Echo/fcb_photo_review
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

过滤页码异常的值

Browse Source
This commit is contained in:
liuyebo
2024-10-18 10:05:38 +08:00
parent 3710450221
commit 9556da47e9
1 changed files with 2 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
util/data_util.py
View File

@@ -195,6 +195,8 @@ def parse_page_num(page_list):
page_texts = [p.get('text', '') for p in page] page_texts = [p.get('text', '') for p in page]
join = ''.join(page_texts) join = ''.join(page_texts)
numbers = re.findall(r'\d+', join) numbers = re.findall(r'\d+', join)
# 过滤异常值
numbers = [num for num in numbers if int(num) <= 30]
if not numbers: if not numbers:
continue continue
pages.append(min(numbers)) pages.append(min(numbers))