Using Python Iterparse For Large XML Files

iterparse() lets you do stuff while building the tree, that means that unless you remove what you don't need anymore, you'll still end up with the whole tree in the end.

For more information: read this by the author of the original ElementTree implementation (but it's also applicable to lxml)

Why won't you use the "callback" approach of sax?

Try Liza Daly's fast_iter. After processing an element, elem, it calls elem.clear() to remove descendants and also removes preceding siblings.

def fast_iter(context, func, *args, **kwargs):
    """
    http://lxml.de/parsing.html#modifying-the-tree
    Based on Liza Daly's fast_iter
    http://www.ibm.com/developerworks/xml/library/x-hiperfparse/
    See also http://effbot.org/zone/element-iterparse.htm
    """
    for event, elem in context:
        func(elem, *args, **kwargs)
        # It's safe to call clear() here because no descendants will be
        # accessed
        elem.clear()
        # Also eliminate now-empty references from the root node to elem
        for ancestor in elem.xpath('ancestor-or-self::*'):
            while ancestor.getprevious() is not None:
                del ancestor.getparent()[0]
    del context


def process_element(elem):
    print elem.xpath( 'description/text( )' )

context = etree.iterparse( MYFILE, tag='item' )
fast_iter(context,process_element)

Daly's article is an excellent read, especially if you are processing large XML files.

---

Edit: The fast_iter posted above is a modified version of Daly's fast_iter. After processing an element, it is more aggressive at removing other elements that are no longer needed.

The script below shows the difference in behavior. Note in particular that orig_fast_iter does not delete the A1 element, while the mod_fast_iter does delete it, thus saving more memory.

import lxml.etree as ET
import textwrap
import io

def setup_ABC():
    content = textwrap.dedent('''\
      <root>
        <A1>
          <B1></B1>
          <C>1<D1></D1></C>
          <E1></E1>
        </A1>
        <A2>
          <B2></B2>
          <C>2<D></D></C>
          <E2></E2>
        </A2>
      </root>
        ''')
    return content


def study_fast_iter():
    def orig_fast_iter(context, func, *args, **kwargs):
        for event, elem in context:
            print('Processing {e}'.format(e=ET.tostring(elem)))
            func(elem, *args, **kwargs)
            print('Clearing {e}'.format(e=ET.tostring(elem)))
            elem.clear()
            while elem.getprevious() is not None:
                print('Deleting {p}'.format(
                    p=(elem.getparent()[0]).tag))
                del elem.getparent()[0]
        del context

    def mod_fast_iter(context, func, *args, **kwargs):
        """
        http://www.ibm.com/developerworks/xml/library/x-hiperfparse/
        Author: Liza Daly
        See also http://effbot.org/zone/element-iterparse.htm
        """
        for event, elem in context:
            print('Processing {e}'.format(e=ET.tostring(elem)))
            func(elem, *args, **kwargs)
            # It's safe to call clear() here because no descendants will be
            # accessed
            print('Clearing {e}'.format(e=ET.tostring(elem)))
            elem.clear()
            # Also eliminate now-empty references from the root node to elem
            for ancestor in elem.xpath('ancestor-or-self::*'):
                print('Checking ancestor: {a}'.format(a=ancestor.tag))
                while ancestor.getprevious() is not None:
                    print(
                        'Deleting {p}'.format(p=(ancestor.getparent()[0]).tag))
                    del ancestor.getparent()[0]
        del context

    content = setup_ABC()
    context = ET.iterparse(io.BytesIO(content), events=('end', ), tag='C')
    orig_fast_iter(context, lambda elem: None)
    # Processing <C>1<D1/></C>
    # Clearing <C>1<D1/></C>
    # Deleting B1
    # Processing <C>2<D/></C>
    # Clearing <C>2<D/></C>
    # Deleting B2

    print('-' * 80)
    """
    The improved fast_iter deletes A1. The original fast_iter does not.
    """
    content = setup_ABC()
    context = ET.iterparse(io.BytesIO(content), events=('end', ), tag='C')
    mod_fast_iter(context, lambda elem: None)
    # Processing <C>1<D1/></C>
    # Clearing <C>1<D1/></C>
    # Checking ancestor: root
    # Checking ancestor: A1
    # Checking ancestor: C
    # Deleting B1
    # Processing <C>2<D/></C>
    # Clearing <C>2<D/></C>
    # Checking ancestor: root
    # Checking ancestor: A2
    # Deleting A1
    # Checking ancestor: C
    # Deleting B2

study_fast_iter()