fix log issue

This commit is contained in:
weiweiw 2024-04-30 08:48:58 +08:00
parent 80530f8b77
commit 1799c04a92
2 changed files with 177 additions and 1 deletions

View File

@ -14,7 +14,20 @@ class Extractor:
# 使用join()方法将列表中的行重新连接成字符串
cleaned_text = '\n'.join(lines)
return cleaned_text
def extract_birthday_from_id(self, id_number):
# 假设身份证号码为18位
if len(id_number) == 18:
year = id_number[6:10]
month = id_number[10:12]
day = id_number[12:14]
return f"{year}{int(month)}{int(day)}"
else:
return ""
def get_gender_from_id(self, id_num):
# 假设id_num是一个有效的身份证号码
gender = '' if int(id_num[-2]) % 2 == 1 else ''
return gender
# def remove_blank_lines(text:str)->str:
# # 使用splitlines()方法将字符串按行分割成列表,并去除空行

163
OCRPython/maincopydet.py Normal file
View File

@ -0,0 +1,163 @@
# -*- coding: utf-8 -*-
import sys
import io
import os
from paddleocr import PaddleOCR
import time
from configs.basic_config import logger
from extractor.identitycard_extractor import IdentityCardExtractor
import base64
import json
sys.stdout = io.TextIOWrapper(sys.stdout.buffer, encoding='utf-8')
def extractIdCardInfo(type: int, filePath1: str, filePath2: str) -> str:
if (0 == type):
return extractIdCardInfoByPath(filePath1, filePath2)
elif (1 == type):
return extractIdCardInfoByBase64Data(filePath1, filePath2)
else:
pass
def extractIdCardInfoByPath(filePath1: str, filePath2: str) -> str:
# ocr = PaddleOCR(use_angle_cls=True, lang="ch", det_model_dir="./models/ch_PP-OCRv3_det_slim_infer",
# rec_model_dir="./models/ch_PP-OCRv3_rec_slim_infer",
# cls_model_dir="./models/ch_ppocr_mobile_v2.0_cls_slim_infer") # need to run only once to download and load model into memory
# ocr = PaddleOCR(use_angle_cls=True, lang="ch", det_model_dir="./models/infer/ch_PP-OCRv3_det_infer",
# rec_model_dir="./models/infer/ch_PP-OCRv3_rec_infer",
# cls_model_dir="./models/infer/ch_ppocr_mobile_v2.0_cls_infer")
ocr = PaddleOCR(use_angle_cls=True, lang="ch")
text = ""
start_time = time.time() # 记录结束时间
jsonString = ""
try:
if os.path.exists(filePath1):
result = ocr.ocr(filePath1, cls=False)
for idx in range(len(result)):
res = result[idx]
for line in res:
text += (line[1][0] + '\n')
if os.path.exists(filePath2):
result = ocr.ocr(filePath2, cls=False)
for idx in range(len(result)):
res = result[idx]
for line in res:
text += (line[1][0] + '\n')
except Exception as e:
logger.error(e)
print(e)
if 0 != len(text):
logger.info(f"text:{text}")
extractor = IdentityCardExtractor()
tempdict = extractor.extract_textbyPaddle(text)
jsonString = json.dumps(tempdict, ensure_ascii=False)
end_time = time.time() # 记录结束时间
execution_time = end_time - start_time # 计算执行时间
logger.info(f"extractIdCardInfoByBase64Data 耗时{execution_time}")
return jsonString
def extractIdCardInfoByBase64Data(base64data1: str, base64Data2: str) -> str:
logger.info(f"extractIdCardInfoByBase64Data")
start_time = time.time() # 记录结束时间
jsonString = ""
try:
if 0 != len(base64data1):
logger.info(f"not base64data1.empty()")
image_data1 = base64.b64decode(base64data1)
with open("file1.png", "wb") as file:
file.write(image_data1)
if 0 != len(base64Data2):
logger.info(f"not base64Data2.empty()")
image_data2 = base64.b64decode(base64Data2)
with open("file2.png", "wb") as file:
file.write(image_data2)
if os.path.exists("file1.png") and os.path.exists("file2.png"):
logger.info(f"file1.png and file2.png exist")
jsonString = extractIdCardInfoByPath("file1.png", "file2.png")
os.remove("file1.png")
os.remove("file2.png")
elif os.path.exists("file1.png"):
logger.info(f"file1.png exist")
jsonString = extractIdCardInfoByPath("file1.png", "")
os.remove("file1.png")
elif os.path.exists("file2.png"):
logger.info(f"file2.png exist")
jsonString = extractIdCardInfoByPath("file2.png", "")
os.remove("file2.png")
except Exception as e:
logger.error(e)
end_time = time.time() # 记录结束时间
execution_time = end_time - start_time # 计算执行时间
logger.info(f"extractIdCardInfoByBase64Data 耗时{execution_time}")
return jsonString
# with open('/Users/wangvivi/Desktop/Code/ocrtest/images/id_card.JPG', 'rb') as image_file:
# base64_image_string = base64.b64encode(image_file.read()).decode('utf-8')
#
# jsonString = extractIdCardInfoByBase64Data(base64_image_string,"")
# jsonString = extractIdCardInfoByBase64Data("/Users/wangvivi/Desktop/Code/ocrtest/images/2.jpg","/Users/wangvivi/Desktop/Code/ocrtest/images/1.jpg")
# print(jsonString)
# #
# jsonString = extractIdCardInfoByPath("./images/han.jpg","")
# logger.info(f"test")
# jsonString = extractIdCardInfoByPath("./images/龙辉正.jpg","./images/龙辉反.jpg")#, "./images/江六斤反.jpg./images/han.jpg
# print(jsonString)
#
if __name__ == "__main__":
try:
logger.info(f"main.py len of parameter: {len(sys.argv)}")
jsonString = ""
if len(sys.argv) > 3:
logger.info(f"{sys.argv[1]}")
logger.info(f"{sys.argv[2]}")
logger.info(f"{sys.argv[3]}")
jsonString = extractIdCardInfo(int(sys.argv[1]), sys.argv[2], sys.argv[3])
elif len(sys.argv) > 1:
logger.info(f"python 脚本里的接收到的参数是:")
logger.info(f"{sys.argv[1]}")
logger.info(f"开始执行sys.stdin.read")
input_data = sys.stdin.read()
logger.info(f"len(input_data):{len(input_data)}")
# imageData = base64.b64decode(input_data)
# logger.info(f"image_data1:{image_data1}")
#logger.info(f"input_data:{input_data}")
split_data = input_data.split(os.linesep)
data1 = ""
data2 = ""
if 2 == len(split_data):
logger.info("2 == len(split_data)")
data1 = split_data[0]
data2 = split_data[1]
elif 1 == len(split_data):
data1 = split_data[0]
# logger.info(data1)
# logger.info(data2)
jsonString = extractIdCardInfo(int(sys.argv[1]), data1, data2)
print(jsonString)
except KeyboardInterrupt:
logger.error("KeyboardInterrupt")
except IndexError:
# 如果参数过长,捕获 IndexError 异常并进行处理
logger.error("参数过长,未指定足够的参数")
except OverflowError:
# 如果发生了 OverflowError 异常,捕获并进行相应的处理
logger.error("命令行参数过长,导致溢出错误")
except EOFError:
# 如果达到输入流的末尾,捕获 EOFError 异常并进行处理
logger.error("已经到达输入流的末尾")
except Exception as e:
# 如果发生了其他异常,捕获并进行相应的处理
logger.error("发生了异常:", e)