def getverify1(name):
im = Image.open('yzm/'+name)
for ii in xrange(4):
subname = bytes(ii)+'_'+name
region = (0+13*ii,0,13*(ii+1),20)
subIm = im.crop(region)
subIm.save('subyzm/'+subname)
imgry = subIm.convert('L')
imgry.save('gyzm/g' + subname)
pixel,slope,maxSlope = getPixelandSlop(imgry)
setNewImg(imgry,pixel,slope,maxSlope)
imgry.save('nyzm/' + subname)
thr = 200#ImageStat.Stat(imgry).mean[0]*0.85
#print thr
table = []
for i in range(256):
if i < thr:
table.append(0)
else:
table.append(1)
out = imgry.point(table, '1')
print pytesser.image_to_string(out)
out.save('byzm/b' + subname)
#print imgry.size
print name
def crackCaptcha(file):
img = Image.open(file)
#convert it to black and white
img = img.convert("L")
#pixdata = img.load()
# Clean the background noise, if color != black, then set to white.
#for y in xrange(img.size[1]):
# for x in xrange(img.size[0]):
# if pixdata[x, y] != (255, 255, 255, 255): #by condition :if not white ,then set it to black
# pixdata[x, y] = (0, 0, 0, 0)
img.save("input-black.gif", "GIF")
# Make the image bigger (needed for OCR)
im_orig = Image.open('input-black.gif')
big = im_orig.resize((116, 56), Image.NEAREST)
ext = ".tif"
big.save("input-NEAREST" + ext)
# Perform OCR using pytesser library
from pytesser import image_to_string
im = Image.open('input-NEAREST.tif')
text = image_to_string(im)
text = text.rstrip()
print text
return text
def get(self):
im = Image.open(self.img_file)
#im = ImageEnhance.Sharpness(im).enhance(2)
#im.show()
#im1 = self.test(im)
#
#转化到灰度图
imgry = im.convert('L')
self.clearNoise(im, 50, 4, 4)
#保存图像
imgry.save('g' + self.img_file)
#imgry.show()
#二值化，采用阈值分割法，threshold为分割点
out = imgry.point(self.table_2value(), '1')
out.save('b' + self.img_file)
#out.show()
#识别
text = image_to_string(out)
#print 111
#识别对吗
text = text.strip()
text = text.upper()
for r in self.rep:
text = text.replace(r, self.rep[r])
#print text
return text
def imageToString(img):
'''please input a grayscale image(using cv2.imread(<filename>,0))'''
img = processImage(img)
cv2.imwrite('processed.bmp', img)
new_img = Image.open('processed.bmp')
rawCode = pytesser.image_to_string(new_img)
code = ""
for letter in rawCode:
#handle possible mismatches
if letter >= '0' and letter <= '9':
code += letter
elif letter == 'z' or letter == 'Z' or letter == 'L':
code += '2'
elif letter == 'o' or letter == 'O' or letter == 'Q':
code += '0'
elif letter == 'A':
code += '4'
elif letter == 'S' or letter == 's' or letter == '$':
code += '5'
elif letter == 'g':
code += '9'
elif letter == '&' or letter == 'R' or letter == '%' or letter == 'a':
code += '8'
elif letter == '>' or letter == '?' or letter == ')':
code += '7'
elif letter == 'I' or letter == 'l':
code += '1'
elif letter == 'G' or letter == 'U':
code += '6'
# else:
# code += letter
return (code, img)
def phenotype(self):
pyautogui.PAUSE = 1
counter = 0
for i in self.__genoUnitCollection:
i.phenotype()
if counter % 5 == 0:
# Grab screenshot and crop score area
screenshot = ImageGrab.grab()
scoreRectangle = (560, 650, 660, 680)
cropped_rectangle = screenshot.crop(scoreRectangle)
# Filter and enhance area to better recognize digits
cropped_rectangle = cropped_rectangle.filter(
ImageFilter.MedianFilter())
enhancer = ImageEnhance.Contrast(cropped_rectangle)
cropped_rectangle = enhancer.enhance(2)
cropped_rectangle = cropped_rectangle.convert('1')
text = image_to_string(cropped_rectangle)
# Remove non-digits from score
all = string.maketrans('', '')
nodigits = all.translate(all, string.digits)
# Convert to Int and save as Fitness
if text.translate(all, nodigits) == '':
break
self.__fitness = int(text.translate(all, nodigits))
counter += 1
def check_picture_action(self):
print 'taking picture of check'
time = str(datetime.now())
camera = picamera.PiCamera()
camera.start_preview(fullscreen = False, window=(400, 400, 640, 480))
waiter = pic_window(self)
self.wait_window(waiter.top)
camera.capture(time+'.jpg')
camera.stop_preview()
im = Image.open(time+".jpg")
text = image_to_string(im)
im = im.resize((480, 270), Image.ANTIALIAS)
photo = ImageTk.PhotoImage(im)
self.df_pic_label.config(image = photo)
self.df_pic_label.photo = photo
try:
self.deposit_amount = int(text)
self.df_value_label.config("$"+monies+" detected")
except:
self.df_value_label.config("No money detected")
def getCode(self, im):
im = im.convert('L')
im = im.point(lambda x:255 if x > 128 else x)
im = im.point(lambda x:0 if x < 255 else 255)
box = (2, 2, im.size[0] - 2, im.size[1] - 2)
im = im.crop(box)
code = pytesser.image_to_string(im).replace(' ', '').strip()
return code
def __getvldcode(self):
cont = requests.get(url('vld.bmp?0.30659009179925256'),
data='0.30659009179925256',
headers=self.header)
f = open('tmp.bmp', 'wb').write(cont.content)
img = Image.open('tmp.bmp').resize((72, 18), Image.ANTIALIAS)
vcode = pytesser.image_to_string(img).strip()
return vcode
def image_process_extract_string(s, mask, x, y, w, h):
im = mask[y:y + h, x:x + w]
cv2.imwrite(s, im)
size = 2 * w, 2 * h
im = Image.open(s)
im_resized = im.resize(size, Image.ANTIALIAS)
im_resized.save(s, dpi=(100, 100))
return pytesser.image_to_string(s, 6)
def checkObjTitle(self, a_str):
# gets object title & compares the text
self.updateImg()
self.cropImg(Coords.obj_title_box)
img_str = pytesser.image_to_string(self.img)
if a_str.lower() in img_str.lower():
return True
return False
def get_captcha():
CAPTCHA=""
while CAPTCHA == "":
req=urllib2.Request(ipclient_init.CAPTCHA_URL,'',ipclient_init.HEADER)
gif=opener.open(req)
f=open(os.path.join(ipclient_init.CAPTCHA_PATH,'captcha.gif'),'wb')
f.write(gif.read())
f.close()
CAPTCHA = pytesser.image_to_string('./captcha.gif')
return CAPTCHA
def write():
text = ""
if request.method == 'POST':
file = request.files['file']
if file and allowed_file(file.filename):
filestream = file.read()
im = Image.open(StringIO(filestream))
text = pytesser.image_to_string(im)
return render_template('write.html', text = text)
return render_template("write.html",text=text)
def __init__(self, img):
self.img = img
## Screenshot Resolution
iQuestion = img.crop((0, 120, 640, 400))
iAnswerA = img.crop((55, 410, 585, 565))
iAnswerB = img.crop((55, 590, 585, 745))
iAnswerC = img.crop((55, 770, 585, 925))
iAnswerD = img.crop((55, 950, 585, 1105))
## Q2
# iQuestion = img.crop((50, 80, 480, 200))
# img = img.filter(ImageFilter.MinFilter(3))
# iAnswerA = img.crop((55, 200, 480, 300))
# iAnswerB = img.crop((55, 300, 480, 400))
# iAnswerC = img.crop((55, 400, 480, 500))
# iAnswerD = img.crop((55, 500, 480, 600))
self.tQuestion = pytesser.image_to_string(iQuestion)
self.tAnswerA = pytesser.image_to_string(iAnswerA)
self.tAnswerB = pytesser.image_to_string(iAnswerB)
self.tAnswerC = pytesser.image_to_string(iAnswerC)
self.tAnswerD = pytesser.image_to_string(iAnswerD)
# def ParseImage(self, img):
# Screenshot Resolution
# iQuestion = img.crop((0, 120, 640, 400))
# iAnswerA = img.crop((55, 410, 585, 565))
# iAnswerB = img.crop((55, 590, 585, 745))
# iAnswerC = img.crop((55, 770, 585, 925))
# iAnswerD = img.crop((55, 950, 585, 1105))
pyplot.imshow(iQuestion)
pyplot.show()
pyplot.imshow(iAnswerA)
pyplot.show()
pyplot.imshow(iAnswerB)
pyplot.show()
pyplot.imshow(iAnswerC)
pyplot.show()
pyplot.imshow(iAnswerD)
pyplot.show()
def get_captcha():
CAPTCHA = ""
while CAPTCHA == "":
req = urllib2.Request(ipclient_init.CAPTCHA_URL, '',
ipclient_init.HEADER)
gif = opener.open(req)
f = open(os.path.join(ipclient_init.CAPTCHA_PATH, 'captcha.gif'), 'wb')
f.write(gif.read())
f.close()
CAPTCHA = pytesser.image_to_string('./captcha.gif')
return CAPTCHA
def isHungry(self):
# needs testing
self.updateImg()
self.cropImg(Coords.current_hunger_box)
img_str = pytesser.image_to_string(self.img)
img_str = letter_to_snumb(img_str) # uses the func I made to convert letter o to number 0 in a string
print img_str # debug
hunger = int(img_str) # uses the func get_int from string_to_int.py that I created
if hunger <= 300:
return True
return False
def OCR2(filename):
# Converts tiff image to text format using pytesser
pdf = PythonMagick.Image(filename)
pdf.write(filename[0:-3] + "png")
print(filename[0:-3] + "png")
im = Image.open(filename)
text = image_to_string(im)
print text
return(text)
def __init__(self, img):
self.img = img
## Screenshot Resolution
iQuestion = img.crop((0, 120, 640, 400))
iAnswerA = img.crop((55, 410, 585, 565))
iAnswerB = img.crop((55, 590, 585, 745))
iAnswerC = img.crop((55, 770, 585, 925))
iAnswerD = img.crop((55, 950, 585, 1105))
## Q2
# iQuestion = img.crop((50, 80, 480, 200))
# img = img.filter(ImageFilter.MinFilter(3))
# iAnswerA = img.crop((55, 200, 480, 300))
# iAnswerB = img.crop((55, 300, 480, 400))
# iAnswerC = img.crop((55, 400, 480, 500))
# iAnswerD = img.crop((55, 500, 480, 600))
self.tQuestion = pytesser.image_to_string(iQuestion)
self.tAnswerA = pytesser.image_to_string(iAnswerA)
self.tAnswerB = pytesser.image_to_string(iAnswerB)
self.tAnswerC = pytesser.image_to_string(iAnswerC)
self.tAnswerD = pytesser.image_to_string(iAnswerD)
# def ParseImage(self, img):
# Screenshot Resolution
# iQuestion = img.crop((0, 120, 640, 400))
# iAnswerA = img.crop((55, 410, 585, 565))
# iAnswerB = img.crop((55, 590, 585, 745))
# iAnswerC = img.crop((55, 770, 585, 925))
# iAnswerD = img.crop((55, 950, 585, 1105))
pyplot.imshow(iQuestion)
pyplot.show()
pyplot.imshow(iAnswerA)
pyplot.show()
pyplot.imshow(iAnswerB)
pyplot.show()
pyplot.imshow(iAnswerC)
pyplot.show()
pyplot.imshow(iAnswerD)
pyplot.show()
def ocr(self):
if not self.image:
return ""
image_path = self.image.path
text = pytesser.image_to_string(image_path)
text = os.linesep.join([s for s in text.splitlines() if s])
self.image_text = text
self.save()
os.remove(image_path)
return text
def ocr(self):
if not self.image:
return ""
image_path = self.image.path
text = pytesser.image_to_string(image_path)
text = os.linesep.join([s for s in text.splitlines() if s])
self.image_text = text
self.save()
os.remove(image_path)
return text
def ocr_question_extract(im):
# [email protected]:madmaze/pytesseract.git
global pytesser
try:
import pytesser
except:
print("[ERROR] pytesseract not installed")
return
im = im.crop((117, 0, 180, 30))
im = pre_ocr_processing(im)
im.show()
return pytesser.image_to_string(im, language='chi_sim').strip()
def __init__(self, img):
self.img = img
img = Image.fromarray(img)
iQuestion = img.crop((0, 90, 360, 220))
# iAnswerA = img.crop((40, 215, 330, 300))
# iAnswerB = img.crop((40, 310, 330, 400))
# iAnswerC = img.crop((40, 410, 330, 500))
# iAnswerD = img.crop((40, 510, 330, 600))
# iQuestion = img.crop((0, 500, 1500, 900))
iAnswerA = img.crop((510, 280, 780, 350))
iAnswerB = img.crop((510, 380, 780, 450))
iAnswerC = img.crop((510, 480, 780, 550))
iAnswerD = img.crop((510, 580, 780, 650))
# img = PIL.ImageOps.autocontrast(iAnswerA)
# img = PIL.ImageOps.autocontrast(iAnswerB)
# img = PIL.ImageOps.autocontrast(iAnswerC)
# img = PIL.ImageOps.autocontrast(iAnswerD)
self.tQuestion = pytesser.image_to_string(iQuestion)
self.tAnswerA = pytesser.image_to_string(iAnswerA)
self.tAnswerB = pytesser.image_to_string(iAnswerB)
self.tAnswerC = pytesser.image_to_string(iAnswerC)
self.tAnswerD = pytesser.image_to_string(iAnswerD)
if debugImgCrop == True:
pyplot.imshow(iQuestion)
print self.tQuestion
pyplot.show()
pyplot.imshow(iAnswerA)
print self.tAnswerA
pyplot.show()
pyplot.imshow(iAnswerB)
print self.tAnswerB
pyplot.show()
pyplot.imshow(iAnswerC)
print self.tAnswerC
pyplot.show()
pyplot.imshow(iAnswerD)
print self.tAnswerD
pyplot.show()
def __init__(self, img):
self.img = img
img = Image.fromarray(img)
iQuestion = img.crop((0, 90, 360, 220))
# iAnswerA = img.crop((40, 215, 330, 300))
# iAnswerB = img.crop((40, 310, 330, 400))
# iAnswerC = img.crop((40, 410, 330, 500))
# iAnswerD = img.crop((40, 510, 330, 600))
# iQuestion = img.crop((0, 500, 1500, 900))
iAnswerA = img.crop((510, 280, 780, 350))
iAnswerB = img.crop((510, 380, 780, 450))
iAnswerC = img.crop((510, 480, 780, 550))
iAnswerD = img.crop((510, 580, 780, 650))
# img = PIL.ImageOps.autocontrast(iAnswerA)
# img = PIL.ImageOps.autocontrast(iAnswerB)
# img = PIL.ImageOps.autocontrast(iAnswerC)
# img = PIL.ImageOps.autocontrast(iAnswerD)
self.tQuestion = pytesser.image_to_string(iQuestion)
self.tAnswerA = pytesser.image_to_string(iAnswerA)
self.tAnswerB = pytesser.image_to_string(iAnswerB)
self.tAnswerC = pytesser.image_to_string(iAnswerC)
self.tAnswerD = pytesser.image_to_string(iAnswerD)
if debugImgCrop == True:
pyplot.imshow(iQuestion)
print self.tQuestion
pyplot.show()
pyplot.imshow(iAnswerA)
print self.tAnswerA
pyplot.show()
pyplot.imshow(iAnswerB)
print self.tAnswerB
pyplot.show()
pyplot.imshow(iAnswerC)
print self.tAnswerC
pyplot.show()
pyplot.imshow(iAnswerD)
print self.tAnswerD
pyplot.show()
def image_process_extract_string(s, mask, x, y, w, h):
Y = y
X = x
if Y - 10 >= 0:
Y = Y - 10
if X - 10 >= 0:
X = X - 10
im = mask[y: y + h, x: x + w]
cv2.imwrite(s, im)
size = 2 * w, 2 * h
im = Image.open(s)
im_resized = im.resize(size, Image.ANTIALIAS)
im_resized.save(s, dpi=(100, 100))
return pytesser.image_to_string(s, 6)
def parseTextos():
for file in listdir("tinder_uah"):
try:
img = cv2.imread("tinder_uah/" + file)
#img = Image.open("tinder_uah/"+file)
if img is not None:
txt = pytesser.image_to_string(
img, "spa") #Analyse image as a spanish word
parsed_txt = txt.encode('cp1252').decode('utf8')
text.append(
p.limpiar((parsed_txt.replace("\n", " ")).replace(
" ", "."))) # Hacemos el texto legible, lo limpiamos
except (UnicodeDecodeError, UnicodeError) as e:
print(str(e))
print(file, "Descartado")
continue
def getImageCodeAndCookie(self):
try:
im = self.opener.open(self.imageUrl).read() #获取验证码和cookies值
img_buffer = StringIO.StringIO(im)
img = Image.open(img_buffer)
textcode = pytesser.image_to_string(img)
print 'Cookies:'
for item in self.cookieJar:
if item.name =='ASP.NET_SessionId':
self.sessionId = item.value
print ' Name = '+item.name
print ' Value = '+item.value
print 'ImageCode=',textcode
return textcode
except Exception as e:
print 'Failed to get imagecode!', e
return ''
def identifyCode(codename):
# 二值化
threshold = 140
table = []
for i in range(256):
if i < threshold:
table.append(0)
else:
table.append(1)
im=Image.open(codename)
imgry = im.convert('L')
imgry.save('g'+codename)
out = imgry.point(table,'1')
out.save('b'+codename)
os.chdir("D:\\Python27\\Lib\\site-packages\\pytesser_v0.0.1")
text=pytesser.image_to_string(out)
return text
def tesser_engine(image_file_name, image_resize_procent = 250, corrector=corrector_globalsources):
"""
Распознавание
"""
email_image = Image.open(image_file_name)
image_size_x, image_size_y = email_image.size
image_size_x *= image_resize_procent/100
image_size_y *= image_resize_procent/100
email_image = email_image.resize((image_size_x, image_size_y))
email_text = pytesser.image_to_string(email_image)
email_text = email_text.strip()
email_text = corrector(email_text)
try:
email_text_unicode = unicode(email_text)
except UnicodeDecodeError:
print 'can not convert:', email_text,
email_text_unicode = ''
return email_text_unicode
def verify(name):
#打开图片
im = Image.open(name)
#转化到亮度
imgry = im.convert('L')
#imgry.save('a' + name)
#二值化
out = imgry.point(table, '1')
#out.save('b' + name)
out = rec(out)
#out.save('c' + name)
#识别
text = image_to_string(out)
#识别对吗
text = text.strip()
text = text.upper()
#os.system('rm '+name)
return text[0:4]
def verify(name):
#打开图片
im = Image.open(name)
#转化到亮度
imgry = im.convert('L')
#imgry.save('a' + name)
#二值化
out = imgry.point(table, '1')
#out.save('b' + name)
out = rec(out)
#out.save('c' + name)
#识别
text = image_to_string(out)
#识别对吗
text = text.strip()
text = text.upper()
#os.system('rm '+name)
return text[0:4]
def tesser_engine(image_file_name,
image_resize_procent=250,
corrector=corrector_globalsources):
"""
Распознавание
"""
email_image = Image.open(image_file_name)
image_size_x, image_size_y = email_image.size
image_size_x *= image_resize_procent / 100
image_size_y *= image_resize_procent / 100
email_image = email_image.resize((image_size_x, image_size_y))
email_text = pytesser.image_to_string(email_image)
email_text = email_text.strip()
email_text = corrector(email_text)
try:
email_text_unicode = unicode(email_text)
except UnicodeDecodeError:
print 'can not convert:', email_text,
email_text_unicode = ''
return email_text_unicode
def getCode(self):
codeUrl = 'http://uems.sysu.edu.cn/elect/login/code'
loginUrl = "http://uems.sysu.edu.cn/elect/login"
print u'加载验证码...'
while True:
try:
open(get_desktop() + "\code.jpeg",
"wb").write(urllib2.urlopen(codeUrl).read())
try:
im = Image.open(get_desktop() + '\code.jpeg').convert('L')
im = im.point(lambda x: 255 if x > 128 else x)
im = im.point(lambda x: 0 if x < 255 else 255)
box = (2, 2, im.size[0] - 2, im.size[1] - 2)
im = im.crop(box)
j_code = pytesser.image_to_string(im).replace(
' ', '').replace(']',
'J').replace('0',
'O').strip().upper()
print u'自动识别验证码...'
except Exception, e:
j_code = raw_input(
u'请输入桌面的code.jpeg所对应的验证码(不分大小写): '.encode(
self.coding)).upper().strip()
postData = 'username='******'&password='******'&j_code=' + j_code + '<=&_eventId=submit&gateway=true'
res = urllib2.urlopen(loginUrl, postData)
html = BeautifulSoup(res.read(), "html.parser")
self.sid = html.select('input[id=sid]')[0]['value']
if self.sid != '':
self.xnd = html.select('input[id=xnd]')[0]['value']
self.xq = html.select('input[id=xq]')[0]['value']
print u'登录成功'
if os.path.exists(get_desktop() + '\student.txt') == False:
demjson.encode_to_file(get_desktop() + '\student.txt',
{self.stuNum: self.password})
print u'账号密码已存于桌面文件student.txt,下次可直接登录!!!\n'
break
except urllib2.HTTPError, e:
print u'登录失败,重新加载验证码...'
time.sleep(1.0)
def verification(jpgName):
'''
验证码识别
'''
# Step 1 打开图像
im = Image.open(jpgName)
# Step 2 把彩色图像转化为灰度图像,转化到亮度
imgry = im.convert('L')
# imgry.save('g'+jpgName)
# Step 3 需要把图像中的噪声去除掉
threshold = 140
table = []
for i in xrange(256):
if i < threshold:
table.append(0)
else:
table.append(1)
# 二值化
out = imgry.point(table, '1')
# out.save('b'+jpgName)
# Step 4 把图片中的字符转化为文本,识别
text = image_to_string(out)
# Step 5 优化。根据观察，验证码中只有数字，并且上面的文字识别程序经常把8识别为S
rep = {
'O': '0', 'I': '1', 'L': '1', 'Z': '2', 'S': '8'
}
text = text.strip()
text = text.upper()
for r in rep:
text = text.replace(r, rep[r])
return text
def ocr():
print "OCR..."
# 二值化初始化
threshold = 127
table = []
for i in range(256):
if i < threshold:
table.append(0)
else:
table.append(1)
# 替换表初始化
rep = {'A': '6', 'E': '6', 'I': '1', 'O': '0', 'S': '8', '£': '8'}
rgb = Image.open('img.gif').convert('RGB')
for x in range(200):
for y in range(30):
(r, g, b) = rgb.getpixel((x, y))
if r in (51, 102, 153, 204, 255) \
and g in (43, 85, 128, 170, 213, 255) \
and b in (51, 102, 153, 204, 255):
rgb.putpixel((x, y), (255, 255, 255))
rgb = rgb.convert('L').point(table, '1')
# rgb.show()
code = pytesser.image_to_string(rgb)
result = ''
for words in code.splitlines():
result += words
result = ''.join(result.split()).upper()
for r in rep:
result = result.replace(r, rep[r])
result = filter(str.isdigit, result)
reg = r'^(\d{6})$'
try:
result = re.match(reg, result).group(1)
except:
print "Error occurred in OCR."
rgb.close()
return "Error"
rgb.close()
return result
def ocr(self):
# We can use this to stop ourselves getting into an infinite loop.
self.iteration += 1
# Get the co-ordinates for the "Nexus 5" window and the crop to just
# the letters of the app.
bbox = win32gui.GetWindowRect(win32gui.FindWindow(None, "Nexus 5"))
bbox = (bbox[0] + 45, bbox[1] + 325, bbox[2] - 70, bbox[3] - 200)
# Bring the application to the front.
shell = win32com.client.Dispatch("WScript.Shell")
shell.AppActivate("Nexus 5")
grab = ImageGrab.grab(bbox)
# Convert all non-white pixels to black, this greatly improves the
# effectiveness of the OCR library.
data = grab.getdata()
new_data = []
for item in data:
if item != (255, 255, 255):
new_data.append((0, 0, 0))
else:
new_data.append((255, 255, 255))
grab.putdata(new_data)
text = image_to_string(grab).strip().lower()
# Only try and solve if we have 9 letters, otherwise try to OCR again.
if len(text) == 9:
Countdown(text)
else:
print 'Bad length, was {}. Detected {}'.format(len(text), text)
if self.iteration < 5:
self.ocr()
def login(self):
r = self.s.get(ZHYCW.LOGIN_URL_GET)
print r.text
r = self.s.get('http://passport.chinahr.com/m/genpic')
i = Image.open(StringIO(r.content))
i.show()
imgCode = pytesser.image_to_string(i)
print '-->', imgCode
params = {
'backUrl': "http://www.chinahr.com/shenzhen/",
'from': '',
'imgCode': imgCode,
'input': '15728567842',
'pwd': "31af4a634cf808c8a7572b741dec6234b751165471560d368e4dd8fb84428c3db240c478a9d1afb455c9\
e5235d84dd51bdc8ddf1fc621b3b0d4a10664ff13cd3846804a242d0cb7fab7a88f82d9e71ae6bc815d0191691\
532bfd45c8ee3955250f17b50d16e76c937ab7de4a0aa4ae1040ee50465a45c753e2a8909016a04291",
'rember': '1'
}
r = self.s.post(ZHYCW.LOGIN_URL_POST, data=params)
print r.text
def getValidator():
url = 'http://yjxt.bupt.edu.cn/Public/ValidateCode.aspx?image=1079919554'
request = urllib2.Request(url)
response = urllib2.urlopen(request)
text = response.read()
fd=open('validator.png','wb')
fd.write(text)
fd.close()
threshlod = 200
table=[]
for i in range(256):
if i<threshlod:
table.append(0)
else:
table.append(1)
name = 'validator.png'
im = Image.open(name)
imgry = im.convert('L')
imgry.save('g'+name)
out = imgry.point(table,'1')
text = pytesser.image_to_string(out)[:4]
return text
# -*- coding: utf-8 -*-
"""
Created on Tue Jun 30 15:59:37 2015
@author: James
"""
import PIL
from pytesser import image_to_string
print int('50\n\n')
print range(1)
img = PIL.Image.open('numb_in_pic.png')
print (image_to_string(img))
def sudokuSolve(img):
ticks=time.time()
gray = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)
gray = cv2.GaussianBlur(gray,(5,5),0)
thresh = cv2.adaptiveThreshold(gray,255,1,1,11,2)
hierarchy,contours,_ = cv2.findContours(thresh, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
biggest = None
max_area = 0
for i in contours:
area = cv2.contourArea(i)
if area > 100:
peri = cv2.arcLength(i,True)
approx = cv2.approxPolyDP(i,0.02*peri,True)
if area > max_area and len(approx)==4:
biggest = approx
max_area = area
cv2.drawContours(img, biggest, -1, (0,255,0), 8)
biggest=rectify(biggest)
thresh = cv2.adaptiveThreshold(gray,255,1,1,11,2)
h = np.array([ [0,0],[449,0],[449,449],[0,449] ],np.float32)
retval = cv2.getPerspectiveTransform(biggest,h)
warp = cv2.warpPerspective(thresh,retval,(450,450))
cv2.imwrite('box.jpg',warp)
# mask=cv2.imread('mask.jpg')
# mask = cv2.cvtColor(mask,cv2.COLOR_BGR2GRAY)
# ret, mask = cv2.threshold(mask, 10, 255, cv2.THRESH_BINARY)
# i was trying something else!
for y in range (0,9):
for x in range (0,9) :
morph=warp[(50*y):((50*y)+50),(50*x):((50*x)+50)]
morph=morph[5:45,5:45]
cv2.imwrite('sudokuDigits/cell'+str(y)+str(x)+'.jpg',morph)
y=0
x=0
text=''
fullResult=''
print "| Recognizing Numbers. . . . "
keys = [i for i in range(48,58)]
for y in range (0,9):
for x in range (0,9) :
im = Image.open('sudokuDigits/cell'+str(y)+str(x)+'.jpg')
text =pytesser.image_to_string(im)
if text=='\n' or ord(text[0]) not in keys:
fullResult=fullResult+'0'
else:
fullResult=fullResult+str(text[0])
print "Detected Game!"
for i in range(0,81):
print fullResult[i],
if (i+1)%9 == 0:
print ""
print ""
print "| Solving . . . ."
solve.r(fullResult)
timetaken=time.time()-ticks
print "SolvedIn>> "+str(timetaken)+"secs"
for x in xrange(im.size[0]):
if pixdata[x, y][0] < 90:
pixdata[x, y] = (0, 0, 0, 255)
for y in xrange(im.size[1]):
for x in xrange(im.size[0]):
if pixdata[x, y][1] < 136:
pixdata[x, y] = (0, 0, 0, 255)
for y in xrange(im.size[1]):
for x in xrange(im.size[0]):
if pixdata[x, y][2] > 0:
pixdata[x, y] = (255, 255, 255, 255)
#box = (0,0,sizey,sizex)
box = (2, 2, sizey - 2, sizex - 2)
region = im.crop(box)
region.save("input-black.jpg", "jpeg")
im_orig = Image.open('input-black.jpg')
#big = im_orig.resize((540, 160), Image.NEAREST)
#big.show()
#big.save("test.bmp")
file_o.write(pytesser.image_to_string(im_orig))
file_o.close()
"""
imageSize = (20, 58)
image = Image.frombytes('RGB', imageSize, rawData, "F;16")
image.save("foo.png")
"""
from PIL import Image
from pytesser import image_to_string
import pyscreenshot as ImageGrab
import time
import sys
# Captures Screenshot
if __name__ == "__main__":
driver.get(url)
time.sleep(5)
t_end = time.time() + 60 * 2
counter = 1
while time.time() < t_end:
im = ImageGrab.grab(bbox=(80, 170, 400, 400))
im.show()
ImageGrab.grab_to_file("im" + str(counter) + ".png")
counter = counter + 1
counter = counter + 1
for num in range(counter):
im = Image.open("C:\Users\Tomonari\Desktop\seizureDection" + "\im" +
str(counter) + ".png")
text = image_to_string(im.convert('RGB'))
busted = text.strip()
busted = busted[8:-1]
print busted.strip()
def getverify1():
headers_1 = {
'Accept':'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8',
'Accept-Encoding':'gzip, deflate, sdch',
'Accept-Language':'zh-CN,zh;q=0.8',
'Connection':'keep-alive',
'Cookie':'loginInfo=TrZ8QGOkMeDViIlqMt8yaddowAuqeCbj+xWgsjQMFHHolBC5kzI+KONdjuAU/ARb; md=341C882D880E8E665AAC53AC1F31B570B6817396',
'Host':'125.88.59.131:10001',
'Upgrade-Insecure-Requests':'1',
'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/50.0.2661.102 Safari/537.36'
}
threshold = 140
table = []
for i in range(256):
if i < threshold:
table.append(0)
else:
table.append(1)
rep = {'O': '0',
'I': '1',
'L': '1',
'Z': '2',
'S': '8'
}
r = requests.get('http://125.88.59.131:10001/login.jsp?wlanuserip=10.101.187.210&wlanacip=113.98.13.29', headers=headers_1)
codecookies = r.cookies['JSESSIONID']
headers_2 = {
'Accept':'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8',
'Accept-Encoding':'gzip, deflate, sdch',
'Accept-Language':'zh-CN,zh;q=0.8',
'Cache-Control':'max-age=0',
'Connection':'keep-alive',
'Cookie':'loginInfo=TrZ8QGOkMeDViIlqMt8yaddowAuqeCbj+xWgsjQMFHHolBC5kzI+KONdjuAU/ARb; md=341C882D880E8E665AAC53AC1F31B570B6817396 ;JSESSIONID='+codecookies+'; signature=D0AB8BE4413F52D798C67E23DC8E8A78',
'Host':'125.88.59.131:10001',
'Referer':'http://125.88.59.131:10001/login.jsp?wlanuserip=10.101.187.210&wlanacip=113.98.13.29',
'Upgrade-Insecure-Requests':'1',
'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/50.0.2661.102 Safari/537.36'
}
timestamp = str(int(time.time()))
r = requests.get('http://125.88.59.131:10001/common/image.jsp?time='+timestamp, stream=True, headers=headers_2)
# r = requests.get('http://125.88.59.131:10001/common/image.jsp?time=1463198266151', stream=True, headers=headers)
try:
with open('image.jpg', 'wb') as f:
f.write(r.content)
f.close()
except IOError:
print("IO Error\n")
im = Image.open('image.jpg')
imgry = im.convert('L')
out = imgry.point(table, '1')
text = image_to_string(out)
text = text.strip()
text = text.upper()
for r in rep:
text = text.replace(r, rep[r])
#out.save(text+'.jpg')
print text
return text, codecookies
def save_captcha(s, link, filename):
r = s.get(link)
source = r.text.encode('utf-8')
source = source.split('base64,')[1]
source = source.split('" /><br>')[0]
with open(filename, 'wb') as f:
f.write(base64.b64decode(source))
pytesser.tesseract_exe_name = 'C:/Python27/Lib/site-packages/tesseract.exe'
filename = 'temp.png'
s = requests.Session()
save_captcha(s, 'http://challenge01.root-me.org/programmation/ch8/', filename)
imgx = Image.open(filename)
imgx = imgx.convert("RGBA")
pix = imgx.load()
for y in xrange(imgx.size[1]):
for x in xrange(imgx.size[0]):
if pix[x, y] == (0, 0, 0, 255):
pix[x, y] = (255, 255, 255, 255)
imgx.save("bw.gif", "GIF")
original = Image.open('bw.gif')
captcha = ''.join(pytesser.image_to_string(original).strip().split())
print captcha
r = s.post('http://challenge01.root-me.org/programmation/ch8/',
data={'cametu': captcha})
source = r.text.encode('utf-8')
print strip_tags(source)
def Procesar():
size = 1022, 653 #Size of image
ErrorCount = 0 # Error Counter
Success = 0 # Success Image
ErrorDesconocido = 0 # Unknown error
log = "" # Log string from Successful image process
errorlog = "" # Log string from ERROR image process
# Activate a button when Process is called
botonCinco = ttk.Button(ventana,
text="Ir a la carpeta procesada",
command=Function,
state=ACTIVE).place(height=30,
width=300,
x=240,
y=220)
origen = Origen.get() # Get text from Field Origen
destino = Destino.get() #Get text from Field destino
#Exception to create a directory
try:
directory = destino + "/Procesado" #Intenta crear el repositorio (carpeta) si no esta creado con el nombre Procesado
os.mkdir(directory)
except:
pass # If have lready created
location = directory + "/" # Specifies where the images created will be saved.
try:
Errores = location + "Errores" # Try to create the folder where the images are stored error
os.mkdir(Errores)
except:
pass # If have already created
location_two = Errores + "/" # Location from Errors
cnt = 1 # Rename string with errors counter to cast in advance
# Sum of elements in directory with extensions specified (.jpg, .png, etc)
suma = (len(glob.glob(origen + "*.jpg")) +
len(glob.glob(origen + "*.png")) +
len(glob.glob(origen + "*.jpeg")) +
len(glob.glob(origen + "*.gif")) +
len(glob.glob(origen + "*.wmp")))
if (suma != 0): # If sum isn't Zero
div = (740 / suma) # Make a div
# Critic Operation
for infile in glob.glob(origen + "*.jpg") or glob.glob(
origen + "*.png"
) or glob.glob(origen + "*.jpeg") or glob.glob(
origen + "*.gif"
) or glob.glob(
origen + "*.wmp"
): #Busca todos los archivos de la ubicacion especificada con la extension *.jpg
flag = 0 # Flag
progressbar.step(div) # Progressbar
ventana.update() # Update master Tk
# Evaluates and modifies the string to remove spaces and invalid characters in the path as Pytesser not process all the strings.
string = EvaluarString(infile)
#print infile # To debug
#print string # To debug
# Rename exception, if infile equals to string
try:
os.rename(infile, string)
infile = string
except:
pass # If infile is equals to string
im = Image.open(infile) # Open image File
#im.thumbnail(size, Image.ANTIALIAS) # Default size from image defined up
x, y, w, h = crop_image(
infile) # x, y, w, h get values from crop_image function return
# If success exception
if (x == 0 and y == 0 and w == 0 and h == 0):
ErrorDesconocido += 1 # Unknown error count ++
continue # Skip all below
#im.crop((int(x+x-x*0.20)+10, y+y/2+10, w+y, h - h/4 - 40)) # Default coordinates values
image = im.crop((x, y, w + x, y + h)) # Crop rectangle image.
im = image # im get image value
im.thumbnail(
size, Image.ANTIALIAS) # resize image to default size defined up
#im = im.crop((int(x*0.70)+10, y/2 + 10 , w , h/4 + 40)) # To debug
#im = im.crop((294, 135, 1022, 203)) # to debug
# Image crop with coordinates default
try:
im = im.crop((294, 100, 1022, 250))
except:
pass # If cant crop.
# To debug, coordinates default value
## x = int(x*0.70)+10
## y = y/2 + 10
## w = w
## h = h/4 + 40
#print x, y, w, h
#im = im[y: y+h/4, x+x/4:x+w+w/2]
#cv2.imshow('Load', im)
text = image_to_string(
im) # Image to text with pytesseract, return a string
## text = image_file_to_string(infile)
## text = image_file_to_string(infile, graceful_errors=True)
# print(text)
# Here ID digits are extracted to rename the file with
filename = Archivos(text, location)
if filename is None: # If cant get correct name returned
filename = "Error" + str(cnt) # file name get name
flag = 1 # Flag if error
if (flag == 0): # If not error
## T.insert(END, str(location) + str(filename) + ".jpg" + "\n") # To show in Text field
Success += 1 # Success count increases
T.insert(END, infile + "\n") # Show route from file in Text Field
#cv2.imwrite(location + filename + ".jpg", image)
# Exception if cant save image
try:
image.save(location + filename + ".jpg")
log += infile + "\n"
except:
ErrorDesconocido += 1 # Unknown error increases
pass
else: # If flag == 1, as ERROR
## T.insert(END, str(location_two) + str(filename) + ".jpg" + "\n")
ErrorCount += 1 # Error counter increases
T.insert(END, infile + " # Error" +
"\n") # Show route in textfield from error file
#cv2.imwrite(location_two + filename + ".jpg", image) #Exporta la imagen y la guarda con el nombre file que retorno el metodo Archivos
# Exception if cant save image
try:
image.save(location_two + filename + ".jpg")
errorlog += infile + "\n" # String for log
except:
ErrorDesconocido += 1
pass
cnt += 1
Log(log, errorlog, location) # Creates a log txt file in directory
root = Tk() # Creates a new window
ttk.Style().configure("Button",
padding=6,
relief="flat",
background="#ccc") # Window button
botonSalir = Button(root, text="OK", command=root.destroy) # Exit button
botonSalir.pack(side=BOTTOM) # Button position
root.title("Procesamiento de Datos OCR") # Window title
Area = Text(root, height=5, width=40) # Window size
Area.pack(side=LEFT) # TextField place
#Text area LOG
Area.insert(
END, "Imagenes Procesadas: " + str(suma) + "\nErrores: " +
str(ErrorCount) + "\nSatisfactoriamente Procesadas: " + str(Success) +
"\nSobreescritura (Repeticiones): " + str(suma -
(ErrorCount + Success)) +
"\nErroresDesconocidos: " + str(ErrorDesconocido))
progressbar.stop() # Progressbar stop
#T.config(state = "disable")
root.mainloop()
for y in xrange(image.size[1]):
for x in xrange(image.size[0]):
if is_white(pixdata[x, y]) | is_noise(pixdata, x, y):
pixdata[x, y] = white
else:
pixdata[x, y] = black
return image
def remove_line(image):
threshold = 100
pixdata = image.load()
# Clean the background noise, if color != black, then set to white.
for y in xrange(image.size[1]):
for x in xrange(image.size[0]):
if not (pixdata[x, y][0] > threshold and pixdata[x, y][1] > threshold and pixdata[x, y][2] > threshold):
pixdata[x, y] = (0, 0, 0, 255)
else:
pixdata[x, y] = (255, 255, 255, 255)
image = Image.open('2.jpg')
image = remove_noise(image)
for i in xrange(5):
image = remove_noise(image)
image.show()
print(pytesser.image_to_string(image))
def OCR(img):
print img
#im = PIL.Image.open(img) #.convert()
im = Image.open(img) #.convert()
textcode = pytesser.image_to_string(im)
return textcode
#!/usr/bin/python
import pytesser
import gtk.gdk
import os
# take a screenshot
def screenshot():
w = gtk.gdk.get_default_root_window()
sz = w.get_size()
pb = gtk.gdk.Pixbuf(gtk.gdk.COLORSPACE_RGB, False, 8, sz[0], sz[1])
pb = pb.get_from_drawable(w,w.get_colormap(), 0, 0, 0, 0, sz[0], sz[1])
if (pb != None):
pb.save("screenshot.png","png")
else:
print "Unable to get the screenshot."
if __name__ == "__main__":
screenshot()
print "working..."
txt = pytesser.image_to_string("screenshot.png")
os.remove("screenshot.png")
print txt
startNums = []
tmp = []
tmparray = []
for j in range(len(test)):
image = test[j]
for i in range(len(image)):
tmparray.append(image[i])
if (i+1)%28==0:
tmp.append(tmparray)
tmparray = []
tmp = np.array(tmp)
#tmp = hf.erode(hf.dilate(tmp))
cv2.imwrite('tmp.png',tmp)
imagefile = Image.open('tmp.png')
tekst = pytesser.image_to_string(imagefile)
tekst = tekst.translate(None,'\n')
tekst = tekst.translate(None,',')
if tekst == '\"I':
tekst = '1'
elif tekst == 'Z':
tekst = '2'
elif tekst == '`I':
tekst = '1'
elif tekst == 'S':
tekst = '5'
elif tekst == "'I":
tekst = '1'
elif tekst == 'I':
from PIL import Image
from pytesser import image_to_string
im = Image.open('abc.png')
# im.save('11.tif')
# im = Image.open('11.tif')
p = image_to_string(im)
print p
# or (r, g, b) == (255, 255, 204) or (r, g, b) == (204, 170, 153) or (r, g, b) == (255, 213, 204) \
# or (r, g, b) == (204, 255, 204) or (r, g, b) == (153, 170, 153) or (r, g, b) == (204, 255, 255) \
# or (r, g, b) == (204, 213, 255) or (r, g, b) == (153, 213, 153) or (r, g, b) == (204, 213, 255) \
# or (r, g, b) == (153, 170, 204) or (r, g, b) == (153, 213, 204) or (r, g, b) == (204, 213, 153) \
# or (r, g, b) == (255, 255, 255):
# rgb.putpixel((x, y), (255, 255, 255))
# else:
# rgb.putpixel((x, y), (0, 0, 0))
if r in (51, 102, 153, 204,
255) and g in (43, 85, 128, 170, 213,
255) and b in (51, 102, 153, 204, 255):
rgb.putpixel((x, y), (255, 255, 255))
rgb = rgb.convert('L').point(table, '1')
# rgb.show()
image.close()
code = pytesser.image_to_string(rgb)
result = ''
for words in code.splitlines():
result += words
result = ''.join(result.split()).upper()
for r in rep:
result = result.replace(r, rep[r])
result = filter(str.isdigit, result)
reg = r'^(\d{6})$'
try:
result = re.match(reg, result).group(1)
except:
result = "Error occurred in OCR."
print i, result
print "success"
from pytesser import image_to_string import Image import ImageOps import ImageGrab print image_to_string( )
#coding=utf8
from PIL import Image
from pytesser import image_to_string
import requests
import time
PATH ="vcode.png"
r = requests.Session()
while True:
c=r.get("http://www.hualixy.com/inc/checkcode.asp?r=%s"%time.time()).content
#print(c)
with open(PATH,'wb') as f:
f.write(c)
f.close()
code = image_to_string(Image.open(PATH)).strip()
print(code)
只有 “pytesser-v0.0.1”字符串。(没有引号)
"""
#我主机python2.7这个版本无法安装PIL
#说明pytesser使用的网址如下：
#http://www.cnblogs.com/txw1958/archive/2012/08/09/python-PyTesser.html
import Image
import socket
import base64
import pytesser
sock=socket.socket(socket.AF_INET,socket.SOCK_STREAM)
sock.connect(('41.231.53.40',9090))
c=''
while True:
t=sock.recv(100)
c=c+t
if len(t)<100:
break
with open('t.png','wb').write(base64.decodestring(c[:---8]))
img=Image.new('RGB',(160,20))#创建一个新的图片
out=img.load()
pix=Image.open('t.png').load()
for i in xrange(20):
if reduce(lambda x,y:x+y,pix[105+j,190-i]+pix[94-j,9+j])<1000:
out[i,j]=(255,255,255)
ans=pytesser.image_to_string(img)
print ans
sock.send(ans)
print sock.recv(1024)
img_data = base64.b64decode(img_coded)
f = open("img","w+")
f.write(img_data)
f.close()
image = Image.open("img")
image1 = image.convert("RGBA")
pixdata = image1.load()
#if noise then trying to clean it out
if noise=="yes":
for y in xrange(image1.size[1]):
for x in xrange(image1.size[0]):
if pixdata[x, y] == (0, 0, 0, 255):
pixdata[x, y] = (255, 255, 255, 255)
image1.save("result.gif","gif")
image_final = Image.open("result.gif")
captcha = pytesser.image_to_string(image_final).strip()
print "[*] captcha found is "+captcha
data = {
"cametu":captcha
}
#getting the cookies
result = requests.post(URL, data=data, cookies=cookies)
print result.text
res = open("results.html","w+")
res.write(result.text)
res.close()
print "[*] end with no errors"
for x in xrange(im.size[0]):
if pixdata[x, y][0] < 90:
pixdata[x, y] = (0, 0, 0, 255)
for y in xrange(im.size[1]):
for x in xrange(im.size[0]):
if pixdata[x, y][1] < 136:
pixdata[x, y] = (0, 0, 0, 255)
for y in xrange(im.size[1]):
for x in xrange(im.size[0]):
if pixdata[x, y][2] > 0:
pixdata[x, y] = (255, 255, 255, 255)
#box = (0,0,sizey,sizex)
box = (2, 2, sizey-2, sizex-2)
region = im.crop(box)
region.save("input-black.jpg", "jpeg")
im_orig = Image.open('input-black.jpg')
#big = im_orig.resize((540, 160), Image.NEAREST)
#big.show()
#big.save("test.bmp")
file_o.write(pytesser.image_to_string(im_orig))
file_o.close()
"""
imageSize = (20, 58)
image = Image.frombytes('RGB', imageSize, rawData, "F;16")
image.save("foo.png")
"""
def getCheckCodeStringWindows(self, imageObj:Image):
text = str(ocr.image_to_string(imageObj))
print("验证码: " + text)
text = text.strip()
return text
