mineru-document-extractor

【文档与办公】Convert PDFs, scanned documents, images, Word, PowerPoint, Excel, and web pages into clean Markdown, HTML, LaTeX, or DOCX using the MinerU CLI (mineru-open-api). Supports two modes: flash-extract (token-free, fast, Markdown only, 10 MB/20-page limit) and precision extract (token required, VLM layout analysis, multiple formats, batch mode). Use it to …

独立 GitHub 快照 · 自动分类 · 以原作者文档为准