检查lxml2json(披露:我写的)

https://github.com/rparelius/lxml2json

它非常快速、轻量级(只需要lxml)，一个优点是您可以控制某些元素是转换为列表还是字典

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"
                      }
                    ]
                  }
                ]
              }
            ]
          }
        ]
      }
    ]
  }
]

当我在python中处理XML时，我几乎总是使用lxml包。我怀疑大多数人都使用lxml。您可以使用xmltodict，但您将不得不再次解析XML。

用lxml将XML转换为json:

用lxml解析XML文档 将lxml转换为dict 将列表转换为json

我在我的项目中使用下面的类。使用toJson方法。

from lxml import etree 
import json


class Element:
    '''
    Wrapper on the etree.Element class.  Extends functionality to output element
    as a dictionary.
    '''

    def __init__(self, element):
        '''
        :param: element a normal etree.Element instance
        '''
        self.element = element

    def toDict(self):
        '''
        Returns the element as a dictionary.  This includes all child elements.
        '''
        rval = {
            self.element.tag: {
                'attributes': dict(self.element.items()),
            },
        }
        for child in self.element:
            rval[self.element.tag].update(Element(child).toDict())
        return rval


class XmlDocument:
    '''
    Wraps lxml to provide:
        - cleaner access to some common lxml.etree functions
        - converter from XML to dict
        - converter from XML to json
    '''
    def __init__(self, xml = '<empty/>', filename=None):
        '''
        There are two ways to initialize the XmlDocument contents:
            - String
            - File

        You don't have to initialize the XmlDocument during instantiation
        though.  You can do it later with the 'set' method.  If you choose to
        initialize later XmlDocument will be initialized with "<empty/>".

        :param: xml Set this argument if you want to parse from a string.
        :param: filename Set this argument if you want to parse from a file.
        '''
        self.set(xml, filename) 

    def set(self, xml=None, filename=None):
        '''
        Use this to set or reset the contents of the XmlDocument.

        :param: xml Set this argument if you want to parse from a string.
        :param: filename Set this argument if you want to parse from a file.
        '''
        if filename is not None:
            self.tree = etree.parse(filename)
            self.root = self.tree.getroot()
        else:
            self.root = etree.fromstring(xml)
            self.tree = etree.ElementTree(self.root)


    def dump(self):
        etree.dump(self.root)

    def getXml(self):
        '''
        return document as a string
        '''
        return etree.tostring(self.root)

    def xpath(self, xpath):
        '''
        Return elements that match the given xpath.

        :param: xpath
        '''
        return self.tree.xpath(xpath);

    def nodes(self):
        '''
        Return all elements
        '''
        return self.root.iter('*')

    def toDict(self):
        '''
        Convert to a python dictionary
        '''
        return Element(self.root).toDict()

    def toJson(self, indent=None):
        '''
        Convert to JSON
        '''
        return json.dumps(self.toDict(), indent=indent)


if __name__ == "__main__":
    xml='''<system>
    <product>
        <demod>
            <frequency value='2.215' units='MHz'>
                <blah value='1'/>
            </frequency>
        </demod>
    </product>
</system>
'''
    doc = XmlDocument(xml)
    print doc.toJson(indent=4)

内置main的输出是:

{
    "system": {
        "attributes": {}, 
        "product": {
            "attributes": {}, 
            "demod": {
                "attributes": {}, 
                "frequency": {
                    "attributes": {
                        "units": "MHz", 
                        "value": "2.215"
                    }, 
                    "blah": {
                        "attributes": {
                            "value": "1"
                        }
                    }
                }
            }
        }
    }
}

它是xml的一个转换:

<system>
    <product>
        <demod>
            <frequency value='2.215' units='MHz'>
                <blah value='1'/>
            </frequency>
        </demod>
    </product>
</system>

Jsonpickle或者如果你使用feedparser，你可以尝试feed_parser_to_json.py

您可以使用xmljson库使用不同的XML JSON约定进行转换。

例如，这个XML:

<p id="1">text</p>

通过BadgerFish惯例翻译为:

{
  'p': {
    '@id': 1,
    '$': 'text'
  }
}

并通过GData约定转换成这个(不支持属性):

{
  'p': {
    '$t': 'text'
  }
}

．.． 并通过Parker约定转换为这个(不支持属性):

{
  'p': 'text'
}

可以使用相同的方法从XML转换为JSON，也可以从JSON转换为XML 约定:

>>> import json, xmljson
>>> from lxml.etree import fromstring, tostring
>>> xml = fromstring('<p id="1">text</p>')
>>> json.dumps(xmljson.badgerfish.data(xml))
'{"p": {"@id": 1, "$": "text"}}'
>>> xmljson.parker.etree({'ul': {'li': [1, 2]}})
# Creates [<ul><li>1</li><li>2</li></ul>]

披露:这个库是我写的。希望它能帮助未来的搜索者。