OCR It Chrome Extension Uses Tesseract for Text Extraction from PDFs

OCR It is a Chrome extension that utilizes the Tesseract OCR engine for text extraction from un-copyable documents. Users can start or stop the automatic run with the hotkey ⌥⇧A, capture a specific region using ⌥⇧S, and redraw the region with ⌥⇧R. The extension can process up to 300 pages in a single run and supports English, Portuguese, and Spanish by default, with the capability to add approximately 100 additional languages from Tesseract. Each processed page is displayed with a thumbnail of the cropped content, allowing for easy review. Notably, OCR runs locally with a bundled Tesseract build, ensuring user data privacy. However, the auto-advance feature does not function within the PDF viewer, which may affect user experience. This tool provides a direct method for practitioners to extract text for summarization with models like Claude and ChatGPT, enhancing their ability to work with non-editable documents. More details are available on Hacker News (AI filtered).