readabilite: handle another weird html stuff

This commit is contained in:
pictuga 2020-03-19 10:24:09 +01:00
parent f48961a7e4
commit 2704e91a3d

View File

@ -187,7 +187,7 @@ def clean_node(node):
return
# remove comments
if isinstance(node, lxml.html.HtmlComment):
if isinstance(node, lxml.html.HtmlComment) or isinstance(node, lxml.html.HtmlProcessingInstruction):
parent.remove(node)
return