def getText(self,nodelist):
rc=""
for node in nodelist:
if node.nodeType == node.TEXT_NODE or node.nodeType == node.CDATA_SECTION_NODE:
rc = rc + node.data
return rc
def parseXML(self,requesturl,xml):
dom = minidom.parse(requesturl)
for node in dom.getElementsByTagName('category'):
xml.append({
'categoryid': self.getText(node.getElementsByTagName("categoryid")[0].childNodes),
'categoryname': self.getText(node.getElementsByTagName("categoryname")[0].childNodes)
})
主函数：
xml=[]
self.parseXML(self.file_path,xml)
已知有一个XML文件（bookstore.xml）如下：
<?xml version="1.0" encoding="gb2312"?>
<bookstore>
<book genre="fantasy" ISBN="2-3631-4">
<title>Oberon's Legacy</title>
<author>Corets, Eva</author>
<price>5.95</price>
</book>
< ......
