以下 XML-to-Python-dict 片段解析实体以及以下属性这个 XML 到 JSON“规范” http://www.xml.com/pub/a/2006/05/31/converting-between-xml-and-json.html:
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
它的用途是:
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)
此示例的输出(根据上面链接的“规范”)应该是:
{'root': {'e': [None,
'text',
{'@name': 'value'},
{'#text': 'text', '@name': 'value'},
{'a': 'text', 'b': 'text'},
{'a': ['text', 'text']},
{'#text': 'text', 'a': 'text'}]}}
不一定漂亮,但它是明确的,更简单的 XML 输入会导致更简单的 JSON。 :)
Update
如果你想做reverse,发出一个来自 JSON/dict 的 XML 字符串, 您可以使用:
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)))