Merge pull request #7 from dkasak/unescape-html-entities

Unescape HTML entities prior to parsing HTML.
This commit is contained in:
poljar 2018-03-19 15:21:10 +01:00 committed by GitHub
commit 808f652d5f
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
2 changed files with 51 additions and 0 deletions

View file

@ -32,6 +32,9 @@ try:
except ImportError:
from html.parser import HTMLParser
import html
from html.entities import name2codepoint
FormattedString = namedtuple('FormattedString', ['text', 'attributes'])
quote_wrapper = textwrap.TextWrapper(
@ -314,6 +317,21 @@ class MatrixHtmlParser(HTMLParser):
self.substrings = [] # type: List[FormattedString]
self.attributes = DEFAULT_ATRIBUTES.copy()
def unescape(self, text):
"""Shim to unescape HTML in both Python 2 and 3.
The instance method was deprecated in Python 3 and html.unescape
doesn't exist in Python 2 so this is needed.
"""
try:
return html.unescape(text)
except AttributeError:
return HTMLParser.unescape(self, text)
def feed(self, text):
text = self.unescape(text)
return HTMLParser.feed(self, text)
def _toggle_attribute(self, attribute):
if self.text:
self.substrings.append(