summaryrefslogtreecommitdiffstats
path: root/captcha
diff options
context:
space:
mode:
authorGravatar RaNaN <Mast3rRaNaN@hotmail.de> 2009-08-10 10:43:57 +0200
committerGravatar RaNaN <Mast3rRaNaN@hotmail.de> 2009-08-10 10:43:57 +0200
commit2e76cf0f532ff89ffa58e5db264a14deb60db6da (patch)
tree7732fdbdceb957e3596ee275815957ecc2d84045 /captcha
parentfixed megaupload bug (diff)
downloadpyload-2e76cf0f532ff89ffa58e5db264a14deb60db6da.tar.xz
plugin fixes, core config functions
Diffstat (limited to 'captcha')
-rw-r--r--captcha/captcha.py313
1 files changed, 157 insertions, 156 deletions
diff --git a/captcha/captcha.py b/captcha/captcha.py
index 5fa8bfc45..fbbf20fee 100644
--- a/captcha/captcha.py
+++ b/captcha/captcha.py
@@ -17,11 +17,12 @@
# along with this program; if not, see <http://www.gnu.org/licenses/>.
#
###
+import logging
import subprocess
import tempfile
+import threading
import Image
-import threading
class RunThread(threading.Thread):
def __init__(self):
@@ -47,7 +48,7 @@ class RunThread(threading.Thread):
class OCR(object):
def __init__(self):
- pass
+ self.logger = logging.getLogger("log")
def load_image(self, image):
self.image = Image.open(image)
@@ -71,207 +72,207 @@ class OCR(object):
# "Error running: %s\n\n%s" % (command, errdata)
# return outputdata
- thread = RunThread()
- result = thread.e(command, inputdata)
- return result
+ thread = RunThread()
+ result = thread.e(command, inputdata)
+ return result
- def run_gocr(self):
- tmp = tempfile.NamedTemporaryFile(suffix=".jpg")
- self.image.save(tmp)
- self.result_captcha = self.run(['gocr', tmp.name]).replace("\n", "")
+def run_gocr(self):
+ tmp = tempfile.NamedTemporaryFile(suffix=".jpg")
+ self.image.save(tmp)
+ self.result_captcha = self.run(['gocr', tmp.name]).replace("\n", "")
- def run_tesser(self):
- tmp = tempfile.NamedTemporaryFile(suffix=".tif")
- tmpTxt = tempfile.NamedTemporaryFile(suffix=".txt")
+def run_tesser(self):
+ 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.image.save(tmp.name, 'TIFF')
+ self.run(['tesseract', tmp.name, tmpTxt.name.replace(".txt", "")])
- self.result_captcha = self.run(['cat', tmpTxt.name]).replace("\n", "")
+ self.result_captcha = self.run(['cat', tmpTxt.name]).replace("\n", "")
- def get_captcha(self):
- raise NotImplementedError
+def get_captcha(self):
+ raise NotImplementedError
- def to_greyscale(self):
- if self.image.mode != 'L':
- self.image = self.image.convert('L')
+def to_greyscale(self):
+ if self.image.mode != 'L':
+ self.image = self.image.convert('L')
- self.pixels = self.image.load()
+ self.pixels = self.image.load()
- def eval_black_white(self, limit):
- self.pixels = self.image.load()
- w, h = self.image.size
- for x in xrange(w):
- for y in xrange(h):
- if self.pixels[x, y] > limit:
- self.pixels[x, y] = 255
- else:
- self.pixels[x, y] = 0
+def eval_black_white(self, limit):
+ self.pixels = self.image.load()
+ w, h = self.image.size
+ for x in xrange(w):
+ for y in xrange(h):
+ if self.pixels[x, y] > limit:
+ self.pixels[x, y] = 255
+ else:
+ self.pixels[x, y] = 0
- def clean(self, allowed):
- pixels = self.pixels
+def clean(self, allowed):
+ pixels = self.pixels
- w, h = self.image.size
+ w, h = self.image.size
- for x in xrange(w):
- for y in xrange(h):
- 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
- except:
- pass
-
- # 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)
- for x in xrange(w):
- for y in xrange(h):
- if pixels[x, y] == 1: pixels[x, y] = 255
+ for x in xrange(w):
+ for y in xrange(h):
+ if pixels[x, y] == 255: continue
+ # no point in processing white pixels since we only want to remove black pixel
+ count = 0
- self.pixels = pixels
+ 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
+ except:
+ pass
- def derotate_by_average(self):
- """rotate by checking each angle and guess most suitable"""
+ # not enough neighbors are dark pixels so mark this pixel
+ # to be changed to white
+ if count < allowed:
+ pixels[x, y] = 1
- w, h = self.image.size
- pixels = self.pixels
+ # 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
- for x in xrange(w):
- for y in xrange(h):
- if pixels[x, y] == 0:
- pixels[x, y] = 155
+ self.pixels = pixels
+
+def derotate_by_average(self):
+ """rotate by checking each angle and guess most suitable"""
- highest = {}
- counts = {}
+ w, h = self.image.size
+ pixels = self.pixels
- for angle in range(-45, 45):
+ for x in xrange(w):
+ for y in xrange(h):
+ if pixels[x, y] == 0:
+ pixels[x, y] = 155
- tmpimage = self.image.rotate(angle)
+ highest = {}
+ counts = {}
+
+ for angle in range(-45, 45):
+
+ tmpimage = self.image.rotate(angle)
- pixels = tmpimage.load()
+ pixels = tmpimage.load()
- w, h = self.image.size
+ w, h = self.image.size
- for x in xrange(w):
- for y in xrange(h):
- if pixels[x, y] == 0:
- pixels[x, y] = 255
+ for x in xrange(w):
+ for y in xrange(h):
+ if pixels[x, y] == 0:
+ pixels[x, y] = 255
- count = {}
+ count = {}
- for x in xrange(w):
- count[x] = 0
- for y in xrange(h):
- if pixels[x, y] == 155:
- count[x] += 1
+ for x in xrange(w):
+ count[x] = 0
+ for y in xrange(h):
+ if pixels[x, y] == 155:
+ count[x] += 1
- sum = 0
- cnt = 0
+ sum = 0
+ cnt = 0
- for x in count.values():
- if x != 0:
- sum += x
- cnt += 1
+ for x in count.values():
+ if x != 0:
+ sum += x
+ cnt += 1
- avg = sum / cnt
- counts[angle] = cnt
- highest[angle] = 0
- for x in count.values():
- if x > highest[angle]:
- highest[angle] = x
+ avg = sum / cnt
+ counts[angle] = cnt
+ highest[angle] = 0
+ for x in count.values():
+ if x > highest[angle]:
+ highest[angle] = x
- highest[angle] = highest[angle] - avg
+ highest[angle] = highest[angle] - avg
- hkey = 0
- hvalue = 0
+ hkey = 0
+ hvalue = 0
- for key, value in highest.iteritems():
- if value > hvalue:
- hkey = key
- hvalue = value
+ for key, value in highest.iteritems():
+ if value > hvalue:
+ hkey = key
+ hvalue = value
- self.image = self.image.rotate(hkey)
- pixels = self.image.load()
+ self.image = self.image.rotate(hkey)
+ pixels = self.image.load()
- for x in xrange(w):
- for y in xrange(h):
- if pixels[x, y] == 0:
- pixels[x, y] = 255
+ for x in xrange(w):
+ for y in xrange(h):
+ if pixels[x, y] == 0:
+ pixels[x, y] = 255
- if pixels[x, y] == 155:
- pixels[x, y] = 0
+ if pixels[x, y] == 155:
+ pixels[x, y] = 0
- self.pixels = pixels
+ self.pixels = pixels
- def split_captcha_letters(self):
- captcha = self.image
- started = False
- letters = []
- width, height = captcha.size
- bottomY, topY = 0, height
- pixels = captcha.load()
+def split_captcha_letters(self):
+ captcha = self.image
+ started = False
+ letters = []
+ width, height = captcha.size
+ bottomY, topY = 0, height
+ pixels = captcha.load()
- for x in xrange(width):
- black_pixel_in_col = False
- for y in xrange(height):
- if pixels[x, y] != 255:
- if started == False:
- started = True
- firstX = x
- lastX = x
+ for x in xrange(width):
+ black_pixel_in_col = False
+ for y in xrange(height):
+ if pixels[x, y] != 255:
+ if started == False:
+ started = True
+ firstX = x
+ lastX = x
- if y > bottomY: bottomY = y
- if y < topY: topY = y
- if x > lastX: lastX = x
+ if y > bottomY: bottomY = y
+ if y < topY: topY = y
+ if x > lastX: lastX = x
- black_pixel_in_col = True
+ black_pixel_in_col = True
- if black_pixel_in_col == False and started == True:
- rect = (firstX, topY, lastX, bottomY)
- new_captcha = captcha.crop(rect)
+ if black_pixel_in_col == False and started == True:
+ rect = (firstX, topY, lastX, bottomY)
+ new_captcha = captcha.crop(rect)
- w, h = new_captcha.size
- if w > 5 and h > 5:
- letters.append(new_captcha)
+ w, h = new_captcha.size
+ if w > 5 and h > 5:
+ letters.append(new_captcha)
- started = False
- bottomY, topY = 0, height
+ started = False
+ bottomY, topY = 0, height
- return letters
+ return letters
- def correct(self, values, var=None):
+def correct(self, values, var=None):
- if var:
- result = var
- else:
- result = self.result_captcha
-
- for key, item in values.iteritems():
+ if var:
+ result = var
+ else:
+ result = self.result_captcha
- if key.__class__ == str:
- result = result.replace(key, item)
- else:
- for expr in key:
- result = result.replace(expr, item)
+ for key, item in values.iteritems():
- if var:
- return result
+ if key.__class__ == str:
+ result = result.replace(key, item)
else:
- self.result_captcha = result
+ for expr in key:
+ result = result.replace(expr, item)
+
+ if var:
+ return result
+ else:
+ self.result_captcha = result
if __name__ == '__main__':