ofdkit
轻量的 Python 工具,用来读取 OFD 文件,提取里面的文字和发票字段,并能接入 AI 工具。OFD 是中国的国家标准版式文档格式(GB/T 33190),常见于电子发票和公文。
A lightweight Python toolkit for reading OFD documents (GB/T 33190, the Chinese fixed-layout format used for e-invoices and official documents): extract text and invoice fields, and use them from AI tools.
状态:0.1 版,接口以后可能还会调整。更新记录见 CHANGELOG。 Status: 0.1, the API may still change. See the CHANGELOG.
能做什么 / What it does
- 按阅读顺序提取文字,包括模板和复合对象里的文字。 Text in reading order, including text in templates and composite objects.
- 读取电子发票字段(数电票和增值税电子发票),输出 JSON:发票号码、开票日期、购买方、销售方、金额、税额、价税合计、明细。 Invoice fields from e-invoices as JSON: number, date, buyer, seller, amounts, tax, total, line items.
- 把一个文件夹里的发票汇总成 CSV,Excel 可以直接打开,并提示重复的发票号码。 A folder of invoices summarised as CSV (opens in Excel), with duplicate invoice numbers flagged.
- 只用 Python 标准库,没有任何第三方依赖;能读很多不规范的文件(路径写法不对、编码不对、XML 前缀错误等)。 Standard library only, no dependencies; reads many non-conforming files (bad paths, encodings, XML prefixes).
安装 / Install
需要 Python 3.10 或更新版本。Requires Python 3.10+.
pip install ofdkit
命令行 / Command line
ofdkit text 文件.ofd # 提取文字 / print text
ofdkit invoice 发票.ofd # 发票字段(JSON)/ invoice fields as JSON
ofdkit batch 发票文件夹/ -o 发票汇总.csv # 批量汇总 / summarise a folder as CSV
ofdkit info 文件.ofd # 页数、作者等信息 / pages and metadata
ofdkit invoice 的输出示例(数据是虚构的)/ Example output (fictional data):
{
"invoice_number": "00000000000000000001",
"invoice_code": null,
"issue_date": "2026-01-02",
"check_code": null,
"machine_number": null,
"buyer": {"name": "测试单位甲", "tax_id": "TESTBUYER0001", "address_phone": null, "bank_account": null},
"seller": {"name": "测试单位乙", "tax_id": "TESTSELLER0002", "address_phone": null, "bank_account": null},
"amount_without_tax": "100.00",
"tax_amount": "6.00",
"total_amount": "106.00",
"issuer": "测试人员",
"payee": null,
"reviewer": null,
"note": null,
"items": [
{"name": "*测试*服务项目", "specification": null, "unit": null, "quantity": null,
"unit_price": null, "amount": "100.00", "tax_rate": "6%", "tax_amount": "6.00"}
],
"sources": ["custom_tags"],
"warnings": []
}
金额是字符串,不会丢失精度。如果"合计金额 + 合计税额"不等于"价税合计",warnings 里会提示。
Amounts are decimal strings, so no precision is lost. warnings notes totals that do not add up.
在 AI 工具里使用 / Use from AI tools
MCP 服务器 / MCP server
让 Claude、Codex、Cursor 等 AI 工具直接读取 OFD 文件。需要先安装 uv。所有工具都是只读的。 Lets Claude, Codex, Cursor and other AI tools read OFD files. Requires uv. All tools are read-only.
| 工具 / Tool | 作用 / What it does |
|---|---|
read_ofd_text |
按阅读顺序提取文字,可选 Markdown 和页码范围 / text in reading order, optional Markdown and page range |
read_ofd_invoice |
发票字段 / invoice fields |
ofd_info |
页数、尺寸、元数据 / pages, sizes, metadata |
list_ofd_invoices |
汇总一个文件夹里的发票 / summarise a folder of invoices |
Claude Code:
claude mcp add ofdkit -- uvx --from "ofdkit[mcp]" ofdkit mcp
Claude Desktop、Cursor 等使用 JSON 配置的工具 / tools with a JSON config:
{
"mcpServers": {
"ofdkit": {
"command": "uvx",
"args": ["--from", "ofdkit[mcp]", "ofdkit", "mcp"]
}
}
}
Codex(~/.codex/config.toml):
[mcp_servers.ofdkit]
command = "uvx"
args = ["--from", "ofdkit[mcp]", "ofdkit", "mcp"]
加上 --root 文件夹 可以只允许读取这个文件夹里的文件。
Add --root FOLDER to allow only files inside that folder.
Agent Skill
skills/ofd-reader 告诉 AI 什么时候、怎么用 ofdkit 命令行,适用于支持 Agent Skills 的工具。把这个文件夹复制到:
skills/ofd-reader tells an AI agent when and how to use the ofdkit command line. Copy the folder to:
- Claude Code:
~/.claude/skills/ofd-reader/ - Codex:
~/.codex/skills/ofd-reader/
MarkItDown 插件 / MarkItDown plugin
MarkItDown 是把各种文件转成 Markdown 给 AI 读的工具。安装插件后它就能读 OFD: MarkItDown converts files to Markdown for AI. With this plugin it reads OFD too:
pip install "ofdkit[markitdown]"
markitdown --use-plugins 发票.ofd
Python
import ofdkit
with ofdkit.open("发票.ofd") as doc:
print(doc.text())
invoice = doc.invoice() # 不是发票时返回 None / None if not an invoice
if invoice:
print(invoice.invoice_number, invoice.total_amount)
注意 / Notes
- ofdkit 只读取文件里写了什么,不验证发票真伪。查验真伪请使用国家税务总局的发票查验平台。 ofdkit reports what a file contains. It does not verify that an invoice is genuine.
- 文字如果是画成图形或图片的,就读不出来(需要 OCR,不在本项目范围内)。 Text drawn as shapes or images cannot be extracted (that needs OCR, which is out of scope).
- 多栏排版的页面,目前两栏的文字会出现在同一行,用三个空格隔开。 On multi-column pages, both columns currently share each line, separated by three spaces.
原则 / Principles
- 只读取 OFD,不生成、不修改发票。 Reads OFD only. It never creates or modifies invoices.
- 本项目大部分代码由 AI(Claude)编写,维护者负责决定方向和批准发布。 Most code is written with AI assistance (Claude). The maintainer sets the direction and approves releases.
许可证 / License
Metadata
Release files for ofdkit 0.1.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | |
|---|---|---|---|---|
| ofdkit-0.1.0.tar.gz | 30.4 kB | With provenance | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| ofdkit-0.1.0-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 66.5 kB
Release files / ofdkit-0.1.0.tar.gz
| Download URL | ofdkit-0.1.0.tar.gz |
|---|---|
| Size | 30.4 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
ee2ec570b00fa584511972ba32dab89f1eb75af4e2e102180191dc47fdb211b9
|
|
BLAKE2b-256 checksum How to use checksums |
b66cbc52ccdce45b70277871752cda8ad3166be957040a6070b61962662bb63d
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.16
|
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.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 26, 2026.
Transparency logRelease files / ofdkit-0.1.0-py3-none-any.whl
| Download URL | ofdkit-0.1.0-py3-none-any.whl |
|---|---|
| Size | 36.0 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
d7ff990e506b636420c60b9e2dad59a6e80ee5217255bb010dbd04b0729fa163
|
|
BLAKE2b-256 checksum How to use checksums |
91cb83a5f223298afefe06af0cbf85f0fa251e1c2539c0105115f1ecc78f7a15
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.16
|
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.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 26, 2026.
Transparency logSecurity for ofdkit 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.
Full provenance
All 2 files in this release have been uploaded with provenance metadata.
Attestation for ofdkit-0.1.0.tar.gz
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 26, 2026.
Transparency logA 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.
To learn more about protecting yourself from malicious actors, visit our package security documentation.