How Can I extract the text for each bookmarked section of a pdf book

Question

How Can I extract the text for each bookmarked section of a pdf book in Python using PyPDF2 and split it into html files based on the list of bookmarks?

I've been working with this code but I can't quite make it work:

import PyPDF2
from bs4 import BeautifulSoup

# Open the PDF file
pdf_file = PyPDF2.PdfReader(open("book.pdf", "rb"))

# Get the bookmarks from the PDF file
bookmarks = pdf_file.outline

# Create a folder to store the HTML files
import os

folder = "html_pages"
if not os.path.exists(folder):
    os.makedirs(folder)

# Iterate over the bookmarks
for i, bookmark in enumerate(bookmarks):
    # Extract the text from the page associated with the bookmark
    page_number = bookmark[0]
    page = pdf_file.pages[page_number - 1]
    content = page.extract_text()

    # Convert the text to HTML
    soup = BeautifulSoup(content, "html.parser")
    html_content = str(soup)

    # Write the HTML content to a file
    file_path = os.path.join(folder, f"{i}.html")
    with open(file_path, "w") as f:
    f.write(html_content)