hardscript

mechanize.Browser().retrieve(url, 'captcha.jpg')

from PIL import Image
import hashlib, time, os, math, _imaging

img = Image.open(fic)
img = img.convert("RGBA")
 
pixdata = img.load()
 
for y in xrange(img.size[1]):
    for x in xrange(img.size[0]):
    if pixdata[x, y][0] ; 0:
            pixdata[x, y] = (255, 255, 255, 255)

img = img.resize((1000, 300), Image.NEAREST)
im2 = Image.new("P",img.size,255)
im = img.convert("P")

pas = 5
alone = True
 
for x in range(0,im.size[1],pas):
  for y in range(0,im.size[0],pas):
    if im.getpixel((y,x)) == 0:
  for i in range(-pas,pas,1):
    for j in range(-pas,pas,1):
      if (y+i ;= 0 and x+j >;= 0):
        if im.getpixel((y+i,x+j)):
      alone = False
  for i in range(-pas,pas,1):
    for j in range(-pas,pas,1):
      if (y+i ;= 0 and x+j >;= 0):
        if not alone:
      im2.putpixel((y+i,x+j),0)
  alone = True


saut = 9
inletter = False
foundletter=False
 
start_ab = 0
end_ab = 0
start_or = im2.size[1]-1
end_or = 0
size = 0
 
debut = True
 
letters = []
 
for y in range(0,im2.size[0],saut): # slice across
  for x in range(0,im2.size[1],1): # slice down
    pix = im2.getpixel((y,x))
    if pix != 255:
  start_or = min(start_or,x)
  end_or = max(end_or,x)
  inletter = True
 
  if foundletter == False and inletter == True:
    foundletter = True
    start_ab = y
 
  if foundletter == True and inletter == False:
    foundletter = False
    end_ab = y
    size = max(size,end_ab)
    letters.append((start_ab,end_ab,start_or,end_or))
    start_or = im2.size[1]-1
    end_or = 0
  inletter=False

class VectorCompare:
  def magnitude(self,concordance):
    if type(concordance) != dict:
      raise ValueError('Supplied Argument should be of type dict')
    total = 0
    for word,count in concordance.iteritems():
      total += count ** 2
    return math.sqrt(total)
 
  def relation(self,concordance1, concordance2):
    if type(concordance1) != dict:
      raise ValueError('Supplied Argument 1 should be of type dict')
    if type(concordance2) != dict:
      raise ValueError('Supplied Argument 2 should be of type dict')
    relevance = 0
    topvalue = 0
    for word, count in concordance1.iteritems():
      if concordance2.has_key(word):
        topvalue += count * concordance2[word]
    if (self.magnitude(concordance1) * self.magnitude(concordance2)) != 0:
      return topvalue / (self.magnitude(concordance1) * self.magnitude(concordance2))
    else:
      return 0
 
  def concordance(self,document):
    if type(document) != str:
      raise ValueError('Supplied Argument should be of type string')
    con = {}
    for word in document.split(' '):
      if con.has_key(word):
        con[word] = con[word] + 1
      else:
        con[word] = 1
    return con
 
def buildvector(im):
  d1 = {}
  count = 0
  for i in im.getdata():
    d1[count] = i
    count += 1
  return d1
v = VectorCompare()

iconset = ['1','2','3','4','5','6','7','8','a','b','c','d','e','f','h','j','k','l','m','n','p','q','r','t','u','v','w','x','y','z','']
 
  imageset = []
 
  for letter in iconset:
    for img in os.listdir('./iconset/%s/'%(letter)):
      temp = []
      temp.append(buildvector(Image.open("./iconset/%s/%s"%(letter,img))))
      imageset.append({letter:temp})
 
  count = 0
  res = ""
 
  for letter in letters:
    m = hashlib.md5()
    im3 =  im2.crop(( letter[0] , letter[2], letter[1],letter[3] ))
    m.update("%s%s"%(time.time(),count))
    #im3.save("./%d_%s.gif"%(count,m.hexdigest()))
 
    guess = []
 
    for image in imageset:
      for x,y in image.iteritems():
    if (x == "''"):
      x = ''
    if len(y) != 0:
      guess.append( ( v.relation(y[0],buildvector(im3)),x) )
 
    guess.sort(reverse=True)
    res += guess[0][1]
    count += 1
  return res