如何将 XML 字符串转换为字典?
- 2025-02-18 09:23:00
- admin 原创
- 101
问题描述:
我有一个从套接字读取 XML 文档的程序。我将 XML 文档存储在一个字符串中,我想将其直接转换为 Python 字典,就像在 Django 的库中一样simplejson
。
举个例子:
str ="<?xml version="1.0" ?><person><name>john</name><age>20</age></person"
dic_xml = convert_to_dic(str)
然后dic_xml
看起来像{'person' : { 'name' : 'john', 'age' : 20 } }
解决方案 1:
xmltodict(完整披露:是我写的)就是这样做的:
import xmltodict
xmltodict.parse("""<?xml version="1.0" ?>
<person>
<name>john</name>
<age>20</age>
</person>""")
# {'person': {'age': '20', 'name': 'john'}}
解决方案 2:
这是某人创建的一个很棒的模块。我已经用过好几次了。http
://code.activestate.com/recipes/410469-xml-as-dictionary/
这是来自网站的代码,以防链接出现故障。
from xml.etree import cElementTree as ElementTree
class XmlListConfig(list):
def __init__(self, aList):
for element in aList:
if element:
# treat like dict
if len(element) == 1 or element[0].tag != element[1].tag:
self.append(XmlDictConfig(element))
# treat like list
elif element[0].tag == element[1].tag:
self.append(XmlListConfig(element))
elif element.text:
text = element.text.strip()
if text:
self.append(text)
class XmlDictConfig(dict):
'''
Example usage:
>>> tree = ElementTree.parse('your_file.xml')
>>> root = tree.getroot()
>>> xmldict = XmlDictConfig(root)
Or, if you want to use an XML string:
>>> root = ElementTree.XML(xml_string)
>>> xmldict = XmlDictConfig(root)
And then use xmldict for what it is... a dict.
'''
def __init__(self, parent_element):
if parent_element.items():
self.update(dict(parent_element.items()))
for element in parent_element:
if element:
# treat like dict - we assume that if the first two tags
# in a series are different, then they are all different.
if len(element) == 1 or element[0].tag != element[1].tag:
aDict = XmlDictConfig(element)
# treat like list - we assume that if the first two tags
# in a series are the same, then the rest are the same.
else:
# here, we put the list in dictionary; the key is the
# tag name the list elements all share in common, and
# the value is the list itself
aDict = {element[0].tag: XmlListConfig(element)}
# if the tag has attributes, add those to the dict
if element.items():
aDict.update(dict(element.items()))
self.update({element.tag: aDict})
# this assumes that if you've got an attribute in a tag,
# you won't be having any text. This may or may not be a
# good idea -- time will tell. It works for the way we are
# currently doing XML configuration files...
elif element.items():
self.update({element.tag: dict(element.items())})
# finally, if there are no child tags and no attributes, extract
# the text
else:
self.update({element.tag: element.text})
使用示例:
tree = ElementTree.parse('your_file.xml')
root = tree.getroot()
xmldict = XmlDictConfig(root)
//或者,如果您想使用 XML 字符串:
root = ElementTree.XML(xml_string)
xmldict = XmlDictConfig(root)
解决方案 3:
以下 XML-to-Python-dict 代码片段按照此 XML-to-JSON“规范”解析实体和属性。它是处理所有 XML 情况的最通用解决方案。
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:
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
pprint(etree_to_dict(e))
此示例的输出(按照上面链接的“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 输入会产生更简单的 JSON。:)
更新
如果要执行相反的操作,从 JSON/dict发出XML 字符串,则可以使用:
try:
basestring
except NameError: # python3
basestring = str
def dict_to_etree(d):
def _to_etree(d, root):
if not d:
pass
elif isinstance(d, basestring):
root.text = d
elif isinstance(d, dict):
for k,v in d.items():
assert isinstance(k, basestring)
if k.startswith('#'):
assert k == '#text' and isinstance(v, basestring)
root.text = v
elif k.startswith('@'):
assert isinstance(v, basestring)
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:
raise TypeError('invalid type: ' + str(type(d)))
assert isinstance(d, dict) and len(d) == 1
tag, body = next(iter(d.items()))
node = ET.Element(tag)
_to_etree(body, node)
return ET.tostring(node)
pprint(dict_to_etree(d))
解决方案 4:
这个轻量级版本虽然不可配置,但很容易根据需要进行定制,并且适用于旧版 Python。此外,它是固定的 - 这意味着无论是否存在属性,结果都是相同的。
import xml.etree.ElementTree as ET
from copy import copy
def dictify(r,root=True):
if root:
return {r.tag : dictify(r, False)}
d=copy(r.attrib)
if r.text:
d["_text"]=r.text
for x in r.findall("./*"):
if x.tag not in d:
d[x.tag]=[]
d[x.tag].append(dictify(x,False))
return d
所以:
root = ET.fromstring("<erik><a x='1'>v</a><a y='2'>w</a></erik>")
dictify(root)
结果:
{'erik': {'a': [{'x': '1', '_text': 'v'}, {'y': '2', '_text': 'w'}]}}
解决方案 5:
免责声明:这个修改后的 XML 解析器受到Adam Clark的启发
,原始 XML 解析器适用于大多数简单情况。但是,它不适用于一些复杂的 XML 文件。我逐行调试代码,最终修复了一些问题。如果您发现一些错误,请告诉我。我很乐意修复它。
class XmlDictConfig(dict):
'''
Note: need to add a root into if no exising
Example usage:
>>> tree = ElementTree.parse('your_file.xml')
>>> root = tree.getroot()
>>> xmldict = XmlDictConfig(root)
Or, if you want to use an XML string:
>>> root = ElementTree.XML(xml_string)
>>> xmldict = XmlDictConfig(root)
And then use xmldict for what it is... a dict.
'''
def __init__(self, parent_element):
if parent_element.items():
self.updateShim( dict(parent_element.items()) )
for element in parent_element:
if len(element):
aDict = XmlDictConfig(element)
# if element.items():
# aDict.updateShim(dict(element.items()))
self.updateShim({element.tag: aDict})
elif element.items(): # items() is specialy for attribtes
elementattrib= element.items()
if element.text:
elementattrib.append((element.tag,element.text )) # add tag:text if there exist
self.updateShim({element.tag: dict(elementattrib)})
else:
self.updateShim({element.tag: element.text})
def updateShim (self, aDict ):
for key in aDict.keys(): # keys() includes tag and attributes
if key in self:
value = self.pop(key)
if type(value) is not list:
listOfDicts = []
listOfDicts.append(value)
listOfDicts.append(aDict[key])
self.update({key: listOfDicts})
else:
value.append(aDict[key])
self.update({key: value})
else:
self.update({key:aDict[key]}) # it was self.update(aDict)
解决方案 6:
我编写了一个简单的递归函数来完成这项工作:
from xml.etree import ElementTree
root = ElementTree.XML(xml_to_convert)
def xml_to_dict_recursive(root):
if len(root.getchildren()) == 0:
return {root.tag:root.text}
else:
return {root.tag:list(map(xml_to_dict_recursive, root.getchildren()))}
解决方案 7:
PicklingTools 库的最新版本(1.3.0 和 1.3.1)支持从 XML 转换为 Python 字典的工具。
可从此处下载: PicklingTools 1.3.1
这里有相当多的转换器文档:文档详细描述了在 XML 和 Python 字典之间进行转换时会出现的所有决策和问题(有许多边缘情况:属性、列表、匿名列表、匿名字典、eval 等,大多数转换器无法处理)。但总的来说,转换器很容易使用。如果“example.xml”包含:
<top>
<a>1</a>
<b>2.2</b>
<c>three</c>
</top>
然后将其转换为字典:
>>> from xmlloader import *
>>> example = file('example.xml', 'r') # A document containing XML
>>> xl = StreamXMLLoader(example, 0) # 0 = all defaults on operation
>>> result = xl.expect XML()
>>> print result
{'top': {'a': '1', 'c': 'three', 'b': '2.2'}}
C++ 和 Python 都有转换工具:C++ 和 Python 进行相同的转换,但 C++ 的速度大约快 60 倍
解决方案 8:
你可以使用 lxml 轻松完成此操作。首先安装它:
[sudo] pip install lxml
下面是我编写的一个递归函数,它可以为您完成繁重的工作:
from lxml import objectify as xml_objectify
def xml_to_dict(xml_str):
""" Convert xml to dict, using lxml v3.4.2 xml processing library """
def xml_to_dict_recursion(xml_object):
dict_object = xml_object.__dict__
if not dict_object:
return xml_object
for key, value in dict_object.items():
dict_object[key] = xml_to_dict_recursion(value)
return dict_object
return xml_to_dict_recursion(xml_objectify.fromstring(xml_str))
xml_string = """<?xml version="1.0" encoding="UTF-8"?><Response><NewOrderResp>
<IndustryType>Test</IndustryType><SomeData><SomeNestedData1>1234</SomeNestedData1>
<SomeNestedData2>3455</SomeNestedData2></SomeData></NewOrderResp></Response>"""
print xml_to_dict(xml_string)
以下变体保留父键/元素:
def xml_to_dict(xml_str):
""" Convert xml to dict, using lxml v3.4.2 xml processing library, see http://lxml.de/ """
def xml_to_dict_recursion(xml_object):
dict_object = xml_object.__dict__
if not dict_object: # if empty dict returned
return xml_object
for key, value in dict_object.items():
dict_object[key] = xml_to_dict_recursion(value)
return dict_object
xml_obj = objectify.fromstring(xml_str)
return {xml_obj.tag: xml_to_dict_recursion(xml_obj)}
如果只想返回一个子树并将其转换为字典,可以使用Element.find()获取子树,然后进行转换:
xml_obj.find('.//') # lxml.objectify.ObjectifiedElement instance
请参阅此处的lxml 文档。希望对您有所帮助!
解决方案 9:
另一种选择(按层次结构为相同的标签建立列表):
from xml.etree import cElementTree as ElementTree
def xml_to_dict(xml, result):
for child in xml:
if len(child) == 0:
result[child.tag] = child.text
else:
if child.tag in result:
if not isinstance(result[child.tag], list):
result[child.tag] = [result[child.tag]]
result[child.tag].append(xml_to_dict(child, {}))
else:
result[child.tag] = xml_to_dict(child, {})
return result
xmlTree = ElementTree.parse('my_file.xml')
xmlRoot = xmlTree.getroot()
dictRoot = xml_to_dict(xmlRoot, {})
result = {xmlRoot.tag: dictRoot}
解决方案 10:
def xml_to_dict(node):
u'''
@param node:lxml_node
@return: dict
'''
return {'tag': node.tag, 'text': node.text, 'attrib': node.attrib, 'children': {child.tag: xml_to_dict(child) for child in node}}
解决方案 11:
http://code.activestate.com/recipes/410469-xml-as-dictionary/中的代码运行良好,但如果层次结构中给定位置有多个相同的元素,它就会覆盖它们。
我在两者之间添加了一个垫片,用于在 self.update() 之前查看元素是否已经存在。如果存在,则弹出现有条目并创建一个包含现有条目和新条目的列表。任何后续重复项都将添加到列表中。
不确定是否可以更好地处理这个问题,但它确实有效:
import xml.etree.ElementTree as ElementTree
class XmlDictConfig(dict):
def __init__(self, parent_element):
if parent_element.items():
self.updateShim(dict(parent_element.items()))
for element in parent_element:
if len(element):
aDict = XmlDictConfig(element)
if element.items():
aDict.updateShim(dict(element.items()))
self.updateShim({element.tag: aDict})
elif element.items():
self.updateShim({element.tag: dict(element.items())})
else:
self.updateShim({element.tag: element.text.strip()})
def updateShim (self, aDict ):
for key in aDict.keys():
if key in self:
value = self.pop(key)
if type(value) is not list:
listOfDicts = []
listOfDicts.append(value)
listOfDicts.append(aDict[key])
self.update({key: listOfDicts})
else:
value.append(aDict[key])
self.update({key: value})
else:
self.update(aDict)
解决方案 12:
@dibrovsd:如果 xml 中有多个同名标签,则解决方案将不起作用
按照你的思路,我稍微修改了一下代码,将其编写为通用节点而不是根节点:
from collections import defaultdict
def xml2dict(node):
d, count = defaultdict(list), 1
for i in node:
d[i.tag + "_" + str(count)]['text'] = i.findtext('.')[0]
d[i.tag + "_" + str(count)]['attrib'] = i.attrib # attrib gives the list
d[i.tag + "_" + str(count)]['children'] = xml2dict(i) # it gives dict
return d
解决方案 13:
根据@K3---rnc 的回应(对我来说是最好的),我添加了一些小修改,以从 XML 文本中获取 OrderedDict(有时顺序很重要):
def etree_to_ordereddict(t):
d = OrderedDict()
d[t.tag] = OrderedDict() if t.attrib else None
children = list(t)
if children:
dd = OrderedDict()
for dc in map(etree_to_ordereddict, children):
for k, v in dc.iteritems():
if k not in dd:
dd[k] = list()
dd[k].append(v)
d = OrderedDict()
d[t.tag] = OrderedDict()
for k, v in dd.iteritems():
if len(v) == 1:
d[t.tag][k] = v[0]
else:
d[t.tag][k] = v
if t.attrib:
d[t.tag].update(('@' + k, v) for k, v in t.attrib.iteritems())
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
按照@K3---rnc 示例,您可以使用它:
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
pprint(etree_to_ordereddict(e))
希望有帮助;)
解决方案 14:
这是ActiveState 解决方案的链接- 以及以防它再次消失时的代码。
==================================================
xmlreader.py:
==================================================
from xml.dom.minidom import parse
class NotTextNodeError:
pass
def getTextFromNode(node):
"""
scans through all children of node and gathers the
text. if node has non-text child-nodes, then
NotTextNodeError is raised.
"""
t = ""
for n in node.childNodes:
if n.nodeType == n.TEXT_NODE:
t += n.nodeValue
else:
raise NotTextNodeError
return t
def nodeToDic(node):
"""
nodeToDic() scans through the children of node and makes a
dictionary from the content.
three cases are differentiated:
- if the node contains no other nodes, it is a text-node
and {nodeName:text} is merged into the dictionary.
- if the node has the attribute "method" set to "true",
then it's children will be appended to a list and this
list is merged to the dictionary in the form: {nodeName:list}.
- else, nodeToDic() will call itself recursively on
the nodes children (merging {nodeName:nodeToDic()} to
the dictionary).
"""
dic = {}
for n in node.childNodes:
if n.nodeType != n.ELEMENT_NODE:
continue
if n.getAttribute("multiple") == "true":
# node with multiple children:
# put them in a list
l = []
for c in n.childNodes:
if c.nodeType != n.ELEMENT_NODE:
continue
l.append(nodeToDic(c))
dic.update({n.nodeName:l})
continue
try:
text = getTextFromNode(n)
except NotTextNodeError:
# 'normal' node
dic.update({n.nodeName:nodeToDic(n)})
continue
# text node
dic.update({n.nodeName:text})
continue
return dic
def readConfig(filename):
dom = parse(filename)
return nodeToDic(dom)
def test():
dic = readConfig("sample.xml")
print dic["Config"]["Name"]
print
for item in dic["Config"]["Items"]:
print "Item's Name:", item["Name"]
print "Item's Value:", item["Value"]
test()
==================================================
sample.xml:
==================================================
<?xml version="1.0" encoding="UTF-8"?>
<Config>
<Name>My Config File</Name>
<Items multiple="true">
<Item>
<Name>First Item</Name>
<Value>Value 1</Value>
</Item>
<Item>
<Name>Second Item</Name>
<Value>Value 2</Value>
</Item>
</Items>
</Config>
==================================================
output:
==================================================
My Config File
Item's Name: First Item
Item's Value: Value 1
Item's Name: Second Item
Item's Value: Value 2
解决方案 15:
firelion.cis发布的更新方法(因为 getchildren 已被弃用):
from xml.etree import ElementTree
root = ElementTree.XML(xml_to_convert)
def xml_to_dict_recursive(root):
if len(list(root)) == 0:
return {root.tag:root.text}
else:
return {root.tag:list(map(xml_to_dict_recursive, list(root)))}
解决方案 16:
有一次,我不得不解析和编写仅由没有属性的元素组成的 XML,因此很容易实现从 XML 到 dict 的 1:1 映射。这是我想到的,以防其他人也不需要属性:
def xmltodict(element):
if not isinstance(element, ElementTree.Element):
raise ValueError("must pass xml.etree.ElementTree.Element object")
def xmltodict_handler(parent_element):
result = dict()
for element in parent_element:
if len(element):
obj = xmltodict_handler(element)
else:
obj = element.text
if result.get(element.tag):
if hasattr(result[element.tag], "append"):
result[element.tag].append(obj)
else:
result[element.tag] = [result[element.tag], obj]
else:
result[element.tag] = obj
return result
return {element.tag: xmltodict_handler(element)}
def dicttoxml(element):
if not isinstance(element, dict):
raise ValueError("must pass dict type")
if len(element) != 1:
raise ValueError("dict must have exactly one root key")
def dicttoxml_handler(result, key, value):
if isinstance(value, list):
for e in value:
dicttoxml_handler(result, key, e)
elif isinstance(value, basestring):
elem = ElementTree.Element(key)
elem.text = value
result.append(elem)
elif isinstance(value, int) or isinstance(value, float):
elem = ElementTree.Element(key)
elem.text = str(value)
result.append(elem)
elif value is None:
result.append(ElementTree.Element(key))
else:
res = ElementTree.Element(key)
for k, v in value.items():
dicttoxml_handler(res, k, v)
result.append(res)
result = ElementTree.Element(element.keys()[0])
for key, value in element[element.keys()[0]].items():
dicttoxml_handler(result, key, value)
return result
def xmlfiletodict(filename):
return xmltodict(ElementTree.parse(filename).getroot())
def dicttoxmlfile(element, filename):
ElementTree.ElementTree(dicttoxml(element)).write(filename)
def xmlstringtodict(xmlstring):
return xmltodict(ElementTree.fromstring(xmlstring).getroot())
def dicttoxmlstring(element):
return ElementTree.tostring(dicttoxml(element))
解决方案 17:
我已经根据自己的喜好修改了其中一个答案,并使用了同一个标签的多个值,例如考虑保存在 XML.xml 文件中的以下 xml 代码
<A>
<B>
<BB>inAB</BB>
<C>
<D>
<E>
inABCDE
</E>
<E>value2</E>
<E>value3</E>
</D>
<inCout-ofD>123</inCout-ofD>
</C>
</B>
<B>abc</B>
<F>F</F>
</A>
在 Python 中
import xml.etree.ElementTree as ET
class XMLToDictionary(dict):
def __init__(self, parentElement):
self.parentElement = parentElement
for child in list(parentElement):
child.text = child.text if (child.text != None) else ' '
if len(child) == 0:
self.update(self._addToDict(key= child.tag, value = child.text.strip(), dict = self))
else:
innerChild = XMLToDictionary(parentElement=child)
self.update(self._addToDict(key=innerChild.parentElement.tag, value=innerChild, dict=self))
def getDict(self):
return {self.parentElement.tag: self}
class _addToDict(dict):
def __init__(self, key, value, dict):
if not key in dict:
self.update({key: value})
else:
identical = dict[key] if type(dict[key]) == list else [dict[key]]
self.update({key: identical + [value]})
tree = ET.parse('./XML.xml')
root = tree.getroot()
parseredDict = XMLToDictionary(root).getDict()
print(parseredDict)
输出是
{'A': {'B': [{'BB': 'inAB', 'C': {'D': {'E': ['inABCDE', 'value2', 'value3']}, 'inCout-ofD': '123'}}, 'abc'], 'F': 'F'}}
解决方案 18:
import xml.etree.ElementTree as ET
root = ET.parse(xml_filepath).getroot()
def parse_xml(node):
ans = {}
for child in node:
if len(child) == 0:
ans[child.tag] = child.text
elif child.tag not in ans:
ans[child.tag] = parse_xml(child)
elif not isinstance(ans[child.tag], list):
ans[child.tag] = [ans[child.tag]]
ans[child.tag].append(parse_xml(child))
else:
ans[child.tag].append(parse_xml(child))
return ans
它将相同的字段合并到列表中,并挤压包含一个子字段的字段。
解决方案 19:
fvg对firelion.cis 答案的修复的略微改进版本。该函数很简单,适用于简单的 XML,并避免使用最内层的单例字典。不适用于带有标签的复杂 XML,或者 XML 中有多个同名标签的情况。
from xml.etree import ElementTree
# Replace xml_to_convert below
root = ElementTree.XML(xml_to_convert)
def xml_to_dict(root):
if len(root):
return {root.tag:{k:v for d in map(xml_to_dict, root)
for k,v in d.items() }}
else:
return {root.tag:root.text}
示例 XML:
<student>
<FirstName>SMITH</FirstName>
<LastName>JAMES</LastName>
<fees>
<Amount>2400</Amount>
<Currency>USD</Currency>
</fees>
</student>
输出(格式化):
{'student': {'FirstName': 'SMITH',
'LastName': 'JAMES',
'fees': {'Amount': '2400',
'Currency': 'USD'}
}
}
解决方案 20:
我有一个递归方法可以从 lxml 元素中获取字典
def recursive_dict(element):
return (element.tag.split('}')[1],
dict(map(recursive_dict, element.getchildren()),
**element.attrib))
扫码咨询,免费领取项目管理大礼包!