INNER CODE UNIT · Python

epub_to_text

cognitivetech/ollama-ebook-summary · book2text.py:94

def epub_to_text(epub_path):
    book = epub.read_epub(epub_path)
    text_content = []
    for item in book.get_items():
        if item.get_type() == ebooklib.ITEM_DOCUMENT:
            # Parse the HTML content using BeautifulSoup
            soup = BeautifulSoup(item.get_content(), 'html.parser')
            # Extract just the text, removing HTML tags
            chapter_text = soup.get_text(separator=' ', strip=True)
            text_content.append(chapter_text)
    return '\n'.join(text_content)

def html_to_text(html_path):
    with open(html_path, 'r', encoding='utf-8') as file:
        soup = BeautifulSoup(file, 'html.parser')
        return soup.get_text()

def pdf_to_text(pdf_path):

View source record →