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

商务技术评分能处理多评分表情况，规范响应返回接口，判断上传文件是否为招标文件

Browse Source
This commit is contained in:
zy123 2025-01-09 15:57:35 +08:00
parent fc67ef8e52
commit 5efdfb2007
8 changed files with 28 additions and 28 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
flask_app/general/判断是否是招标文件.py
View File

@ -4,10 +4,10 @@ from flask_app.general.通义千问long import upload_file, qianwen_long
def judge_zbfile(pdf_path): def judge_zbfile(pdf_path):
reader = PdfReader(pdf_path) # reader = PdfReader(pdf_path)
num_pages = len(reader.pages) # num_pages = len(reader.pages)
if num_pages <= 5: # if num_pages <= 5:
return False # return False
user_query="""该文件是否属于招标文件？如果是的话，请返回'是',如果不是的话，返回'否'。请不要返回其他解释或内容。 user_query="""该文件是否属于招标文件？如果是的话，请返回'是',如果不是的话，返回'否'。请不要返回其他解释或内容。
以下是常见的招标文件类型： 以下是常见的招标文件类型：
公开招标文件、邀请招标文件、竞争性谈判文件、竞争性磋商文件、询价文件、问询文件、货物类招标文件、工程类招标文件、施工类招标文件、服务类招标文件、比选文件。 公开招标文件、邀请招标文件、竞争性谈判文件、竞争性磋商文件、询价文件、问询文件、货物类招标文件、工程类招标文件、施工类招标文件、服务类招标文件、比选文件。

2
flask_app/routes/get_deviation.py
View File

@ -1,6 +1,6 @@
# flask_app/routes/get_deviation.py # flask_app/routes/get_deviation.py
from flask import Blueprint, jsonify, Response, g from flask import Blueprint, Response, g
import os import os
from flask_app.general.format_change import download_file from flask_app.general.format_change import download_file
from flask_app.routes.偏离表main import get_tech_and_business_deviation from flask_app.routes.偏离表main import get_tech_and_business_deviation

6
flask_app/routes/偏离表main.py
View File

@ -551,6 +551,9 @@ def process_functions_in_parallel(tech_deviation_info, busi_requirements_dict, z
def get_tech_and_business_deviation(file_path,file_type,unique_id,output_folder,zb_type=2): def get_tech_and_business_deviation(file_path,file_type,unique_id,output_folder,zb_type=2):
global logger global logger
logger = get_global_logger(unique_id) logger = get_global_logger(unique_id)
judge_res = judge_zbfile(file_path)
if not judge_res:
return None
# 第一步：根据文件类型进行转换 # 第一步：根据文件类型进行转换
if file_type == 1: # docx if file_type == 1: # docx
docx_path=file_path docx_path=file_path
@ -565,9 +568,6 @@ def get_tech_and_business_deviation(file_path,file_type,unique_id,output_folder,
else: else:
logger.error("不支持的文件类型！") logger.error("不支持的文件类型！")
return None return None
judge_res = judge_zbfile(pdf_path)
if not judge_res:
return None
# 第二步：根据zb_type确定选择项和类别，并截取PDF # 第二步：根据zb_type确定选择项和类别，并截取PDF
if zb_type == 2: if zb_type == 2:
selections = [1, 2, 3, 5] selections = [1, 2, 3, 5]

6
flask_app/routes/小解析main.py
View File

@ -99,6 +99,9 @@ def little_parse_main(output_folder, file_path, file_type,zb_type,unique_id):
""" """
logger = get_global_logger(unique_id) logger = get_global_logger(unique_id)
logger.info("zb_type:"+str(zb_type)) logger.info("zb_type:"+str(zb_type))
judge_res = judge_zbfile(file_path)
if not judge_res:
return None
# 根据文件类型处理文件路径 # 根据文件类型处理文件路径
if file_type == 1: # docx if file_type == 1: # docx
docx_path = file_path docx_path = file_path
@ -112,9 +115,6 @@ def little_parse_main(output_folder, file_path, file_type,zb_type,unique_id):
else: else:
logger.error("Unsupported file type provided. Preprocessing halted.") logger.error("Unsupported file type provided. Preprocessing halted.")
return None return None
judge_res = judge_zbfile(pdf_path)
if not judge_res:
return None
# 根据招标类型调用相应的解析函数 # 根据招标类型调用相应的解析函数
if zb_type == 2: # 货物标 if zb_type == 2: # 货物标
combined_data = little_parse_goods(output_folder, pdf_path,logger) combined_data = little_parse_goods(output_folder, pdf_path,logger)

6
flask_app/routes/工程标解析main.py
View File

@ -28,6 +28,9 @@ def preprocess_files(output_folder, file_path, file_type,logger):
logger.info("starting 文件预处理...") logger.info("starting 文件预处理...")
logger.info("output_folder..." + output_folder) logger.info("output_folder..." + output_folder)
start_time=time.time() start_time=time.time()
judge_res = judge_zbfile(file_path)
if not judge_res:
return None
# 根据文件类型处理文件路径 # 根据文件类型处理文件路径
if file_type == 1: # docx if file_type == 1: # docx
# docx_path = file_path # docx_path = file_path
@ -41,9 +44,6 @@ def preprocess_files(output_folder, file_path, file_type,logger):
else: else:
logger.error("Unsupported file type provided. Preprocessing halted.") logger.error("Unsupported file type provided. Preprocessing halted.")
return None return None
judge_res = judge_zbfile(pdf_path)
if not judge_res:
return None
# 调用截取PDF多次 # 调用截取PDF多次
truncate_files = truncate_pdf_multiple(pdf_path, output_folder,logger,'engineering') truncate_files = truncate_pdf_multiple(pdf_path, output_folder,logger,'engineering')
print("切割出的文件："+str(truncate_files)) print("切割出的文件："+str(truncate_files))

6
flask_app/routes/货物标解析main.py
View File

@ -24,6 +24,9 @@ executor = ThreadPoolExecutor()
def preprocess_files(output_folder, file_path, file_type,logger): def preprocess_files(output_folder, file_path, file_type,logger):
logger.info("starting 文件预处理...") logger.info("starting 文件预处理...")
start_time = time.time() start_time = time.time()
judge_res = judge_zbfile(file_path)
if not judge_res:
return None
logger.info("output_folder..." + output_folder) logger.info("output_folder..." + output_folder)
# 根据文件类型处理文件路径 # 根据文件类型处理文件路径
if file_type == 1: # docx if file_type == 1: # docx
@ -39,9 +42,6 @@ def preprocess_files(output_folder, file_path, file_type,logger):
logger.error("Unsupported file type provided. Preprocessing halted.") logger.error("Unsupported file type provided. Preprocessing halted.")
return None return None
judge_res=judge_zbfile(pdf_path)
if not judge_res:
return None
# 调用截取PDF多次 # 调用截取PDF多次
truncate_files = truncate_pdf_multiple(pdf_path, output_folder,logger,'goods') # index: 0->商务技术服务要求 1->评标办法 2->资格审查 3->投标人须知前附表 4->投标人须知正文 truncate_files = truncate_pdf_multiple(pdf_path, output_folder,logger,'goods') # index: 0->商务技术服务要求 1->评标办法 2->资格审查 3->投标人须知前附表 4->投标人须知正文

10
flask_app/工程标/截取pdf工程标版.py
View File

@ -68,7 +68,7 @@ def extract_pages_tobidders_notice(pdf_path, output_folder, begin_pattern, begin
# 定义基础的 mid_pattern # 定义基础的 mid_pattern
base_mid_pattern = r'^\s*(?:[（(]\s*[一二12]?\s*[)）]\s*[、．.]*|' \ base_mid_pattern = r'^\s*(?:[（(]\s*[一二12]?\s*[)）]\s*[、．.]*|' \
r'[一二12][、．.]+|[、．.]+)\s*(说\s*明|总\s*则|名\s*词\s*解\s*释)' \ r'[一二12][、．.]+|[、．.]+)\s*(说\s*明|总\s*则|名\s*词\s*解\s*释)' \
r'|(?<!见\s*)(?<!与\s*)(?<!"\s*)(?<!“\s*)(?<!”\s*)(?:投标人?|磋商|谈判|供应商|谈判供应商|磋商供应商|应答人)\s*须知正文\s*$' r'|(?<!见\s*)(?<!与\s*)(?<!"\s*)(?<!“\s*)(?<!”\s*)(?:投标人?|磋商|谈判|供应商|应答人)\s*须知正文\s*$'
# 合并基础模式和额外模式 # 合并基础模式和额外模式
if additional_mid_pattern: if additional_mid_pattern:
combined_mid_pattern = regex.compile( combined_mid_pattern = regex.compile(
@ -323,8 +323,8 @@ def truncate_pdf_main_engineering(input_path, output_folder, selection, logger,
pattern_pairs = [ pattern_pairs = [
( (
regex.compile( regex.compile(
r'(?:第[一二三四五六七八九十百千]+(?:章|部分).*(?:投标人?|磋商|谈判|供应商|谈判供应商|磋商供应商|应答人)须知|' r'^第[一二三四五六七八九十百千]+(?:章|部分).*(?:投标人?|磋商|谈判|供应商|应答人)须知+|'
r'(?:投标人?|磋商|谈判|供应商|谈判供应商|磋商供应商|应答人)须知前附表)\s*$', r'(?<!见\s*)(?<!与\s*)(?<!"\s*)(?<!"\s*)(?<!"\s*)(?:投标人?|磋商|谈判|供应商|应答人)须知前附表\s*$',
regex.MULTILINE regex.MULTILINE
), ),
regex.compile( regex.compile(
@ -334,8 +334,8 @@ def truncate_pdf_main_engineering(input_path, output_folder, selection, logger,
), ),
( (
regex.compile( regex.compile(
r'.*(?<!见\s*)(?<!与\s*)(?<!"\s*)(?<!“\s*)(?<!”\s*)(?:投标人?|磋商|谈判|供应商|谈判供应商|磋商供应商|应答人)须知\s*$|' r'.*(?<!见\s*)(?<!与\s*)(?<!"\s*)(?<!“\s*)(?<!”\s*)(?:投标人?|磋商|谈判|供应商|应答人)须知\s*$|'
r'(?<!见\s*)(?<!与\s*)(?<!"\s*)(?<!“\s*)(?<!”\s*)(?:投标人?|磋商|谈判|供应商|谈判供应商|磋商供应商|应答人)须知前附表\s*$', r'(?<!见\s*)(?<!与\s*)(?<!"\s*)(?<!“\s*)(?<!”\s*)(?:投标人?|磋商|谈判|供应商|应答人)须知前附表\s*$',
regex.MULTILINE regex.MULTILINE
), ),
regex.compile( regex.compile(

12
flask_app/货物标/截取pdf货物标版.py
View File

@ -215,7 +215,7 @@ def extract_pages_tobidders_notice(pdf_path, begin_pattern, begin_page, common_h
# 定义基础的 mid_pattern # 定义基础的 mid_pattern
base_mid_pattern = r'^\s*(?:[（(]\s*[一二12]?\s*[)）]\s*[、．.]*|' \ base_mid_pattern = r'^\s*(?:[（(]\s*[一二12]?\s*[)）]\s*[、．.]*|' \
r'[一二12][、．.]+|[、．.]+)\s*(说\s*明|总\s*则|名\s*词\s*解\s*释)' \ r'[一二12][、．.]+|[、．.]+)\s*(说\s*明|总\s*则|名\s*词\s*解\s*释)' \
r'|(?<!见\s*)(?<!与\s*)(?<!"\s*)(?<!“\s*)(?<!”\s*)(?:投标人?|磋商|谈判|供应商|谈判供应商|磋商供应商|应答人)\s*须知正文\s*$' r'|(?<!见\s*)(?<!与\s*)(?<!"\s*)(?<!“\s*)(?<!”\s*)(?:投标人?|磋商|谈判|供应商|应答人)\s*须知正文\s*$'
# 合并基础模式和额外模式 # 合并基础模式和额外模式
if additional_mid_pattern: if additional_mid_pattern:
@ -282,8 +282,8 @@ def extract_pages_tobidders_notice(pdf_path, begin_pattern, begin_page, common_h
else: else:
# 定义新的 begin_pattern 和 end_pattern # 定义新的 begin_pattern 和 end_pattern
new_begin_pattern = regex.compile( new_begin_pattern = regex.compile(
r'.*(?:投标人|磋商|谈判|供应商|谈判供应商|磋商供应商|应答人)须知\s*$|' r'.*(?:投标人|磋商|谈判|供应商|应答人)须知\s*$|'
r'(?:一\s*、\s*)?(?:投标人?|磋商|谈判|供应商|谈判供应商|磋商供应商|应答人)须知前附表', r'(?:一\s*、\s*)?(?:投标人?|磋商|谈判|供应商|应答人)须知前附表',
regex.MULTILINE regex.MULTILINE
) )
new_end_pattern = regex.compile( new_end_pattern = regex.compile(
@ -300,7 +300,7 @@ def extract_pages_tobidders_notice(pdf_path, begin_pattern, begin_page, common_h
def extract_pages_twice_tobidders_notice(pdf_document, common_header, begin_page): def extract_pages_twice_tobidders_notice(pdf_document, common_header, begin_page):
output_suffix = "tobidders_notice" output_suffix = "tobidders_notice"
begin_pattern = regex.compile( begin_pattern = regex.compile(
r'^第[一二三四五六七八九十百千]+(?:章|部分).*(?:(?:投标人?|磋商|谈判|供应商|谈判供应商|磋商供应商|应答人)须知)+', r'^第[一二三四五六七八九十百千]+(?:章|部分).*(?:(?:投标人?|磋商|谈判|供应商|应答人)须知)+',
regex.MULTILINE regex.MULTILINE
) )
end_pattern = regex.compile( end_pattern = regex.compile(
@ -523,8 +523,8 @@ def truncate_pdf_main_goods(input_path, output_folder, selection,logger, output_
local_output_suffix = "qualification1" local_output_suffix = "qualification1"
elif selection == 4: elif selection == 4:
begin_pattern = regex.compile( begin_pattern = regex.compile(
r'^第[一二三四五六七八九十百千]+(?:章|部分).*(?:投标人?|磋商|谈判|供应商|谈判供应商|磋商供应商|应答人)须知+|' r'^第[一二三四五六七八九十百千]+(?:章|部分).*(?:投标人?|磋商|谈判|供应商|应答人)须知+|'
r'(?<!见\s*)(?<!与\s*)(?<!"\s*)(?<!“\s*)(?<!”\s*)(?:投标人?|磋商|谈判|供应商|谈判供应商|磋商供应商|应答人)须知前附表\s*$', r'(?<!见\s*)(?<!与\s*)(?<!"\s*)(?<!"\s*)(?<!"\s*)(?:投标人?|磋商|谈判|供应商|应答人)须知前附表\s*$',
regex.MULTILINE regex.MULTILINE
) )
end_pattern = None end_pattern = None