xml的解析例子

xml解析的一个例子，如下所示：

#!/usr/bin/env python
#-*-coding:utf-8-*-
import xml.sax.handler
class TestHander(xml.sax.handler.ContentHandler):
    def __init__(self):
        self.mapping={}
        self.content=""

    #标签的开始    
    def startElement(self, name, attributes):
        self.buffer=""
        #if name=="link":
        #    self.mapping[self.buffer.encode("utf-8")]=""

    #数据内容        
    def characters(self, data):
        self.buffer+=data+"\n"

    #标签的结束 ，在这里可以做数据的处理等   
    def endElement(self, name):
        ss=self.buffer        
        if name=="title":
            self.content+=deleteCharacter(u"标题："+ss);
            #print self.buffer.encode("utf-8")
        if name=="link":
            self.content+=deleteCharacter(u"链接地址："+ss);
            #print self.buffer.encode("utf-8")
        if name=="description":
            self.content+=deleteCharacter(u"内容："+ss);
            #print self.buffer.encode("utf-8")
        if name=="pubDate":
            self.content+=deleteCharacter(u"发布时间："+ss);
            #print self.buffer.encode("utf-8")    

def deleteCharacter(string):
    ret=""
    #sub=("&nbsp","","nbsp;","","<br />","\n","<br/>","\n","<p>","","</p>","")
    ret=string.encode("utf-8")
    ret=ret.replace(" ","")
    ret=ret.replace("nbsp;","")
    ret=ret.replace("<br />","\n")
    ret=ret.replace("<br/>","\n")
    ret=ret.replace("<p>","")
    ret=ret.replace("</p>","")
    return ret

if __name__=="__main__":
    import xml.sax.handler
    parser=xml.sax.make_parser()
    hander=TestHander()
    parser.setContentHandler(hander)
    parser.parse("http://blog.sina.com.cn/rss/soundfragment.xml")
    #parser.parse("c:\\rss.xml")
    #print hander.content
    #写入文件
    file_path="c:\\wt.txt";
    infile=file(file_path,"w")
    infile.write(hander.content)
    infile.close()
    #parser.parse(unicode(file('c:\\rss.xml', 'r', 'utf-8').read(),'utf-8').encode('utf-8'))