74 lines
3.4 KiB
Python
74 lines
3.4 KiB
Python
import concurrent.futures
|
||
import json
|
||
import time
|
||
|
||
from flask_app.general.doubao import pdf2txt
|
||
from flask_app.general.file2markdown import convert_file_to_markdown
|
||
from flask_app.general.format_change import pdf2docx
|
||
from flask_app.货物标.技术参数要求提取 import get_technical_requirements
|
||
from flask_app.general.通义千问long import upload_file
|
||
from flask_app.货物标.商务服务其他要求提取 import get_business_requirements
|
||
|
||
|
||
# 获取采购清单
|
||
def fetch_procurement_reqs(procurement_path, invalid_path):
|
||
#procurement_path可能是pdf\docx
|
||
# 定义默认的 procurement_reqs 字典
|
||
DEFAULT_PROCUREMENT_REQS = {
|
||
"采购需求": "",
|
||
"技术要求": "",
|
||
"商务要求": "",
|
||
"服务要求": "",
|
||
"其他要求": ""
|
||
}
|
||
|
||
# 如果 procurement_docpath 是空字符串，直接返回包含空字符串的字典
|
||
if not procurement_path:
|
||
return DEFAULT_PROCUREMENT_REQS.copy()
|
||
|
||
try:
|
||
processed_filepath = convert_file_to_markdown(procurement_path) # 转markdown格式
|
||
# processed_filepath = pdf2txt(procurement_path) # 纯文本提取
|
||
# 使用 ThreadPoolExecutor 并行处理 get_technical_requirements 和 get_business_requirements
|
||
with concurrent.futures.ThreadPoolExecutor() as executor:
|
||
|
||
# 提交任务给线程池
|
||
future_technical = executor.submit(get_technical_requirements, invalid_path, processed_filepath)
|
||
time.sleep(0.5) # 保持原有的延时
|
||
future_business = executor.submit(get_business_requirements, procurement_path, processed_filepath)
|
||
# 获取并行任务的结果
|
||
technical_requirements = future_technical.result()
|
||
business_requirements = future_business.result()
|
||
# 构建最终的采购需求字典
|
||
procurement_reqs = {
|
||
"采购需求": technical_requirements.get("采购需求", {})
|
||
}
|
||
|
||
procurement_reqs.update(business_requirements)
|
||
|
||
# 如果需要确保所有默认键存在，可以取消下面的注释
|
||
# for key, default_value in DEFAULT_PROCUREMENT_REQS.items():
|
||
# procurement_reqs.setdefault(key, default_value)
|
||
|
||
return procurement_reqs
|
||
|
||
except Exception as e:
|
||
print(f"Error in fetch_procurement_reqs: {e}")
|
||
# 在出错时返回默认的包含空字符串的字典
|
||
return DEFAULT_PROCUREMENT_REQS.copy()
|
||
|
||
|
||
# TODO:技术要求可以在技术参数之后执行，把完整的技术参数输入，问大模型，除了上述内容还有哪些，这样的话把技术标和其他的区分开。
|
||
|
||
if __name__ == "__main__":
|
||
start_time = time.time()
|
||
output_folder = "C:\\Users\\Administrator\\Desktop\\货物标\\货物标output"
|
||
# file_path="C:\\Users\\Administrator\\Desktop\\货物标\\output1\\2-招标文件（2020年广水市中小学教师办公电脑系统及多媒体“班班通”设备采购安装项目）_procurement.pdf"
|
||
procurement_path = r"C:\Users\Administrator\Downloads\ztbfile_procurement.pdf"
|
||
procurement_docpath = r"C:\Users\Administrator\Desktop\fsdownload\fa0d51a1-0d63-4c0d-9002-cf8ac3f2211a"
|
||
invalid_path = "C:\\Users\\Administrator\\Desktop\\fsdownload\\db79e9e0-830e-442c-8cb6-1d036215f8ff\\ztbfile.pdf"
|
||
res = fetch_procurement_reqs(procurement_path, invalid_path)
|
||
print(json.dumps(res, ensure_ascii=False, indent=4))
|
||
end_time = time.time()
|
||
print("耗时:" + str(end_time - start_time))
|