53 lines
2.2 KiB
Python
53 lines
2.2 KiB
Python
from flask_app.general.format_change import pdf2docx
|
||
from flask_app.general.通义千问long import upload_file
|
||
from flask_app.货物标.截取pdf货物标版 import truncate_pdf_main
|
||
from flask_app.货物标.技术参数要求提取 import get_technical_requirements
|
||
|
||
|
||
def extract_matching_keys(data_dict, good_list):
|
||
"""
|
||
递归遍历data_dict，查找good_list中存在的键，并将匹配的键及其值添加到结果字典中。
|
||
|
||
参数:
|
||
- data_dict (dict): 要遍历的嵌套字典。
|
||
- good_list (list): 包含要查找的键的列表。
|
||
|
||
返回:
|
||
- dict: 包含所有匹配键及其值的字典。
|
||
"""
|
||
result = {}
|
||
|
||
def recurse(current_dict):
|
||
if isinstance(current_dict, dict):
|
||
for key, value in current_dict.items():
|
||
if key in good_list:
|
||
result[key] = value
|
||
# 递归遍历子字典
|
||
recurse(value)
|
||
elif isinstance(current_dict, list):
|
||
for item in current_dict:
|
||
recurse(item)
|
||
# 如果current_dict不是dict或list，则无需进一步处理
|
||
|
||
recurse(data_dict)
|
||
return result
|
||
|
||
def get_technical_requirements_main(file_path,output_folder):
|
||
truncate_file=truncate_pdf_main(file_path,output_folder,5)[0]
|
||
truncate_file_docx=pdf2docx(truncate_file)
|
||
file_id=upload_file(truncate_file_docx)
|
||
# file_id=upload_file(truncate_file)
|
||
final_res=get_technical_requirements(file_id)
|
||
# 安全地提取 "技术要求" 内部的字典内容
|
||
if isinstance(final_res, dict) and '技术要求' in final_res and isinstance(final_res['技术要求'], dict):
|
||
technical_requirements = final_res['技术要求']
|
||
good_list = technical_requirements.pop('货物列表', []) # 如果 '货物列表' 不存在，返回 []
|
||
return extract_matching_keys(technical_requirements,good_list)
|
||
else:
|
||
return final_res
|
||
if __name__ == "__main__":
|
||
file_path="C:\\Users\\Administrator\\Desktop\\fsdownload\\45f650ce-e519-457b-9ad6-5840e2ede539\\ztbfile.pdf"
|
||
output_folder = "C:\\Users\\Administrator\\Desktop\\fsdownload\\45f650ce-e519-457b-9ad6-5840e2ede539\\tmp"
|
||
res=get_technical_requirements_main(file_path,output_folder)
|
||
print(res)
|