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

2.15 应该是pypdf2库的问题

Browse Source
This commit is contained in:
zy123 2025-02-15 22:32:27 +08:00
parent cef8ff5415
commit 515249d4f7
1 changed files with 0 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
flask_app/货物标/截取pdf货物标版.py
View File

@ -23,7 +23,6 @@ def extract_pages(pdf_path, output_folder, begin_pattern, begin_page, end_patter
except Exception as e: except Exception as e:
print(f"Error processing {pdf_path}: {e}") print(f"Error processing {pdf_path}: {e}")
return "" return ""
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|项目|货物)(?:内容|要求|需求)).*|'
def get_patterns_for_procurement(): def get_patterns_for_procurement():
begin_pattern = regex.compile( begin_pattern = regex.compile(
r'(?<!对应\s*)(?<!根据\s*)(?<!按照\s*)(?<!见\s*)(?<!与\s*)(?<!同\s*)(?<!"\s*)(?<!“\s*)(?<!”\s*)' r'(?<!对应\s*)(?<!根据\s*)(?<!按照\s*)(?<!见\s*)(?<!与\s*)(?<!同\s*)(?<!"\s*)(?<!“\s*)(?<!”\s*)'