Created
August 31, 2011 20:01
-
-
Save nriley/1184554 to your computer and use it in GitHub Desktop.
Unescape for XML
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import re, htmlentitydefs | |
# from http://effbot.org/zone/re-sub.htm#unescape-html | |
def unescape(text): | |
def fixup(m): | |
text = m.group(0) | |
if text[:2] == "&#": | |
# character reference | |
try: | |
if text[:3] == "&#x": | |
return unichr(int(text[3:-1], 16)) | |
else: | |
return unichr(int(text[2:-1])) | |
except ValueError: | |
pass | |
else: | |
# named entity | |
try: | |
text = unichr(htmlentitydefs.name2codepoint[text[1:-1]]) | |
except KeyError: | |
pass | |
return text # leave as is | |
return re.sub("&#?\w+;", fixup, text) | |
print unescape('für').encode('ascii', 'xmlcharrefreplace') |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment