app.py
|
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 |
import requests from bs4 import BeautifulSoup import xml.etree.ElementTree as ET from urllib.parse import urljoin,urlparse # Function to get all links from the website def get_all_links(url): response = requests.get(url) soup = BeautifulSoup(response.content, 'html.parser') # Extract all anchor tags links = set() for a_tag in soup.find_all('a', href=True): link = a_tag['href'] # Join relative links with the base URL full_url = urljoin(url, link) # Filter out non-http(s) URLs or other irrelevant links if full_url.startswith("http"): links.add(full_url) return links def create_sitemap(url,filename="sitemap.xml"): urls = get_all_links(url) print(urls) urlset = ET.Element("urlset", xmlns="http://www.sitemaps.org/schemas/sitemap/0.9") for link in urls: url_element = ET.SubElement(urlset,"url") loc = ET.SubElement(url_element,'loc') loc.text = link tree = ET.ElementTree(urlset) tree.write(filename,encoding='UTF-8',xml_declaration=True) print("XML SITEMAP GENERATED YOU CAN CHECK") if __name__ == "__main__": site_url = "https://freemediatools.com" create_sitemap(site_url,"sitemap.xml") |
