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

1.6 insert_del_pagemark.py修改

Browse Source
This commit is contained in:
zy123 2025-01-06 11:55:34 +08:00
parent 04816cdedf
commit 691883cc99
1 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
flask_app/货物标/截取pdf货物标版.py
View File

@ -99,7 +99,7 @@ def get_patterns_for_procurement():
r'第[一二三四五六七八九十1-9]+(?:章|部分)\s*(?!.*说明)' # 匹配“第X章”或“第X部分”
r'[\u4e00-\u9fff、()（）]*?' # 匹配允许的字符
r'(?:(?:服务|项目|商务|技术|供货)[\u4e00-\u9fff、()（）]*?要求[\u4e00-\u9fff、()（）]*?\s*$|' # 匹配“服务”、“项目”、“商务”或“技术”后跟“要求”
r'(?:采购.*?(?:内容|要求|需求)?|招标(?:内容|要求|需求))[\u4e00-\u9fff、()（）]*?|'
r'(?:采购.*?(?:内容|要求|需求)|招标(?:内容|要求|需求))[\u4e00-\u9fff、()（）]*?|'
r'需求书[\u4e00-\u9fff、()（）]*?)\s*$',
regex.MULTILINE
)
@ -525,7 +525,7 @@ def truncate_pdf_main_goods(input_path, output_folder, selection,logger, output_
elif selection == 5:
begin_pattern = regex.compile(
r'^第[一二三四五六七八九十百千]+(?:章|部分).*?(?:服务|项目|商务|技术|供货).*?要求|'
r'^第[一二三四五六七八九十百千]+(?:章|部分)(?!.*说明).*(?:采购.*?(?:内容|要求|需求)?|招标(?:内容|要求|需求)).*|'
r'^第[一二三四五六七八九十百千]+(?:章|部分)(?!.*说明).*(?:采购.*?(?:内容|要求|需求)|招标(?:内容|要求|需求)).*|'
r'^第[一二三四五六七八九十百千]+(?:章|部分).*?需求书'
)
end_pattern = regex.compile(