zy123/zbparse
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

11.7 开评定标 投标改为平级

Browse Source
This commit is contained in:
zy123 2024-11-07 10:16:35 +08:00
parent 23a31da9e9
commit ef064b9fc7
1 changed files with 9 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

16
flask_app/main/投标人须知正文提取指定内容.py
View File

@ -100,7 +100,7 @@ post_process 函数尝试将长字符串按特定模式分割成块，每块至
""" """
# 读取JSON数据，提取内容，转换结构，并打印结果 # 读取JSON数据，提取内容，转换结构，并打印结果
def extract_from_notice(invalid_path,clause_path, type): def extract_from_notice(merged_baseinfo_path,clause_path, type):
if type == 1: if type == 1:
target_values = ["投标","投标文件","响应文件"] target_values = ["投标","投标文件","响应文件"]
elif type == 2: elif type == 2:
@ -115,23 +115,25 @@ def extract_from_notice(invalid_path,clause_path, type):
with open(clause_path, 'r', encoding='utf-8') as file: with open(clause_path, 'r', encoding='utf-8') as file:
data = json.load(file) data = json.load(file)
extracted_data = extract_json(data, target_values) # 读取json extracted_data = extract_json(data, target_values) # 读取json
if not extracted_data:
final_result = get_requirements_with_gpt(merged_baseinfo_path, type) # 万一没用正则匹配到，那就调用大模型
return final_result
# print(json.dumps(extracted_data,ensure_ascii=False,indent=4)) # print(json.dumps(extracted_data,ensure_ascii=False,indent=4))
res=extract_sections(extracted_data,target_values) final_result=extract_sections(extracted_data,target_values)
print(json.dumps(res, ensure_ascii=False, indent=4)) return final_result
# print(json.dumps(res, ensure_ascii=False, indent=4))
# sorted_data = sort_clean_data_keys(extracted_data) # 对输入的字典 data 的键进行预处理和排序 # sorted_data = sort_clean_data_keys(extracted_data) # 对输入的字典 data 的键进行预处理和排序
# transformed_data = transform_json(sorted_data) # transformed_data = transform_json(sorted_data)
# print(json.dumps(transformed_data,ensure_ascii=False,indent=4)) # print(json.dumps(transformed_data,ensure_ascii=False,indent=4))
# final_result = process_nested_data(transformed_data) # final_result = process_nested_data(transformed_data)
# if not final_result:
# final_result = get_requirements_with_gpt(invalid_path, type)
# return final_result # return final_result
if __name__ == "__main__": if __name__ == "__main__":
# file_path = 'C:\\Users\\Administrator\\Desktop\\fsdownload\\3bffaa84-2434-4bd0-a8ee-5c234ccd7fa0\\clause1.json' # file_path = 'C:\\Users\\Administrator\\Desktop\\fsdownload\\3bffaa84-2434-4bd0-a8ee-5c234ccd7fa0\\clause1.json'
invalid_path="C:\\Users\\Administrator\\Desktop\\fsdownload\\4e5bc6c2-c2b8-4c0b-8e57-81a498b982f6\\ztbfile_invalid.pdf" merged_baseinfo_path="C:\\Users\\Administrator\\Desktop\\fsdownload\\4e5bc6c2-c2b8-4c0b-8e57-81a498b982f6\\ztbfile_tobidders_notice.pdf"
clause_path="C:\\Users\\Administrator\\Desktop\\fsdownload\\4e5bc6c2-c2b8-4c0b-8e57-81a498b982f6\\clause1.json" clause_path="C:\\Users\\Administrator\\Desktop\\fsdownload\\4e5bc6c2-c2b8-4c0b-8e57-81a498b982f6\\clause1.json"
try: try:
res = extract_from_notice(invalid_path,clause_path, 1) # 可以改变此处的 type 参数测试不同的场景 res = extract_from_notice(merged_baseinfo_path,clause_path, 1) # 可以改变此处的 type 参数测试不同的场景
res2 = json.dumps(res, ensure_ascii=False, indent=4) res2 = json.dumps(res, ensure_ascii=False, indent=4)
print(res2) print(res2)
except ValueError as e: except ValueError as e: