python lxml.etree.iterparse

new version

import lxml.etree as tr
context = tr.iterparse('content.rdf.u8', events=('end',), tag='{http://dmoz.org/rdf/}ExternalPage')

for event, elem in context:
        print('%s' % elem[0].text.encode('utf-8'))
        print('%s' % elem[1].text.encode('utf-8'))
        print(elem.attrib['about']+"\n")
        #print('%s\n' % elem[1].text.encode('utf-8'))
        elem.clear()
        while elem.getprevious() is not None:
                del elem.getparent()[0]

Random error

Traceback (most recent call last):
  File "parser.py", line 6, in <module>
    print('%s' % elem[1].text.encode('utf-8'))
AttributeError: 'NoneType' object has no attribute 'encode'

xml

<ExternalPage about="http://www.castles99.ukprint.com/Essays/stapleton.html">
    <d:Title>Stapleton Castle, Herefordshire</d:Title>
    <d:Description></d:Description>
    <topic>Top/Arts/Architecture/Building_Types/Fortifications/Castles/United_Kingdom/England</topic>
  </ExternalPage>