PDF Processor for VS Code

Open PDF files directly in VS Code. Extract tables, text, and images. Compare two PDFs side by side. Edit the extracted HTML in a built-in Monaco editor. Everything runs locally with no file upload.

PDF Processor demo

Install and use

Install this extension.
Right-click any .pdf file in Explorer.
Pick "Open with PDF Processor."

The PDF opens in a VS Code custom editor with five views: PDF canvas, Doc (rendered HTML), Visual Diff (PDF vs extracted output), Editor (Monaco code editor on the HTML output), and Compare Diff (load a second PDF to diff).

Commands

Command	What it does
`Ginexys: Open with PDF Processor`	Open a PDF in the custom editor
`Ginexys: Extract PDF Text (Analyze)`	Open the Analyze tab on a PDF
`Ginexys: View PDF`	Open in PDF canvas view
`Ginexys: Edit Extracted PDF Content`	Open the Monaco code editor on the extracted output

Each command also appears in the Explorer context menu for .pdf files.

File types

.pdf

Key features

Browser-native extraction. High-speed PDF parsing using PDF.js and local Web Workers. Native PDF text fidelity preserved with no rasterization.
Structured output. Layout-aware conversion to HTML with CSS preservation. Tables, headings, lists, images, columns, zones.
Visual diff. Side-by-side verification of the original PDF against the extracted output. IntersectionObserver-driven page sync.
Compare Diff. Load two PDFs and diff them with split or unified view, word-level and character-level highlighting.
Rich text editor. Built-in Monaco editor specialized for document refinement. Edit the extracted HTML and watch the rendered Doc view update live.
Selection Mode. Treat the rendered HTML like CAD. Drag zones and regions, group them into columns, apply Bootstrap-style layouts.
Export. Markdown, HTML, DOC, XML, JSON, plus Notion and Google Sheets (Pro).
Zero data upload. All processing happens locally. No PDF ever leaves your machine.

Pro features

Some features require a Ginexys Pro account:

Advance Extraction. AI-powered layout analysis via Docling and OpenRouter. Currently a waitlist feature.
Analyze tab. Per-region confidence scores, zone flag inspector, tolerance controls, and per-page re-extraction.
Export to Notion and Google Sheets. Direct integration with both platforms.
Visual Diff report export. Full PDF diff report as a downloadable file.

Free extraction runs as normal. Pro features are clearly marked with a gold PRO badge.

Requires

Ginexys Core Extension is a dependency. VS Code installs it automatically.

Part of the Ginexys pipeline

PDF Processor is the Extract step:

Extract  (PDF/image to structured data)   PDF Processor  (this extension)
   v
Transform  (reshape, edit, clean)         TAFNE
   v
Engineer   (schematic / topology editor)  Schema Editor

Get the whole pipeline: Ginexys Developer Tools.

Privacy

PDFs never leave your machine. Extraction runs entirely in a local Web Worker. The extension contains no telemetry. Pro features that route through Ginexys backend (Docling, OpenRouter) only run when you explicitly enable Advance Extraction on a given file.

License

MIT. See LICENSE.

Source and issues

https://github.com/carnworkstudios/doc-extractor

Web version

https://ginexys.com/tools/pdf-processor/