maryjane
/
gpodder
1
0
Fork 0
Code Issues Pull Requests Projects Releases 1 Wiki Activity

Handle HTML entities using name2codepoint

This commit is contained in:
Mathias Rav 2016-08-08 20:00:28 +02:00
parent 33af39d69d
commit 9cc600208f
1 changed files with 13 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
src/gpodder/util.py
View File

@ -71,8 +71,10 @@ import collections
if sys.hexversion < 0x03000000:
from HTMLParser import HTMLParser
from htmlentitydefs import name2codepoint
else:
from html.parser import HTMLParser
from html.entities import name2codepoint
if gpodder.ui.win32:
try:
@ -794,6 +796,17 @@ class ExtractHyperlinkedText2(HTMLParser):
def handle_data(self, data):
self.output(self.htmlws(data))
def handle_entityref(self, name):
c = unichr(name2codepoint[name])
self.output(c)
def handle_charref(self, name):
if name.startswith('x'):
c = unichr(int(name[1:], 16))
else:
c = unichr(int(name))
self.output(c)
def output_newline(self, attrs=None):
self.output('\n')