Support Unicode HTML escapes and solve Python3 incompatibility

bordaigorl · Oct 14, 2014 · bfdf029 · bfdf029
1 parent 5970d8c
commit bfdf029
Showing 1 changed file with 4 additions and 4 deletions.
diff --git a/lib/html2text.py b/lib/html2text.py
@@ -39,7 +39,7 @@ def has_key(x, y):
     xrange = range
 
 # Use Unicode characters instead of their ascii psuedo-replacements
-UNICODE_SNOB = 0
+UNICODE_SNOB = 1
 
 # Escape all special characters.  Output is less readable, but avoids corner case formatting issues.
 ESCAPE_SNOB = 0
@@ -281,7 +281,7 @@ def close(self):
 
         self.outtext = self.outtext.join(self.outtextlist)
         if self.unicode_snob:
-            nbsp = unichr(name2cp('nbsp'))
+            nbsp = chr(name2cp('nbsp'))
         else:
             nbsp = u' '
         self.outtext = self.outtext.replace(u'&nbsp_place_holder;', nbsp)
@@ -801,7 +801,7 @@ def charref(self, name):
             return unifiable_n[c]
         else:
             try:
-                return unichr(c)
+                return chr(c)
             except NameError: #Python3
                 return chr(c)
 
@@ -813,7 +813,7 @@ def entityref(self, c):
             except KeyError: return "&" + c + ';'
             else:
                 try:
-                    return unichr(name2cp(c))
+                    return chr(name2cp(c))
                 except NameError: #Python3
                     return chr(name2cp(c))