Embed.ly Challenge

embedly.py

import math
import re

##############################
####     Challenge 1      ####
##############################

def R(n):
    factorial, summed = str(math.factorial(n)), 0
    for i in factorial: summed += int(i)
    return summed

def find_min(n):
    trial, i = R(0), 0
    while trial != n:
        i += 1
        trial = R(i)
    return i

print find_min(8001)

##############################
####     Challenge 2      ####
##############################

def get_tag_depths(filename, tag):
    f = open(filename, 'r')
    data = f.read()
    f.close()
    matches = re.findall("(<[^>]*>)", data)
    depth, matched_depths = 0, []
    for match in matches:
        if match.startswith("</"): depth -= 1
        else:
            if len(match) == (len(tag) + 2) and tag in match:
                matched_depths.append(depth)
            if not match.endswith("/>"):
                depth += 1
    return matched_depths

def std_dev(numbers):
    m = float(sum(numbers)) / len(numbers)
    d = [(x - m)**2.0 for x in numbers]
    return (sum(d) / len(d))**(0.5)

print std_dev(get_tag_depths('embedly.html', 'p'))

##############################
####     Challenge 3      ####
##############################

def find_words(start, uniques, point):
    total = 0
    for i in xrange(1, uniques + 1):
        total += max(1, (float(start) / i))
    sofar = 0
    for i in xrange(1, uniques + 1):
        sofar += max(1, (float(start) / i))
        if sofar >= (total / point): return i
    return None

print find_words(2520, 900, 2)