diff options
Diffstat (limited to 'captcha/captcha.py')
| -rw-r--r-- | captcha/captcha.py | 81 | 
1 files changed, 55 insertions, 26 deletions
| diff --git a/captcha/captcha.py b/captcha/captcha.py index de3e61cf0..a76a7aa25 100644 --- a/captcha/captcha.py +++ b/captcha/captcha.py @@ -1,6 +1,27 @@ +#!/usr/bin/env python +# -*- coding: utf-8 -*- +# +#Copyright (C) 2009 kingzero, RaNaN +# +#This program is free software; you can redistribute it and/or modify +#it under the terms of the GNU General Public License as published by +#the Free Software Foundation; either version 3 of the License, +#or (at your option) any later version. +# +#This program is distributed in the hope that it will be useful, +#but WITHOUT ANY WARRANTY; without even the implied warranty of +#MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. +#See the GNU General Public License for more details. +# +#You should have received a copy of the GNU General Public License +# along with this program; if not, see <http://www.gnu.org/licenses/>. +# +### +import subprocess +import tempfile +  import Image  import ImageOps -import subprocess  class OCR(object):      def __init__(self): @@ -9,28 +30,37 @@ class OCR(object):      def load_image(self, image):          self.image = Image.open(image)          self.pixels = self.image.load() -        self.image_name = 'captcha_clean.png'          self.result_captcha = '' -    def unload(): +    def unload(self):          """delete all tmp images"""          pass      def threshold(self, value): -        self.image = self.image.point(lambda a: a * value +10) +        self.image = self.image.point(lambda a: a * value + 10) + +    def run(self, command, inputdata=None): +        """Run a command and return standard output""" +        pipe = subprocess.PIPE +        popen = subprocess.Popen(command, stdout=pipe, stderr=pipe) +        outputdata, errdata = popen.communicate(inputdata) +        assert (popen.returncode == 0), \ +            "Error running: %s\n\n%s" % (command, errdata) +        return outputdata      def run_gocr(self): -        self.image.save(self.image_name) -        cmd = ['gocr', self.image_name] -        self.result_captcha = subprocess.Popen(cmd, stdout=subprocess.PIPE).communicate()[0].replace('\n','') +        tmp = tempfile.NamedTemporaryFile(suffix=".jpg") +        self.image.save(tmp) +        self.result_captcha = self.run(['gocr', tmp.name]).replace("\n", "")      def run_tesser(self): -        self.image.save('captcha.tif', 'TIFF') -        cmd = ['tesseract', 'captcha.tif', '0'] -        self.result_captcha = subprocess.Popen(cmd) -        self.result_captcha.wait() -        cmd = ['cat', '0.txt'] -        self.result_captcha = subprocess.Popen(cmd, stdout=subprocess.PIPE).communicate()[0].replace('\n','') +        tmp = tempfile.NamedTemporaryFile(suffix=".tif") +        tmpTxt = tempfile.NamedTemporaryFile(suffix=".txt") + +        self.image.save(tmp.name, 'TIFF') +        self.run(['tesseract', tmp.name, tmpTxt.name.replace(".txt", "")]) + +        self.result_captcha = self.run(['cat', tmpTxt.name])      def get_captcha(self):          raise NotImplementedError @@ -49,29 +79,28 @@ class OCR(object):          for x in xrange(w):              for y in xrange(h): -           # no point in processing white pixels since we only want to remove black pixels                  if pixels[x, y] == 255: continue - +                # no point in processing white pixels since we only want to remove black pixel                  count = 0                  try:                      if pixels[x-1, y-1] != 255: count += 1 -                    if pixels[x-1, y  ] != 255: count += 1 -                    if pixels[x-1, y+1] != 255: count += 1 -                    if pixels[x, y+1  ] != 255: count += 1 -                    if pixels[x+1, y+1] != 255: count += 1 -                    if pixels[x+1, y  ] != 255: count += 1 -                    if pixels[x+1, y-1] != 255: count += 1 -                    if pixels[x, y-1  ] != 255: count += 1 +                    if pixels[x-1, y] != 255: count += 1 +                    if pixels[x-1, y + 1] != 255: count += 1 +                    if pixels[x, y + 1] != 255: count += 1 +                    if pixels[x + 1, y + 1] != 255: count += 1 +                    if pixels[x + 1, y] != 255: count += 1 +                    if pixels[x + 1, y-1] != 255: count += 1 +                    if pixels[x, y-1] != 255: count += 1                  except:                      pass -           # not enough neighbors are dark pixels so mark this pixel -           # to be changed to white +        # not enough neighbors are dark pixels so mark this pixel +            # to be changed to white                  if count < allowed:                      pixels[x, y] = 1 -                     -           # second pass: this time set all 1's to 255 (white) + +            # second pass: this time set all 1's to 255 (white)          for x in xrange(w):              for y in xrange(h):                  if pixels[x, y] == 1: pixels[x, y] = 255 | 
