If you clarify what kind of "feature" you need, I'll give you a concrete solution. Options include: import ebooklib from ebooklib import epub from bs4 import BeautifulSoup def extract_epub_text(epub_path): book = epub.read_epub(epub_path) text = [] for item in book.get_items(): if item.get_type() == ebooklib.ITEM_DOCUMENT: soup = BeautifulSoup(item.get_content(), 'html.parser') text.append(soup.get_text()) return "\n".join(text) Use it content = extract_epub_text("Un templo encantador - Heather Del Rey.epub")