[utils] Handle HTMLParseError in extract_attributes (closes #13349)

This commit is contained in:
Sergey M․
2017-06-12 01:52:24 +07:00
parent 72b409559c
commit b4a3d461e4
2 changed files with 9 additions and 2 deletions

View File

@ -36,6 +36,7 @@ import xml.etree.ElementTree
import zlib
from .compat import (
compat_HTMLParseError,
compat_HTMLParser,
compat_basestring,
compat_chr,
@ -409,8 +410,12 @@ def extract_attributes(html_element):
but the cases in the unit test will work for all of 2.6, 2.7, 3.2-3.5.
"""
parser = HTMLAttributeParser()
parser.feed(html_element)
parser.close()
try:
parser.feed(html_element)
parser.close()
# Older Python may throw HTMLParseError in case of malformed HTML
except compat_HTMLParseError:
pass
return parser.attrs