problem1.py

import math
import sys
def fact( num):
    if num == 0 or num == 1:
      return 1
    else:
      return num * fact(num-1)
for i in xrange(100000):
  sum=0
  for dig in str(fact(i)):
    sum = sum + int(dig)
  if sum == 8001:
    print i
    sys.exit(0)

problem2.py

import urllib
f = urllib.urlopen("http://apply.embed.ly/static/data/2.html")
s = f.read()
f.close()
import re

###DISCLAIMER, I ripped the code to do this calculation from 
###http://www.physics.rutgers.edu/~masud/computing/WPark_recipes_in_python.html
def meanstdv(x):
    from math import sqrt
    n, mean, std = len(x), 0, 0
    for a in x:
	mean = mean + a
    mean = mean / float(n)
    for a in x:
	std = std + (a - mean)**2
    std = sqrt(std / float(n-1))
    return mean, std
    
#s=" <article>\
#   <p>Sign Up Today</p>\
#  <div>\
 #    <p>Content</p>\
 #    <div>\
 #     <img />\
 #     <p>Img Caption</p></div>\
 #    <p>Content</p> </div></article>"

print s
stack = []
values = []
for match in re.findall(r'(\<.*?\>)', s):
  if (match.rfind("</") != -1):
    stack.pop()
  elif (match.rfind("/>") != -1):
    print "skip"
  else:
    print match,",",len(stack)
    values.append(len(stack))
    stack.append(match)

mean,stdev = meanstdv(values)
print "mean ", mean
print "std ", stdev

problem3.py

import sys
import math
most_frequent = 2520
totalWords = 0
wordSum = 0
for x in xrange(1,901):
  totalWords = totalWords + math.floor(most_frequent/x)
print totalWords

for x in xrange(1,901):
  wordSum = wordSum + most_frequent/x
  if wordSum >= math.floor(totalWords/2):
    print "ans ", x+1
    sys.exit(0)