PyCon JP 2012 Get RedBull Challenge

pyconjp2012_redbull.py

import sys
from HTMLParser import HTMLParser

value = dict()

class MyHTMLParser(HTMLParser):
    isuser = False
    
    def handle_starttag(self, tag, attrs):
        if tag == "p" and dict(attrs).get("class", None) == "user":
            self.isuser = True
            
    def handle_data(self, data):
        if data.strip() and self.isuser:
            self.isuser = False
            for c in data:
                i = c.upper()
                value[i] = value.get(i, 0) + 1

    def handle_endtag(self, tag):
        pass


parser = MyHTMLParser()
f = open(sys.argv[1])
txt = f.read()
parser.feed(txt)
parser.close()
f.close()

#print value
#print list(value)
a = value.items()
a.sort(cmp=lambda x,y: cmp(x[1], y[1]))
print a