我在网上看到过相当多笨拙的XML->JSON代码，并与Stack的用户进行了一些互动，我相信这群人能比谷歌结果的前几页提供更多的帮助。
因此，我们正在解析一个天气提要，我们需要在许多网站上填充天气小部件。我们现在正在研究基于python的解决方案。
这个公共weather.com RSS提要是我们将要解析的内容的一个很好的例子(我们实际的weather.com提要包含额外的信息，因为与他们有合作关系)。
简而言之，如何使用Python将XML转换为JSON ?
当前回答
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"
}
]
}
]
}
]
}
]
}
]
}
]
其他回答
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 ):
...
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"
}
]
}
]
}
]
}
]
}
]
}
]
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。
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
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()
推荐文章
- 在Python中获取大文件的MD5哈希值
- 在Python格式字符串中%s是什么意思?
- 如何循环通过所有但最后一项的列表?
- python用什么方法避免默认参数为空列表?
- ValueError: numpy。Ndarray大小改变，可能表示二进制不兼容。期望从C头得到88，从PyObject得到80
- Anaconda /conda -安装特定的软件包版本
- 我在哪里调用Keras的BatchNormalization函数?
- 打印测试执行时间并使用py.test锁定缓慢的测试
- 插入一行到熊猫数据框架
- 要列出Pandas DataFrame列
- 在Django模型中存储电话号码的最佳方法是什么?
- 从导入的模块中模拟函数
- 使用Jackson将JSON字符串转换为漂亮的打印JSON输出
- 滚动或滑动窗口迭代器?
- python的方法找到最大值和它的索引在一个列表?
