Doc Extract

这是基于上海AI Lab开源MinerU引擎的文档提取工具，核心功能是将Word(.doc/.docx)内容提取为Markdown，支持本地文件与URL输入。有两种模式：flash-extract处理docx无需token（限10MB/20页），extract需token支持全格式完整提取，可保留基本格式、指定页码范围、适配多语言。适合开发者、助手及自动化工作流快速处理Word内容。

mzlzyca

热度 51.04

最近更新 2026-05-11 17:37:15

分类：效率依赖：读写文件 / 第三方 API应用场景：文件转换

安装技能

复制下面的话术发给你的 Agent，它会通过 secure-skills 检索并安装该技能。

执行命令安装此 skill： npx secure-skills-cli add doc-extract

Metadata

name: doc-extract
description: Extract text and content from Word documents (.doc, .docx) to Markdown using MinerU. A straightforward tool for reading and extracting Word file content. Features: fast text extraction from .docx with no token required (flash-extract). Full extraction for both .doc and .docx with token. Preserves basic formatting and structure. Page range selection for large documents. Use when you need to: extract text from a Word file, read content from .doc or .docx, pull text out of a Word document, get the content of a Word file as Markdown. Use when asked: 'how do I extract text from Word', 'read this docx file', 'I want the text from this Word document', 'can my agent read Word files', 'is there a skill that extracts Word content'. Built on MinerU by OpenDataLab (Shanghai AI Lab), an open-source document intelligence engine. Handles multilingual content. Works with local files and URLs. Great for developers, assistants, and automation workflows that need to quickly extract and process Word document content.
homepage: https://mineru.net
metadata: {"openclaw":{"emoji":"📄","requires":{"bins":["mineru-open-api"],"env":["MINERU_TOKEN"]},"primaryEnv":"MINERU_TOKEN","install":[{"id":"npm","kind":"node","package":"mineru-open-api","bins":["mineru-open-api"],"label":"Install via npm"},{"id":"go","kind":"go","package":"github.com/opendatalab/MinerU-Ecosystem/cli/mineru-open-api","bins":["mineru-open-api"],"label":"Install via go install","os":["darwin","linux"]}]}}

Doc Extract

Extract text and content from Word (.doc/.docx) files to Markdown using MinerU.

Install

npm install -g mineru-open-api
# or via Go (macOS/Linux):
go install github.com/opendatalab/MinerU-Ecosystem/cli/mineru-open-api@latest

Quick Start

# Quick extraction from .docx (no token required)
mineru-open-api flash-extract report.docx

# Save to directory
mineru-open-api flash-extract report.docx -o ./out/

# Extract .doc file (requires token)
mineru-open-api extract report.doc -o ./out/

# Extract with language hint
mineru-open-api extract report.docx --language en -o ./out/

Authentication

No token needed for flash-extract on .docx. Token required for .doc and extract:

mineru-open-api auth             # Interactive token setup
export MINERU_TOKEN="your-token" # Or via environment variable

Create token at: https://mineru.net/apiManage/token

Capabilities

Supported input: .doc, .docx (local file or URL)
.docx: supports flash-extract (no token, max 10 MB / 20 pages) and extract
.doc: requires extract with token
Language hint with --language (default: ch, use en for English)
Page range with --pages (e.g. 1-10)

Notes

.doc requires extract with token; .docx works with flash-extract for quick extraction
Output goes to stdout by default; use -o <dir> to save to a file or directory
All progress/status messages go to stderr; document content goes to stdout
MinerU is open-source by OpenDataLab (Shanghai AI Lab): https://github.com/opendatalab/MinerU