mineru-pdf

To parse a PDF into Markdown locally, use this Skill to extract text, tables, and images on your machine, preserving document structure without uploading data. It outputs a well-formatted Markdown file.

Yes, you can extract tables from a scanned PDF into JSON. The Skill uses OCR to process scanned documents locally, extracting structured tabular data and outputting it as a JSON file for analysis.

Yes, this PDF parsing approach preserves document headings and lists. It uses the magic-pdf library to maintain the original document hierarchy, ensuring structured Markdown or JSON output that reflects the source layout.

The best way to convert a research paper PDF for easier reading is using this Skill. It transforms the document into structured Markdown locally, preserving headings and extracting images while ensuring data privacy.

No, you do not need an internet connection to extract data from PDFs into JSON. The Skill operates entirely on your local machine, ensuring data privacy by processing both text-based and scanned PDFs offline.

Limitations when parsing PDFs locally with magic-pdf depend on document complexity. While it handles text, tables, images, and OCR for scanned files, heavily corrupted or non-standard PDF structures may not parse correctly into Markdown or JSON.