重要前提
安装AI Skills的关键前提是:必须科学上网,且开启TUN模式,这一点至关重要,直接决定安装能否顺利完成,在此郑重提醒三遍:科学上网,科学上网,科学上网。查看完整安装教程 →
ocr by trpc-group/trpc-agent-go
npx skills add https://github.com/trpc-group/trpc-agent-go --skill ocr使用 Tesseract OCR 引擎从图像中提取文本。
python3 scripts/ocr.py <image_file> <output_file>
# 指定语言(默认:eng)
python3 scripts/ocr.py image.png text.txt --lang eng
# 中文文本
python3 scripts/ocr.py image.png text.txt --lang chi_sim
# 多种语言
python3 scripts/ocr.py image.png text.txt --lang eng+chi_sim
# 使用图像预处理(提高准确性)
python3 scripts/ocr.py image.png text.txt --preprocess
# 输出带置信度分数的 JSON 格式
python3 scripts/ocr.py image.png output.json --format json
# 对远程图像进行 OCR
python3 scripts/ocr_url.py <image_url> <output_file>
# 使用选项
python3 scripts/ocr_url.py https://example.com/image.jpg text.txt --lang eng --preprocess
广告位招租
在这里展示您的产品或服务
触达数万 AI 开发者,精准高效
image_file / image_url (必需):本地图像路径或图像 URLoutput_file (必需):输出文本/JSON 文件的路径--lang:语言代码(例如:eng、chi_sim、jpn、fra、deu)。默认值:eng--preprocess:应用图像预处理(灰度化、阈值化)以提高准确性--format:输出格式(text/json,默认值:text)| 语言 | 代码 |
|---|---|
| 英语 | eng |
| 中文(简体) | chi_sim |
| 中文(繁体) | chi_tra |
| 日语 | jpn |
| 韩语 | kor |
| 法语 | fra |
| 德语 | deu |
| 西班牙语 | spa |
| 俄语 | rus |
| 阿拉伯语 | ara |
PNG、JPG、JPEG、GIF、BMP、TIFF、WEBP
# Python 包
pip install pytesseract Pillow
# Tesseract OCR 引擎
sudo apt-get install tesseract-ocr # Ubuntu/Debian
sudo yum install tesseract # CentOS/RHEL
brew install tesseract # macOS
每周安装次数
54
代码仓库
GitHub 星标数
1.0K
首次出现
2026年1月27日
安全审计
已安装于
codex53
opencode53
github-copilot51
gemini-cli51
kimi-cli50
cursor50
Extract text from images using Tesseract OCR engine.
python3 scripts/ocr.py <image_file> <output_file>
# Specify language (default: eng)
python3 scripts/ocr.py image.png text.txt --lang eng
# Chinese text
python3 scripts/ocr.py image.png text.txt --lang chi_sim
# Multiple languages
python3 scripts/ocr.py image.png text.txt --lang eng+chi_sim
# With image preprocessing (improves accuracy)
python3 scripts/ocr.py image.png text.txt --preprocess
# JSON output with confidence scores
python3 scripts/ocr.py image.png output.json --format json
# OCR from remote image
python3 scripts/ocr_url.py <image_url> <output_file>
# With options
python3 scripts/ocr_url.py https://example.com/image.jpg text.txt --lang eng --preprocess
image_file / image_url (required): Path to local image or image URLoutput_file (required): Path to output text/JSON file--lang: Language code (e.g., eng, chi_sim, jpn, fra, deu). Default: eng--preprocess: Apply image preprocessing (grayscale, thresholding) for better accuracy--format: Output format (text/json, default: text)| Language | Code |
|---|---|
| English | eng |
| Chinese (Simplified) | chi_sim |
| Chinese (Traditional) | chi_tra |
| Japanese | jpn |
| Korean | kor |
| French | fra |
| German | deu |
| Spanish | spa |
| Russian | rus |
| Arabic | ara |
PNG, JPG, JPEG, GIF, BMP, TIFF, WEBP
# Python packages
pip install pytesseract Pillow
# Tesseract OCR engine
sudo apt-get install tesseract-ocr # Ubuntu/Debian
sudo yum install tesseract # CentOS/RHEL
brew install tesseract # macOS
Weekly Installs
54
Repository
GitHub Stars
1.0K
First Seen
Jan 27, 2026
Security Audits
Gen Agent Trust HubFailSocketPassSnykWarn
Installed on
codex53
opencode53
github-copilot51
gemini-cli51
kimi-cli50
cursor50
AI产品摄影生成器 - 一键创建专业电商主图、白底图、生活场景照
1,100 周安装