XML.com: Introducing PyXML

python setup.py install

from xml.dom.ext.reader import Sax2

DOC = """<?xml version="1.0" encoding="UTF-8"?>
<verse>
  <attribution>Christopher Okibgo</attribution>
  <line>For he was a shrub among the poplars,</line>
  <line>Needing more roots</line>
  <line>More sap to grow to sunlight,</line>
  <line>Thirsting for sunlight</line>
</verse>
"""

#Create an XML reader object
reader = Sax2.Reader()
#Create a 4DOM document node parsed from XML in a string
doc_node = reader.fromString(DOC)

#You can execute regular DOM operations on the document node
verse_element = doc_node.documentElement
#And you can even use "Pythonic" shortcuts for things like
#Node lists and named node maps
#The first child of the verse element is a white space text node
#The second is the attribution element
attribution_element = verse_element.childNodes[1]
#attribution_string becomes "Christopher Okibgo"
attribution_string = attribution_element.firstChild.data

from xml.dom.ext.reader import HtmlLib

#Create an HTML reader object
reader = HtmlLib.Reader()
#Create a 4DOM document node parsed from HTML at a URL
doc_node = reader.fromUri("http://www.python.org")

#Get the title of the HTML document
title_elem = doc_node.documentElement.getElementsByTagName("TITLE")[0]
#title_string becomes "Python Language Website"
title_string = title_elem.firstChild.data

from xml.dom.ext import StripXml, Print
#Strip the white space nodes in place and return the same node
StripXml(doc_node)
#Print the node as serialized XML to stdout
Print(doc_node)
#Write the node as serialized XML to a file
f = open("tmp.xml", "w")
Print(doc_node, stream=f)
f.close()

from xml.dom import implementation
from xml.dom import EMPTY_NAMESPACE, XML_NAMESPACE
from xml.dom.ext import Print

#Create a document type node using the doctype name "message"
#A blank system ID and blank public ID (i.e. no DTD information)
doctype = implementation.createDocumentType("message", None, None)

#Create a document node, which also creates a document element node
#For the element, use a blank namespace URI and local name "message"
doc = implementation.createDocument(EMPTY_NAMESPACE, "message", doctype)

#Get the document element
msg_elem = doc.documentElement

#Create an xml:lang attribute on the new element
msg_elem.setAttributeNS(XML_NAMESPACE, "xml:lang", "en")

#Create a text node with some data in it
new_text = doc.createTextNode("You need Python")

#Add the new text node to the document element
msg_elem.appendChild(new_text)

#Print out the result
Print(doc)

from xml.ns import XSLT
#The XSLT namespace http://www.w3.org/1999/XSL/Transform
NS = XSLT.BASE

from xml.xpath import Context, Evaluate
#Create an XPath context with the given DOM node
#With no other nodes in the context list
#(list size 1, current position 1)
#And the given prefix/namespace mapping
con = Context.Context(doc, 1, 1, processorNss={"xsl": NS})

#Evaluate the XPath expression and return the resulting
#Python list of nodes
result = Evaluate("//xsl:*", context=con)

from xml.marshal.generic import Marshaller
marshal = Marshaller()
obj = {1: [2, 3], 'a': 'b'}
#Dump to a string
xml_form = marshal.dumps(obj)

<?xml version="1.0"?>
<marshal>
  <dictionary id="i2">
    <int>1</int>
    <list id="i3"><int>2</int><int>3</int></list>
    <string>a</string>
    <string>b</string>
  </dictionary>
</marshal>

Happenings...

Setting up PyXML

SAX

DOM

Canonicalization

XPath

Et cetera

Wrap up