forked from Ponysearch/Ponysearch
[fix] handle single closing element in HTMLTextExtractor
This commit is contained in:
parent
06186e72a9
commit
699fe60e50
1 changed files with 4 additions and 0 deletions
|
@ -82,8 +82,12 @@ class HTMLTextExtractor(HTMLParser):
|
||||||
self.tags.append(tag)
|
self.tags.append(tag)
|
||||||
|
|
||||||
def handle_endtag(self, tag):
|
def handle_endtag(self, tag):
|
||||||
|
if not self.tags:
|
||||||
|
return
|
||||||
|
|
||||||
if tag != self.tags[-1]:
|
if tag != self.tags[-1]:
|
||||||
raise Exception("invalid html")
|
raise Exception("invalid html")
|
||||||
|
|
||||||
self.tags.pop()
|
self.tags.pop()
|
||||||
|
|
||||||
def is_valid_tag(self):
|
def is_valid_tag(self):
|
||||||
|
|
Loading…
Reference in a new issue