nutrient-document-processing

affaan-m ｜ Office 與 PDF ｜原文｜ MIT

用 Nutrient DWS API 轉換、OCR、擷取、遮蔽、簽署與填寫文件

中文翻譯

---
name: nutrient-document-processing
description: 用 Nutrient DWS API 處理、轉換、OCR、擷取、遮蔽、簽署和填寫文件。支援 PDF、DOCX、XLSX、PPTX、HTML 和圖片。透過 Nutrient DWS API 轉換、OCR、擷取、遮蔽、簽署或填寫文件時使用。
metadata:
  origin: ECC
---

# Nutrient Document Processing

> **注意：** 這個 skill 整合的是 Nutrient 的商業 API。使用前請先看過他們的條款。

用 [Nutrient DWS Processor API](https://www.nutrient.io/api/) 處理文件。轉換格式、擷取文字和表格、對掃描文件做 OCR、遮蔽 PII、加浮水印、數位簽署，以及填寫 PDF 表單。

## Setup

到 **[nutrient.io](https://dashboard.nutrient.io/sign_up/?product=processor)** 免費取得 API key

```bash
export NUTRIENT_API_KEY="pdf_live_..."
```

所有請求都用 multipart POST 送到 `https://api.nutrient.io/build`，並帶一個 `instructions` JSON 欄位。

## Operations

### Convert Documents

```bash
# DOCX 轉 PDF
curl -X POST https://api.nutrient.io/build \
  -H "Authorization: Bearer $NUTRIENT_API_KEY" \
  -F "document.docx=@document.docx" \
  -F 'instructions={"parts":[{"file":"document.docx"}]}' \
  -o output.pdf

# PDF 轉 DOCX
curl -X POST https://api.nutrient.io/build \
  -H "Authorization: Bearer $NUTRIENT_API_KEY" \
  -F "document.pdf=@document.pdf" \
  -F 'instructions={"parts":[{"file":"document.pdf"}],"output":{"type":"docx"}}' \
  -o output.docx

# HTML 轉 PDF
curl -X POST https://api.nutrient.io/build \
  -H "Authorization: Bearer $NUTRIENT_API_KEY" \
  -F "index.html=@index.html" \
  -F 'instructions={"parts":[{"html":"index.html"}]}' \
  -o output.pdf
```

支援的輸入：PDF、DOCX、XLSX、PPTX、DOC、XLS、PPT、PPS、PPSX、ODT、RTF、HTML、JPG、PNG、TIFF、HEIC、GIF、WebP、SVG、TGA、EPS。

### Extract Text and Data

```bash
# 擷取純文字
curl -X POST https://api.nutrient.io/build \
  -H "Authorization: Bearer $NUTRIENT_API_KEY" \
  -F "document.pdf=@document.pdf" \
  -F 'instructions={"parts":[{"file":"document.pdf"}],"output":{"type":"text"}}' \
  -o output.txt

# 把表格擷取成 Excel
curl -X POST https://api.nutrient.io/build \
  -H "Authorization: Bearer $NUTRIENT_API_KEY" \
  -F "document.pdf=@document.pdf" \
  -F 'instructions={"parts":[{"file":"document.pdf"}],"output":{"type":"xlsx"}}' \
  -o tables.xlsx
```

### OCR Scanned Documents

```bash
# OCR 成可搜尋的 PDF（支援 100 種以上語言）
curl -X POST https://api.nutrient.io/build \
  -H "Authorization: Bearer $NUTRIENT_API_KEY" \
  -F "scanned.pdf=@scanned.pdf" \
  -F 'instructions={"parts":[{"file":"scanned.pdf"}],"actions":[{"type":"ocr","language":"english"}]}' \
  -o searchable.pdf
```

語言：透過 ISO 639-2 代碼支援 100 種以上語言（例如 `eng`、`deu`、`fra`、`spa`、`jpn`、`kor`、`chi_sim`、`chi_tra`、`ara`、`hin`、`rus`）。像 `english` 或 `german` 這樣的完整語言名稱也可以用。所有支援的代碼請見[完整的 OCR 語言表](https://www.nutrient.io/guides/document-engine/ocr/language-support/)。

### Redact Sensitive Information

```bash
# 以樣式為基礎（SSN、email）
curl -X POST https://api.nutrient.io/build \
  -H "Authorization: Bearer $NUTRIENT_API_KEY" \
  -F "document.pdf=@document.pdf" \
  -F 'instructions={"parts":[{"file":"document.pdf"}],"actions":[{"type":"redaction","strategy":"preset","strategyOptions":{"preset":"social-security-number"}},{"type":"redaction","strategy":"preset","strategyOptions":{"preset":"email-address"}}]}' \
  -o redacted.pdf

# 以 regex 為基礎
curl -X POST https://api.nutrient.io/build \
  -H "Authorization: Bearer $NUTRIENT_API_KEY" \
  -F "document.pdf=@document.pdf" \
  -F 'instructions={"parts":[{"file":"document.pdf"}],"actions":[{"type":"redaction","strategy":"regex","strategyOptions":{"regex":"\\b[A-Z]{2}\\d{6}\\b"}}]}' \
  -o redacted.pdf
```

預設樣式：`social-security-number`、`email-address`、`credit-card-number`、`international-phone-number`、`north-american-phone-number`、`date`、`time`、`url`、`ipv4`、`ipv6`、`mac-address`、`us-zip-code`、`vin`。

### Add Watermarks

```bash
curl -X POST https://api.nutrient.io/build \
  -H "Authorization: Bearer $NUTRIENT_API_KEY" \
  -F "document.pdf=@document.pdf" \
  -F 'instructions={"parts":[{"file":"document.pdf"}],"actions":[{"type":"watermark","text":"CONFIDENTIAL","fontSize":72,"opacity":0.3,"rotation":-45}]}' \
  -o watermarked.pdf
```

### Digital Signatures

```bash
# 自簽的 CMS 簽章
curl -X POST https://api.nutrient.io/build \
  -H "Authorization: Bearer $NUTRIENT_API_KEY" \
  -F "document.pdf=@document.pdf" \
  -F 'instructions={"parts":[{"file":"document.pdf"}],"actions":[{"type":"sign","signatureType":"cms"}]}' \
  -o signed.pdf
```

### Fill PDF Forms

```bash
curl -X POST https://api.nutrient.io/build \
  -H "Authorization: Bearer $NUTRIENT_API_KEY" \
  -F "form.pdf=@form.pdf" \
  -F 'instructions={"parts":[{"file":"form.pdf"}],"actions":[{"type":"fillForm","formFields":{"name":"Jane Smith","email":"jane@example.com","date":"2026-02-06"}}]}' \
  -o filled.pdf
```

## MCP Server (Alternative)

想要原生的工具整合，就用 MCP server 取代 curl：

```json
{
  "mcpServers": {
    "nutrient-dws": {
      "command": "npx",
      "args": ["-y", "@nutrient-sdk/dws-mcp-server"],
      "env": {
        "NUTRIENT_DWS_API_KEY": "YOUR_API_KEY",
        "SANDBOX_PATH": "/path/to/working/directory"
      }
    }
  }
}
```

## When to Use

- 在不同格式之間轉換文件（PDF、DOCX、XLSX、PPTX、HTML、圖片）
- 從 PDF 擷取文字、表格或鍵值對
- 對掃描文件或圖片做 OCR
- 分享文件之前遮蔽 PII
- 替草稿或機密文件加浮水印
- 對合約或協議做數位簽署
- 以程式填寫 PDF 表單

## Links

- [API Playground](https://dashboard.nutrient.io/processor-api/playground/)
- [Full API Docs](https://www.nutrient.io/guides/dws-processor/)
- [npm MCP Server](https://www.npmjs.com/package/@nutrient-sdk/dws-mcp-server)

英文原文

---
name: nutrient-document-processing
description: Process, convert, OCR, extract, redact, sign, and fill documents using the Nutrient DWS API. Works with PDFs, DOCX, XLSX, PPTX, HTML, and images. Use when converting, OCRing, extracting from, redacting, signing, or filling documents via the Nutrient DWS API.
metadata:
  origin: ECC
---

# Nutrient Document Processing

> **Note:** This skill integrates with the Nutrient commercial API. Review their terms before use.

Process documents with the [Nutrient DWS Processor API](https://www.nutrient.io/api/). Convert formats, extract text and tables, OCR scanned documents, redact PII, add watermarks, digitally sign, and fill PDF forms.

## Setup

Get a free API key at **[nutrient.io](https://dashboard.nutrient.io/sign_up/?product=processor)**

```bash
export NUTRIENT_API_KEY="pdf_live_..."
```

All requests go to `https://api.nutrient.io/build` as multipart POST with an `instructions` JSON field.

## Operations

### Convert Documents

```bash
# DOCX to PDF
curl -X POST https://api.nutrient.io/build \
  -H "Authorization: Bearer $NUTRIENT_API_KEY" \
  -F "document.docx=@document.docx" \
  -F 'instructions={"parts":[{"file":"document.docx"}]}' \
  -o output.pdf

# PDF to DOCX
curl -X POST https://api.nutrient.io/build \
  -H "Authorization: Bearer $NUTRIENT_API_KEY" \
  -F "document.pdf=@document.pdf" \
  -F 'instructions={"parts":[{"file":"document.pdf"}],"output":{"type":"docx"}}' \
  -o output.docx

# HTML to PDF
curl -X POST https://api.nutrient.io/build \
  -H "Authorization: Bearer $NUTRIENT_API_KEY" \
  -F "index.html=@index.html" \
  -F 'instructions={"parts":[{"html":"index.html"}]}' \
  -o output.pdf
```

Supported inputs: PDF, DOCX, XLSX, PPTX, DOC, XLS, PPT, PPS, PPSX, ODT, RTF, HTML, JPG, PNG, TIFF, HEIC, GIF, WebP, SVG, TGA, EPS.

### Extract Text and Data

```bash
# Extract plain text
curl -X POST https://api.nutrient.io/build \
  -H "Authorization: Bearer $NUTRIENT_API_KEY" \
  -F "document.pdf=@document.pdf" \
  -F 'instructions={"parts":[{"file":"document.pdf"}],"output":{"type":"text"}}' \
  -o output.txt

# Extract tables as Excel
curl -X POST https://api.nutrient.io/build \
  -H "Authorization: Bearer $NUTRIENT_API_KEY" \
  -F "document.pdf=@document.pdf" \
  -F 'instructions={"parts":[{"file":"document.pdf"}],"output":{"type":"xlsx"}}' \
  -o tables.xlsx
```

### OCR Scanned Documents

```bash
# OCR to searchable PDF (supports 100+ languages)
curl -X POST https://api.nutrient.io/build \
  -H "Authorization: Bearer $NUTRIENT_API_KEY" \
  -F "scanned.pdf=@scanned.pdf" \
  -F 'instructions={"parts":[{"file":"scanned.pdf"}],"actions":[{"type":"ocr","language":"english"}]}' \
  -o searchable.pdf
```

Languages: Supports 100+ languages via ISO 639-2 codes (e.g., `eng`, `deu`, `fra`, `spa`, `jpn`, `kor`, `chi_sim`, `chi_tra`, `ara`, `hin`, `rus`). Full language names like `english` or `german` also work. See the [complete OCR language table](https://www.nutrient.io/guides/document-engine/ocr/language-support/) for all supported codes.

### Redact Sensitive Information

```bash
# Pattern-based (SSN, email)
curl -X POST https://api.nutrient.io/build \
  -H "Authorization: Bearer $NUTRIENT_API_KEY" \
  -F "document.pdf=@document.pdf" \
  -F 'instructions={"parts":[{"file":"document.pdf"}],"actions":[{"type":"redaction","strategy":"preset","strategyOptions":{"preset":"social-security-number"}},{"type":"redaction","strategy":"preset","strategyOptions":{"preset":"email-address"}}]}' \
  -o redacted.pdf

# Regex-based
curl -X POST https://api.nutrient.io/build \
  -H "Authorization: Bearer $NUTRIENT_API_KEY" \
  -F "document.pdf=@document.pdf" \
  -F 'instructions={"parts":[{"file":"document.pdf"}],"actions":[{"type":"redaction","strategy":"regex","strategyOptions":{"regex":"\\b[A-Z]{2}\\d{6}\\b"}}]}' \
  -o redacted.pdf
```

Presets: `social-security-number`, `email-address`, `credit-card-number`, `international-phone-number`, `north-american-phone-number`, `date`, `time`, `url`, `ipv4`, `ipv6`, `mac-address`, `us-zip-code`, `vin`.

### Add Watermarks

```bash
curl -X POST https://api.nutrient.io/build \
  -H "Authorization: Bearer $NUTRIENT_API_KEY" \
  -F "document.pdf=@document.pdf" \
  -F 'instructions={"parts":[{"file":"document.pdf"}],"actions":[{"type":"watermark","text":"CONFIDENTIAL","fontSize":72,"opacity":0.3,"rotation":-45}]}' \
  -o watermarked.pdf
```

### Digital Signatures

```bash
# Self-signed CMS signature
curl -X POST https://api.nutrient.io/build \
  -H "Authorization: Bearer $NUTRIENT_API_KEY" \
  -F "document.pdf=@document.pdf" \
  -F 'instructions={"parts":[{"file":"document.pdf"}],"actions":[{"type":"sign","signatureType":"cms"}]}' \
  -o signed.pdf
```

### Fill PDF Forms

```bash
curl -X POST https://api.nutrient.io/build \
  -H "Authorization: Bearer $NUTRIENT_API_KEY" \
  -F "form.pdf=@form.pdf" \
  -F 'instructions={"parts":[{"file":"form.pdf"}],"actions":[{"type":"fillForm","formFields":{"name":"Jane Smith","email":"jane@example.com","date":"2026-02-06"}}]}' \
  -o filled.pdf
```

## MCP Server (Alternative)

For native tool integration, use the MCP server instead of curl:

```json
{
  "mcpServers": {
    "nutrient-dws": {
      "command": "npx",
      "args": ["-y", "@nutrient-sdk/dws-mcp-server"],
      "env": {
        "NUTRIENT_DWS_API_KEY": "YOUR_API_KEY",
        "SANDBOX_PATH": "/path/to/working/directory"
      }
    }
  }
}
```

## When to Use

- Converting documents between formats (PDF, DOCX, XLSX, PPTX, HTML, images)
- Extracting text, tables, or key-value pairs from PDFs
- OCR on scanned documents or images
- Redacting PII before sharing documents
- Adding watermarks to drafts or confidential documents
- Digitally signing contracts or agreements
- Filling PDF forms programmatically

## Links

- [API Playground](https://dashboard.nutrient.io/processor-api/playground/)
- [Full API Docs](https://www.nutrient.io/guides/dws-processor/)
- [npm MCP Server](https://www.npmjs.com/package/@nutrient-sdk/dws-mcp-server)