HOW EXCITED IS DAN SINKER

ALLCAPS.py

import lxml.html
import lxml.cssselect
import urllib
import re

def main(victim):
    sel = lxml.cssselect.CSSSelector('p.js-tweet-text')
    tweets = sel(lxml.html.parse(victim))
    tweet_text = [lxml.html.tostring(x, encoding="unicode", method="text").encode("ascii", "ignore").strip() for x in tweets]
    # ignoring whitespace...
    total_chars = sum(sum(len(x.strip()) for x in y.split()) for y in tweet_text)
    # match any uppercase chars
    matcher = re.compile("[A-Z]*")
    uppercase_chars = sum(sum(len(x.strip()) for x in matcher.findall(y)) for y in tweet_text)
    print total_chars, uppercase_chars, (100.0*uppercase_chars)/total_chars

if __name__ == "__main__":
    VICTIM = "http://twitter.com/dansinker"
    main(VICTIM)