How to Scrape Web Novels in EPUB/PDF/DOCX Files

pip install requests
pip install beautifulsoup4
pip install ebooklib
pip install fpdf
pip install python-docx

import requests
from bs4 import BeautifulSoup

# URL of the web novel platform
url = 'https://www.examplewebnovelplatform.com'

# Send a GET request to the URL
response = requests.get(url)

# Parse the HTML content using BeautifulSoup
soup = BeautifulSoup(response.content, 'html.parser')

# Find and extract the desired data (e.g., novel titles, authors, summaries)
novels = soup.find_all('div', class_='novel-item')

for novel in novels:
    title = novel.find('h2', class_='novel-title').text
    author = novel.find('span', class_='novel-author').text
    summary = novel.find('p', class_='novel-summary').text
    
    print(f'Title: {title}')
    print(f'Author: {author}')
    print(f'Summary: {summary}')
    print('---')

from ebooklib import epub

# Create an ePUB book
book = epub.EpubBook()

# Add metadata
book.set_title('Sample Web Novel')
book.set_language('en')

# Create a chapter
chapter = epub.EpubHtml(title='Chapter 1', file_name='chap_01.xhtml', lang='en')
chapter.content = '<h1>Chapter 1</h1><p>This is the first chapter of the sample web novel.</p>'

# Add chapter to the book
book.add_item(chapter)

# Define Table Of Contents
book.toc = (epub.Link('chap_01.xhtml', 'Chapter 1', 'chap_01'),)

# Add default NCX and Nav files
book.add_item(epub.EpubNcx())
book.add_item(epub.EpubNav())

# Define CSS style
style = 'BODY {color: black;}'
nav_css = epub.EpubItem(uid='style_nav', file_name='style/nav.css', media_type='text/css', content=style)
book.add_item(nav_css)

# Create the ePUB file
epub.write_epub('sample_web_novel.epub', book, {})

from fpdf import FPDF

# Create a PDF document
pdf = FPDF()
pdf.add_page()

# Set font
pdf.set_font('Arial', size=12)

# Add a cell
pdf.cell(200, 10, txt='Sample Web Novel', ln=True, align='C')

# Add content
pdf.multi_cell(0, 10, 'This is the first chapter of the sample web novel.')

# Save the PDF
pdf.output('sample_web_novel.pdf')

from docx import Document

# Create a Word document
doc = Document()

# Add a heading
doc.add_heading('Sample Web Novel', 0)

# Add a paragraph
doc.add_paragraph('This is the first chapter of the sample web novel.')

# Save the document
doc.save('sample_web_novel.docx')