您好,登錄后才能下訂單哦!
本文實例講述了Python3實現的簡單驗證碼識別功能。分享給大家供大家參考,具體如下:
這次的需求是自動登錄某機構網站, 其驗證碼很具特色, 很適合做驗證碼識別入門demo, 先貼主要代碼, 其中圖片對比使用了編輯距離算法, 腳本使用了pillow庫
from PIL import Image import requests import re splitter = re.compile(r'\d{30}') # 分割二值化后的圖片 # distance('11110000', '00000000') # 比較兩個字符串有多少位不同, 返回不同的位數 def distance(string1, string2): d_str1 = len(string1) d_str2 = len(string2) d_arr = [[0] * d_str2 for i in range(d_str1)] for i in range(d_str1): for j in range(d_str2): if string1[i] == string2[j]: if i == 0 and j == 0: d_arr[i][j] = 0 elif i != 0 and j == 0: d_arr[i][j] = d_arr[i - 1][j] elif i == 0 and j != 0: d_arr[i][j] = d_arr[i][j - 1] else: d_arr[i][j] = d_arr[i - 1][j - 1] else: if i == 0 and j == 0: d_arr[i][j] = 1 elif i != 0 and j == 0: d_arr[i][j] = d_arr[i - 1][j] + 1 elif i == 0 and j != 0: d_arr[i][j] = d_arr[i][j - 1] + 1 else: d_arr[i][j] = min(d_arr[i][j - 1], d_arr[i - 1][j], d_arr[i - 1][j - 1]) + 1 current = max(d_arr[d_str1 - 1][d_str2 - 1], abs(d_str2 - d_str1)) # print("Levenshtein Distance is",current) # print(current) return current # 去除字符串里面連續的1 def no_one(string): n_arr = splitter.findall(string) n_arr = filter(lambda each_str: each_str != '111111111111111111111111111111', n_arr) n_result = '' for n_each in n_arr: n_result += str(n_each) return n_result opener = requests.session() res = opener.get('http://60.211.254.236:8402/Ajax/ValidCodeImg.ashx').content with open('verify.gif', 'wb') as v: v.write(res) img = Image.open('verify.gif') img = img.convert('L') size = img.size # img = img.point(table, '1') img_arr = img.load() # for x in range(size[0]): # for y in range(size[1]): # if img_arr[x, y] > 210: # img_arr[x, y] = 1 # else: # img_arr[x, y] = 0 # img.save('after.gif') inc = 0 str1 = '' str2 = '' str3 = '' cur_str = '' for x in range(size[0]): for y in range(size[1]): if img_arr[x, y] > 210: cur_str += '1' else: cur_str += '0' # print(img_arr[i, j], end='') # cur_str += str(img_arr[x, y]) inc += 1 # if inc % 18 == 0: # print('\n----') # else: # print('') if inc == 18: str1 = cur_str cur_str = '' elif inc == 36: str2 = cur_str cur_str = '' elif inc == 54: str3 = cur_str cur_str = '' str1 = str1[:-60] str2 = str2[:-60] str3 = str3[:-60] str1 = no_one(str1) str2 = no_one(str2) str3 = no_one(str3) str1 = str1.strip('1') str2 = str2.strip('1') str3 = str3.strip('1') # print(str1) # print(str3) with open('./dict/plus') as plus: with open('./dict/minus') as minus: p = plus.read() m = minus.read() is_add = 1 if distance(p, str2) < distance(m, str2) else 0 arr1 = [] arr3 = [] for each in range(1, 10): with open('./dict/{}'.format(each)) as f: ff = f.read() arr1.append([each, distance(ff, str1)]) arr3.append([each, distance(ff, str3)]) arr1 = sorted(arr1, key=lambda item: item[1]) arr3 = sorted(arr3, key=lambda item: item[1]) result = arr1[0][0] + arr3[0][0] if is_add else arr1[0][0] - arr3[0][0] print(result) # login_url = 'http://60.211.254.236:8402/Ajax/Login.ashx?Method=G3_Login' # login_data = { # 'loginname': usn, # 'password': pwd, # 'validcode': result, # # } # opener.get(login_url, login_data)
字庫已經部署到GitHub地址:https://github.com/hldh314/validCode/
更多關于Python相關內容感興趣的讀者可查看本站專題:《Python圖片操作技巧總結》、《Python數據結構與算法教程》、《Python Socket編程技巧總結》、《Python函數使用技巧總結》、《Python字符串操作技巧匯總》、《Python入門與進階經典教程》及《Python文件與目錄操作技巧匯總》
希望本文所述對大家Python程序設計有所幫助。
免責聲明:本站發布的內容(圖片、視頻和文字)以原創、轉載和分享為主,文章觀點不代表本網站立場,如果涉及侵權請聯系站長郵箱:is@yisu.com進行舉報,并提供相關證據,一經查實,將立刻刪除涉嫌侵權內容。