def parsefile(path):
   try:
      file = open(path, "r")
      fileread = file.read()
      fileread = unescape(fileread.decode('utf-8')).encode('utf-8')
      file.close()
   except:
      print "Reading File Bug"
      sys.exit(1)
   return ET.fromstring(fileread)

def unescape(text):
   """Removes HTML or XML character references 
      and entities from a text string.
      keep &, >, < in the source code.
   from Fredrik Lundh
   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 "error of value"
            pass
      else:
         # named entity
         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)


# http://www.crystalfaeries.net/linux/bin/unescape