f"暂不支持的文件格式: {file_ext}")
                return None
        except Exception as e:
            print(f"读取文件 {file_path} 失败: {e}")
            return None
        return content

    def write_translated_file(self, original_content, translated_content, original_path, output_dir):
        """将翻译后的内容写回文件，保持相同格式。"""
        original_path = Path(original_path)
        # 构建输出路径，可在原文件名后添加语言后缀
        output_filename = original_path.stem + f'_{self.to_lang}' + original_path.suffix
        output_path = Path(output_dir) / output_filename

        file_ext = original_path.suffix.lower()
        try:
            if file_ext in ['.txt', '.md']:
                with open(output_path, 'w', encoding='utf-8') as f:
                    f.write('\n'.join(translated_content))
            elif file_ext == '.docx':
                # 创建一个新的文档，并逐段落写入翻译后的文本
                doc = Document()
                for para in translated_content:
                    doc.add_paragraph(para)
                doc.save(output_path)
            # 此处可扩展其他格式的写入逻辑...
            print(f"已生成: {output_path}")
        except Exception as e:
            print(f"写入文件 {output_path} 失败: {e}")

    def process_file(self, file_path, output_dir):
        """处理单个文件：读取->翻译->写入。"""
        print(f"正在处理: {file_path}")
        original_content = self.read_file(file_path)
        if original_content is None:
            return False

        translated_content = []
        for i, paragraph in enumerate(original_content):
            # 添加简单进度提示
            if i % 10 == 0:
                print(f"  进度: 第 {i+1}/{len(original_content)} 段")
            translated_para = self.translate_text(paragraph)
            translated_content.append(translated_para)
            # 出于API频率限制考虑，可添加短暂延时
            # time.sleep(0.1)

        self.write_translated_file(original_content, translated_content, file_path, output_dir)
        return True

    def process_folder(self, input_folder, output_folder, recursive=True):
        """处理整个文件夹。"""
        input_path = Path(input_folder)
        output_path = Path(output_folder)
        output_path.mkdir(parents=True, exist_ok=True)

        # 决定是遍历所有文件还是仅当前目录
        iterator = input_path.rglob('*') if recursive else input_path.glob('*')

        for item in iterator:
            if item.is_file() and item.suffix.lower() in self.supported_extensions:
                # 保持输出目录的相同子目录结构
                relative_path = item.relative_to(input_path)
                target_output_dir = output_path / relative_path.parent
                target_output_dir.mkdir(parents=True, exist_ok=True)
                self.process_file(str(item), str(target_output_dir))

# 主程序入口
if __name__ == '__main__':
    # 请替换成您自己的APP Key和APP Secret
    APP_KEY = '您的应用ID'
    APP_SECRET = '您的应用密钥'

    translator = YoudaoBatchTranslator(
        app_key=APP_KEY,
        app_secret=APP_SECRET,
        from_lang='zh-CHS', # 源语言：简体中文
        to_lang='en'        # 目标语言：英语
    )

    INPUT_DIR = './source_docs'   # 待翻译的源文件夹
    OUTPUT_DIR = './translated_docs' # 翻译后的输出文件夹

    # 开始处理
    translator.process_folder(INPUT_DIR, OUTPUT_DIR, recursive=True)
    print("批量翻译任务完成！")

@echo off
setlocal enabledelayedexpansion
set APP_KEY=你的APP_KEY
set APP_SECRET=你的APP_SECRET
set FROM_LANG=zh-CHS
set TO_LANG=en

set INPUT_DIR=.\source
set OUTPUT_DIR=.\translated

if not exist "%OUTPUT_DIR%" mkdir "%OUTPUT_DIR%"

for /r "%INPUT_DIR%" %%f in (*.txt) do (
    echo 正在处理: %%f
    rem 读取文件内容（此处简化处理，实际需考虑编码和长文本）
    set /p file_content=<"%%f"
    rem 调用PowerShell脚本进行API请求（更可靠）
    powershell -ExecutionPolicy Bypass -File "translate.ps1" -text "!file_content!" -appKey "%APP_KEY%" -appSecret "%APP_SECRET%" -from "%FROM_LANG%" -to "%TO_LANG%" > "%OUTPUT_DIR%\%%~nxf"
)
echo 完成。
pause