Web scraping Python

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

def save_page_to_pdf(url, page_number):
    options = {
        'quiet': ''
    }
    pdfkit.from_url(url, f'output_page_{page_number}.pdf', options=options)

def crawl_and_save(base_url, page_number, visited_urls=set()):
    if base_url in visited_urls:
        print(f"Already visited: {base_url}")
        return
    visited_urls.add(base_url)

    print(f"Processing: {base_url}")
    save_page_to_pdf(base_url, page_number)

    response = requests.get(base_url)
    soup = BeautifulSoup(response.text, 'html.parser')

    for link in soup.find_all('a', href=True):
        absolute_url = urljoin(base_url, link['href'])
        crawl_and_save(absolute_url, page_number + 1, visited_urls)

if __name__ == "__main__":
    base_url = "your_base_url"
    
    # Make sure to set the correct path to wkhtmltopdf executable
    pdfkit_config = pdfkit.configuration(wkhtmltopdf='/path/to/wkhtmltopdf')

    crawl_and_save(base_url, page_number=1)

//https://wkhtmltopdf.org/downloads.html

pdfkit_config = pdfkit.configuration(wkhtmltopdf=r'"C:\path with spaces\wkhtmltopdf.exe"')