'XML tag not found

After extracting XML from CDATA I can't find tags in the extracted XML. If I convert to string and then back to an ElementTree I can find the tags I'm looking for (un-comment the lines marked "UNCOMMENT ME"). Looking for a better / more correct way.

    import xml.etree.ElementTree as ElementTree

    XML = '''<?xml version="1.0" encoding="UTF-8"?>
    <Catalog>
    <Data><![CDATA[
    <Book>
        <Author>George Orwell</Author>
        <Title>1984</Title>
    </Book>
    ]]></Data>
    </Catalog>
    '''
    def get_cdata_xml(xml_str: str) -> ElementTree:
        xml_root = ElementTree.fromstring(xml_str)
        cdata_xml = xml_root.find('.//Data')
        return cdata_xml

    if __name__ == '__main__':
        cdata_xml = get_cdata_xml(XML)

        #xml_str = cdata_xml.text  # UNCOMMENT ME
        #cdata_xml = ElementTree.fromstring(xml_str) #UNCOMMENT ME

        # type(cdata_xml) = xml.etree.ElementTree.Element
        author = cdata_xml.find('.//Author')

        print(author.text)

python

Sources

This article follows the attribution requirements of Stack Overflow and is licensed under CC BY-SA 3.0.

Source: Stack Overflow

Solution	Source

'XML tag not found

Sources

Related Questions