全球最受推崇的免费开源
OCR 文字识别引擎

# 使用 Homebrew 安装 Tesseract
brew install tesseract

# 安装全语言包 (推荐):
brew install tesseract-lang

# 验证安装及语言列表:
tesseract --version
tesseract --list-langs

# Ubuntu / Debian
sudo apt update
sudo apt install tesseract-ocr tesseract-ocr-chi-sim tesseract-ocr-eng

# CentOS / RHEL / Fedora
sudo dnf install tesseract tesseract-langpack-chi_sim

# Arch Linux
sudo pacman -S tesseract tesseract-data-chi_sim tesseract-data-eng

pip install pytesseract pillow opencv-python

# Python 代码示例:
import pytesseract
from PIL import Image

# 从图片提取中英文文本
image = Image.open('document.jpg')
text = pytesseract.image_to_string(image, lang='chi_sim+eng')
print(text)

# 生成双层可搜索 PDF
pdf = pytesseract.image_to_pdf_or_hocr('document.png', extension='pdf', lang='chi_sim')
with open('output.pdf', 'wb') as f:
    f.write(pdf)

npm install tesseract.js

// Node.js 或浏览器代码:
import { createWorker } from 'tesseract.js';

const worker = await createWorker('chi_sim');
const ret = await worker.recognize('image.png');
console.log(ret.data.text);
await worker.terminate();