diff options
Diffstat (limited to 'module')
| -rw-r--r-- | module/plugins/captcha/LinksaveIn.py | 2 | ||||
| -rw-r--r-- | module/plugins/captcha/captcha.py | 57 |
2 files changed, 32 insertions, 27 deletions
diff --git a/module/plugins/captcha/LinksaveIn.py b/module/plugins/captcha/LinksaveIn.py index 8ce26fbac..a92572fb3 100644 --- a/module/plugins/captcha/LinksaveIn.py +++ b/module/plugins/captcha/LinksaveIn.py @@ -1,7 +1,7 @@ # -*- coding: utf-8 -*- from captcha import OCR -import Image +from PIL import Image from os import sep from os.path import dirname from os.path import abspath diff --git a/module/plugins/captcha/captcha.py b/module/plugins/captcha/captcha.py index 7e4dec697..919739ad6 100644 --- a/module/plugins/captcha/captcha.py +++ b/module/plugins/captcha/captcha.py @@ -1,5 +1,4 @@ # -*- coding: utf-8 -*- - # #Copyright (C) 2009 kingzero, RaNaN # @@ -17,23 +16,22 @@ # along with this program; if not, see <http://www.gnu.org/licenses/>. # ### + from __future__ import with_statement import os from os.path import join from os.path import abspath import logging import subprocess -#import tempfile -import Image -import TiffImagePlugin -import PngImagePlugin -import GifImagePlugin -import JpegImagePlugin +from PIL import Image +from PIL import TiffImagePlugin +from PIL import PngImagePlugin +from PIL import GifImagePlugin +from PIL import JpegImagePlugin class OCR(object): - __name__ = "OCR" def __init__(self): @@ -54,16 +52,15 @@ class OCR(object): def run(self, command): """Run a command""" - popen = subprocess.Popen(command, bufsize = -1, stdout=subprocess.PIPE, stderr=subprocess.PIPE) + popen = subprocess.Popen(command, bufsize=-1, stdout=subprocess.PIPE, stderr=subprocess.PIPE) popen.wait() - output = popen.stdout.read() +" | "+ popen.stderr.read() + output = popen.stdout.read() + " | " + popen.stderr.read() popen.stdout.close() popen.stderr.close() self.logger.debug("Tesseract ReturnCode %s Output: %s" % (popen.returncode, output)) def run_tesser(self, subset=False, digits=True, lowercase=True, uppercase=True): #self.logger.debug("create tmp tif") - #tmp = tempfile.NamedTemporaryFile(suffix=".tif") tmp = open(join("tmp", "tmpTif_%s.tif" % self.__name__), "wb") tmp.close() @@ -76,11 +73,11 @@ class OCR(object): self.image.save(tmp.name, 'TIFF') if os.name == "nt": - tessparams = [join(pypath,"tesseract","tesseract.exe")] + tessparams = [join(pypath, "tesseract", "tesseract.exe")] else: tessparams = ['tesseract'] - tessparams.extend( [abspath(tmp.name), abspath(tmpTxt.name).replace(".txt", "")] ) + tessparams.extend([abspath(tmp.name), abspath(tmpTxt.name).replace(".txt", "")]) if subset and (digits or lowercase or uppercase): #self.logger.debug("create temp subset config") @@ -143,28 +140,37 @@ class OCR(object): for x in xrange(w): for y in xrange(h): - if pixels[x, y] == 255: continue + 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 - 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 @@ -198,7 +204,6 @@ class OCR(object): if pixels[x, y] == 0: pixels[x, y] = 255 - count = {} for x in xrange(w): |