207                 

   207                 

   208     # do not use pandoc to convert from html to html

   208     # do not use pandoc to convert from html to html

   209     if from_format==to_format=='html':

   209     if from_format==to_format=='html':

   210       # get body content

   210       # get body content

   211       stdoutdata = (content.encode('utf8'))

   211       stdoutdata = (content.encode('utf8'))

   212       # if for some reason, tidy has not guess the doctype, make xml.dom.minidom happy with HTML entities ( )

   214       # if for some reason, tidy has not guess the doctype, make xml.dom.minidom happy with HTML entities ( )

   213       stdoutdata = re.sub(r" ", '\xc2\xa0', stdoutdata)

   215       stdoutdata = re.sub(r" ", '\xc2\xa0', stdoutdata)

   214       dom = parseString(stdoutdata)

   216       dom = parseString(stdoutdata)

   215       body = dom.getElementsByTagName("body")[0].toxml()

   217       body = dom.getElementsByTagName("body")[0].toxml()

   216       stdoutdata = body[body.find('>')+1:body.rfind('</')]

   218       stdoutdata = body[body.find('>')+1:body.rfind('</')]