172 lines
7.0 KiB
Python
172 lines
7.0 KiB
Python
# -*- coding: utf-8 -*-
|
||
import sys
|
||
import io
|
||
from paddleocr import PaddleOCR
|
||
import time
|
||
from configs.basic_config import *
|
||
from extractor.identitycard_extractor import IdentityCardExtractor
|
||
import base64
|
||
import json
|
||
|
||
sys.stdout = io.TextIOWrapper(sys.stdout.buffer, encoding='utf-8')
|
||
def extractIdCardInfo(type:int=0, 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") # need to run only once to download and load model into memory
|
||
text = ""
|
||
start_time = time.time() # 记录结束时间
|
||
finalResult = {
|
||
"code": LOCAL_PATH_NOT_EXIST,
|
||
"msg": error_codes[LOCAL_PATH_NOT_EXIST],
|
||
|
||
}
|
||
try:
|
||
if len(filePath1) > 0:
|
||
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')
|
||
else:
|
||
logger.error(f"{filePath1} doesn't exist,error information:{finalResult}")
|
||
return json.dumps(finalResult, ensure_ascii=False)
|
||
|
||
if len(filePath2) > 0:
|
||
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')
|
||
else:
|
||
logger.error(f"{filePath2} doesn't exist,error information:{finalResult}")
|
||
return json.dumps(finalResult, ensure_ascii=False)
|
||
|
||
except Exception as e:
|
||
finalResult["code"] = OCR_RECOGNIZE_OTHER_EXCEPTION
|
||
finalResult["msg"] = error_codes[OCR_RECOGNIZE_OTHER_EXCEPTION]
|
||
logger.error(f"{e} ,error information:{finalResult}")
|
||
return json.dumps(finalResult, ensure_ascii=False)
|
||
|
||
if 0 != len(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}秒")
|
||
return jsonString
|
||
else:
|
||
finalResult["code"] = NO_TEXT_RECOGNIZED
|
||
finalResult["msg"] = error_codes[NO_TEXT_RECOGNIZED]
|
||
logger.error(f"{filePath1},{filePath2} can't be recognized,error information:{finalResult}")
|
||
return json.dumps(finalResult, ensure_ascii=False)
|
||
|
||
def extractIdCardInfoByBase64Data(base64data1:str, base64Data2: str)->str:
|
||
finalResult = {
|
||
"code": BASE64_DATA_INCOMPLETE,
|
||
"msg": error_codes[BASE64_DATA_INCOMPLETE],
|
||
}
|
||
logger.info(f"extractIdCardInfoByBase64Data")
|
||
start_time = time.time() # 记录结束时间
|
||
jsonString = ""
|
||
try:
|
||
if 0 != len(base64data1):
|
||
image_data1 = base64.b64decode(base64data1)
|
||
with open("file1.png", "wb") as file:
|
||
file.write(image_data1)
|
||
|
||
if 0 != len(base64Data2):
|
||
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"):
|
||
jsonString = extractIdCardInfoByPath("file1.png","file2.png")
|
||
os.remove("file1.png")
|
||
os.remove("file2.png")
|
||
elif os.path.exists("file1.png"):
|
||
jsonString = extractIdCardInfoByPath("file1.png","")
|
||
os.remove("file1.png")
|
||
elif os.path.exists("file2.png"):
|
||
jsonString = extractIdCardInfoByPath("file2.png","")
|
||
os.remove("file2.png")
|
||
except Exception as e:
|
||
logger.error(e)
|
||
logger.error(f"{e},error information:{finalResult}")
|
||
return json.dumps(finalResult, 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}秒")
|
||
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 = extractIdCardInfoByPath("/Users/wangvivi/Desktop/Code/ocrtest/images/id_card.JPG")
|
||
#jsonString = extractIdCardInfoByPath("./images/bf4343cfb5806c77ae21c56a8c35f474.jpeg")
|
||
#print(jsonString)
|
||
|
||
# jsonString = extractIdCardInfoByPath("/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/43302919641130423X_202311061953_front.jpg","./images/43302919641130423X_202311061953_back.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)}")
|
||
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]
|
||
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)
|
||
|