Vroum

#!/usr/bin/env python
import urllib, urllib2
import HTMLParser
import re
import time

class JeuALaConParser(HTMLParser.HTMLParser):
  def __init__(self):
    HTMLParser.HTMLParser.__init__(self)
    self.enregistrage = False
    self.traitsdesprit = []

  def handle_starttag(self, tag, attributes):
    if tag != 'div':
      return
    for name, value in attributes:
      if name == 'class' and value == 'postmsg':
        break
    else:
      return
    self.enregistrage = True

  def handle_endtag(self, tag):
    if tag == 'div' and self.enregistrage:
      self.enregistrage = False

  def handle_data(self, data):
    if self.enregistrage:
      try:
        tde = data.decode('iso-8859-1')
      except UnicodeEncodeError:
        try:
          tde = data.decode('utf-8')
        except:
          print("Klonk: " + data)
          return
      self.traitsdesprit.append(tde)

#proxy = urllib2.ProxyHandler({'http': 'http://leusername:lemotdepasse@leproxy:leporc'})
#auth = urllib2.HTTPBasicAuthHandler()
#opener = urllib2.build_opener(proxy, auth, urllib2.HTTPHandler)
#urllib2.install_opener(opener)

nonantedeuxpagesdetraitsdesprit = []
for i in range(1, 92):
    moissoneuse = JeuALaConParser()
    unepagedelols =  urllib2.urlopen('http://leliendufauxrhum/viewtopic.php?id=323&p=' + str(i))
    moissoneuse.feed(unepagedelols.read())
    nonantedeuxpagesdetraitsdesprit += moissoneuse.traitsdesprit
    time.sleep(1)

compilationdenonantedeuxpagesdetraitsdesprit = u''
for traitdesprit in nonantedeuxpagesdetraitsdesprit:
    if re.match('^[\n\t]*$', traitdesprit):
        continue
    compilationdenonantedeuxpagesdetraitsdesprit += traitdesprit + u' '

print(compilationdenonantedeuxpagesdetraitsdesprit)