import os, glob, string
from operator import itemgetter
from urllib import urlopen
"""Method that prints the results nicely"""
def printResults():
#Produce a sorted list of tuples
scores = sorted(results.items(), key=itemgetter(1), reverse=True)
for score in scores: #Iterate over the tuples, printing them
print score[0].ljust(25) , score[1]
"""Method that add's a person's posts to the results dictionary"""
def addPost(person):
if results.has_key(person):
results[person] += 1
else:
results[person] = 1
"""Method that finds all the posts in a page, and adds the posts to the dictionary of results"""
def findPosts(text):
startPost, startName, endName = 0,0,0
while True:
startPost = text.find('><a name=', endName)
if startPost == -1:
break
startName = text.find('<b>',startPost) + 3
endName = text.find('</b>', startName)
addPost(text[startName:endName])
"""Method that grabs all the pages in the thread from the web"""
def grabFiles():
thread = input('Enter the thread id of the thread to be counted: ')
pages = input('Enter the number of pages to be counted: ')
html = ''
for page in range (0, pages):
url = 'http://www.pcpro.co.uk/phpbb/viewtopic.php?t=' + `thread` + '&start=' + `15*page`
html += urlopen(url).read()
return html
results = {} #Dictionary to store each poster's current post count
findPosts(grabFiles())
printResults()
