Python-XML to Dict

# Converting xml to dictionary using ElementTree

XML转字典

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

字典转XML

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

试验

from xml.etree import cElementTree as ET
e = ET.XML('''
   <train file_name="208-2.xls" table_number="350" train_number="6184," train_type="TGV">
      <station depart="1457" font="b" name="Nice Ville" stop_id="0">
         <ref>360</ref>
      </station>
      <station depart="1513" name="Antibes" stop_id="1">
         <ref>360</ref>
      </station>
      <station depart="1527" font="b" name="Cannes" stop_id="2">
         <ref>360</ref>
      </station>
      <station depart="1554" name="Saint-Raphaël-Valescure" stop_id="3">
         <ref>360</ref>
      </station>
      <station depart="1648" font="b" name="Toulon" stop_id="4">
         <ref>360</ref>
      </station>
      <station depart="1801" font="b" name="Avignon TGV" stop_id="5"/>
      <station arrive="2041" font="b" name="Paris Gare de Lyon" stop_id="6"/>
   </train>
''')

from pprint import pprint
d = etree_to_dict(e)
pprint(d)
"""
输出字典为：
{'train': {'@file_name': '208-2.xls',
           '@table_number': '350',
           '@train_number': '6184,',
           '@train_type': 'TGV',
           'station': [{'@depart': '1457',
                        '@font': 'b',
                        '@name': 'Nice Ville',
                        '@stop_id': '0',
                        'ref': '360'},
                       {'@depart': '1513',
                        '@name': 'Antibes',
                        '@stop_id': '1',
                        'ref': '360'},
                       {'@depart': '1527',
                        '@font': 'b',
                        '@name': 'Cannes',
                        '@stop_id': '2',
                        'ref': '360'},
                       {'@depart': '1554',
                        '@name': 'Saint-Raphaël-Valescure',
                        '@stop_id': '3',
                        'ref': '360'},
                       {'@depart': '1648',
                        '@font': 'b',
                        '@name': 'Toulon',
                        '@stop_id': '4',
                        'ref': '360'},
                       {'@depart': '1801',
                        '@font': 'b',
                        '@name': 'Avignon TGV',
                        '@stop_id': '5'},
                       {'@arrive': '2041',
                        '@font': 'b',
                        '@name': 'Paris Gare de Lyon',
                        '@stop_id': '6'}]}}
"""
# 变回来
print(ET.tostring(dict_to_etree(d)))