Extract the text out of an ePub

TextExtract.py

# pip install ebooklib beautifulsoup4 python-dotenv
import ebooklib
from dotenv import load_dotenv
import os
from ebooklib import epub
from bs4 import BeautifulSoup


def extract_text_from_epub(file_path):
    book = epub.read_epub(file_path)
    text_content = []

    for item in book.get_items():
        if item.get_type() == ebooklib.ITEM_DOCUMENT:
            soup = BeautifulSoup(item.content, 'html.parser')
            text_content.append(soup.get_text())

    return "\n\n".join(text_content)


load_dotenv()
epub_path = os.getenv("EPUB_PATH")
# Specify the path to your EPUB file
text = extract_text_from_epub(epub_path)
print(text)
# TODO decide where text should be saved or whatever