from .Document import Document

class TextDocument(Document):
    def extract_content(self):
        with open(self.path, "r", encoding="utf-8") as f:
            text = f.read()
        text = self.clean_text(text)
        text = self.remove_repeated_lines(text)
        # return self.fix_text(text)
        images = []
        return text, images