pdf-to-markdown
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
ChinesePDF to Markdown Converter
PDF转Markdown转换器
Convert PDF files to clean, well-structured Markdown. Tables become markdown tables. Images and graphics are described as text (no image files generated).
将PDF文件转换为结构清晰、格式整洁的Markdown。表格会转换为Markdown表格格式。图片和图形会以文本形式描述（不生成图片文件）。
Quick Start
快速开始
bash
uv run skills/pdf-to-markdown/scripts/convert_to_markdown.py input.pdfOutput:
~/Desktop/{filename}.mdbash
uv run skills/pdf-to-markdown/scripts/convert_to_markdown.py input.pdf输出文件：
~/Desktop/{filename}.mdOptions
选项
| Flag | Description |
|---|---|
| Skip LLM processing (faster, images become |
| Force OCR on all pages (for scanned PDFs) |
| Process specific pages only |
| 参数 | 说明 |
|---|---|
| 跳过LLM处理（速度更快，图片会变为 |
| 强制对所有页面进行OCR识别（适用于扫描版PDF） |
| 仅处理指定页面 |
Common Use Cases
常见使用场景
Convert a PDF with default settings
使用默认设置转换PDF
bash
uv run skills/pdf-to-markdown/scripts/convert_to_markdown.py ~/Documents/report.pdfbash
uv run skills/pdf-to-markdown/scripts/convert_to_markdown.py ~/Documents/report.pdfSpecify output location
指定输出位置
bash
uv run skills/pdf-to-markdown/scripts/convert_to_markdown.py report.pdf ~/Documents/report.mdbash
uv run skills/pdf-to-markdown/scripts/convert_to_markdown.py report.pdf ~/Documents/report.mdFast conversion (no image descriptions)
快速转换（不生成图片描述）
bash
uv run skills/pdf-to-markdown/scripts/convert_to_markdown.py --no-llm report.pdfbash
uv run skills/pdf-to-markdown/scripts/convert_to_markdown.py --no-llm report.pdfScanned PDF (force OCR)
扫描版PDF（强制OCR识别）
bash
uv run skills/pdf-to-markdown/scripts/convert_to_markdown.py --force-ocr scanned_doc.pdfbash
uv run skills/pdf-to-markdown/scripts/convert_to_markdown.py --force-ocr scanned_doc.pdfExtract specific pages
提取指定页面
bash
uv run skills/pdf-to-markdown/scripts/convert_to_markdown.py --page-range "0-5" large_report.pdfbash
uv run skills/pdf-to-markdown/scripts/convert_to_markdown.py --page-range "0-5" large_report.pdfOutput
输出说明
- Pure Markdown text (no embedded images)
- Tables converted to Markdown table format
- Images/charts described as text using LLM
- Clean formatting suitable for AI processing
- 纯Markdown文本（无嵌入图片）
- 表格转换为Markdown表格格式
- 图片/图表通过LLM转换为文本描述
- 格式整洁，适合AI工具处理
Requirements
依赖要求
- GEMINI_API_KEY: Required for LLM image descriptions (loaded from 1Password)
- Use flag if you don't have Gemini API access
--no-llm
- GEMINI_API_KEY：生成图片描述需要此密钥（从1Password加载）
- 若没有Gemini API权限，可使用参数
--no-llm
First Run Note
首次运行说明
The first run downloads ML models (~1-2GB) which are cached at . Subsequent runs are faster.
~/.cache/marker/首次运行时会下载机器学习模型（约1-2GB），缓存路径为。后续运行速度会更快。
~/.cache/marker/