Converting xml to dictionary using ElementTree

Solution 1:

The following XML-to-Python-dict snippet parses entities as well as attributes following this XML-to-JSON "specification":

from collections import defaultdict

def etree_to_dict(t):
    d = {t.tag: {} if t.attrib else None}
    children = list(t)
    if children:
        dd = defaultdict(list)
        for dc in map(etree_to_dict, children):
            for k, v in dc.items():
                dd[k].append(v)
        d = {t.tag: {k: v[0] if len(v) == 1 else v
                     for k, v in dd.items()}}
    if t.attrib:
        d[t.tag].update(('@' + k, v)
                        for k, v in t.attrib.items())
    if t.text:
        text = t.text.strip()
        if children or t.attrib:
            if text:
                d[t.tag]['#text'] = text
        else:
            d[t.tag] = text
    return d

It is used:

from xml.etree import cElementTree as ET
e = ET.XML('''
<root>
  <e />
  <e>text</e>
  <e name="value" />
  <e name="value">text</e>
  <e> <a>text</a> <b>text</b> </e>
  <e> <a>text</a> <a>text</a> </e>
  <e> text <a>text</a> </e>
</root>
''')

from pprint import pprint

d = etree_to_dict(e)

pprint(d)

The output of this example (as per above-linked "specification") should be:

{'root': {'e': [None,
                'text',
                {'@name': 'value'},
                {'#text': 'text', '@name': 'value'},
                {'a': 'text', 'b': 'text'},
                {'a': ['text', 'text']},
                {'#text': 'text', 'a': 'text'}]}}

Not necessarily pretty, but it is unambiguous, and simpler XML inputs result in simpler JSON. :)

Update

If you want to do the reverse, emit an XML string from a JSON/dict, you can use:

try:
  basestring
except NameError:  # python3
  basestring = str

def dict_to_etree(d):
    def _to_etree(d, root):
        if not d:
            pass
        elif isinstance(d, str):
            root.text = d
        elif isinstance(d, dict):
            for k,v in d.items():
                assert isinstance(k, str)
                if k.startswith('#'):
                    assert k == '#text' and isinstance(v, str)
                    root.text = v
                elif k.startswith('@'):
                    assert isinstance(v, str)
                    root.set(k[1:], v)
                elif isinstance(v, list):
                    for e in v:
                        _to_etree(e, ET.SubElement(root, k))
                else:
                    _to_etree(v, ET.SubElement(root, k))
        else:
            assert d == 'invalid type', (type(d), d)
    assert isinstance(d, dict) and len(d) == 1
    tag, body = next(iter(d.items()))
    node = ET.Element(tag)
    _to_etree(body, node)
    return node

print(ET.tostring(dict_to_etree(d)))

Solution 2:

def etree_to_dict(t):
    d = {t.tag : map(etree_to_dict, t.iterchildren())}
    d.update(('@' + k, v) for k, v in t.attrib.iteritems())
    d['text'] = t.text
    return d

Call as

tree = etree.parse("some_file.xml")
etree_to_dict(tree.getroot())

This works as long as you don't actually have an attribute text; if you do, then change the third line in the function body to use a different key. Also, you can't handle mixed content with this.

(Tested on LXML.)

Solution 3:

Based on @larsmans, if you don't need attributes, this will give you a tighter dictionary --

def etree_to_dict(t):
    return {t.tag : map(etree_to_dict, t.iterchildren()) or t.text}

Solution 4:

For transforming XML from/to python dictionaries, xmltodict has worked great for me:

import xmltodict

xml = '''
<root>
  <e />
  <e>text</e>
  <e name="value" />
  <e name="value">text</e>
  <e> <a>text</a> <b>text</b> </e>
  <e> <a>text</a> <a>text</a> </e>
  <e> text <a>text</a> </e>
</root>
'''

xdict = xmltodict.parse(xml)

xdict will now look like

OrderedDict([('root',
              OrderedDict([('e',
                            [None,
                             'text',
                             OrderedDict([('@name', 'value')]),
                             OrderedDict([('@name', 'value'),
                                          ('#text', 'text')]),
                             OrderedDict([('a', 'text'), ('b', 'text')]),
                             OrderedDict([('a', ['text', 'text'])]),
                             OrderedDict([('a', 'text'),
                                          ('#text', 'text')])])]))])

If your XML data is not in raw string/bytes form but in some ElementTree object, you just need to print it out as a string and use xmldict.parse again. For instance, if you are using lxml to process the XML documents, then

from lxml import etree
e = etree.XML(xml)
xmltodict.parse(etree.tostring(e))

will produce the same dictionary as above.

Solution 5:

Here is a simple data structure in xml (save as file.xml):

<?xml version="1.0" encoding="UTF-8"?>
<Data>
  <Person>
    <First>John</First>
    <Last>Smith</Last>
  </Person>
  <Person>
    <First>Jane</First>
    <Last>Doe</Last>
  </Person>
</Data>

Here is the code to create a list of dictionary objects from it.

from lxml import etree
tree = etree.parse('file.xml')
root = tree.getroot()
datadict = []
for item in root:
    d = {}
    for elem in item:
        d[elem.tag]=elem.text
    datadict.append(d)

datadict now contains:

[{'First': 'John', 'Last': 'Smith'},{'First': 'Jane', 'Last': 'Doe'}]

and can be accessed like so:

datadict[0]['First']
'John'
datadict[1]['Last']
'Doe'