Skip to main content

multi-ocr

多引擎 OCR 工具包,将 PDF 和图片转换为 Markdown 文档。

  • CLI 工具:全局安装后一行命令完成 OCR
  • SDK 依赖:作为 Python 库集成到你的项目中

支持的引擎

引擎 说明 类型
SiliconFlow + DeepSeek-OCR 云端 OCR,精度高 API
SiliconFlow + PaddleOCR-VL-1.5 云端 OCR,轻量快速 API
DashScope + Qwen-VL-OCR 阿里云百炼 API
LiteParse 本地 PDF 解析,无需联网 本地
Ollama + DeepSeek-OCR 本地部署 OCR 本地

安装

CLI 全局安装

uv tool install multi-ocr
# 或
pip install multi-ocr

SDK 依赖安装

pip install multi-ocr
# 或
uv add multi-ocr

CLI 使用

# 单文件 OCR
multi-ocr document.pdf

# 指定引擎和页码范围
multi-ocr document.pdf --model dashscope-qwen-vl-ocr --pages 1-5

# 批量处理目录
multi-ocr ./scans/ --model silicon-deepseek-ocr -j 4

# 查看帮助
multi-ocr --help

环境变量

引擎 环境变量
SiliconFlow SILICONFLOW_API_KEY
DashScope DASHSCOPE_API_KEY
Ollama OLLAMA_BASE_URL(可选,默认 http://127.0.0.1:11434)

也可通过 --api-key 参数直接传入。

SDK 使用

from pathlib import Path
from multi_ocr import get_engine, ocr_file, OCREngine

# 创建引擎
engine = get_engine(
    provider="siliconflow",
    model="deepseek-ai/DeepSeek-OCR",
    api_key="your-api-key",
)

# 识别图片
text = engine.parse_image(Path("scan.jpg"))

# 识别 PDF
result = ocr_file(Path("document.pdf"), engine, pages="1-3")

# 批量处理目录
from multi_ocr import ocr_directory
ocr_directory(Path("./scans/"), engine, concurrency=4)

自定义引擎

from multi_ocr import OCREngine

class MyEngine(OCREngine):
    def parse_image(self, image_path: Path) -> str:
        # 你的 OCR 逻辑
        return "recognized text"

要求

  • Python >= 3.11

协议

MIT License

Metadata

Release files for multi-ocr-py 0.1.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for multi-ocr-py 0.1.0
File Size Uploaded Provenance
multi_ocr_py-0.1.0.tar.gz 1.0 MB Without provenance Details

Built distribution (wheel)

Table of built distributions (wheels) for multi-ocr-py 0.1.0
File Interpreter ABI Platform
multi_ocr_py-0.1.0-py3-none-any.whl Python 3 none any Details

Total release size: 1.1 MB

Release files / multi_ocr_py-0.1.0.tar.gz

Download URL multi_ocr_py-0.1.0.tar.gz
Size 1.0 MB
Tags Source
SHA-256 checksum
How to use checksums
16e42d3b3cf193696abe54084ca8f614baccee81d51ddb68314aa767fe56f969
BLAKE2b-256 checksum
How to use checksums
8ae43fcf66ec9c1497fa850ba77a76c67f7019e56132e0857910ed255f5dcdce
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via uv/0.11.26 {"installer":{"name":"uv","version":"0.11.26","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"macOS","version":null,"id":null,"libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}

Release files / multi_ocr_py-0.1.0-py3-none-any.whl

Download URL multi_ocr_py-0.1.0-py3-none-any.whl
Size 19.0 kB
Tags Python 3
SHA-256 checksum
How to use checksums
1f2fe7958911165942d471c2eccef0d84e6b70e2d159a0619d8fafd1377a317a
BLAKE2b-256 checksum
How to use checksums
47562a56d3dfedceca31d32523650104d95ef903b5bc4d68728b2f37728c1327
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via uv/0.11.26 {"installer":{"name":"uv","version":"0.11.26","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"macOS","version":null,"id":null,"libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}

Security for multi-ocr-py 0.1.0

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page