#coding=utf-8
from captcha.image import ImageCaptcha # pip install captcha
import numpy as np
import matplotlib.pyplot as plt
from PIL import Image
import random

# 验证码中的字符, 就不用汉字了

number = ['0', '1', '2', '3', '4', '5', '6', '7', '8', '9']
alphabet = ['a', 'b', 'c', 'd', 'e', 'f', 'g', 'h', 'i', 'j', 'k', 'l', 'm', 'n', 'o', 'p', 'q', 'r', 's', 't', 'u',
      'v', 'w', 'x', 'y', 'z']

ALPHABET = ['A', 'B', 'C', 'D', 'E', 'F', 'G', 'H', 'I', 'J', 'K', 'L', 'M', 'N', 'O', 'P', 'Q', 'R', 'S', 'T', 'U',
      'V', 'W', 'X', 'Y', 'Z']
'''
number=['0','1','2','3','4','5','6','7','8','9']
alphabet =[]
ALPHABET =[]
'''

# 验证码一般都无视大小写；验证码长度4个字符
def random_captcha_text(char_set=number + alphabet + ALPHABET, captcha_size=4):
  captcha_text = []
  for i in range(captcha_size):
    c = random.choice(char_set)
    captcha_text.append(c)
  return captcha_text


# 生成字符对应的验证码
def gen_captcha_text_and_image():
  while(1):
    image = ImageCaptcha()

    captcha_text = random_captcha_text()
    captcha_text = ''.join(captcha_text)

    captcha = image.generate(captcha_text)
    #image.write(captcha_text, captcha_text + '.jpg') # 写到文件

    captcha_image = Image.open(captcha)
    #captcha_image.show()
    captcha_image = np.array(captcha_image)
    if captcha_image.shape==(60,160,3):
      break

  return captcha_text, captcha_image






if __name__ == '__main__':
  # 测试
  text, image = gen_captcha_text_and_image()
  print image
  gray = np.mean(image, -1)
  print gray

  print image.shape
  print gray.shape
  f = plt.figure()
  ax = f.add_subplot(111)
  ax.text(0.1, 0.9, text, ha='center', va='center', transform=ax.transAxes)
  plt.imshow(image)

  plt.show()

#coding=utf-8
from gen_captcha import gen_captcha_text_and_image
from gen_captcha import number
from gen_captcha import alphabet
from gen_captcha import ALPHABET

import numpy as np
import tensorflow as tf

"""
text, image = gen_captcha_text_and_image()
print "验证码图像channel:", image.shape # (60, 160, 3)
# 图像大小
IMAGE_HEIGHT = 60
IMAGE_WIDTH = 160
MAX_CAPTCHA = len(text)
print  "验证码文本最长字符数", MAX_CAPTCHA # 验证码最长4字符; 我全部固定为4,可以不固定. 如果验证码长度小于4，用'_'补齐
"""
IMAGE_HEIGHT = 60
IMAGE_WIDTH = 160
MAX_CAPTCHA = 4

# 把彩色图像转为灰度图像（色彩对识别验证码没有什么用）
def convert2gray(img):
  if len(img.shape) > 2:
    gray = np.mean(img, -1)
    # 上面的转法较快，正规转法如下
    # r, g, b = img[:,:,0], img[:,:,1], img[:,:,2]
    # gray = 0.2989 * r + 0.5870 * g + 0.1140 * b
    return gray
  else:
    return img


"""
cnn在图像大小是2的倍数时性能最高, 如果你用的图像大小不是2的倍数，可以在图像边缘补无用像素。
np.pad(image,((2,3),(2,2)), 'constant', constant_values=(255,)) # 在图像上补2行，下补3行，左补2行，右补2行
"""

# 文本转向量
char_set = number + alphabet + ALPHABET + ['_'] # 如果验证码长度小于4, '_'用来补齐
CHAR_SET_LEN = len(char_set)


def text2vec(text):
  text_len = len(text)
  if text_len > MAX_CAPTCHA:
    raise ValueError('验证码最长4个字符')

  vector = np.zeros(MAX_CAPTCHA * CHAR_SET_LEN)

  def char2pos(c):
    if c == '_':
      k = 62
      return k
    k = ord(c) - 48
    if k > 9:
      k = ord(c) - 55
      if k > 35:
        k = ord(c) - 61
        if k > 61:
          raise ValueError('No Map')
    return k

  for i, c in enumerate(text):
    #print text
    idx = i * CHAR_SET_LEN + char2pos(c)
    #print i,CHAR_SET_LEN,char2pos(c),idx
    vector[idx] = 1
  return vector

#print text2vec('1aZ_')

# 向量转回文本
def vec2text(vec):
  char_pos = vec.nonzero()[0]
  text = []
  for i, c in enumerate(char_pos):
    char_at_pos = i # c/63
    char_idx = c % CHAR_SET_LEN
    if char_idx < 10:
      char_code = char_idx + ord('0')
    elif char_idx < 36:
      char_code = char_idx - 10 + ord('A')
    elif char_idx  0.9:         ##我这里设了0.9，设得越大训练要花的时间越长，如果设得过于接近1，很难达到。如果使用cpu，花的时间很长，cpu占用很高电脑发烫。
          saver.save(sess, "crack_capcha.model", global_step=step)
          print time.time()-start_time
          break

      step += 1


train_crack_captcha_cnn()

output = crack_captcha_cnn()
saver = tf.train.Saver()
sess = tf.Session()
saver.restore(sess, tf.train.latest_checkpoint('.'))

while(1):
  

  text, image = gen_captcha_text_and_image()
  image = convert2gray(image)
  image = image.flatten() / 255

  predict = tf.argmax(tf.reshape(output, [-1, MAX_CAPTCHA, CHAR_SET_LEN]), 2)
  text_list = sess.run(predict, feed_dict={X: [image], keep_prob: 1})
  predict_text = text_list[0].tolist()

  vector = np.zeros(MAX_CAPTCHA * CHAR_SET_LEN)
  i = 0
  for t in predict_text:
    vector[i * 63 + t] = 1
    i += 1
    # break



  print("正确: {} 预测: {}".format(text, vec2text(vector)))