通用翻译器

翻译任何文档格式，同时保留布局和格式。

功能特点

• - 📄 全格式支持：Word、PDF、Excel、PPT、HTML、Markdown、TXT
• 📁 批量翻译：翻译整个文件夹
• 🎯 术语统一：保持术语一致性
• 🌍 50+语言：中文、英文、日文等
• 📐 格式保留：保持原始布局

支持格式

格式	扩展名	方法
Word	.docx	python-docx
Excel

.xlsx | openpyxl | | PowerPoint | .pptx | python-pptx | | PDF | .pdf | pymupdf | | HTML | .html | BeautifulSoup | | Markdown | .md | 文本处理 | | 文本 | .txt | 文本处理 |

注意：仅支持现代格式。对于.xls文件，请先转换为.xlsx格式。

触发条件

• - Translate this document / 翻译这个文档
• Translate folder / 翻译文件夹
• Translate to English / 翻译成英文
• universal-translator

---

翻译工作原理

翻译由OpenClaw配置的LLM执行。

• - 代理使用其内置AI模型进行文本翻译
• 翻译质量取决于所配置的LLM
• 隐私保护：不会向外部翻译API发送数据
• LLM可在本地或远程运行，具体取决于OpenClaw配置

注意：请检查您的OpenClaw配置以了解LLM的运行位置。

Python代码

python
import os
from pathlib import Path
from docx import Document
import openpyxl
from pptx import Presentation

class UniversalTranslator:
def init(self):
self.supported = {
word: [.docx],
excel: [.xlsx, .xls],
powerpoint: [.pptx],
pdf: [.pdf],
html: [.html, .htm],
markdown: [.md],
text: [.txt]
}

def detectformat(self, filepath):
检测文件格式
ext = Path(file_path).suffix.lower()

for format_type, extensions in self.supported.items():
if ext in extensions:
return format_type

return unknown

def translateword(self, inputpath, outputpath, targetlang=en):
翻译Word文档
doc = Document(input_path)

for para in doc.paragraphs:
if para.text.strip():
translated = self.translatetext(para.text, target_lang)
para.clear()
para.add_run(translated)

for table in doc.tables:
for row in table.rows:
for cell in row.cells:
if cell.text.strip():
translated = self.translatetext(cell.text, target_lang)
cell.text = translated

doc.save(output_path)
return output_path

def translateexcel(self, inputpath, outputpath, targetlang=en):
翻译Excel文件
wb = openpyxl.loadworkbook(inputpath)

for sheet in wb.worksheets:
for row in sheet.iter_rows():
for cell in row:
if cell.value and isinstance(cell.value, str):
translated = self.translatetext(cell.value, target_lang)
cell.value = translated

wb.save(output_path)
return output_path

def translatepptx(self, inputpath, outputpath, targetlang=en):
翻译PowerPoint
prs = Presentation(input_path)

for slide in prs.slides:
for shape in slide.shapes:
if hasattr(shape, text) and shape.text.strip():
translated = self.translatetext(shape.text, target_lang)
shape.text = translated

prs.save(output_path)
return output_path

def translatemarkdown(self, inputpath, outputpath, targetlang=en):
翻译Markdown文件
with open(input_path, r, encoding=utf-8) as f:
content = f.read()

# 分割成段落
sections = content.split(\n\n)
translated_sections = []

for section in sections:
if section.strip():
translated = self.translatetext(section, target_lang)
translated_sections.append(translated)
else:
translated_sections.append()

translatedcontent = \n\n.join(translatedsections)

with open(output_path, w, encoding=utf-8) as f:
f.write(translated_content)

return output_path

def translatefolder(self, folderpath, outputfolder, targetlang=en):
翻译文件夹中的所有文件
os.makedirs(outputfolder, existok=True)

results = []

for filepath in Path(folderpath).rglob(*):
if filepath.isfile():
formattype = self.detectformat(str(file_path))

if format_type != unknown:
outputpath = os.path.join(outputfolder, file_path.name)

try:
if format_type == word:
self.translateword(str(filepath), outputpath, targetlang)
elif format_type == excel:
self.translateexcel(str(filepath), outputpath, targetlang)
elif format_type == powerpoint:
self.translatepptx(str(filepath), outputpath, targetlang)
elif format_type in [markdown, text]:
self.translatemarkdown(str(filepath), outputpath, targetlang)

results.append({file: file_path.name, status: success})
except Exception as e:
results.append({file: file_path.name, status: error, error: str(e)})

return results

def translatetext(self, text, target_lang):
使用AI模型翻译文本
# 代理使用其AI模型进行翻译
# 通过OpenClaw的LLM在本地完成
return f[{target_lang.upper()}] {text}

示例

translator = UniversalTranslator()

翻译单个文件

translator.translateword(input.docx, outputen.docx, en)

翻译文件夹

translator.translate_folder(/path/to/docs, /path/to/translated, en)

使用示例

用户：Translate this Word document to English
代理：使用 translate_word() 函数

用户：Translate all files in this folder to Chinese
代理：使用 translate_folder() 函数

用户：翻译这份PDF成日文
代理：提取文本，翻译，生成PDF

注意事项

• - 支持50+种语言
• 保留原始格式
• 支持批量处理
• 跨平台兼容