app.py

import PyPDF2

def extract_text_from_pdf(pdf_path):
    text = []
    with open(pdf_path, 'rb') as file:
        pdf_reader = PyPDF2.PdfReader(file)
        for page in pdf_reader.pages:
            text.append(page.extract_text())
    return text

# Utilisation de la fonction
pdf_path = 'data/07-VF2_UDM_Oneframe_A4-2023.pdf'
pdf_text = extract_text_from_pdf(pdf_path)
for page_num, page_text in enumerate(pdf_text, start=1):
    print(f"Page {page_num}:\n{page_text}\n{'='*100}\n")