romaresccoa

from PyPDF2 import PdfFileReader


class Extractor:
    def __init__(self, file_name: str) -> None:
        self.pdf_reader = PdfFileReader(file_name)
        self.sections = self._extract_sections(self.pdf_reader.outlines)
        self.pages_range = self._find_pages_range()
        self.raw_text = self._extract_raw_text()  # useful for creating / testing new functionality