how to working with XML files in python

What is XML?

• The Extensible Markup Language (XML) is a markup language much like HTML or SGML.

The two most basic and broadly used APIs to XML data are the SAX and DOM interfaces.

• Simple API for XML (SAX)

• Document Object Model (DOM) API 

movies.xml:

<collection shelf="New Arrivals">

<movie title="Enemy Behind">

   <type>War, Thriller</type>

   <format>DVD</format>

   <year>2003</year>

   <rating>PG</rating>

   <stars>10</stars>

   <description>Talk about a US-Japan war</description>

</movie>

<movie title="Transformers">

   <type>Anime, Science Fiction</type>

   <format>DVD</format>

   <year>1989</year>

   <rating>R</rating>

   <stars>8</stars>

   <description>A schientific fiction</description>

</movie>

   <movie title="Trigun">

   <type>Anime, Action</type>

   <format>DVD</format>

   <episodes>4</episodes>

   <rating>PG</rating>

   <stars>10</stars>

   <description>Vash the Stampede!</description>

</movie>

<movie title="Ishtar">

   <type>Comedy</type>

   <format>VHS</format>

   <rating>PG</rating>

   <stars>2</stars>

   <description>Viewable boredom</description>

</movie>

</collection>

Parsing xml with SAX API:

import xml.sax

class MovieHandler( xml.sax.ContentHandler ):

   def __init__(self):

      self.CurrentData = ""

      self.type = ""

      self.format = ""

      self.year = ""

      self.rating = ""

      self.stars = ""

      self.description = ""

   # Call when an element starts

   def startElement(self, tag, attributes):

      self.CurrentData = tag

      if tag == "movie":

         print "*****Movie*****"

         title = attributes["title"]

         print "Title:", title

   # Call when an elements ends

   def endElement(self, tag):

      if self.CurrentData == "type":

         print "Type:", self.type

      elif self.CurrentData == "format":

         print "Format:", self.format

      elif self.CurrentData == "year":

         print "Year:", self.year

      elif self.CurrentData == "rating":

         print "Rating:", self.rating

      elif self.CurrentData == "stars":

         print "Stars:", self.stars

      elif self.CurrentData == "description":

         print "Description:", self.description

      self.CurrentData = ""

   # Call when a character is read

   def characters(self, content):

      if self.CurrentData == "type":

         self.type = content

      elif self.CurrentData == "format":

         self.format = content

      elif self.CurrentData == "year":

         self.year = content

      elif self.CurrentData == "rating":

         self.rating = content

      elif self.CurrentData == "stars":

         self.stars = content

      elif self.CurrentData == "description":

         self.description = content

  

if ( __name__ == "__main__"):

   

   # create an XMLReader

   parser = xml.sax.make_parser()

   # turn off namepsaces

   parser.setFeature(xml.sax.handler.feature_namespaces, 0)

   # override the default ContextHandler

   Handler = MovieHandler()

   parser.setContentHandler( Handler )

   

   parser.parse("movies.xml")

Output:

*****Movie*****

Title: Enemy Behind

Type: War, Thriller

Format: DVD

Year: 2003

Rating: PG

Stars: 10

Description: Talk about a US-Japan war

*****Movie*****

Title: Transformers

Type: Anime, Science Fiction

Format: DVD

Year: 1989

Rating: R

Stars: 8

Description: A schientific fiction

*****Movie*****

Title: Trigun

Type: Anime, Action

Format: DVD

Rating: PG

Stars: 10

Description: Vash the Stampede!

*****Movie*****

Title: Ishtar

Type: Comedy

Format: VHS

Rating: PG

Stars: 2

Description: Viewable boredom

Parsing xml with DOM API:

from xml.dom.minidom import parse

import xml.dom.minidom

# Open XML document using minidom parser

DOMTree = xml.dom.minidom.parse("movies.xml")

collection = DOMTree.documentElement

if collection.hasAttribute("shelf"):

   print "Root element : %s" % collection.getAttribute("shelf")

# Get all the movies in the collection

movies = collection.getElementsByTagName("movie")

# Print detail of each movie.

for movie in movies:

   print "*****Movie*****"

   if movie.hasAttribute("title"):

      print "Title: %s" % movie.getAttribute("title")

   type = movie.getElementsByTagName('type')[0]

   print "Type: %s" % type.childNodes[0].data

   format = movie.getElementsByTagName('format')[0]

   print "Format: %s" % format.childNodes[0].data

   rating = movie.getElementsByTagName('rating')[0]

   print "Rating: %s" % rating.childNodes[0].data

   description = movie.getElementsByTagName('description')[0]

   print "Description: %s" % description.childNodes[0].data

Output:

Root element : New Arrivals

*****Movie*****

Title: Enemy Behind

Type: War, Thriller

Format: DVD

Rating: PG

Description: Talk about a US-Japan war

*****Movie*****

Title: Transformers

Type: Anime, Science Fiction

Format: DVD

Rating: R

Description: A schientific fiction

*****Movie*****

Title: Trigun

Type: Anime, Action

Format: DVD

Rating: PG

Description: Vash the Stampede!

*****Movie*****

Title: Ishtar

Type: Comedy

Format: VHS

Rating: PG

Description: Viewable boredom