mineru-pdf-converter

To convert large PDFs to Markdown, this tool automatically splits documents exceeding 600 pages into smaller chunks, processes them via the MinerU cloud API, and merges the results into a single Markdown file.

Yes, you can convert PDFs to LaTeX, DOCX, and HTML in addition to Markdown. The conversion uses the MinerU API to preserve formulas, tables, and layout across these output formats.

Yes, you need a MinerU API token to convert local PDF files. The batch upload workflow requires token-based authentication to process your documents through the MinerU cloud API.

To extract specific page ranges into Markdown, use the URL-based task flow which supports optional page range parameters, allowing you to convert only the sections you need without processing the entire document.

Converting PDFs with tables and formulas to Markdown works by sending files to the MinerU API, which parses the document structure and preserves complex elements like mathematical formulas and table layouts in the output.

Large PDF conversions fail due to processing limits, but this tool handles it by automatically splitting documents over 600 pages into chunks, converting each separately, and merging the Markdown output.