[fix] handle single closing element in HTMLTextExtractor
commit699fe60e5072eeffebfb2f3b9b85cefe6dd1b7bc
authorAdam Tauber <asciimoo@gmail.com>
dateThu 22 Jan 2015, 17:43 (12 years ago)
parent06186e7
searx/utils.py+4
@@ -82,8 +82,12 @@ class HTMLTextExtractor(HTMLParser):
8282 self.tags.append(tag)
8383
8484 def handle_endtag(self, tag):
85+ if not self.tags:
86+ return
87+
8588 if tag != self.tags[-1]:
8689 raise Exception("invalid html")
90+
8791 self.tags.pop()
8892
8993 def is_valid_tag(self):