word_counter.py

from datetime import datetime
a = open('gs2.txt')
b = a.read()
a.close()
b = b.decode('utf-8')
c = b.split()
thelist = []
print "Starting find at", str(datetime.now())
for word in c:
    didfind = False
    for entry in thelist:
        if word in entry:
            thelist[thelist.index(entry)][1] += 1
            didfind = True
    if didfind == False:
        thelist.append([word, 1])
print "Finished find at", str(datetime.now())
final = sorted(thelist, key=lambda word: word[1])
final.reverse()
with open('output.txt', 'w') as d:
    for item in final:
        d.write(str(item[0].encode('utf-8')) + ' ' + str(item[1]) + '\n')

import re


RE_WORDS = re.compile('\W+')


def words_count(text):
    return len([w for w in RE_WORDS.split(text) if text])