gistfile1.py

from datetime import datetime
import BeautifulSoup as soup
import requests

host = 'http://news.ycombinator.com'

def chunks(l, n):
    """ Yield successive n-sized chunks from l.
    """
    for i in xrange(0, len(l), n):
        yield l[i:i+n]

def get_news(depth):
    def _get_news(page, acc, depth):
        if not page.startswith('/'):
            page = '/' + page

        r = requests.get(host + page)
        doc = soup.BeautifulSoup(r.content)
        titles = doc.table.findAll(True, {'class': 'title'})

        articles = titles[:-1]
        for no, title in chunks(articles, 2):
            acc.append( (title.a.string, title.a['href']) )

        if depth > 1:
            more = titles[-1]
            return _get_news(more.a['href'], acc, depth - 1)
        else:
            return acc
    return _get_news('/', [], depth)

def main():
    print 'Hacker News Scrap'
    print 'generated at %s' % datetime.now().strftime('%a, %d %b %Y %H:%M:%S')
    print 
    for no,(title, href) in enumerate(get_news(5)):
        print '%d. %s (%s)' % (no+1, title, href)

if __name__ == '__main__':
    main()