The world's highest performing e-book retention layout translation library
English | 简体中文 | 繁體中文 | 日本語 | 한국어
llms has been added as the translation api of choice, Doubao ,Qwen ,deepseek v3 , gpt4-o-mini are recommended. The color space error can be resolved by filling the white areas in PDF files. The old text to text translation api has been removed.
In addition, consider adding arxiv search function and rendering arxiv papers after latex translation.
Apply through Volcengine platform:
Apply through Alibaba Cloud platform:
PolyglotPDF(EbookTranslation) is an advanced PDF processing tool that employs specialized techniques for ultra-fast text, table, and formula recognition in PDF documents, typically completing processing within 1 second. It features OCR capabilities and layout-preserving translation, with full document translations usually completed within 10 seconds (speed may vary depending on the translation API provider).
pip install EbookTranslator
Basic usage:
EbookTranslator your_file.pdf
Usage with parameters:
EbookTranslator your_file.pdf -o en -t zh -b 1 -e 10 -c /path/to/config.json -d 300
from EbookTranslator import main_function
translator = main_function(
pdf_path="your_file.pdf",
original_language="en",
target_language="zh",
bn=1,
en=10,
config_path="/path/to/config.json",
DPI=300
)
translator.main()
| Parameter | Command Line Option | Description | Default Value |
|---|---|---|---|
pdf_path | Positional argument | PDF file path | Required |
original_language | -o, --original | Source language | auto |
target_language | -t, --target | Target language | zh |
bn | -b, --begin | Starting page number | 1 |
en | -e, --end | Ending page number | Last page of the document |
config_path | -c, --config | Configuration file path | config.json in the current working directory |
DPI | -d, --dpi | DPI for OCR mode | 72 |
The configuration file is a JSON file, by default located at config.json in the current working directory. If it doesn't exist, the program will use built-in default settings.
{
"count": 4,
"PPC": 20,
"translation_services": {
"Doubao": {
"auth_key": "",
"model_name": ""
},
"Qwen": {
"auth_key": "",
"model_name": "qwen-plus"
},
"deepl": {
"auth_key": ""
},
"deepseek": {
"auth_key": "",
"model_name": "ep-20250218224909-gps4n"
},
"openai": {
"auth_key": "",
"model_name": "gpt-4o-mini"
},
"youdao": {
"app_key": "",
"app_secret": ""
}
},
"ocr_services": {
"tesseract": {
"path": "C:\\Program Files\\Tesseract-OCR\\tesseract.exe"
}
},
"default_services": {
"ocr_model": false,
"line_model": false,
"Enable_translation": true,
"Translation_api": "openai"
}
}
translation_service: Translation service provider (e.g., "google", "deepl", "baidu")api_key: Translation API key (if required)translation_mode: Translation mode, "online" or "offline"ocr_enabled: Whether to enable OCR recognitiontesseract_path: Path to Tesseract OCR engine (if not in system PATH)output_dir: Output directorylanguage_codes: Language code mappingfont_mapping: Fonts corresponding to different languagesTranslated PDF files will be saved in the directory specified by output_dir (default is the target folder in the current working directory).
MIT
git clone https://github.com/CBIhalsen/PolyglotPDF.git
cd polyglotpdf
pip install -r requirements.txt
Configure your API key in config.json. The alicloud translation API is not recommended.
Run the application:
python app.py
http://127.0.0.1:8000This project leverages PyMuPDF's capabilities for efficient PDF processing and layout preservation.
code=4: only Gray, RGB, and CMYK colorspaces supportedCurrent font configuration in the start function of main.py:
# Current configuration
css=f"* {{font-family:{get_font_by_language(self.target_language)};font-size:auto;color: #111111 ;font-weight:normal;}}"
You can optimize font display through the following methods:
# Custom font styles
css=f"""* {{
font-family: {get_font_by_language(self.target_language)};
font-size: auto;
color: #111111;
font-weight: normal;
letter-spacing: 0.5px; # Adjust letter spacing
line-height: 1.5; # Adjust line height
}}"""
fonts directory@font-face to declare custom fonts in CSScss=f"""
@font-face {{
font-family: 'CustomFont';
src: url('fonts/your-font.ttf') format('truetype');
}}
* {{
font-family: 'CustomFont', {get_font_by_language(self.target_language)};
font-size: auto;
font-weight: normal;
}}
"""
This project follows similar basic principles as Adobe Acrobat DC's PDF editing, using PyMuPDF for text block recognition and manipulation:
# Get text blocks from the page
blocks = page.get_text("dict")["blocks"]
# Process each text block
for block in blocks:
if block.get("type") == 0: # text block
bbox = block["bbox"] # get text block boundary
text = ""
font_info = None
# Collect text and font information
for line in block["lines"]:
for span in line["spans"]:
text += span["text"] + " "
This approach directly processes PDF text blocks, maintaining the original layout while achieving efficient text extraction and modification.
Technical Choices:
Why Avoid Complex Processing:
Project Scope:
Performance:
Related questions answered and discussed：
QQ group: 1031477425
FAQs
The world's highest performing e-book retention layout translation library
We found that EbookTranslator demonstrated a healthy version release cadence and project activity because the last version was released less than a year ago. It has 1 open source maintainer collaborating on the project.
Did you know?
Socket for GitHub automatically highlights issues in each pull request and monitors the health of all your open source dependencies. Discover the contents of your packages and block harmful activity before you install or update your dependencies.
Research
Security News
Malicious PyPI checkers validate stolen emails against TikTok and Instagram APIs, enabling targeted account attacks and dark web credential sales.
Security News
The Node.js TSC opted not to endorse a feature bounty program, citing concerns about incentives, governance, and project neutrality.
Research
Security News
A look at the top trends in how threat actors are weaponizing open source packages to deliver malware and persist across the software supply chain.