1.6 insert_del_pagemark.py修改

This commit is contained in:
zy123 2025-01-06 11:55:34 +08:00
parent 04816cdedf
commit 691883cc99

View File

@ -34,7 +34,7 @@ def extract_pages_generic(pdf_document, begin_pattern, end_pattern, begin_page,
end_page = i
break
else:
if regex.search(end_pattern, cleaned_text) and (i > start_page) and not regex.search(begin_pattern,cleaned_text):
if regex.search(end_pattern, cleaned_text) and (i > start_page) and not regex.search(begin_pattern, cleaned_text):
end_page = i
break
return start_page, end_page
@ -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(