Captcha breaking code. See http://tangopardo.com.ar/2cf7/2015/04/17/breaking-a-simple-captcha-with-python-and-pillow

captcha_breaker.py

#!/usr/bin/python

from PIL import Image
import sys, os


imgpatrones = []
pixelpatrones = []

for idx in range(10):
    img = Image.open("patrones/%i.png" % idx).convert('RGB')
    imgpatrones.append(img)
    pixelpatrones.append( list(img.getdata()) )


def compara(region, patron):
    pixels = list(region.getdata())
    size = min(len(pixels), len(patron))

    res = 0.0
    for idx in range(size):
        if pixels[idx] == patron[idx]:
            res = res + 1

    return res / size


def elimina_lineas(src):
    cropeada = src.crop( (4, 1, 49, 19) )
    w,h = cropeada.size
    stripes = []

    for x in range(w):
        count = 0
        for y in range(h):
            if cropeada.getpixel( (x,y) ) != (248, 255, 255):
                count += 1

        if count == h:
            stripes.append(x)

    for x in stripes:
        for y in range(h):
            cropeada.putpixel( (x,y),  (248, 255, 255) )
            cropeada.putpixel( (x,y),  (255, 0, 0) )

    return cropeada

def crear_crops(src, celda):
    limites = range(38)
    xceldas = [0, 8, 16, 24, 32, 40]
    xoffsets = range(-3,4)
    yceldas = range(6)
    boxes = []
    crops = []

    x = xceldas[celda]
    x = [ (x+off) for off in xoffsets if (x+off) in limites ]

    for left in x:
        for top in yceldas:
            boxes.append( (left, top, left+8, top+13) )

    for box in boxes:
        crops.append( src.crop(box) )

    return crops

def compara_crops_con_patron(crops, patron):
    scores = []
    for crop in crops:
        scores.append( compara(crop, pixelpatrones[patron] ))
    return max(scores)

def decodifica_celda(src, celda):
    pesos = []
    crops = crear_crops(src, celda)

    for patron in range(10):
        pesos.append( compara_crops_con_patron(crops, patron) )

    return pesos.index( max(pesos) )

def decodifica(filename):
    original = Image.open(filename)
    src = elimina_lineas(original)
    res = []

    for celda in range(6):
        res.append( decodifica_celda(src, celda) )

    return ''.join( str(x) for x in res )

if __name__ == '__main__':
    print decodifica(sys.argv[1])