html 转移的编码转换

html 转移的编码转换
php的解决方案

<?
echo mb_convert_encoding('&#30334;&#20998;', 'UTF-8', 'HTML-ENTITIES');
?>

python解决方案

def unescape(text):
   """Removes HTML or XML character references 
      and entities from a text string.
   @param text The HTML (or XML) source text.
   @return The plain text, as a Unicode string, if necessary.
   from Fredrik Lundh
   2008-01-03: input only unicode characters string.
   http://effbot.org/zone/re-sub.htm#unescape-html
   """
   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:
            print "Value Error"
            pass
      else:
         # named entity
         # reescape the reserved characters.
         try:
            if text[1:-1] == "amp":
               text = "&"
            elif text[1:-1] == "gt":
               text = ">"
            elif text[1:-1] == "lt":
               text = "<"
            else:
               print text[1:-1]
               text = unichr(htmlentitydefs.name2codepoint[text[1:-1]])
         except KeyError:
            print "keyerror"
            pass
      return text # leave as is
   return re.sub("&#?\w+;", fixup, text)