document-processor-api

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Nutrient Document Processing

Nutrient 文档处理

Use Nutrient DWS for managed document workflows where fidelity, compliance, or multi-step processing matters more than local-tool convenience.

当保真度、合规性或多步骤处理比本地工具便利性更重要时，使用Nutrient DWS进行托管文档工作流。

Setup

设置

Get a Nutrient DWS API key at https://dashboard.nutrient.io/sign_up/?product=processor.

Direct API calls use

Authorization: Bearer $NUTRIENT_API_KEY

bash

export NUTRIENT_API_KEY="nutr_sk_..."

MCP setups commonly use

@nutrient-sdk/dws-mcp-server

with

NUTRIENT_DWS_API_KEY

Scripts live in
```
scripts/
```
relative to this SKILL.md. Use the directory containing this SKILL.md as the working directory:
bash
```
cd <directory containing this SKILL.md> && uv run scripts/<script>.py --help
```
Page ranges use
```
start:end
```
with 0-based indexes and end-exclusive semantics. Negative indexes count from the end.

在https://dashboard.nutrient.io/sign_up/?product=processor获取Nutrient DWS API密钥。

直接API调用使用

Authorization: Bearer $NUTRIENT_API_KEY

。

bash

export NUTRIENT_API_KEY="nutr_sk_..."

MCP设置通常结合

NUTRIENT_DWS_API_KEY

使用

@nutrient-sdk/dws-mcp-server

。

脚本位于本SKILL.md相对路径的
```
scripts/
```
目录下。将包含本SKILL.md的目录作为工作目录：
bash
```
cd <directory containing this SKILL.md> && uv run scripts/<script>.py --help
```
页面范围使用
```
start:end
```
格式，采用0起始索引且不包含结束索引。负索引从文档末尾开始计数。

When to use

使用场景

Generate PDFs from HTML templates, uploaded assets, or remote URLs.
Convert Office, HTML, image, and PDF files between supported formats.
OCR scans and extract text, tables, or key-value pairs.
Redact PII, watermark, sign, fill forms, merge, split, rotate, flatten, or encrypt PDFs.
Produce delivery targets like PDF/A, PDF/UA, optimized PDFs, or linearized PDFs.
Check credits before large, batch, or AI-heavy runs.

从HTML模板、上传资源或远程URL生成PDF。
在支持的格式之间转换Office、HTML、图片和PDF文件。
对扫描件进行OCR识别，并提取文本、表格或键值对。
对PDF进行PII脱敏、添加水印、数字签名、填写表单、合并、拆分、旋转、扁平化或加密。
生成PDF/A、PDF/UA、优化PDF或线性化PDF等交付格式。
在执行大规模、批量或AI密集型任务前检查可用额度。

Tool preference

工具优先级

Prefer
```
scripts/*.py
```
for covered single-operation workflows.
Use
```
assets/templates/custom-workflow-template.py
```
for multi-step jobs that should still run through the Python client.
Use the modular
```
references/
```
docs and direct API payloads for capabilities that do not yet have a dedicated helper script, especially HTML/URL generation and compliance tuning.
Use local PDF utilities only for lightweight inspection. Use Nutrient when output fidelity or compliance matters.

对于已覆盖的单操作工作流，优先使用
```
scripts/*.py
```
脚本。
对于多步骤任务，若仍需通过Python客户端运行，使用
```
assets/templates/custom-workflow-template.py
```
。
对于尚无专用辅助脚本的功能（尤其是HTML/URL生成和合规性调优），使用模块化的
```
references/
```
文档和直接API负载。
仅将本地PDF工具用于轻量级检查。当输出保真度或合规性很重要时，使用Nutrient。

Single-operation scripts

单操作脚本

convert.py

-> convert between

pdf

pdfa

pdfua

docx

xlsx

pptx

png

jpeg

webp

html

, and

markdown

```
merge.py
```
-> merge multiple files into one PDF
```
split.py
```
-> split one PDF into multiple PDFs by page ranges
```
add-pages.py
```
-> append blank pages
```
delete-pages.py
```
-> remove specific pages
```
duplicate-pages.py
```
-> reorder or duplicate pages into a new PDF
```
rotate.py
```
-> rotate selected pages
```
ocr.py
```
-> OCR scanned PDFs or images
```
extract-text.py
```
-> extract text to JSON
```
extract-table.py
```
-> extract tables
```
extract-key-value-pairs.py
```
-> extract key-value pairs
```
watermark-text.py
```
-> apply a text watermark
```
redact-ai.py
```
-> detect and apply AI-powered redactions
```
sign.py
```
-> digitally sign a local PDF
```
password-protect.py
```
-> write encrypted output PDFs
```
optimize.py
```
-> apply optimization and linearization-style options via JSON

convert.py

-> 在

pdf

、

pdfa

、

pdfua

、

docx

、

xlsx

、

pptx

、

png

、

jpeg

、

webp

、

html

和

markdown

格式之间转换

```
merge.py
```
-> 将多个文件合并为单个PDF
```
split.py
```
-> 按页面范围将单个PDF拆分为多个PDF
```
add-pages.py
```
-> 添加空白页
```
delete-pages.py
```
-> 删除指定页面
```
duplicate-pages.py
```
-> 重新排序或复制页面以生成新PDF
```
rotate.py
```
-> 旋转选定页面
```
ocr.py
```
-> 对扫描PDF或图片进行OCR识别
```
extract-text.py
```
-> 将文本提取为JSON格式
```
extract-table.py
```
-> 提取表格
```
extract-key-value-pairs.py
```
-> 提取键值对
```
watermark-text.py
```
-> 添加文本水印
```
redact-ai.py
```
-> 检测并应用AI驱动的脱敏处理
```
sign.py
```
-> 对本地PDF进行数字签名
```
password-protect.py
```
-> 生成加密的输出PDF
```
optimize.py
```
-> 通过JSON应用优化和线性化类选项

Multi-Step Workflow Rule

多步骤工作流规则

Do not add new committed pipeline scripts under

scripts/

When the user asks for multiple operations in one run:

Copy

assets/templates/custom-workflow-template.py

to a temporary location such as

/tmp/ndp-workflow-<task>.py

Implement the combined workflow in that temporary script.
Run it with
```
uv run /tmp/ndp-workflow-<task>.py ...
```
.
Return generated output files.
Delete the temporary script unless the user explicitly asks to keep it.

不要在

scripts/

目录下添加新的已提交管道脚本。

当用户要求在一次运行中执行多个操作时：

将

assets/templates/custom-workflow-template.py

复制到临时位置，例如

/tmp/ndp-workflow-<task>.py

。

在该临时脚本中实现组合工作流。
使用
```
uv run /tmp/ndp-workflow-<task>.py ...
```
运行脚本。
返回生成的输出文件。
除非用户明确要求保留，否则删除临时脚本。

PDF Requirements

PDF要求

```
split.py
```
requires a multi-page PDF and cannot extract ranges from a single-page document.
```
delete-pages.py
```
must retain at least one page and cannot delete the entire document.
```
sign.py
```
only accepts local file paths for the main PDF.

```
split.py
```
需要多页PDF，无法从单页文档中提取页面范围。
```
delete-pages.py
```
必须至少保留一页，不能删除整个文档。
```
sign.py
```
仅接受主PDF的本地文件路径。

Decision rules

决策规则

Prefer a helper script when one already covers the requested operation cleanly.
If you control the source markup, prefer HTML generation over browser print workflows.
Use remote
```
file.url
```
inputs when the source already lives at a stable URL and you want to avoid local uploads.
Use
```
output.type
```
for conversion and finalization targets. Use
```
actions
```
for transformations when building direct API payloads.
OCR before text extraction, key-value extraction, or semantic redaction on scans.
Prefer preset or regex redaction when the target is explicit. Use AI redaction only for contextual or natural-language requests.
Use the PDF manipulation reference for merge, split, rotate, flatten, and page-range workflows instead of inferring those payloads from conversion examples.
Treat PDF/A and PDF/UA as compliance targets, not cosmetic export formats. Choose the target up front and validate final artifacts when requirements are contractual.
For PDF/UA, clean born-digital inputs and structured HTML usually tag better than rasterized or flattened source PDFs.
For delivery optimization, linearize or optimize unsigned output artifacts instead of mutating already signed files.
When the user asks for multiple steps, keep destructive or final steps late in the sequence. Use the workflow recipes when ordering is ambiguous.

如果已有辅助脚本能清晰覆盖请求的操作，优先使用该脚本。
如果您控制源标记，优先使用HTML生成而非浏览器打印工作流。
当源文件已存储在稳定URL且您希望避免本地上传时，使用远程
```
file.url
```
输入。
转换和最终化目标使用
```
output.type
```
。构建直接API负载时，使用
```
actions
```
进行转换操作。
对扫描件进行文本提取、键值提取或语义脱敏前，先执行OCR识别。
当目标明确时，优先使用预设或正则表达式脱敏。仅在处理上下文或自然语言请求时使用AI脱敏。
对于合并、拆分、旋转、扁平化和页面范围工作流，使用PDF操作参考文档，而非从转换示例中推断负载。
将PDF/A和PDF/UA视为合规目标，而非美化导出格式。提前选择目标格式，当要求具有合约性质时，验证最终产物。
对于PDF/UA，原生数字输入和结构化HTML通常比光栅化或扁平化的源PDF标记效果更好。
针对交付优化，对未签名的输出产物进行线性化或优化，而非修改已签名文件。
当用户要求多个步骤时，将破坏性或最终步骤放在序列后期。当顺序不明确时，使用工作流配方。

Anti-patterns

反模式

Do not OCR born-digital PDFs just because the task mentions extraction. Extract first and OCR only if the text layer is missing.
Do not flatten forms or annotations until the user confirms the artifact no longer needs to stay editable.
Do not sign, archive, or linearize intermediate working files. Keep those as final-delivery steps.
Do not promise PDF/A or PDF/UA compliance without a validation step when the requirement is contractual.
Do not commit temporary workflow scripts under
```
scripts/
```
.

不要仅仅因为任务提到提取就对原生数字PDF进行OCR识别。先提取文本，仅当文本层缺失时再进行OCR。
除非用户确认产物不再需要保持可编辑状态，否则不要扁平化表单或注释。
不要对中间工作文件进行签名、归档或线性化处理。将这些操作保留为最终交付步骤。
当合规要求具有合约性质时，不要在未进行验证步骤的情况下承诺PDF/A或PDF/UA合规性。
不要将临时工作流脚本提交到
```
scripts/
```
目录下。

Reference map

参考映射

Read only what you need:

```
references/request-basics.md
```
-> endpoint model, auth, multipart vs JSON, credits, limits, and errors
```
references/generation-and-conversion.md
```
-> HTML/URL generation and format conversion
```
references/pdf-manipulation.md
```
-> merge, split, page-range, rotate, and flatten workflows
```
references/extraction-and-ocr.md
```
-> OCR, text extraction, tables, and key-value workflows
```
references/security-signing-and-forms.md
```
-> redaction, watermarking, signatures, forms, and passwords
```
references/compliance-and-optimization.md
```
-> PDF/A, PDF/UA, optimization, and linearization
```
references/workflow-recipes.md
```
-> end-to-end sequencing patterns for common business document workflows

按需阅读：

```
references/request-basics.md
```
-> 端点模型、认证、多部分表单与JSON、额度、限制和错误
```
references/generation-and-conversion.md
```
-> HTML/URL生成和格式转换
```
references/pdf-manipulation.md
```
-> 合并、拆分、页面范围、旋转和平铺工作流
```
references/extraction-and-ocr.md
```
-> OCR、文本提取、表格和键值对工作流
```
references/security-signing-and-forms.md
```
-> 脱敏、水印、签名、表单和密码

references/compliance-and-optimization.md

-> PDF/A、PDF/UA、优化和线性化

```
references/workflow-recipes.md
```
-> 常见业务文档工作流的端到端序列模式

Rules

规则

Fail fast when required arguments are missing.
Write outputs to explicit paths and print created files.
Do not log secrets.
All client methods are async and should run via
```
asyncio.run(main())
```
.
If import fails, install dependency with
```
uv add nutrient-dws
```
.

当缺少必要参数时快速失败。
将输出写入明确路径并打印已创建的文件。
不要记录机密信息。
所有客户端方法均为异步，应通过
```
asyncio.run(main())
```
运行。
如果导入失败，使用
```
uv add nutrient-dws
```
安装依赖。

Security Hardening Addendum

安全加固补充说明

Prefer a pinned, preinstalled MCP server binary over runtime package fetches.
- Preferred:
```
npm i -g @nutrient-sdk/dws-mcp-server@<pinned-version>
```
- Avoid unpinned runtime fetch in production paths.
Never store
```
NUTRIENT_DWS_API_KEY
```
in committed JSON config files.
- Use process env injection at runtime (shell/export, secrets manager, or host env).
Restrict file access with
```
SANDBOX_PATH
```
to the minimum required working directory.
Before enabling MCP mode in production, verify package provenance and lock version.

优先使用固定版本的预安装MCP服务器二进制文件，而非运行时包获取。
- 推荐：
```
npm i -g @nutrient-sdk/dws-mcp-server@<pinned-version>
```
- 避免在生产路径中使用未固定版本的运行时获取。
不要将
```
NUTRIENT_DWS_API_KEY
```
存储在已提交的JSON配置文件中。
- 在运行时通过进程环境注入（shell/export、密钥管理器或主机环境）。
使用
```
SANDBOX_PATH
```
限制文件访问至所需的最小工作目录。
在生产环境中启用MCP模式前，验证包来源并锁定版本。