zhuchaowe/maxkb
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

refactor: enhance HTML tag removal in text processing to exclude audio, video, and image tags

Browse Source
This commit is contained in:
wxg0103 2025-07-09 20:34:34 +08:00
parent d0722dc048
commit 0316afa299
1 changed files with 3 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
apps/common/utils/common.py
View File

@ -116,6 +116,9 @@ def markdown_to_plain_text(md: str) -> str:
text = re.sub(r'\n{2,}', '\n', text) text = re.sub(r'\n{2,}', '\n', text)
# 使用正则表达式去除所有 HTML 标签 # 使用正则表达式去除所有 HTML 标签
text = re.sub(r'<[^>]+>', '', text) text = re.sub(r'<[^>]+>', '', text)
# 先移除特定媒体标签（优先级高于通用HTML标签移除）
text = re.sub(r'<(audio|video)[^>]*>.*?</\1>', '', text, flags=re.DOTALL) # 匹配音频/视频标签
text = re.sub(r'<img[^>]*>', '', text) # 匹配图片标签
# 去除多余的空白字符（包括换行符、制表符等） # 去除多余的空白字符（包括换行符、制表符等）
text = re.sub(r'\s+', ' ', text) text = re.sub(r'\s+', ' ', text)
# 去除表单渲染 # 去除表单渲染