Final product of the project.
- Download the sample file.
- Run all commands from Commands_to_run.txt
- Import all the PDFs in Documents folder inside Sample folder
- Run main.py
- All informations will be appended in Book-v2.csv
This script use poppler-utils
to convert a PDF into an image and then uses tesseract-ocr
and arabic tesdata
to extract the text. We run the ocr 2 times as the arabic ocr can't accurately extract numeric values. Finally we use python`s csv library to append the csv and also write name of extracted pdfs into a text file for future reference to reduce redundancy.
sudo apt install tesseract-ocr sudo apt install tesseract-ocr-ara sudo apt install poppler-utils
pip install googletrans==4.0.0-rc1