thought better of the html2text behavior and reverted

This commit is contained in:
Mahmoud Hashemi 2015-07-22 02:29:11 -07:00
parent 2a5cc74a1e
commit 93ae692393
1 changed files with 1 additions and 2 deletions

View File

@ -544,8 +544,7 @@ class HTMLTextExtractor(HTMLParser):
try:
codepoint = htmlentitydefs.name2codepoint[name]
except KeyError:
# likely not a real entity (possibly an unescaped part of a URL)
self.result.append(u'&' + name)
self.result.append(u'&' + name + u';')
else:
self.result.append(unichr(codepoint))