Python Programming/XML Tools

Introduction

xml.sax.handler

importxml.sax.handlerassaxhandler
importxml.saxassaxparser
classMyReport:
 def__init__(self):
 self.Y = 1
classMyCH(saxhandler.ContentHandler):
 def__init__(self, report):
 self.X = 1
 self.report = report
 defstartDocument(self):
 print('startDocument')
 defstartElement(self, name, attrs):
 print('Element:', name)
report = MyReport() #for future use
ch = MyCH(report)
xml = """\
<collection>
 <comic title=\"Sandman\" number='62'>
 <writer>Neil Gaiman</writer>
 <penciller pages='1-9,18-24'>Glyn Dillon</penciller>
 <penciller pages="10-17">Charles Vess</penciller>
 </comic>
</collection>
"""
print(xml)
saxparser.parseString(xml, ch)

xml.dom.minidom

fromxml.domimport minidom as dom
importurllib2
deffetchPage(url):
 a = urllib2.urlopen(url)
 return ''.join(a.readlines())
defextract(page):
 a = dom.parseString(page)
 item = a.getElementsByTagName('item')
 for i in item:
 if i.hasChildNodes():
 t = i.getElementsByTagName('title')[0].firstChild.wholeText
 l = i.getElementsByTagName('link')[0].firstChild.wholeText
 d = i.getElementsByTagName('description')[0].firstChild.wholeText
 print(t, l, d)
if __name__=='__main__':
 page = fetchPage("http://rss.slashdot.org/Slashdot/slashdot")
 extract(page)