web2pdf.py

import pdfkit
import requests
from bs4 import BeautifulSoup
import urllib.parse

def webpage_to_pdf(url, output_file):
    # Fetch webpage content
    response = requests.get(url)
    soup = BeautifulSoup(response.text, 'html.parser')
    
    # Extract links
    links = [a.get('href') for a in soup.find_all('a', href=True)]
    # Convert relative URLs to absolute
    links = [urllib.parse.urljoin(url, link) for link in links]
    
    # Generate PDF from webpage
    pdfkit.from_url(url, output_file)
    
    # Append links to PDF (simple text append)
    with open(output_file.replace('.pdf', '_links.txt'), 'w') as f:
        f.write("Links found on the webpage:\n")
        for link in links:
            f.write(f"{link}\n")

# Example usage
if __name__ == "__main__":
    webpage_url = "https://cs.yale.edu/homes/aspnes/classes/223/notes.html"
    output_pdf = "output.pdf"
    webpage_to_pdf(webpage_url, output_pdf)

run via this oneliner

curl -sSL https://gist.githubusercontent.com/mehdinourollah/5345125664d54955219be9520c464b38/raw/5a96cab89fd1d4b4a2b056611a66994749236ec0/web2pdf.py > web2pdf.py && python3 -m venv venv && source venv/bin/activate && pip install requests beautifulsoup4 pdfkit && python3 web2pdf.py