mirror of
https://github.com/opendatalab/MinerU.git
synced 2026-03-31 13:08:35 +07:00
11 lines
282 B
Python
11 lines
282 B
Python
import re
|
|
|
|
|
|
def minify_html(html):
|
|
# 移除多余的空白字符
|
|
html = re.sub(r'\s+', ' ', html)
|
|
# 移除行尾的空白字符
|
|
html = re.sub(r'\s*>\s*', '>', html)
|
|
# 移除标签前的空白字符
|
|
html = re.sub(r'\s*<\s*', '<', html)
|
|
return html.strip() |