Extract Feed URL's from a given URL

get_feed_links.py

from bs4 import BeautifulSoup
import requests

def detect_feeds_in_HTML(html):
    """
    Extract Feed URL from a given HTML page
    This is achieved by detecting all ``link`` tags that reference a feed in HTML.
    """
    # check if really an input stream
    result = []
    # get the textual data (the HTML) from the input stream
    soup = BeautifulSoup(html,"lxml")
    # find all links that have an "alternate" attribute
    feed_urls = soup.findAll("link", rel="alternate")
    # extract URL and type
    for feed_link in feed_urls:
        url = feed_link.get("href", None)
        # if a valid URL is there
        if url:
            result.append(url)
    return result

def get_html(url):
    return requests.get(url).content


if __name__ == "__main__":
    print(detect_feeds_in_HTML(get_html("https://www.doraithodla.com/")))