import requests
from bs4 import BeautifulSoup
import re
from operator import itemgetter

r = requests.get('http://en.wikipedia.org/wiki/List_of_U.S._states_and_territories_by_population')

soup = BeautifulSoup(r.text)

states = []

for flag in soup.find_all("span", class_="flagicon"):
    if len(states) > 51:
        break
    state = flag.next_sibling.string
    if state == 'District of Columbia':
        state = "Washington D.C"
    population = int(flag.parent.findNext('td').string.replace(',',''))
    states.append((state, population),)

r = requests.get('http://news.ycombinator.com/item?id=5222370')

regex = r'>(?P<state>[\w\s.]+)</font></div></td></tr><tr><td></td><td class="default"><span class="comhead"><span id=score_[\d]+>(?P<score>[\d]*) point[s]?<'

out = []

for match in re.findall(regex, r.text):
    for state in states:
        if state[0] == match[0]:
            out.append((state[0], float(match[1])/state[1]),)

out = sorted(out, key=itemgetter(1), reverse=True)

for r in range(len(out)):
    print "%-2d %-20s : %f" % (r+1, out[r][0], out[r][1]*1000000)