pdftotext.py

import fitz

def texts_from_pdf(input_pdf_data):
    pdf_document = fitz.open('pdf',input_pdf_data)

    for page_num in range(pdf_document.page_count):
        page = pdf_document[page_num]
        text_instances = page.get_text()
        
    print(text_instances)
    return text_instances