1     def getPageText(self, start=0, length=None):
   2         """ Convenience function to get the page text, skipping the header
   3 
   4         @rtype: unicode
   5         @return: page text, excluding the header
   6         """
   7 
   8         # Lazy compile regex on first use. All instances share the
   9         # same regex, compiled once when the first call in an instance is done.
  10         if isinstance(self.__class__.header_re, (str, unicode)):
  11             self.__class__.header_re = re.compile(self.__class__.header_re, re.MULTILINE | re.UNICODE)
  12 
  13         body = self.get_raw_body() or ''
  14         header = self.header_re.search(body) ##<--- IT RECOGNISED A HEADER INSIDE A {{{ 
  15         if header:
  16             start += header.end() ##<--- THIS COUNT IS WRONG
  17 
  18         # Return length characters from start of text
  19         if length is None:
  20             return body[start:]
  21         else:
  22             return body[start:start + length]