arstechnica.py

# import libraries
import urllib2
from bs4 import BeautifulSoup

def getArticles(soup):
    return soup.find_all('item')

def getHeadline(soup):
    return soup.find('title').string

def getArticleUrl(soup):
    return soup.find('guid').string

# specify the url
quote_page = 'http://feeds.arstechnica.com/arstechnica/index'

# query the website and return the html to the variable 'page'
page = urllib2.urlopen(quote_page)

# parse the html using beautiful soup and store in variable 'soup'
soup = BeautifulSoup(page, 'html.parser')

# Get all Articles
articles = getArticles(soup)

for article in articles:
    print(getHeadline(article))
    print(getArticleUrl(article))