使用MinerU 分析 PowerPoint (.pptx) 演示文稿的结构和内容,返回包含幻灯片内容、标题和布局信息的结构化 Markdown 格式。
Analyze and extract structured content from PowerPoint (.pptx) presentations using MinerU. Returns Markdown with slide content and layout preserved.
bash
npm install -g mineru-open-api
# or via Go (macOS/Linux):
go install github.com/opendatalab/MinerU-Ecosystem/cli/mineru-open-api@latest
bash
# Quick analysis, no token required
mineru-open-api flash-extract slides.pptx
# Save to directory
mineru-open-api flash-extract slides.pptx -o ./out/
# Full analysis with token (tables, formulas, multi-format)
mineru-open-api extract slides.pptx -o ./out/
# With language hint
mineru-open-api flash-extract slides.pptx --language en
No token needed for flash-extract. Token required for extract:
bash
mineru-open-api auth # Interactive token setup
export MINERU_TOKEN="your-token" # Or via environment variable
Create token at: https://mineru.net/apiManage/token
flash-extract: quick, no token, max 10 MB / 20 pages, Markdown output onlyextract: token required, full features (tables, formulas, multi-format output)--language (default: ch, use en for English).ppt (legacy format), use ppt-extract skill instead-o <dir> to save to a file or directory