6-4 How to build xml document

 

>>> from xml.etree.ElementTree import Element,ElementTree

Element is the node element

ElementTree is composed of Element

1. Create an element

>>> e = Element( " Data " )    #Create an element, pass in a string <Data> is the name of the head 
>>> e.set( ' name ' , ' abc ' )    # The attributes of this element, get gets the property, set sets the property. The attribute is 'name' and the value is abc

>>> help(Element.set)
Help on method set in module xml.etree.ElementTree:

set(self, key, value) unbound xml.etree.ElementTree.Element method

help(Element.set)

>>> from xml.etree.ElementTree import tostring #Displayed as an XML element and converted into a string 
>>> tostring(e)
 ' <Data name="abc" /> '

All content of #XML elements should be strings and should not be other data types

>>> e.text = 123
>>> tostring(e)

Traceback (most recent call last):
  File "<pyshell#13>", line 1, in <module>
    tostring(e)
  File "C:\Python27\lib\xml\etree\ElementTree.py", line 1126, in tostring
    ElementTree(element).write(file, encoding, method=method)
  File "C:\Python27\lib\xml\etree\ElementTree.py", line 820, in write
    serialize(write, self._root, encoding, qnames, namespaces)
  File "C:\Python27\lib\xml\etree\ElementTree.py", line 937, in _serialize_xml
    write(_escape_cdata(text, encoding))
  File "C:\Python27\lib\xml\etree\ElementTree.py", line 1075, in _escape_cdata
    _raise_serialization_error(text)
  File "C:\Python27\lib\xml\etree\ElementTree.py", line 1052, in _raise_serialization_error
    "cannot serialize %r (type %s)" % (text, type(text).__name__)
TypeError: cannot serialize 123 (type int)

>>> e.text = '123'
>>> tostring(e)
'<Data name="abc">123</Data>'

2. Add child elements to an element

>>> e2 = Element( ' Row ' )           # create an element 
>>> e3 = Element( ' Open ' )
 >>> e3.text = ' 8.80 ' 
>>> e2.append(e3)         # add e3 to e2 becomes its child element 
>>> tostring(e2)
 ' <Row><Open>8.80</Open></Row> '

>>> help(Element.append)
Help on method append in module xml.etree.ElementTree:

append(self, element) unbound xml.etree.ElementTree.Element method

help(Element.append)

#Method to delete an assigned element attribute

>>> e.text
'123'
>>> e.text = None
>>> tostring(e)
'<Data name="abc" />'

>>> e.append(e2)
>>> tostring(e)
'<Data name="abc"><Row><Open>8.80</Open></Row></Data>'

3. Write the string in XML format to the file

(1) Create an ElementTree

>>> et = ElementTree(e)
>>> et
<xml.etree.ElementTree.ElementTree object at 0x027166B0>

(2) Use the write method of the ElementTree object

>>> et.write(r " C:\video\python efficient practice skills notes\6 data encoding and processing related topics\6-4.xml " )

 

Example: Convert the csv file bank-databak.csv in 6-1 into an xml file, the script file is

import csv
from xml.etree.ElementTree import Element, ElementTree
“””
Beautify the xml file, that is, make the output xml file have a reasonable indentation format
“””
def pretty(e,level = 0):
    if(len(e)>0):
        e.text = '\n' + '\t' * (level+1)
        for child in e:
            pretty(child,level+1)
        child.tail = child.tail[:-1]
    e.tail = '\n' +'\t'*level

“”“
CSV file to XML file, the parameter is the path of the CSV file
”“”
def CsvToXml(fname):
    with open(fname) as f:         #Open the CSV file 
        reader = csv.reader(f) #Read         the CSV file 
        head = reader.next() #Get         the header of the CSV file 
        root = Element( ' Data ' )         #Create XML an element as the root node


        for row in reader:         #Iterate over the header of the CSV 
            eRow = Element( ' Row ' )     # #Create an element Row 
            root.append(eRow) #Add         this Row element to the root as a child node 
            for tag, text   in zip(head,row): Iterates each item of the header and each item of each row of the CSV file at the same time
                e = Element(tag)      #Take the item of the CSV header as an element of the XML file 
                e.text = text #Take         the content of each item of each line in the CSV file as the value of each element of the XML. 
                eRow.append(e) #Add       this element of e to Row as a child node 
    pretty(root)             #Beautify the XML file 
    return ElementTree(root)         #Return an EleMentTree object

#Call the conversion function and return an ElementTree object 
et = CsvToXml(r ' C:\video\python efficient practice skills notes\6 topics related to data encoding and processing\bank-databak.csv ' )

#Write the returned ElementTree object to the file 
et.write(r ' C:\video\python efficient practice skills notes\6 topics related to data encoding and processing\bank-databak.xml ' )

 

result: