Extract tables from scanned image PDFs using Optical Character Recognition.
This project aims to extract tables from scanned image PDFs using Optical Character Recognition.
sh sudo apt-get install tesseract-ocr
sh sudo apt-get install imagemagick
sh sudo apt-get install poppler-utils
sh sudo pip install -r requirements.txt
Clear the pdf/ folder and copy all your pdf files to be scanned in it.
Run the OCR:
sh python3 shellocr.py
The scanned text files shall be available in the txt/ folder once the process completes.
If the above doesn't work for you, try the alternate method.
Save your file as input.pdf in the root directory.
sh python3 pdf_miner.py