pythonを使用して認証コード識別を自動的に行います.しかし、正確には修正を手伝ってくれる大物が必要です.ありがとうございます.

この文章は転載するhttps://blog.csdn.net/weixin_38641983/article/details/80899354#commentseditここでとても感谢して、原文の作者は考えとコードを分かち合って、私は転载して、もし不当なところがあれば、私に连络して削除します.
上には原作者の考え方と過程がつながっている.自分で少し修正しました.しかし、まだ問題があります.

import requests
import time
from io import BytesIO
from PIL import Image
import os
import numpy as np

#         
CAPT_URL = "http://my.cnki.net/elibregister/CheckCode.aspx"

#         
CAPT_PATH = "capt/"
if not os.path.exists(CAPT_PATH):
    os.mkdir(CAPT_PATH)

#              "lookup table"
THRESHOLD = 165
LUT = [0]*THRESHOLD + [1]*(256 - THRESHOLD)

#         
def capt_fetch():
    """
            ，      Image  
    :require requests: import requests
    :require time: import time
    :require BytesIO: from io import BytesIO
    :require Image: from PIL import Image
    :param:
    :return capt:   Image  
    """
    #         
    capt_raw = requests.get(CAPT_URL)
    #             IO 
    f = BytesIO(capt_raw.content)
    #        Image  
    capt = Image.open(f)
    return capt

#         
def capt_download():
    """
     Image             
    :require Image: from PIL import Image
    :require os: import os
    :require capt_fetch():  nbsc       
    :require CAPT_PATH:        
    :param:
    :return: 
    """
    capt = capt_fetch()
    capt.show()
    text = input("          ：")
    suffix = str(int(time.time() * 1e3))
    capt.save(CAPT_PATH + text + "_" + suffix + ".jpg")

#      
def capt_process(capt):
    """
         ：             ，     
    :require Image: from PIL import Image
    :require LUT: A lookup table,   256  
    :param capt:    Image  
    :return capt_per_char_list:           ，                   
    """
    capt_gray = capt.convert("L")
    capt_bw = capt_gray.point(LUT, "1")
    capt_per_char_list = []
    for i in range(4):
        x = 5 + i * 15
        y = 2
        capt_per_char = capt_bw.crop((x, y, x + 15, y + 18))
        capt_per_char_list.append(capt_per_char)
    return capt_per_char_list

#          
def capt_inference(capt_per_char):
    """
          
    :require numpy: import numpy as np
    :param capt_per_char:              
    :return char_features:    ，   capt_per_char      
    """
    char_array = np.array(capt_per_char)
    total_pixels = np.sum(char_array)
    cols_pixels = np.sum(char_array, 0)
    rows_pixels = np.sum(char_array, 1)
    char_features = np.append(cols_pixels, rows_pixels)
    char_features = np.append(total_pixels, char_features)
    return char_features.tolist()

#      
def train():
    """
                         
    :require Image: from PIL import Image
    :require os: import os
    :require capt_process():      
    :require capt_inference():       
    :param:
    :return train_table:           
    :return train_labels:           
    """
    files = os.listdir(CAPT_PATH)
    train_table = []
    train_labels = []
    for f in files:
        train_labels += list(f.split("_")[0])
        capt = Image.open(CAPT_PATH + f)
        capt_per_char_list = capt_process(capt)
        for capt_per_char in capt_per_char_list:
            char_features = capt_inference(capt_per_char)
            train_table.append(char_features)
    return train_table, train_labels

#       
def nnc(train_table, test_vec, train_labels):
    """
    Nearest Neighbour Classification（     ），
                 ，              
    :require numpy: import numpy as np
    :param train_table:         
    :param test_vec:     ，             
    :param labels:          
    :return :             
    """
    dist_mat = np.square(np.subtract(train_table, test_vec))
    dist_vec = np.sum(dist_mat, axis = 1)
    pos = np.argmin(dist_vec)
    return train_labels[pos]

#         
def test():
    """
            
    :require Image: from PIL import Image
    :require capt_fetch():  nbsc       
    :require capt_process():      
    :require capt_inference():       
    :train_table, train_labels: train_table, train_labels = train()
    :param:
    :return capt:      
    :return test_labels:        
    """
    test_labels = []
    capt = capt_fetch()
    capt_per_char_list = capt_process(capt)
    for capt_per_char in capt_per_char_list:
        char_features = capt_inference(capt_per_char)
        label = nnc(train_table, char_features, train_labels)
        test_labels.append(label)
    test_labels = "".join(test_labels)
    return capt, test_labels

#     ，     
#   120      
for i in range(1):
    capt_download()

#         
train_table, train_labels = train()
test_capt, test_labels = test()

print(test_labels)

テストは50回のみで、正しく検証されたのは1回のみです.修正をお愿いします、ありがとうございます!!!