# !/usr/bin/python
# -*- coding: utf-8 -*-
"""
@author: chliang
@time: 2022/7/22 11:00
@describe: 识别图片字母和数字
"""
import os
import pytesseract
from PIL import Image
from collections import defaultdict
import base64
import re
import uuid
# 获取图片中像素点数量最多的像素
def get_threshold(image):
pixel_dict = defaultdict(int)
# 像素及该像素出现次数的字典
rows, cols = image.size
for i in range(rows):
for j in range(cols):
pixel = image.getpixel((i, j))
pixel_dict[pixel] += 1
count_max = max(pixel_dict.values()) # 获取像素出现出多的次数
pixel_dict_reverse = {v: k for k, v in pixel_dict.items()}
threshold = pixel_dict_reverse[count_max] # 获取出现次数最多的像素点
return threshold
# 按照阈值进行二值化处理
# threshold: 像素阈值
def get_bin_table(threshold):
# 获取灰度转二值的映射table
table = []
for i in range(256):
rate = 0.1 # 在threshold的适当范围内进行处理
if threshold * (1 - rate) <= i <= threshold * (1 + rate):
table.append(1)
else:
table.append(0)
return table
# 去掉二值化处理后的图片中的噪声点
def cut_noise(image):
rows, cols = image.size # 图片的宽度和高度
change_pos = [] # 记录噪声点位置
# 遍历图片中的每个点,除掉边缘
for i in range(1, rows - 1):
for j in range(1, cols - 1):
# pixel_set用来记录该店附近的黑色像素的数量
pixel_set = []
# 取该点的邻域为以该点为中心的九宫格
for m in range(i - 1, i + 2):
for n in range(j - 1, j + 2):
if image.getpixel((m, n)) != 1: # 1为白色,0位黑色
pixel_set.append(image.getpixel((m, n)))
# 如果该位置的九宫内的黑色数量小于等于4,则判断为噪声
if len(pixel_set) <= 4:
change_pos.append((i, j))
# 对相应位置进行像素修改,将噪声处的像素置为1(白色)
for pos in change_pos:
image.putpixel(pos, 1)
return image # 返回修改后的图片
# 识别图片中的数字加字母
# 传入参数为图片路径,返回结果为:识别结果
def discern_image(img_path):
image = Image.open(img_path) # 打开图片文件
imgry = image.convert('L') # 转化为灰度图
# 获取图片中的出现次数最多的像素,即为该图片的背景
max_pixel = get_threshold(imgry)
# 将图片进行二值化处理
# 注意,是否使用二值化要看具体情况,有些图片二值化之后,可能关键信息会丢失,反而识别不出来
table = get_bin_table(threshold=max_pixel)
out = imgry.point(table, '1')
# 去掉图片中的噪声(孤立点)
out = cut_noise(out)
# 保存图片
# out.save('E://figures/img_gray.jpg')
# 仅识别图片中的数字
# text = pytesseract.image_to_string(out, config='digits')
# 识别图片中的数字和字母
text = pytesseract.image_to_string(out)
# 去掉识别结果中的特殊字符
exclude_char_list = ' .:\\|\'\"?![],()~@#$%^&*_+-={};<>/¥'
text = ''.join([x for x in text if x not in exclude_char_list])
return text
def ocr(source):
# 1、信息提取
result = re.search("data:image/(?P<ext>.*?);base64,(?P<data>.*)", source, re.DOTALL)
if result:
# ext = result.groupdict().get("ext")
data = result.groupdict().get("data")
else:
raise Exception("Do not parse!")
# 2、base64解码
img = base64.urlsafe_b64decode(data)
# 3、二进制文件保存
filename = "{}.{}".format(uuid.uuid4(), 'png')
with open(filename, "wb") as f:
f.write(img)
# img = cv2.imread('./'+filename)
# imgtext = pytesseract.image_to_string(cv2.imread('./'+filename))
imgepath = './'+filename
imgtext = discern_image(imgepath)
if os.path.exists(imgepath):
os.remove(imgepath)
return imgtext
if __name__ == '__main__':
source = 'data:image/gif;base64,iVBORw0KGgoAAAANSUhEUgAAAGQAAAAeCAIAAABVOSykAAAAuElEQVR42u3YsQ3DIBBAUYbIXF4j\nK3gB9y6yiJUN3EUeJ00qy10Kw8Gd0BXAl36FEMUrDkSY5oOUBQjAAqtFrMfnKwVWLdaynVIDYSn3\nZ7Bir/31kxoLSxJUYt281vdTqjcsaT3pkvRqDEs53euxkuveNGB1OrNGxzLdhr3NrHqseDO3oeEJ\nqn9ntT3giy94E1ZxJ1jdYVkDyyuwXHLCyhzL519Z7W8HlsEOLP7gwQILLLAILLB8ugDQEuYGFO41\n5wAAAABJRU5ErkJggg=='
r = ocr(source)
print(r)
# !/usr/bin/python
# -*- coding: utf-8 -*-
"""
@author: chliang
@time: 2022/7/22 11:00
@describe:
"""
import logging
import os
import requests
from imageocr import ocr
logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(name)s - %(levelname)s - %(message)s')
logger = logging.getLogger(__name__)
ROOT_URL = 'https://xxxx'
LOGIN_NAME = 'xxxx'
PASSWORD = os.getenv('password')
class Login:
def __init__(self):
self.num = 0
self.HEADERS = {
'Referer': 'https://xxxx',
'User-Agent': 'xxxx'
}
def _get_image(self):
r = requests.get(url='https://xxxx/getImage', headers=self.HEADERS)
j = r.json()
image = j['object']['image']
img_text = ocr('data:image/gif;base64,'+image)
return {'code': img_text.strip()[0:4], 'session_id': j['object']['sessionId']}
def init_login(self):
def req():
token=''
num = 0
while (num < 10):
v = self._get_image()
logger.info(f"code={v['code']},session_id={v['session_id']}")
self.HEADERS['Authorization'] = v['session_id']
self.HEADERS['Content-Type'] = 'application/x-www-form-urlencoded'
data = {
'loginName': LOGIN_NAME,
'password': PASSWORD,
'code': v['code'],
'JSESSIONID': v['session_id']
}
r = requests.post('https://xxxxxx/login', data=data, headers=self.HEADERS)
j = r.json()
if j['code'] == 1:
logger.info('------------< 登录成功 >--------------')
token = j['object']['token']
break
num = num + 1
logger.info(f'------------< token = {token} >-------------')
return token
try:
return req()
except Exception as e:
logger.error(f'----------login error: {e}')
return req()
if __name__ == '__main__':
lo = Login().init_login()
if len(lo) != 0:
print(lo)