src/read_file.py

import PyPDF2
from clean_text import *
import requests

def read_pdf(file_pdf):
  try:
    pdf_text = ''
    pdf_file = open(file_pdf, 'rb')
    pdf_reader = PyPDF2.PdfReader(pdf_file)

    for page_num in range(len(pdf_reader.pages)):
        page = pdf_reader.pages[page_num]
        text = clean_text(page.extract_text())

        pdf_text += text

    pdf_file.close()
    return pdf_text.strip()

  except requests.exceptions.RequestException as e:
    print("Error:", e)