本文目录导读：
我来介绍几种批量翻译文档的脚本方法,从简单到专业：
使用免费API（适合小批量）
Python + Google翻译（无需API密钥）
from googletrans import Translator
import os
from pathlib import Path
def batch_translate_folder(input_folder, output_folder, src_lang='auto', dest_lang='zh-cn'):
translator = Translator()
# 创建输出文件夹
Path(output_folder).mkdir(parents=True, exist_ok=True)
# 遍历所有txt文件
for file_path in Path(input_folder).glob('*.txt'):
with open(file_path, 'r', encoding='utf-8') as f:
content = f.read()
# 翻译内容（注意：有长度限制）
translated = translator.translate(content, src=src_lang, dest=dest_lang)
# 保存翻译结果
output_path = Path(output_folder) / f"translated_{file_path.name}"
with open(output_path, 'w', encoding='utf-8') as f:
f.write(translated.text)
print(f"已翻译: {file_path.name}")
# 使用示例
batch_translate_folder('input_docs', 'output_docs')
使用DeepL API（更专业，需付费）
import deepl
import os
def translate_with_deepl():
# 注册获取API密钥：https://www.deepl.com/pro-api
auth_key = "你的API密钥"
translator = deepl.Translator(auth_key)
input_dir = "documents"
output_dir = "translated_documents"
for filename in os.listdir(input_dir):
if filename.endswith(('.txt', '.docx', '.pdf')):
input_path = os.path.join(input_dir, filename)
# 读取文件
with open(input_path, 'r', encoding='utf-8') as f:
text = f.read()
# 翻译（支持批量处理）
result = translator.translate_text(
text,
source_lang="EN",
target_lang="ZH"
)
# 保存结果
output_path = os.path.join(output_dir, f"zh_{filename}")
with open(output_path, 'w', encoding='utf-8') as f:
f.write(result.text)
# 使用示例
translate_with_deepl()
处理多种文档格式（Word, PDF等）
from docx import Document
import PyPDF2
from googletrans import Translator
class MultiFormatTranslator:
def __init__(self):
self.translator = Translator()
def translate_word(self, input_path, output_path, target_lang='zh-cn'):
doc = Document(input_path)
for paragraph in doc.paragraphs:
if paragraph.text.strip():
try:
translated = self.translator.translate(
paragraph.text,
dest=target_lang
)
paragraph.text = translated.text
except:
print(f"警告: 无法翻译段落: {paragraph.text[:50]}...")
doc.save(output_path)
def translate_pdf(self, input_path, output_path, target_lang='zh-cn'):
# 读取PDF
with open(input_path, 'rb') as file:
pdf_reader = PyPDF2.PdfReader(file)
text = ""
for page in pdf_reader.pages:
text += page.extract_text()
# 分段翻译（避免超长限制）
chunks = [text[i:i+5000] for i in range(0, len(text), 5000)]
translated_chunks = []
for chunk in chunks:
translated = self.translator.translate(chunk, dest=target_lang)
translated_chunks.append(translated.text)
# 保存为txt
with open(output_path.replace('.pdf', '.txt'), 'w', encoding='utf-8') as f:
f.write(''.join(translated_chunks))
# 使用示例
translator = MultiFormatTranslator()
translator.translate_word('input.docx', 'output.docx')
translator.translate_pdf('input.pdf', 'output.pdf')
批量处理 + 进度显示
import os
from concurrent.futures import ThreadPoolExecutor, as_completed
from tqdm import tqdm
from googletrans import Translator
def translate_file(file_path, output_dir, target_lang='zh-cn'):
translator = Translator()
try:
with open(file_path, 'r', encoding='utf-8') as f:
content = f.read()
# 翻译
result = translator.translate(content, dest=target_lang)
# 保存
output_path = os.path.join(output_dir, f"translated_{os.path.basename(file_path)}")
with open(output_path, 'w', encoding='utf-8') as f:
f.write(result.text)
return True, file_path
except Exception as e:
return False, f"{file_path}: {str(e)}"
def batch_translate_parallel(input_dir, output_dir, max_workers=5):
# 创建输出目录
os.makedirs(output_dir, exist_ok=True)
# 获取所有txt文件
files = [os.path.join(input_dir, f) for f in os.listdir(input_dir)
if f.endswith('.txt')]
# 多线程并行处理
with ThreadPoolExecutor(max_workers=max_workers) as executor:
futures = {executor.submit(translate_file, file, output_dir): file
for file in files}
# 显示进度条
for future in tqdm(as_completed(futures), total=len(files), desc="翻译进度"):
success, msg = future.result()
if not success:
print(f"失败: {msg}")
# 使用示例
batch_translate_parallel('input_folder', 'output_folder')
使用命令行工具（最简单）
安装 trans 工具
# 安装
pip install translate-shell
# 批量翻译所有txt文件
for file in *.txt; do
trans :zh "$file" > "translated_$file"
done
注意事项
- API限制：免费API有每日使用限额
- 大文件处理：建议分段处理，每段不超过5000字符
- 格式保持：Word/PDF可能丢失格式
- 质量验证：建议抽样检查翻译质量
推荐方案
- 小批量免费：使用Google翻译（googletrans库）
- 专业商用：使用DeepL API或百度翻译API
- 大量处理：使用Ray或Dask分布式处理框架
- GUI工具：可以使用OmegaT或Crowdin等专业翻译工具
需要我帮你实现特定格式文档（如Word、Excel、PDF）的批量翻译脚本吗？
