sax4.py

来自「python web programming 部分」· Python 代码 · 共 43 行

#!/usr/bin/python
import sys
from xml.sax import saxutils
from xml.sax import make_parser
from xml.sax import handler

class SimpleHandler(saxutils.DefaultHandler):
    # Obtain a locator object
    def setDocumentLocator(self,locator):
        self.locator = locator

    def startElement(self,name,attrs):
        col = self.locator.getColumnNumber()
        line = self.locator.getLineNumber()
        pubid = self.locator.getPublicId()
        sysid = self.locator.getSystemId()
        print 'startElement (%d,%d,%s,%s): ' % (line,col,pubid,sysid), name, attrs
        
    def endElement(self,name):
        col = self.locator.getColumnNumber()
        line = self.locator.getLineNumber()
        pubid = self.locator.getPublicId()
        sysid = self.locator.getSystemId()
        print 'endElement (%d,%d,%s,%s): ' % (line,col,pubid,sysid), name

    def characters(self,data):
        print 'characters: ', repr(data)
        
# Create a parser
parser = make_parser()

# Create a handler
sh = SimpleHandler()

# Tell the parser about it
parser.setContentHandler(sh)

# Parse a file
parser.parse(sys.argv[1])