pdf-to-word-docx

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

PDF to Word Converter

PDF转Word转换器

Purpose

用途

Wraps the
```
ComPDFKitConversion
```
Python SDK into a reusable local conversion workflow, supporting PDF / image to Word, PPT, Excel, HTML, RTF, Image, TXT, JSON, Markdown, and CSV (10 output formats in total).

将
```
ComPDFKitConversion
```
Python SDK封装为可复用的本地转换工作流，支持PDF/图片转换为Word、PPT、Excel、HTML、RTF、图片、TXT、JSON、Markdown和CSV（共10种输出格式）。

Agent Skills Standard Compatibility

Agent Skills标准兼容性

This Skill uses an Anthropic Agent Skills-compatible directory structure:
```
pdf-to-word-docx/
```
.
The entry point is
```
SKILL.md
```
; helper scripts are placed in
```
scripts/
```
.
The document uses
```
$ARGUMENTS
```
and
```
${CLAUDE_SKILL_DIR}
```
conventions for distribution and execution in Claude Code / Agent Skills-compatible environments.

本Skill采用Anthropic Agent Skills兼容的目录结构：
```
pdf-to-word-docx/
```
。
入口文件为
```
SKILL.md
```
；辅助脚本存放于
```
scripts/
```
目录。
文档使用
```
$ARGUMENTS
```
和
```
${CLAUDE_SKILL_DIR}
```
约定，以便在Claude Code/Agent Skills兼容环境中分发和执行。

Input / Output

输入/输出

Input: The target format (
```
word
```
/
```
excel
```
/
```
ppt
```
/
```
html
```
/
```
rtf
```
/
```
image
```
/
```
txt
```
/
```
json
```
/
```
markdown
```
/
```
csv
```
), the PDF or image path, and the output path are passed via Skill arguments or the command line. An optional PDF password and conversion parameters may also be provided.
Supported input file types:
- PDF files (
```
.pdf
```
  )
- Image files (
```
.jpg
```
  /
```
.jpeg
```
  /
```
.png
```
  /
```
.bmp
```
  /
```
.tif
```
  /
```
.tiff
```
  /
```
.webp
```
  /
```
.jp2
```
  /
```
.gif
```
  /
```
.tga
```
  )
Output: A file in the corresponding format (
```
.docx
```
,
```
.pptx
```
,
```
.xlsx
```
,
```
.html
```
,
```
.rtf
```
, image,
```
.txt
```
,
```
.json
```
,
```
.md
```
,
```
.csv
```
), or a clear error message.

输入：目标格式（
```
word
```
/
```
excel
```
/
```
ppt
```
/
```
html
```
/
```
rtf
```
/
```
image
```
/
```
txt
```
/
```
json
```
/
```
markdown
```
/
```
csv
```
）、PDF或图片路径、输出路径通过Skill参数或命令行传递。还可提供可选的PDF密码和转换参数。
支持的输入文件类型：
- PDF文件（
```
.pdf
```
  ）
- 图片文件（
```
.jpg
```
  /
```
.jpeg
```
  /
```
.png
```
  /
```
.bmp
```
  /
```
.tif
```
  /
```
.tiff
```
  /
```
.webp
```
  /
```
.jp2
```
  /
```
.gif
```
  /
```
.tga
```
  ）
输出：对应格式的文件（
```
.docx
```
、
```
.pptx
```
、
```
.xlsx
```
、
```
.html
```
、
```
.rtf
```
、图片、
```
.txt
```
、
```
.json
```
、
```
.md
```
、
```
.csv
```
），或清晰的错误提示信息。

Prerequisites

前置条件

Supports Windows and macOS.
The conversion SDK must be installed first:
bash
```
pip install ComPDFKitConversion
```
On first run, the script automatically downloads
```
license.xml
```
from the ComPDF server and caches it in the
```
scripts/
```
directory:
text
```
https://download.compdf.com/skills/license/license.xml
```
The script reads the
```
<key>...</key>
```
field from
```
license.xml
```
and uses that key for
```
LibraryManager.license_verify(...)
```
authentication — it does not pass the XML file path directly to the SDK.
To use a custom license, place your own
```
license.xml
```
in the
```
scripts/
```
directory; the script will use it directly without downloading.
During SDK initialization, the
```
resource
```
directory is always set to the directory containing
```
pdf-to-word-docx.py
```
, i.e., the
```
scripts/
```
directory itself.
When
```
--enable-ocr
```
or
```
--enable-ai-layout
```
(enabled by default) is used, the Skill also requires
```
scripts/documentai.model
```
. If the file does not exist, the script will automatically download it from:
text
```
https://download.compdf.com/skills/model/documentai.model
```
To reuse an existing model file, you can override the default model path via an environment variable:
bash
```
export COMPDF_DOCUMENT_AI_MODEL="/path/to/documentai.model"
```

支持Windows和macOS系统。
必须先安装转换SDK：
bash
```
pip install ComPDFKitConversion
```
首次运行时，脚本会自动从ComPDF服务器下载
```
license.xml
```
并缓存到
```
scripts/
```
目录：
text
```
https://download.compdf.com/skills/license/license.xml
```
脚本从
```
license.xml
```
中读取
```
<key>...</key>
```
字段，并使用该密钥进行
```
LibraryManager.license_verify(...)
```
认证——不会直接将XML文件路径传递给SDK。
若要使用自定义许可证，将您自己的
```
license.xml
```
放置在
```
scripts/
```
目录中；脚本会直接使用该文件，不会自动下载。
SDK初始化时，
```
resource
```
目录始终设置为包含
```
pdf-to-word-docx.py
```
的目录，即
```
scripts/
```
目录本身。
当使用
```
--enable-ocr
```
或
```
--enable-ai-layout
```
（默认启用）时，Skill还需要
```
scripts/documentai.model
```
文件。若文件不存在，脚本会自动从以下地址下载：
text
```
https://download.compdf.com/skills/model/documentai.model
```
若要复用现有模型文件，可通过环境变量覆盖默认模型路径：
bash
```
export COMPDF_DOCUMENT_AI_MODEL="/path/to/documentai.model"
```

Workflow

工作流

Confirm the Python package is installed:
bash
```
python -m pip show ComPDFKitConversion
```
The script automatically downloads
```
license.xml
```
on first run; the
```
scripts/
```
directory is used directly as the SDK
```
resource
```
path.

In Agent Skills / Claude Code environments, prefer using the Skill's built-in script path variable:

bash

python "${CLAUDE_SKILL_DIR}/scripts/pdf-to-word-docx.py" word input.pdf output.docx
python "${CLAUDE_SKILL_DIR}/scripts/pdf-to-word-docx.py" ppt input.pdf output.pptx
python "${CLAUDE_SKILL_DIR}/scripts/pdf-to-word-docx.py" excel input.pdf output.xlsx

For more control, append common parameters:

bash

python "${CLAUDE_SKILL_DIR}/scripts/pdf-to-word-docx.py" excel input.pdf output.xlsx --page-ranges "1-3,5" --excel-all-content --excel-worksheet-option for-page
python "${CLAUDE_SKILL_DIR}/scripts/pdf-to-word-docx.py" word input.pdf output.docx --enable-ocr --page-layout-mode flow

On startup, the script ensures
```
scripts/license.xml
```
exists (downloading it automatically from the ComPDF server if missing), reads the
```
<key>
```
field for SDK authentication, and uses the
```
scripts/
```
directory as the
```
resource
```
path.
If
```
--enable-ocr
```
or
```
--enable-ai-layout
```
(enabled by default) is active, the script checks whether
```
scripts/documentai.model
```
exists; if not, it downloads the file automatically before initializing the Document AI model.
Check the return code; if it is not
```
SUCCESS
```
, handle license, password, resource, model, or input file issues according to the error name.

确认Python包已安装：
bash
```
python -m pip show ComPDFKitConversion
```
脚本首次运行时自动下载
```
license.xml
```
；
```
scripts/
```
目录直接用作SDK的
```
resource
```
路径。

在Agent Skills/Claude Code环境中，优先使用Skill内置的脚本路径变量：

bash

python "${CLAUDE_SKILL_DIR}/scripts/pdf-to-word-docx.py" word input.pdf output.docx
python "${CLAUDE_SKILL_DIR}/scripts/pdf-to-word-docx.py" ppt input.pdf output.pptx
python "${CLAUDE_SKILL_DIR}/scripts/pdf-to-word-docx.py" excel input.pdf output.xlsx

如需更多控制，可追加常用参数：

bash

python "${CLAUDE_SKILL_DIR}/scripts/pdf-to-word-docx.py" excel input.pdf output.xlsx --page-ranges "1-3,5" --excel-all-content --excel-worksheet-option for-page
python "${CLAUDE_SKILL_DIR}/scripts/pdf-to-word-docx.py" word input.pdf output.docx --enable-ocr --page-layout-mode flow

启动时，脚本确保
```
scripts/license.xml
```
存在（若缺失则自动从ComPDF服务器下载），读取
```
<key>
```
字段用于SDK认证，并将
```
scripts/
```
目录作为
```
resource
```
路径。
若
```
--enable-ocr
```
或
```
--enable-ai-layout
```
（默认启用）处于激活状态，脚本会检查
```
scripts/documentai.model
```
是否存在；若不存在，会在初始化Document AI模型前自动下载该文件。
检查返回码；若返回码不是
```
SUCCESS
```
，则根据错误名称处理许可证、密码、资源、模型或输入文件相关问题。

documentai.model Download Optimization

documentai.model下载优化

The script preferentially uses the model file pointed to by
```
COMPDF_DOCUMENT_AI_MODEL
```
.
The default model path is
```
scripts/documentai.model
```
.
During automatic download, the file is first written to
```
documentai.model.part
```
and then atomically renamed to the final file upon success, preventing partial file corruption.
On download failure, the script retries automatically with back-off intervals of
```
2s / 5s / 10s
```
.

脚本优先使用
```
COMPDF_DOCUMENT_AI_MODEL
```
指向的模型文件。
默认模型路径为
```
scripts/documentai.model
```
。
自动下载时，文件先写入
```
documentai.model.part
```
，成功后再原子重命名为最终文件，避免文件部分损坏。
下载失败时，脚本会自动重试，退避间隔为
```
2s / 5s / 10s
```
。

Invoking Directly as a Skill

直接作为Skill调用

In environments that support Agent Skills, the Skill can be called directly:

text

/pdf-to-word-docx word input.pdf output.docx
/pdf-to-word-docx excel input.pdf output.xlsx --excel-worksheet-option for-page

When the Skill receives arguments, it passes them through to the script as-is:
bash
```
python "${CLAUDE_SKILL_DIR}/scripts/pdf-to-word-docx.py" $ARGUMENTS
```
If the environment does not support direct Skill invocation, fall back to a regular command-line call.

在支持Agent Skills的环境中，可直接调用该Skill：

text

/pdf-to-word-docx word input.pdf output.docx
/pdf-to-word-docx excel input.pdf output.xlsx --excel-worksheet-option for-page

Skill收到参数后，会原样传递给脚本：

bash

python "${CLAUDE_SKILL_DIR}/scripts/pdf-to-word-docx.py" $ARGUMENTS

若环境不支持直接调用Skill，则退回到常规命令行调用方式。

Supported Output Formats

支持的输出格式

```
word
```
→ calls
```
CPDFConversion.start_pdf_to_word
```
```
excel
```
→ calls
```
CPDFConversion.start_pdf_to_excel
```
```
ppt
```
→ calls
```
CPDFConversion.start_pdf_to_ppt
```
```
html
```
→ calls
```
CPDFConversion.start_pdf_to_html
```
```
rtf
```
→ calls
```
CPDFConversion.start_pdf_to_rtf
```
```
image
```
→ calls
```
CPDFConversion.start_pdf_to_image
```
```
txt
```
→ calls
```
CPDFConversion.start_pdf_to_txt
```
```
json
```
→ calls
```
CPDFConversion.start_pdf_to_json
```

markdown

→ calls

CPDFConversion.start_pdf_to_markdown

```
csv
```
→ reuses
```
CPDFConversion.start_pdf_to_excel
```
with table/Excel parameters to produce CSV-friendly output

```
word
```
→ 调用
```
CPDFConversion.start_pdf_to_word
```
```
excel
```
→ 调用
```
CPDFConversion.start_pdf_to_excel
```
```
ppt
```
→ 调用
```
CPDFConversion.start_pdf_to_ppt
```
```
html
```
→ 调用
```
CPDFConversion.start_pdf_to_html
```
```
rtf
```
→ 调用
```
CPDFConversion.start_pdf_to_rtf
```
```
image
```
→ 调用
```
CPDFConversion.start_pdf_to_image
```
```
txt
```
→ 调用
```
CPDFConversion.start_pdf_to_txt
```
```
json
```
→ 调用
```
CPDFConversion.start_pdf_to_json
```

markdown

→ 调用

CPDFConversion.start_pdf_to_markdown

```
csv
```
→ 复用
```
CPDFConversion.start_pdf_to_excel
```
并配合表格/Excel参数生成适合CSV的输出

Input Source Types

输入源类型

The script supports PDF and image as input sources. The SDK's
```
start_pdf_to_*
```
interfaces natively accept image files with no pre-processing required.
By default, the script auto-detects the input type from the file extension:
- ```
.pdf
```
  →
```
pdf
```
- ```
.png/.jpg/.jpeg/.bmp/.tif/.tiff/.gif/.webp/.tga
```
  →
```
image
```

You can also specify the source type explicitly:

bash

python "${CLAUDE_SKILL_DIR}/scripts/pdf-to-word-docx.py" word input.png output.docx --source-type image

```
image -> *
```
and
```
pdf -> *
```
share the same set of
```
CPDFConversion.start_pdf_to_*
```
interfaces; only the input file type differs.

脚本支持PDF和图片作为输入源。SDK的
```
start_pdf_to_*
```
接口原生支持图片文件输入，无需预处理。
默认情况下，脚本会根据文件扩展名自动检测输入类型：
- ```
.pdf
```
  →
```
pdf
```
- ```
.png/.jpg/.jpeg/.bmp/.tif/.tiff/.gif/.webp/.tga
```
  →
```
image
```

您也可以显式指定源类型：

bash

python "${CLAUDE_SKILL_DIR}/scripts/pdf-to-word-docx.py" word input.png output.docx --source-type image

```
image -> *
```
和
```
pdf -> *
```
使用相同的
```
CPDFConversion.start_pdf_to_*
```
接口集；仅输入文件类型不同。

Smart Defaults

智能默认值

The script automatically adjusts certain parameters based on the input source and output format to reduce manual configuration:

Trigger	Automatic Behavior	User-Overridable	Description
Input source is an image (auto-detected or explicit `--source-type image` )	Automatically enables `--enable-ocr`	No ( `--enable-ocr` uses `store_true` ; there is no `--no-enable-ocr` )	Text in images must be extracted via OCR; without OCR, output will contain only images and no text
Output format is HTML ( `format = html` )	Automatically sets `--page-layout-mode` to `box` (box layout)	Yes — passing `--page-layout-mode flow` explicitly overrides this	Box layout better preserves the original formatting in HTML; specify `flow` explicitly if flow layout is needed

When triggered, the script prints a notice to

stderr

, for example:

text

Auto-enabled OCR for image input.
Auto-set page layout mode to BOX for HTML output.

脚本会根据输入源和输出格式自动调整某些参数，减少手动配置：

触发条件	自动行为	用户可覆盖	描述
输入源为图片（自动检测或显式指定 `--source-type image` ）	自动启用 `--enable-ocr`	否（ `--enable-ocr` 使用 `store_true` ；没有 `--no-enable-ocr` 选项）	图片中的文本必须通过OCR提取；若不启用OCR，输出将仅包含图片，无文本内容
输出格式为HTML（ `format = html` ）	自动将 `--page-layout-mode` 设置为 `box` （框式布局）	是——显式传递 `--page-layout-mode flow` 会覆盖此设置	框式布局能更好地保留HTML中的原始格式；若需要流式布局，需显式指定 `flow`

触发时，脚本会向

stderr

打印提示信息，例如：

text

Auto-enabled OCR for image input.
Auto-set page layout mode to BOX for HTML output.

All Parameters

所有参数

Positional Parameters

位置参数

Parameter	Description
`format`	Target format: `word` / `excel` / `ppt` / `html` / `rtf` / `image` / `txt` / `json` / `markdown` / `csv`
`input_pdf`	Input file path (PDF or image)
`output_path`	Output file path

参数	描述
`format`	目标格式： `word` / `excel` / `ppt` / `html` / `rtf` / `image` / `txt` / `json` / `markdown` / `csv`
`input_pdf`	输入文件路径（PDF或图片）
`output_path`	输出文件路径

General Parameters

通用参数

Parameter	Type	Default	Description
`--source-type`	Option	`auto`	Input source type: `auto` / `pdf` / `image`
`--password`	String	`""`	PDF open password
`--page-ranges`	String	None	Page range, e.g. `1-3,5`
`--font-name`	String	`""`	Output font name

参数	类型	默认值	描述
`--source-type`	选项	`auto`	输入源类型： `auto` / `pdf` / `image`
`--password`	字符串	`""`	PDF打开密码
`--page-ranges`	字符串	None	页面范围，例如 `1-3,5`
`--font-name`	字符串	`""`	输出字体名称

Layout Parameters

布局参数

Parameter	Type	Default	Description
`--enable-ai-layout`	Boolean	True	AI layout analysis (disable with `--no-enable-ai-layout` )
`--page-layout-mode`	Option	SDK default `flow` (auto-switched to `box` for HTML output)	Page layout: `box` (box layout) / `flow` (flow layout)

参数	类型	默认值	描述
`--enable-ai-layout`	布尔值	True	AI布局分析（使用 `--no-enable-ai-layout` 禁用）
`--page-layout-mode`	选项	SDK默认值 `flow` （HTML输出时自动切换为 `box` ）	页面布局： `box` （框式布局）/ `flow` （流式布局）

Content Retention Parameters

内容保留参数

Parameter	Type	Default	Description
`--contain-image`	Boolean	True	Retain images (disable with `--no-contain-image` )
`--contain-annotation`	Boolean	True	Retain annotations (disable with `--no-contain-annotation` )
`--contain-page-background-image`	Boolean	True	Retain page background images (disable with `--no-contain-page-background-image` )
`--formula-to-image`	Boolean	False	Convert formulas to image output
`--transparent-text`	Boolean	False	Preserve transparent text

参数	类型	默认值	描述
`--contain-image`	布尔值	True	保留图片（使用 `--no-contain-image` 禁用）
`--contain-annotation`	布尔值	True	保留注释（使用 `--no-contain-annotation` 禁用）
`--contain-page-background-image`	布尔值	True	保留页面背景图片（使用 `--no-contain-page-background-image` 禁用）
`--formula-to-image`	布尔值	False	将公式转换为图片输出
`--transparent-text`	布尔值	False	保留透明文本

Output Control Parameters

输出控制参数

Parameter	Type	Default	Description
`--output-document-per-page`	Boolean	False	Split output into one document per page
`--auto-create-folder`	Boolean	True	Automatically create output directory (disable with `--no-auto-create-folder` )

参数	类型	默认值	描述
`--output-document-per-page`	布尔值	False	将输出按每页拆分单独文档
`--auto-create-folder`	布尔值	True	自动创建输出目录（使用 `--no-auto-create-folder` 禁用）

OCR Parameters

OCR参数

Parameter Type Default Description

Parameter	Type	Default	Description
`--enable-ocr`	Boolean	False (auto-enabled for image input)	Enable OCR
`--ocr-option`	Option	SDK default `all`	OCR scope: `invalid-character` / `scan-page` / `invalid-character-and-scan-page` / `all`
`--ocr-language`	Multi-select	`auto`	OCR language(s); multiple languages can be specified simultaneously. Options: `auto` / `chinese` / `chinese-tra` / `english` / `korean` / `japanese` / `latin` / `devanagari` / `cyrillic` / `arabic` / `tamil` / `telugu` / `kannada` / `thai` / `greek` / `eslav`

--enable-ocr

Boolean

False (auto-enabled for image input)

Enable OCR

--ocr-option

Option

SDK default

all

OCR scope:

invalid-character

scan-page

invalid-character-and-scan-page

all

--ocr-language

Multi-select

auto

OCR language(s); multiple languages can be specified simultaneously. Options:

auto

chinese

chinese-tra

english

korean

japanese

latin

devanagari

cyrillic

arabic

tamil

telugu

kannada

thai

greek

eslav

参数类型默认值描述

参数	类型	默认值	描述
`--enable-ocr`	布尔值	False（图片输入时自动启用）	启用OCR
`--ocr-option`	选项	SDK默认值 `all`	OCR范围： `invalid-character` / `scan-page` / `invalid-character-and-scan-page` / `all`
`--ocr-language`	多选	`auto`	OCR语言；可同时指定多种语言。选项： `auto` / `chinese` / `chinese-tra` / `english` / `korean` / `japanese` / `latin` / `devanagari` / `cyrillic` / `arabic` / `tamil` / `telugu` / `kannada` / `thai` / `greek` / `eslav`

--enable-ocr

布尔值

False（图片输入时自动启用）

启用OCR

--ocr-option

选项

SDK默认值

all

OCR范围：

invalid-character

scan-page

invalid-character-and-scan-page

all

--ocr-language

多选

auto

OCR语言；可同时指定多种语言。选项：

auto

chinese

chinese-tra

english

korean

japanese

latin

devanagari

cyrillic

arabic

tamil

telugu

kannada

thai

greek

eslav

Excel-Specific Parameters

Excel专属参数

Parameter	Type	Default	Description
`--excel-all-content`	Boolean	False	Include all content in Excel output
`--excel-csv-format`	Boolean	False	Output Excel result in CSV format
`--excel-worksheet-option`	Option	SDK default `for-table`	Worksheet split strategy: `for-table` / `for-page` / `for-document`

参数	类型	默认值	描述
`--excel-all-content`	布尔值	False	在Excel输出中包含所有内容
`--excel-csv-format`	布尔值	False	将Excel结果输出为CSV格式
`--excel-worksheet-option`	选项	SDK默认值 `for-table`	工作表拆分策略： `for-table` / `for-page` / `for-document`

JSON-Specific Parameters

JSON专属参数

Parameter	Type	Default	Description
`--json-contain-table`	Boolean	True	Include table data in JSON output (disable with `--no-json-contain-table` )

参数	类型	默认值	描述
`--json-contain-table`	布尔值	True	在JSON输出中包含表格数据（使用 `--no-json-contain-table` 禁用）

TXT-Specific Parameters

TXT专属参数

Parameter	Type	Default	Description
`--txt-table-format`	Boolean	True	Enable table formatting in TXT output (disable with `--no-txt-table-format` )

参数	类型	默认值	描述
`--txt-table-format`	布尔值	True	在TXT输出中启用表格格式化（使用 `--no-txt-table-format` 禁用）

HTML-Specific Parameters

HTML专属参数

Parameter	Type	Default	Description
`--html-option`	Option	SDK default `single-page`	HTML output mode: `single-page` / `single-page-with-bookmark` / `multiple-page` / `multiple-page-with-bookmark`

参数	类型	默认值	描述
`--html-option`	选项	SDK默认值 `single-page`	HTML输出模式： `single-page` / `single-page-with-bookmark` / `multiple-page` / `multiple-page-with-bookmark`

Image-Specific Parameters

图片专属参数

Parameter	Type	Default	Description
`--image-type`	Option	SDK default `jpg`	Image output format: `jpg` / `jpeg` / `jpeg2000` / `png` / `bmp` / `tiff` / `tga` / `gif` / `webp`
`--image-color-mode`	Option	SDK default `color`	Image color mode: `color` / `gray` / `binary`
`--image-scaling`	Float	`1.0`	Image scaling factor
`--image-path-enhance`	Boolean	False	Enable image path enhancement

参数	类型	默认值	描述
`--image-type`	选项	SDK默认值 `jpg`	图片输出格式： `jpg` / `jpeg` / `jpeg2000` / `png` / `bmp` / `tiff` / `tga` / `gif` / `webp`
`--image-color-mode`	选项	SDK默认值 `color`	图片颜色模式： `color` / `gray` / `binary`
`--image-scaling`	浮点数	`1.0`	图片缩放比例
`--image-path-enhance`	布尔值	False	启用图片路径增强

Parameter Default Value Rules

参数默认值规则

Parameters that default to True (

--enable-ai-layout

--contain-image

--contain-annotation

--contain-page-background-image

--auto-create-folder

--json-contain-table

--txt-table-format

) use

BooleanOptionalAction

; pass

--no-xxx

to disable.

Parameters that default to False (

--enable-ocr

--formula-to-image

--transparent-text

--output-document-per-page

--excel-all-content

--excel-csv-format

--image-path-enhance

) use

store_true

; passing the flag enables them.

All CLI parameter defaults are fully consistent with the SDK's
ConvertOptions()
defaults — omitting a parameter is equivalent to using the SDK's original default value.

默认值为True的参数（

--enable-ai-layout

--contain-image

--contain-annotation

--contain-page-background-image

--auto-create-folder

--json-contain-table

--txt-table-format

）使用

BooleanOptionalAction

；传递

--no-xxx

即可禁用。

默认值为False的参数（

--enable-ocr

--formula-to-image

--transparent-text

--output-document-per-page

--excel-all-content

--excel-csv-format

--image-path-enhance

）使用

store_true

；传递该标志即可启用。

所有CLI参数默认值与SDK的
ConvertOptions()
默认值完全一致——省略参数等效于使用SDK的原始默认值。

Recommended Command Examples

Trial License and Usage Limits

试用许可证及使用限制

The
```
scripts/license.xml
```
auto-downloaded from the ComPDF server is a Trial License, allowing a maximum of 200 conversions.
The script uses a SHA-256 fingerprint to detect whether the current License is the default trial key; no usage limit applies when using any other License.
After each successful conversion using the trial License, the script prints the current used/remaining count to
```
stderr
```
, for example:
text
```
Trial license: 5/200 conversions used, 195 remaining.
```

When the trial limit is reached (200 conversions), the script refuses to convert and prompts the user to purchase a full License:

text

Error: Trial license usage limit reached (200 conversions). Please purchase a license at: https://www.compdf.com/contact-sales?utm_source=clawhub&utm_medium=skillhub&utm_campaign=pdf_skill_to_word&ref_platform_id=clawhub_skills

When the trial License has expired (SDK authentication fails), the error message also includes a purchase link.
After purchasing a full License, place a custom
```
license.xml
```
containing the new
```
<key>
```
in
```
scripts/
```
(overwriting the auto-downloaded trial file) — no script modifications or counter file cleanup are required.

从ComPDF服务器自动下载的
```
scripts/license.xml
```
是试用许可证，最多允许200次转换。
脚本使用SHA-256指纹检测当前许可证是否为默认试用密钥；使用其他任何许可证时无使用限制。
使用试用许可证完成每次成功转换后，脚本会向
```
stderr
```
打印当前已使用/剩余次数，例如：
text
```
Trial license: 5/200 conversions used, 195 remaining.
```

当试用限制达到（200次转换）时，脚本会拒绝转换并提示用户购买完整许可证：

text

Error: Trial license usage limit reached (200 conversions). Please purchase a license at: https://www.compdf.com/contact-sales?utm_source=clawhub&utm_medium=skillhub&utm_campaign=pdf_skill_to_word&ref_platform_id=clawhub_skills

当试用许可证过期（SDK认证失败）时，错误信息也会包含购买链接。
购买完整许可证后，将包含新
```
<key>
```
的自定义
```
license.xml
```
放置在
```
scripts/
```
目录中（覆盖自动下载的试用文件）——无需修改脚本或清理计数器文件。

Confirmed Facts

已确认事实

```
ComPDFKitConversion
```
has been successfully installed on the local machine.

The installed package provides 10 conversion methods including

CPDFConversion.start_pdf_to_word/start_pdf_to_ppt/start_pdf_to_excel

LibraryManager

provides

initialize

license_verify

release

set_document_ai_model

, and

set_ocr_language

Official documentation confirms support for PDF to Word / Excel / PPT / HTML / RTF / Image / TXT / JSON / Markdown.
The SDK's
```
start_pdf_to_*
```
interfaces natively accept image file input (PNG → Word has been verified successfully).
```
enable_ai_layout
```
defaults to
```
True
```
in the SDK;
```
set_document_ai_model()
```
must be called first to load the model before use, otherwise a 0xC0000005 crash will occur.
```
--ocr-language
```
supports specifying multiple languages simultaneously (e.g.
```
--ocr-language chinese english
```
).

```
ComPDFKitConversion
```
已成功安装在本地机器上。

已安装的包提供10种转换方法，包括

CPDFConversion.start_pdf_to_word/start_pdf_to_ppt/start_pdf_to_excel

。

LibraryManager

提供

initialize

、

license_verify

、

release

、

set_document_ai_model

和

set_ocr_language

方法。

官方文档确认支持PDF转Word/Excel/PPT/HTML/RTF/图片/TXT/JSON/Markdown。
SDK的
```
start_pdf_to_*
```
接口原生支持图片文件输入（PNG转Word已验证成功）。
SDK中
```
enable_ai_layout
```
默认值为
```
True
```
；使用前必须先调用
```
set_document_ai_model()
```
加载模型，否则会发生0xC0000005崩溃。
```
--ocr-language
```
支持同时指定多种语言（例如
```
--ocr-language chinese english
```
）。

Risks / Notes

风险/注意事项

The official requirements page states Python
```
>=3.6
```
, while the demo page states
```
<3.11
```
, but PyPI currently provides a
```
cp314
```
wheel in practice; treat the locally installable wheel as the source of truth, but always verify installation in a new environment first.
If the script cannot download
```
license.xml
```
from the server (network issue) and no manual file exists in
```
scripts/
```
, or the
```
<key>
```
field is empty, the script cannot complete SDK authentication and cannot perform any real conversions.
```
documentai.model
```
is a large file (approximately 525 MB); there will be a noticeable download delay the first time OCR / AI layout is enabled. Because
```
--enable-ai-layout
```
defaults to True, the model download will be triggered on the very first run.

If the runtime environment cannot access

https://download.compdf.com/skills/model/documentai.model

, place

documentai.model

in the

scripts/

directory in advance.

Do not directly apply the initialization patterns from ComPDF SDKs for other languages to the Python package; this Skill is based on the locally verified
```
LibraryManager
```
/
```
CPDFConversion
```
API.

官方要求页面说明Python版本
```
>=3.6
```
，而演示页面说明
```
<3.11
```
，但PyPI实际提供
```
cp314
```
版本的wheel包；以本地可安装的wheel包为准，但在新环境中始终要先验证安装情况。
若脚本无法从服务器下载
```
license.xml
```
（网络问题）且
```
scripts/
```
目录中无手动放置的文件，或
```
<key>
```
字段为空，脚本无法完成SDK认证，无法执行任何实际转换。
```
documentai.model
```
是大文件（约525 MB）；首次启用OCR/AI布局时会有明显的下载延迟。由于
```
--enable-ai-layout
```
默认启用，首次运行时会触发模型下载。

若运行环境无法访问

https://download.compdf.com/skills/model/documentai.model

，请提前将

documentai.model

放置在

scripts/

目录中。

不要将其他语言的ComPDF SDK初始化模式直接应用于Python包；本Skill基于本地验证的
```
LibraryManager
```
/
```
CPDFConversion
```
API开发。

Resource Navigation

资源导航

License file:
```
License.txt
```
Script:
```
scripts/pdf-to-word-docx.py
```

SDK authentication file:

scripts/license.xml

(auto-downloaded from

https://download.compdf.com/skills/license/license.xml

if missing)

SDK authentication source: the
```
<key>
```
field in
```
license.xml
```
SDK resource path:
```
scripts/
```
OCR / AI layout model:
```
scripts/documentai.model
```
(auto-downloaded if missing)

Purchase a full License:

https://www.compdf.com/contact-sales?utm_source=clawhub&utm_medium=skillhub&utm_campaign=pdf_skill_to_word&ref_platform_id=clawhub_skills

Official documentation:

https://www.compdf.com/guides/conversion-sdk/python/overview

https://www.compdf.com/guides/conversion-sdk/python/pdf-to-word

https://www.compdf.com/guides/conversion-sdk/python/pdf-to-excel

https://www.compdf.com/guides/conversion-sdk/python/pdf-to-ppt

https://www.compdf.com/guides/conversion-sdk/python/apply-license

许可证文件：
```
License.txt
```
脚本：
```
scripts/pdf-to-word-docx.py
```

SDK认证文件：

scripts/license.xml

（若缺失则从

https://download.compdf.com/skills/license/license.xml

自动下载）

SDK认证来源：
```
license.xml
```
中的
```
<key>
```
字段
SDK资源路径：
```
scripts/
```
OCR/AI布局模型：
```
scripts/documentai.model
```
（若缺失则自动下载）

购买完整许可证：

https://www.compdf.com/contact-sales?utm_source=clawhub&utm_medium=skillhub&utm_campaign=pdf_skill_to_word&ref_platform_id=clawhub_skills

官方文档：

https://www.compdf.com/guides/conversion-sdk/python/overview

https://www.compdf.com/guides/conversion-sdk/python/pdf-to-word

https://www.compdf.com/guides/conversion-sdk/python/pdf-to-excel

https://www.compdf.com/guides/conversion-sdk/python/pdf-to-ppt

https://www.compdf.com/guides/conversion-sdk/python/apply-license

Acceptance Checklist

验收 checklist

```
python -m pip show ComPDFKitConversion
```
shows the installed package

Running

python "${CLAUDE_SKILL_DIR}/scripts/pdf-to-word-docx.py" --help

or an equivalent local command produces normal output

The script auto-downloads
```
scripts/license.xml
```
if missing, then extracts the license key from the
```
<key>
```
field for authentication
The script uses the
```
scripts/
```
directory as the SDK resource path
The script recognizes all 10 target formats:
```
word
```
/
```
excel
```
/
```
ppt
```
/
```
html
```
/
```
rtf
```
/
```
image
```
/
```
txt
```
/
```
json
```
/
```
markdown
```
/
```
csv
```
The script accepts both PDF and image files (
```
.png
```
/
```
.jpg
```
/
```
.jpeg
```
/
```
.bmp
```
/
```
.tif
```
/
```
.tiff
```
/
```
.gif
```
/
```
.webp
```
/
```
.tga
```
) as input
When
```
--enable-ocr
```
or
```
--enable-ai-layout
```
(enabled by default) is active and
```
documentai.model
```
is missing, the script auto-downloads the model
When
```
license.xml
```
cannot be obtained (download fails and no manual file exists) or authentication fails, a clear error is output rather than a silent failure
The 7 parameters that default to True can be disabled with
```
--no-xxx
```
```
--ocr-language
```
supports specifying multiple languages simultaneously
After a conversion using the trial License, the usage count increments
When the trial License reaches 200 conversions, the script refuses to convert and outputs a purchase link
When using a non-trial License, no usage limit applies
For image input, even if
```
--enable-ocr
```
is not passed, the script automatically enables OCR and prints a notice to
```
stderr
```
For HTML output, even if
```
--page-layout-mode
```
is not passed, the script automatically uses
```
box
```
(box layout) and prints a notice to
```
stderr
```
For HTML output, explicitly passing
```
--page-layout-mode flow
```
overrides the automatic box layout behavior

```
python -m pip show ComPDFKitConversion
```
显示已安装的包

运行

python "${CLAUDE_SKILL_DIR}/scripts/pdf-to-word-docx.py" --help

或等效本地命令能正常输出

若
```
scripts/license.xml
```
缺失，脚本会自动下载，然后从
```
<key>
```
字段提取许可证密钥进行认证
脚本将
```
scripts/
```
目录用作SDK资源路径
脚本识别所有10种目标格式：
```
word
```
/
```
excel
```
/
```
ppt
```
/
```
html
```
/
```
rtf
```
/
```
image
```
/
```
txt
```
/
```
json
```
/
```
markdown
```
/
```
csv
```
脚本接受PDF和图片文件（
```
.png
```
/
```
.jpg
```
/
```
.jpeg
```
/
```
.bmp
```
/
```
.tif
```
/
```
.tiff
```
/
```
.gif
```
/
```
.webp
```
/
```
.tga
```
）作为输入
当
```
--enable-ocr
```
或
```
--enable-ai-layout
```
（默认启用）激活且
```
documentai.model
```
缺失时，脚本自动下载模型
若无法获取
```
license.xml
```
（下载失败且无手动文件）或认证失败，输出清晰错误而非静默失败
7个默认值为True的参数可通过
```
--no-xxx
```
禁用
```
--ocr-language
```
支持同时指定多种语言
使用试用许可证完成转换后，使用次数递增
当试用许可证达到200次转换时，脚本拒绝转换并输出购买链接
使用非试用许可证时无使用限制
对于图片输入，即使未传递
```
--enable-ocr
```
，脚本也会自动启用OCR并向
```
stderr
```
打印提示
对于HTML输出，即使未传递
```
--page-layout-mode
```
，脚本也会自动使用
```
box
```
（框式布局）并向
```
stderr
```
打印提示
对于HTML输出，显式传递
```
--page-layout-mode flow
```
会覆盖自动框式布局行为

Distribution Notes

分发说明

This Skill does not depend on any machine-specific absolute paths.

When distributing to other users, the following directory structure is sufficient:

text

pdf-to-word-docx/
├── SKILL.md
├── License.txt
└── scripts/
    └── pdf-to-word-docx.py

Users place this directory under their own skills root directory and the Skill is ready to use.
```
license.xml
```
is auto-downloaded at runtime; no need to include it in the distribution package.

本Skill不依赖任何机器特定的绝对路径。

分发给其他用户时，以下目录结构即可：

text

pdf-to-word-docx/
├── SKILL.md
├── License.txt
└── scripts/
    └── pdf-to-word-docx.py

用户将此目录放置在自己的技能根目录下即可使用。
```
license.xml
```
会在运行时自动下载；无需包含在分发包中。

Common Pitfalls

常见陷阱

```
scripts/license.xml
```
is missing and cannot be auto-downloaded (network unavailable or server error): the script will error out before authentication. If you are in an offline environment, place
```
license.xml
```
manually in the
```
scripts/
```
directory.
```
scripts/license.xml
```
is missing the
```
<key>
```
field or its value is empty: the script will error out before authentication.
SDK resource files required by the SDK are absent from the
```
scripts/
```
directory: conversion may fail after
```
LibraryManager.initialize()
```
.
A password-protected PDF is provided without
```
--password
```
: this will trigger
```
PDF_PASSWORD_ERROR
```
.
OCR / AI layout is enabled but
```
documentai.model
```
is not present locally and the network is unavailable: the model download will fail; place the file in the
```
scripts/
```
directory manually in advance.
When the Excel output strategy is unclear, prefer passing
```
--excel-worksheet-option
```
explicitly to avoid unexpected result structures.
When converting images to other formats, the script already enables OCR automatically; if the output still contains no text, check whether
```
documentai.model
```
is complete and whether the OCR language matches.

Once the trial License usage limit is exhausted, a full License must be purchased to continue; purchase link:

https://www.compdf.com/contact-sales?utm_source=clawhub&utm_medium=skillhub&utm_campaign=pdf_skill_to_word&ref_platform_id=clawhub_skills

```
scripts/license.xml
```
缺失且无法自动下载（网络不可用或服务器错误）：脚本会在认证前报错。若处于离线环境，请手动将
```
license.xml
```
放置在
```
scripts/
```
目录中。
```
scripts/license.xml
```
缺少
```
<key>
```
字段或值为空：脚本会在认证前报错。
SDK所需的SDK资源文件在
```
scripts/
```
目录中缺失：
```
LibraryManager.initialize()
```
后转换可能失败。
提供了受密码保护的PDF但未传递
```
--password
```
：会触发
```
PDF_PASSWORD_ERROR
```
。
启用了OCR/AI布局但本地无
```
documentai.model
```
且网络不可用：模型下载会失败；请提前手动将文件放置在
```
scripts/
```
目录中。
若对Excel输出策略不明确，优先显式传递
```
--excel-worksheet-option
```
以避免意外的结果结构。
将图片转换为其他格式时，脚本已自动启用OCR；若输出仍无文本，请检查
```
documentai.model
```
是否完整以及OCR语言是否匹配。

试用许可证使用限制耗尽后，必须购买完整许可证才能继续；购买链接：

https://www.compdf.com/contact-sales?utm_source=clawhub&utm_medium=skillhub&utm_campaign=pdf_skill_to_word&ref_platform_id=clawhub_skills

。

Copyright

版权声明

This Skill is built on top of the ComPDFKit Conversion SDK.

© 2014-2026 PDF Technologies, Inc., a KDAN Company. All Rights Reserved.

SDK Name: ComPDFKitConversion
SDK Author: PDF Technologies, Inc.
License Type: Commercial License (Commercial / Proprietary) — non-exclusive, non-transferable, non-sublicensable, revocable
Official Website: https://www.compdf.com/?utm_source=clawhub&utm_medium=skillhub&utm_campaign=compdf_pdf_skill_to_word&ref_platform_id=clawhub_skills
Contact: support@compdf.com
Terms of Service: https://www.compdf.com/terms-of-service/?utm_source=clawhub&utm_medium=skillhub&utm_campaign=compdf_pdf_skill_to_word&ref_platform_id=clawhub_skills
Privacy Policy: https://www.compdf.com/privacy-policy/?utm_source=clawhub&utm_medium=skillhub&utm_campaign=compdf_pdf_skill_to_word&ref_platform_id=clawhub_skills

Important: Under the ComPDFKit Terms of Service, distributing the documentation, sample code, or source code of the ComPDFKit Conversion SDK to third parties is prohibited. Please ensure you have obtained a valid ComPDFKit License before using this Skill.

本Skill基于ComPDFKit Conversion SDK构建。

© 2014-2026 PDF Technologies, Inc., a KDAN Company. All Rights Reserved.

SDK名称：ComPDFKitConversion
SDK作者：PDF Technologies, Inc.
许可证类型：商业许可证（Commercial / Proprietary）——非独占、不可转让、不可再许可、可撤销
官方网站：https://www.compdf.com/?utm_source=clawhub&utm_medium=skillhub&utm_campaign=compdf_pdf_skill_to_word&ref_platform_id=clawhub_skills
联系方式：support@compdf.com
服务条款：https://www.compdf.com/terms-of-service/?utm_source=clawhub&utm_medium=skillhub&utm_campaign=compdf_pdf_skill_to_word&ref_platform_id=clawhub_skills
隐私政策：https://www.compdf.com/privacy-policy/?utm_source=clawhub&utm_medium=skillhub&utm_campaign=compdf_pdf_skill_to_word&ref_platform_id=clawhub_skills

重要提示：根据ComPDFKit服务条款，禁止向第三方分发ComPDFKit Conversion SDK的文档、示例代码或源代码。使用本Skill前请确保已获取有效的ComPDFKit许可证。

pdf-to-word-docx

Original

Translation

PDF to Word Converter

PDF转Word转换器

Purpose

用途

Agent Skills Standard Compatibility

Agent Skills标准兼容性

Input / Output

输入/输出

Prerequisites

前置条件

Workflow

工作流

documentai.model Download Optimization

documentai.model下载优化

Invoking Directly as a Skill

直接作为Skill调用

Supported Output Formats

支持的输出格式

Input Source Types

输入源类型

Smart Defaults

智能默认值

All Parameters

所有参数

Positional Parameters

位置参数

General Parameters

通用参数

Layout Parameters

布局参数

Content Retention Parameters

内容保留参数

Output Control Parameters

输出控制参数

OCR Parameters

OCR参数

Excel-Specific Parameters

Excel专属参数

JSON-Specific Parameters

JSON专属参数

TXT-Specific Parameters

TXT专属参数

HTML-Specific Parameters

HTML专属参数

Image-Specific Parameters

图片专属参数

Parameter Default Value Rules

参数默认值规则

Recommended Command Examples

推荐命令示例

PDF to Word (default parameters, AI layout analysis enabled)

PDF转Word（默认参数，启用AI布局分析）

PDF to Word, box layout, no images, no AI layout analysis

PDF转Word，框式布局，不含图片，禁用AI布局分析

PDF to Word, retain annotations and background images, one document per page

PDF转Word，保留注释和背景图片，按每页拆分文档

PDF to Excel, include all content and split worksheets by page

PDF转Excel，包含所有内容并按页面拆分工作表

PDF to TXT, with table formatting enabled

PDF转TXT，启用表格格式化

PDF to HTML, multi-page with bookmarks mode

PDF转HTML，带书签的多页模式

PDF to Image, PNG format, grayscale, 2x scaling

PDF转图片，PNG格式，灰度，2倍缩放

Image to Word (OCR auto-enabled, specify Chinese language)

图片转Word（自动启用OCR，指定中文语言）

PDF with OCR enabled (multiple languages)

启用OCR的PDF转换（多语言）

Trial License and Usage Limits

试用许可证及使用限制

Confirmed Facts

已确认事实

Risks / Notes

风险/注意事项

Resource Navigation

资源导航

Acceptance Checklist