aboutsummaryrefslogtreecommitdiff
path: root/utils.py
diff options
context:
space:
mode:
authorTianhao Wang <tianhao.wang2@mailbox.tu-dresden.de>2023-10-14 00:04:45 +0200
committerTianhao Wang <tianhao.wang2@mailbox.tu-dresden.de>2023-10-14 00:04:45 +0200
commit2580e02140f112e8797807620e36712489039754 (patch)
tree4956d918ecb3d79ff772c52576bfdee20e88a811 /utils.py
init
Diffstat (limited to 'utils.py')
-rw-r--r--utils.py9
1 files changed, 9 insertions, 0 deletions
diff --git a/utils.py b/utils.py
new file mode 100644
index 0000000..aa0f4ed
--- /dev/null
+++ b/utils.py
@@ -0,0 +1,9 @@
+import re
+import html
+
+CLEANR = re.compile('<.*?>')
+
+def sanitize_html(raw_html):
+ cleantext = re.sub(CLEANR, '', raw_html)
+ return html.unescape(cleantext)
+