这是我为此编写的代码。没有对内容进行解析，只是简单的转换。

from xml.dom import minidom
import simplejson as json
def parse_element(element):
    dict_data = dict()
    if element.nodeType == element.TEXT_NODE:
        dict_data['data'] = element.data
    if element.nodeType not in [element.TEXT_NODE, element.DOCUMENT_NODE, 
                                element.DOCUMENT_TYPE_NODE]:
        for item in element.attributes.items():
            dict_data[item[0]] = item[1]
    if element.nodeType not in [element.TEXT_NODE, element.DOCUMENT_TYPE_NODE]:
        for child in element.childNodes:
            child_name, child_dict = parse_element(child)
            if child_name in dict_data:
                try:
                    dict_data[child_name].append(child_dict)
                except AttributeError:
                    dict_data[child_name] = [dict_data[child_name], child_dict]
            else:
                dict_data[child_name] = child_dict 
    return element.nodeName, dict_data

if __name__ == '__main__':
    dom = minidom.parse('data.xml')
    f = open('data.json', 'w')
    f.write(json.dumps(parse_element(dom), sort_keys=True, indent=4))
    f.close()

xmltodict(完全公开:是我写的)可以帮助您按照这个“标准”将XML转换为字典+列表+字符串结构。它是基于expat的，所以速度非常快，而且不需要在内存中加载整个XML树。

一旦你有了这个数据结构，你可以将它序列化为JSON:

import xmltodict, json

o = xmltodict.parse('<e> <a>text</a> <a>text</a> </e>')
json.dumps(o) # '{"e": {"a": ["text", "text"]}}'

我发现对于简单的XML片段，使用正则表达式会省事。例如:

# <user><name>Happy Man</name>...</user>
import re
names = re.findall(r'<name>(\w+)<\/name>', xml_string)
# do some thing to names

正如@Dan所说，要通过XML解析来做到这一点，并没有万能的解决方案，因为数据是不同的。我的建议是使用lxml。虽然没有完成json, lxml。物化的效果很好:

>>> from lxml import objectify
>>> root = objectify.fromstring("""
... <root xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance">
...   <a attr1="foo" attr2="bar">1</a>
...   <a>1.2</a>
...   <b>1</b>
...   <b>true</b>
...   <c>what?</c>
...   <d xsi:nil="true"/>
... </root>
... """)

>>> print(str(root))
root = None [ObjectifiedElement]
    a = 1 [IntElement]
      * attr1 = 'foo'
      * attr2 = 'bar'
    a = 1.2 [FloatElement]
    b = 1 [IntElement]
    b = True [BoolElement]
    c = 'what?' [StringElement]
    d = None [NoneElement]
      * xsi:nil = 'true'

我建议不要直接转换。将XML转换为对象，然后从对象转换为JSON。

在我看来，这为XML和JSON如何对应提供了一个更清晰的定义。

这需要时间来调整，你甚至可以编写工具来帮助你生成一些内容，但它大致如下所示:

class Channel:
  def __init__(self)
    self.items = []
    self.title = ""

  def from_xml( self, xml_node ):
    self.title = xml_node.xpath("title/text()")[0]
    for x in xml_node.xpath("item"):
      item = Item()
      item.from_xml( x )
      self.items.append( item )

  def to_json( self ):
    retval = {}
    retval['title'] = title
    retval['items'] = []
    for x in items:
      retval.append( x.to_json() )
    return retval

class Item:
  def __init__(self):
    ...

  def from_xml( self, xml_node ):
    ...

  def to_json( self ):
    ...

献给任何可能还需要这个的人。下面是一个更新的、简单的代码来进行这种转换。

from xml.etree import ElementTree as ET

xml    = ET.parse('FILE_NAME.xml')
parsed = parseXmlToJson(xml)


def parseXmlToJson(xml):
  response = {}

  for child in list(xml):
    if len(list(child)) > 0:
      response[child.tag] = parseXmlToJson(child)
    else:
      response[child.tag] = child.text or ''

    # one-liner equivalent
    # response[child.tag] = parseXmlToJson(child) if len(list(child)) > 0 else child.text or ''

  return response

如果您不想使用任何外部库和第三方工具，请尝试下面的代码。

Code

import re
import json

def getdict(content):
    res=re.findall("<(?P<var>\S*)(?P<attr>[^/>]*)(?:(?:>(?P<val>.*?)</(?P=var)>)|(?:/>))",content)
    if len(res)>=1:
        attreg="(?P<avr>\S+?)(?:(?:=(?P<quote>['\"])(?P<avl>.*?)(?P=quote))|(?:=(?P<avl1>.*?)(?:\s|$))|(?P<avl2>[\s]+)|$)"
        if len(res)>1:
            return [{i[0]:[{"@attributes":[{j[0]:(j[2] or j[3] or j[4])} for j in re.findall(attreg,i[1].strip())]},{"$values":getdict(i[2])}]} for i in res]
        else:
            return {res[0]:[{"@attributes":[{j[0]:(j[2] or j[3] or j[4])} for j in re.findall(attreg,res[1].strip())]},{"$values":getdict(res[2])}]}
    else:
        return content

with open("test.xml","r") as f:
    print(json.dumps(getdict(f.read().replace('\n',''))))

样例输入

<details class="4b" count=1 boy>
    <name type="firstname">John</name>
    <age>13</age>
    <hobby>Coin collection</hobby>
    <hobby>Stamp collection</hobby>
    <address>
        <country>USA</country>
        <state>CA</state>
    </address>
</details>
<details empty="True"/>
<details/>
<details class="4a" count=2 girl>
    <name type="firstname">Samantha</name>
    <age>13</age>
    <hobby>Fishing</hobby>
    <hobby>Chess</hobby>
    <address current="no">
        <country>Australia</country>
        <state>NSW</state>
    </address>
</details>

输出

[
  {
    "details": [
      {
        "@attributes": [
          {
            "class": "4b"
          },
          {
            "count": "1"
          },
          {
            "boy": ""
          }
        ]
      },
      {
        "$values": [
          {
            "name": [
              {
                "@attributes": [
                  {
                    "type": "firstname"
                  }
                ]
              },
              {
                "$values": "John"
              }
            ]
          },
          {
            "age": [
              {
                "@attributes": []
              },
              {
                "$values": "13"
              }
            ]
          },
          {
            "hobby": [
              {
                "@attributes": []
              },
              {
                "$values": "Coin collection"
              }
            ]
          },
          {
            "hobby": [
              {
                "@attributes": []
              },
              {
                "$values": "Stamp collection"
              }
            ]
          },
          {
            "address": [
              {
                "@attributes": []
              },
              {
                "$values": [
                  {
                    "country": [
                      {
                        "@attributes": []
                      },
                      {
                        "$values": "USA"
                      }
                    ]
                  },
                  {
                    "state": [
                      {
                        "@attributes": []
                      },
                      {
                        "$values": "CA"
                      }
                    ]
                  }
                ]
              }
            ]
          }
        ]
      }
    ]
  },
  {
    "details": [
      {
        "@attributes": [
          {
            "empty": "True"
          }
        ]
      },
      {
        "$values": ""
      }
    ]
  },
  {
    "details": [
      {
        "@attributes": []
      },
      {
        "$values": ""
      }
    ]
  },
  {
    "details": [
      {
        "@attributes": [
          {
            "class": "4a"
          },
          {
            "count": "2"
          },
          {
            "girl": ""
          }
        ]
      },
      {
        "$values": [
          {
            "name": [
              {
                "@attributes": [
                  {
                    "type": "firstname"
                  }
                ]
              },
              {
                "$values": "Samantha"
              }
            ]
          },
          {
            "age": [
              {
                "@attributes": []
              },
              {
                "$values": "13"
              }
            ]
          },
          {
            "hobby": [
              {
                "@attributes": []
              },
              {
                "$values": "Fishing"
              }
            ]
          },
          {
            "hobby": [
              {
                "@attributes": []
              },
              {
                "$values": "Chess"
              }
            ]
          },
          {
            "address": [
              {
                "@attributes": [
                  {
                    "current": "no"
                  }
                ]
              },
              {
                "$values": [
                  {
                    "country": [
                      {
                        "@attributes": []
                      },
                      {
                        "$values": "Australia"
                      }
                    ]
                  },
                  {
                    "state": [
                      {
                        "@attributes": []
                      },
                      {
                        "$values": "NSW"
                      }
                    ]
                  }
                ]
              }
            ]
          }
        ]
      }
    ]
  }
]