python3feedfinder

#!/usr/local/bin/python3.3
from bs4 import BeautifulSoup as bs4
import requests
import feedparser
import urllib.parse

def findfeed(site):
    raw = requests.get(site).text
    result = []
    possible_feeds = []
    html = bs4(raw)
    feed_urls = html.findAll("link", rel="alternate")
    if len(feed_urls) > 1:
        for f in feed_urls:
            t = f.get("type",None)
            if t:
                if "rss" in t or "xml" in t:
                    href = f.get("href",None)
                    if href:
                        possible_feeds.append(href)
    parsed_url = urllib.parse.urlparse(site)
    base = parsed_url.scheme+"://"+parsed_url.hostname
    atags = html.findAll("a")
    for a in atags:
        href = a.get("href",None)
        if href:
            if "xml" in href or "rss" in href or "feed" in href:
                possible_feeds.append(base+href)
    for url in list(set(possible_feeds)):
        f = feedparser.parse(url)
        if len(f.entries) > 0:
            if url not in result:
                result.append(url)
    return(result)

@dvershinin Thanks! Fixed the article so it just shows this embedded gist.

@alexmill Why is the comparison in l.13 strictly > 1, what is there is only one RSS feed linked? Should it not be >= 1

@ranok I think no reason in particular