Extract Ubuntu Vulnerabilities into a easy to copy/paste text form

extract_vulns.py

#!/usr/bin/env python
# Usage: python extract_vulns.py <url>
# Bog-simple screen scraping, will fail unless URL is something like this:
#   http://www.ubuntu.com/usn/lucid/
#   http://www.ubuntu.com/usn/lucid/?page=3
#

from BeautifulSoup import BeautifulSoup
import requests, time, sys

def extract_date(tag):
    dmy = tag.text.split(' ')[-3:]
    dmy[0] = "".join([c for c in dmy[0] if unicode.isnumeric(c)])  # strip ordinal
    time_str = "/".join(dmy)
    return time.strptime(time_str, "%d/%B/%Y")  # for example, "3/May/2012"

def extract_content(soup):
    the_good_stuff = soup.find('div', { 'id': 'content' }).findAll('h3')
    return the_good_stuff[2:]

def extract_title(tag):
    return tag.find('a').text

def extract_vulns(soup):
    content = extract_content(soup)
    vulns = [(extract_date(tag), extract_title(tag)) for tag in content]
    vulns.reverse()

    return vulns

def scrape_vulns(url):
    resp = requests.get(url)
    soup = BeautifulSoup(resp.text)
    return extract_vulns(soup)

def format_vulns(vulns):
    return "\n".join([time.strftime("%m/%d/%Y", v[0]) + "\t" + v[1] for v in vulns])

if __name__ == '__main__':
    vulns = scrape_vulns(sys.argv[1])
    print(format_vulns(vulns))