360 Secure SkillHub
360 安全技能中心

PDF to Markdown

调用 pdfplumber 在本地提取 PDF 文本,清理格式并识别标题与列表,输出 Markdown 文件;声明无网络请求与遥测。文档引用 scripts/pdf2md.py,但文件列表中脚本位于根目录 pdf2md.py,引用路径不一致。

lifei68801
lifei68801
热度 61.85
最近更新 2026-05-11 17:32:16
分类:效率依赖:代码执行 / 读写文件应用场景: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 pdf2md-clean
Metadata
name
pdf2md-clean
version
1.0.0
description
Convert PDF to Markdown using local processing. No external API calls.
license
MIT-0
author
lifei68801
tags
["pdf","markdown","conversion","local"]

PDF to Markdown Converter

Convert PDF documents to clean Markdown format using local processing only.

Quick Start

python scripts/pdf2md.py input.pdf output.md

Features

  • Local Processing: No API calls, no network requests
  • Smart Formatting: Auto-detect headers and lists
  • Clean Output: Properly formatted Markdown

Requirements

pip install pdfplumber

Usage

# Basic usage
python scripts/pdf2md.py document.pdf

# Specify output file
python scripts/pdf2md.py document.pdf output.md

How It Works

  1. Extracts text from PDF using pdfplumber
  2. Cleans up formatting issues
  3. Detects headers and lists
  4. Outputs clean Markdown

Metadata

metadata:
  openclaw:
    requires:
      bins: ["python3"]
      pypi: ["pdfplumber"]
    permissions:
      - "file:read"
      - "file:write"
    behavior:
      network: none
      telemetry: none
      description: "Converts PDF to Markdown using local pdfplumber. No network requests."