def crack(self):
result = []
# 加载数据
with open(os.path.join(current_dir, 'image_data.json'), 'r') as f:
image_data = json.load(f)
for letter in self.handle_split_image():
letter_vector = build_vector(letter)
guess = []
for image in image_data:
for x, y in image.items():
guess.append((distance_hanmming(y, letter_vector), x))
guess.sort()
result.append(guess[0][1])
return ''.join(result)
def crack(self):
# 装载训练数据集
with open(os.path.join(current_dir, 'imageset.dat'), 'rb') as f:
imageset = pickle.load(f)
# 对验证码图片进行切割
result = []
for letter in letters:
final = self.im.crop((letter[0], 0, letter[1], self.im.size[1]))
letter_vector = build_vector(final)
guess = []
# 将切割得到的验证码小片段与每个训练片段进行比较
for image in imageset:
for x, y in image.items():
guess.append((distance_cos(y, letter_vector), x))
guess.sort()
result.append(guess[0][1])
return "".join(result)
def crack(self):
result = []
# 加载数据
with open(os.path.join(current_dir, 'image_data.json'), 'rb') as f:
image_data = json.load(f)
for letter in self.handle_split_image():
letter_vector = build_vector(letter)
guess = []
for image in image_data:
for x, y in image.items():
guess.append((distance_hanmming(y, letter_vector), x))
guess.sort()
neighbors = guess[:15] # 距离最近的十五个向量
class_votes = {} # 投票
for neighbor in neighbors:
class_votes.setdefault(neighbor[-1], 0)
class_votes[neighbor[-1]] += 1
sorted_votes = sorted(class_votes.items(),
key=lambda x: x[1],
reverse=True)
result.append(sorted_votes[0][0])
return ''.join(result)
import os
import json
from PIL import Image
from njupt.utils.captchas import build_vector
if __name__ == "__main__":
# 字符集
letters = ['2', '3', '4', '5', '6', '7', '8', '9']
# 将图像数据转为向量数据并保存
image_data = []
for letter in letters:
for img in os.listdir('captcha_chars/{}/'.format(letter)):
if img != "Thumbs.db" and img != ".DS_Store":
temp = build_vector(
Image.open("captcha_chars/{}/{}".format(letter, img)))
image_data.append({letter: temp})
with open('image_data.json', 'w') as f:
json.dump(image_data, f)
import json
from io import BytesIO
import requests
from PIL import Image
from njupt import Library
from njupt.utils.captchas import build_vector
from njupt.utils.captchas.library.libray_captcha import LibraryCaptcha
if __name__ == "__main__":
image_data = []
for i in range(10):
r = requests.get(Library.URLs.CAPTCHA)
im = Image.open(BytesIO(r.content))
im.show()
captcha = LibraryCaptcha(image=im)
letters = input()
for letter, im in zip(letters, captcha.handle_split_image()):
vector = build_vector(im)
image_data.append({letter: vector})
with open('image_data.json', 'w') as f:
json.dump(image_data, f)