sharonline captcha method

2 files changed, 53 insertions, 10 deletions

diff --git a/captcha/ShareonlineBiz.py b/captcha/ShareonlineBiz.py
index 038f6639e..1e3fc6214 100644
--- a/captcha/ShareonlineBiz.py
+++ b/captcha/ShareonlineBiz.py
@@ -6,16 +6,23 @@ class ShareonlineBiz(OCR):
         OCR.__init__(self)
         
     def get_captcha(self, image):
-        urllib.urlretrieve("http://www.share-online.biz/captcha.php", "captcha.jpeg") 
         self.load_image(image)
-        #self.to_greyscale()
-        #self.image.save('grey.jpeg')
-        self.image.threshold(32500)
-        #self.threshold(1.3)
-        self.run_tesser()
-        self.image.save('captcha_bla.jpeg')
-        return self.result_captcha
+        self.to_greyscale()
+        self.image = self.image.resize((160, 50))
+        self.pixels = self.image.load()
+        self.threshold(1.85)
+        self.eval_black_white(240)
+
+        letters = self.split_captcha_letters()
+        
+        final = ""
+        for letter in letters:
+            self.image = letter
+            self.run_tesser()
+            final += self.result_captcha
+
+        return final
 
 if __name__ == '__main__':
     ocr = ShareonlineBiz()
-    print  ocr.get_captcha('captcha.jpeg')
+    print  ocr.get_captcha('captcha.php3.jpeg')
diff --git a/captcha/captcha.py b/captcha/captcha.py
index 539e51932..48816940d 100644
--- a/captcha/captcha.py
+++ b/captcha/captcha.py
@@ -72,6 +72,7 @@ class OCR(object):
         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):
@@ -115,7 +116,7 @@ class OCR(object):
 
         self.pixels = pixels
 
-    def derotate_by_avergage(self):
+    def derotate_by_average(self):
         """rotate by checking each angle and guess most suitable"""
 
         w, h = self.image.size
@@ -189,7 +190,42 @@ class OCR(object):
 
         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()
+  
+        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
+   
+                    black_pixel_in_col = True
+   
+            if black_pixel_in_col == False and started == True:
+                rect = (firstX, topY, lastX, bottomY)
+                new_captcha = captcha.crop(rect)
+  
+                letters.append(new_captcha)
+  
+                started = False
+                bottomY, topY = 0, height
+  
+        return letters
+
 
+        
 if __name__ == '__main__':
     ocr = OCR()
     ocr.load_image("B.jpg")