OCR_basic

"""
Disclaimer: I do not remember where I picked this info, if it was a tutorial or just some documentation

pip install PyPDF2 pytesseract

pip install ghostscript

pip install poppler - no es necesairo
pip install  tabula-py


"""

import PyPDF2
import pytesseract
from PIL import Image
from pdf2image import convert_from_path

mypath= "C:/Users/User/OneDrive/Desktop/Items_from_Psychometric_Tests_as_Training_Data_for.pdf"
pdf_file = open(mypath, 'rb')
pdf_reader = PyPDF2.PdfReader(pdf_file)

text_content = []
for page in pdf_reader.pages:
    text_content.append(page.extract_text())

text_content= []
for page in pdf_reader.pages:
    text_content = ' '.join(page.extract_text() for page in pdf_reader.pages)

pdf_file.close()


with open('prueba-readpdf.txt', 'w', encoding='utf-8') as txt_file:
    for content in text_content:
        txt_file.write(content)