diff --git a/Excel处理/dataset.xlsx b/Excel处理/dataset.xlsx deleted file mode 100644 index 4c5dec2..0000000 Binary files a/Excel处理/dataset.xlsx and /dev/null differ diff --git a/Excel处理/main.py b/Excel处理/main.py deleted file mode 100644 index d429e51..0000000 --- a/Excel处理/main.py +++ /dev/null @@ -1,73 +0,0 @@ -# -*- coding: utf-8 -*- - -""" -就excel工作表进行处理，包括就指定字段解析JSON -""" - -from json import loads - -from pandas import DataFrame, read_excel - -from utils.pandas_extension import save_as_workbook - -# 打开并读取指定工作表（默认以字符串读取） -sheet = read_excel(io="dataset.xlsx", sheet_name="Sheet1", dtype=str) - -dataset = [] - -for index, row in sheet.iterrows(): - # 就指定字段解析为JSON - response = loads(row["response"]) - - data = {} - - # 根据深圳快瞳票据查验要求解析查验结果 - # 状态码 - status = response.get("status", "") - # 错误码 - code = response.get("code", "") - # 若状态码为200且错误码为10000，则定义为响应成功 - if status == 200 and code == 10000: - # 查验类型，若查验类型为003081则为医疗收费票据=，003082则为增值税发票 - match response.get("data").get( - "productCode" - ): - # 解析医疗收费票据 - case "003081": - data["发票号"] = response.get("data").get( - "billNumber" - ) - # 查验结果 - match response.get("data").get("flushedRed"): - case "true": - data["查验结果"] = "正常" - case "false": - data["查验结果"] = "已红冲" - - # 解析增值税发票 - case "003082": - data["发票号"] = ( - response.get("data").get("details").get("number") - ) - # 查验结果 - match response.get("data").get("details").get( - "invoiceTypeNo" - ): - case "0": - data["查验结果"] = "正常" - case "1": - data["查验结果"] = "无法查验" - case "2" | "3" | "7" | "8": - data["查验结果"] = "已红冲" - - # 若状态码为400且错误码为10001或10100，则定义为假票 - elif status == 400 and (code == 10001 or code == 10100): - data["查验结果"] = "假票" - - else: - data["查验结果"] = "无法查验" - - dataset.append(data) - -# 本地保存 -save_as_workbook(worksheets=[("Sheet1", DataFrame(data=dataset, dtype=str))], workbook_name="results.xlsx") \ No newline at end of file diff --git a/Excel处理/results.xlsx b/Excel处理/results.xlsx deleted file mode 100644 index ce995a8..0000000 Binary files a/Excel处理/results.xlsx and /dev/null differ diff --git a/KANO/main.py b/KANO/main.py index bfb536c..f9af000 100644 --- a/KANO/main.py +++ b/KANO/main.py @@ -12,7 +12,6 @@ import pandas from utils.pandas_extension import save_as_workbook - print("1 打开并读取Excel文件...", end="") try: diff --git a/票据理赔自动化/main.py b/票据理赔自动化/main.py index 5e6ae00..bb2f77f 100644 --- a/票据理赔自动化/main.py +++ b/票据理赔自动化/main.py @@ -5,6 +5,7 @@ 功能清单 https://liubiren.feishu.cn/docx/WFjTdBpzroUjQvxxrNIcKvGnneh?from=from_copylink """ + import json import re import uuid @@ -27,7 +28,6 @@ from utils.client import Authenticator, HTTPClient, CacheClient # from utils.ocr import fuzzy_match - def idcard_extraction(**kwargs) -> dict | None: """居民身份证数据提取""" @@ -908,7 +908,7 @@ def common_extraction(**kwargs) -> dict | None: # 规则模型初始化 def decision(rules_path: Path) -> ZenDecision: def loader(path): - with open(path, "r") as file: + with open(path, "r", encoding="utf-8") as file: return file.read() return ZenEngine({"loader": loader}).get_decision(rules_path.as_posix()) @@ -997,13 +997,12 @@ if __name__ == "__main__": # 加载赔案档案模版 template = environment.get_template("template.html") - # ------------------------- # 自定义方法 # ------------------------- # noinspection PyShadowingNames def image_read( - image_path: Path, + image_path: Path, ) -> Optional[numpy.ndarray | None]: """ 本地打开并读取影像件 @@ -1022,7 +1021,6 @@ if __name__ == "__main__": # 若本地打开并读取影像件发生异常则抛出异常（实际作业需从影像件服务器下载并读取影像件，因签收时会转存，故必可下载） raise RuntimeError("影像件打开并读取发生异常") - # noinspection PyShadowingNames def image_serialize(image_format: str, image_ndarray: numpy.ndarray) -> str: """ @@ -1042,10 +1040,9 @@ if __name__ == "__main__": image_guid = md5(image_bytes).hexdigest().upper() return image_guid - # noinspection PyShadowingNames def images_classify( - image_guid: str, image_format: str, image_ndarray: numpy.ndarray + image_guid: str, image_format: str, image_ndarray: numpy.ndarray ) -> Optional[Tuple[str, str, str]]: """ 影像件分类并旋正 @@ -1057,7 +1054,7 @@ if __name__ == "__main__": # noinspection PyShadowingNames def images_compress( - image_format, image_ndarray, image_size_specified=2 + image_format, image_ndarray, image_size_specified=2 ) -> Optional[str]: """ 影像件压缩 @@ -1090,7 +1087,9 @@ if __name__ == "__main__": break # 影像件BASE64编码 - image_base64 = b64encode(image_ndarray_encoded.tobytes()).decode("utf-8") + image_base64 = b64encode(image_ndarray_encoded.tobytes()).decode( + "utf-8" + ) if len(image_base64) <= image_size_specified: return image_base64 @@ -1110,7 +1109,9 @@ if __name__ == "__main__": return None # 影像件压缩 - image_base64 = images_compress(image_format, image_ndarray, image_size_specified=2) # 深圳快瞳要求为2兆字节 + image_base64 = images_compress( + image_format, image_ndarray, image_size_specified=2 + ) # 深圳快瞳要求为2兆字节 # TODO: 若影像件压缩发生异常则流转至人工处理 if image_base64 is None: raise RuntimeError("影像件压缩发生异常") @@ -1118,7 +1119,9 @@ if __name__ == "__main__": # 请求深圳快瞳影像件分类接口 response = http_client.post( url=(url := "https://ai.inspirvision.cn/s/api/ocr/genalClassify"), - headers={"X-RequestId-Header": image_guid}, # 以影像件唯一标识作为请求唯一标识，用于双方联查 + headers={ + "X-RequestId-Header": image_guid + }, # 以影像件唯一标识作为请求唯一标识，用于双方联查 data={ "token": authenticator.get_token( servicer="szkt" @@ -1180,18 +1183,17 @@ if __name__ == "__main__": }[image_orientation], ) # 旋正后影像件再次压缩 - image_base64 = images_compress(image_format, image_ndarray, image_size_specified=2) + image_base64 = images_compress( + image_format, image_ndarray, image_size_specified=2 + ) # TODO: 若旋正后影像件再次压缩发生异常则流转至人工处理 if image_base64 is None: raise RuntimeError("旋正后影像件再次压缩发生异常") return image_base64, image_type, image_orientation - # 遍历工作目录中赔案目录并创建赔案档案（模拟自动化域就待自动化任务创建理赔档案） - for case_path in [ - x for x in directory_path.iterdir() if x.is_dir() - ]: + for case_path in [x for x in directory_path.iterdir() if x.is_dir()]: # 初始化赔案档案（实际报案层包括保险分公司名称、报案渠道、批次号、报案号和报案时间等） # 报案渠道包括：保司定义，例如中银项目包括总行和各地分行驻场报案和普康宝自助报案等 dossier = { @@ -1228,10 +1230,14 @@ if __name__ == "__main__": # 影像件序列化 # noinspection PyTypeChecker - image["影像件唯一标识"] = (image_guid := image_serialize(image_format, image_ndarray)) + image["影像件唯一标识"] = ( + image_guid := image_serialize(image_format, image_ndarray) + ) # 影像件分类并旋正（较初审自动化，无使能检查） - image_base64, image_type, image_orientation = images_classify(image_guid, image_format, image_ndarray) + image_base64, image_type, image_orientation = images_classify( + image_guid, image_format, image_ndarray + ) image["影像件类型"] = image_type image["影像件方向"] = image_orientation # 将影像件数据添加至影像件层 @@ -1239,7 +1245,6 @@ if __name__ == "__main__": # 影像件识别 - print(dossier) exit() """