Living Code

There are many DOM options in Python, and I have trouble remembering how to load a document into the various DOMs. Here are a few common ones, although there are many variations on them (loading from URL or string, different configurations, etc.). This should provide a starting point.


# Examples for reading in various DOMs from an XML file

# MiniDOM
def parseMinidom(filename):
try:
from xml.dom.minidom import parse
doc = parse(filename)
return doc
except Exception, e:
return 'parseMinidom() failed with exception %s' % e

# 4DOM
def parse4Dom(filename):
try:
from xml.dom.ext.reader.Sax2 import Reader
f = file(filename)
reader = Reader(validate=0,keepAllWs=0,catName=None)
doc = reader.fromStream(f) # slow!
f.close()
return doc
except Exception, e:
return 'parse4Dom() failed with exception %s' % e

# Domlette
def parseDomlette(filename):
try:
from Ft.Xml.Domlette import NonvalidatingReader as reader
f = file(filename)
uri = 'file:///%s' % filename # suppress warning
doc = reader.parseStream(f, uri)
f.close()
return doc
except Exception, e:
return 'parseDomlette() failed with exception %s' % e

# libXml
def parseLibXml(filename):
try:
import libxml2
f = file(filename)
data = f.read()
f.close()
doc = libxml2.parseDoc(data)
return doc
except Exception, e:
return 'parseLibXml() failed with exception %s' % e

# pxDom
def parsePxDom(filename):
try:
import pxdom
doc = pxdom.parse(filename)
return doc
except Exception, e:
return 'parsePxDom() failed with exception %s' % e

def main():
import sys
filename = sys.argv[1]
print '4DOM:', parse4Dom(filename)
print 'Domlette:', parseDomlette(filename)
print 'MiniDom:', parseMinidom(filename)
print 'LibXml:', parseLibXml(filename)
print 'PxDom:', parsePxDom(filename)

if __name__ == '__main__': main()