xml即可扩展标记语言，它可以用来标记数据、定义数据类型，是一种允许用户对自己的标记语言进行定义的源语言。
例子：del.xml
<?xml version="1.0" encoding="utf-8"?><catalog> <maxid>4</maxid> <login username="pytest" passwd='123456'> <caption>Python</caption> <item id="4"> <caption>test</caption> </item> </login> <item id="2"> <caption>Zope</caption> </item></catalog>
从结构上，很像HTML超文本标记语言。但他们被设计的目的是不同的，超文本标记语言被设计用来显示数据，其焦点是数据的外观。它被设计用来传输和存储数据，其焦点是数据的内容。
那么它有如下特征：
#coding: utf-8import xml.dom.minidomdom = xml.dom.minidom.parse("del.xml") #打开xml文档root = dom.documentElement #得到xml文档对象print "nodeName:", root.nodeName #每一个结点都有它的nodeName，nodeValue，nodeType属性print "nodeValue:", root.nodeValue #nodeValue是结点的值，只对文本结点有效print "nodeType:", root.nodeTypeprint "ELEMENT_NODE:", root.ELEMENT_NODE
nodeType是结点的类型。catalog是ELEMENT_NODE类型
现在有以下几种：
1 2 3 4 5 6 7 8 9 10 11 12 | 'ATTRIBUTE_NODE''CDATA_SECTION_NODE''COMMENT_NODE''DOCUMENT_FRAGMENT_NODE''DOCUMENT_NODE''DOCUMENT_TYPE_NODE''ELEMENT_NODE''ENTITY_NODE''ENTITY_REFERENCE_NODE''NOTATION_NODE''PROCESSING_INSTRUCTION_NODE''TEXT_NODE' |
运行结果
1 2 3 4 | nodeName: catalognodeValue: NonenodeType: 1ELEMENT_NODE: 1 |
#coding: utf-8import xml.dom.minidomdom = xml.dom.minidom.parse("del.xml") root = dom.documentElementbb = root.getElementsByTagName('maxid')print type(bb)print bbb = bb[0]print b.nodeNameprint b.nodeValue
运行结果
1 2 3 4 | <class 'xml.dom.minicompat.NodeList'>[<DOM Element: maxid at 0x2707a48>]maxidNone |
#coding: utf-8import xml.dom.minidomdom = xml.dom.minidom.parse("del.xml") root = dom.documentElementitemlist = root.getElementsByTagName('login')item = itemlist[0]print item.getAttribute("username")print item.getAttribute("passwd")itemlist = root.getElementsByTagName("item")item = itemlist[0] #通过在itemlist中的位置区分print item.getAttribute("id") item2 = itemlist[1] #通过在itemlist中的位置区分
print item2.getAttribute("id")
运行结果
1 2 3 4 | pytest12345642 |
#coding: utf-8import xml.dom.minidomdom = xml.dom.minidom.parse("del.xml") root = dom.documentElementitemlist = root.getElementsByTagName('caption')item = itemlist[0]print item.firstChild.dataitem2 = itemlist[1]print item2.firstChild.data
运行结果
1 2 | Pythontest |
<?xml version="1.0" encoding="UTF-8" ?><users> <user id="1000001"> <username>Admin</username> <email>admin@live.cn</email> <age>23</age> <sex>boy</sex> </user> <user id="1000002"> <username>Admin2</username> <email>admin2@live.cn</email> <age>22</age> <sex>boy</sex> </user> <user id="1000003"> <username>Admin3</username> <email>admin3@live.cn</email> <age>27</age> <sex>boy</sex> </user> <user id="1000004"> <username>Admin4</username> <email>admin4@live.cn</email> <age>25</age> <sex>girl</sex> </user> <user id="1000005"> <username>Admin5</username> <email>admin5@live.cn</email> <age>20</age> <sex>boy</sex> </user> <user id="1000006"> <username>Admin6</username> <email>admin6@live.cn</email> <age>23</age> <sex>girl</sex> </user></users>
把name、email、age、sex输出
参考代码
# -*- coding:utf-8 -*-from xml.dom import minidomdef get_attrvalue(node, attrname): return node.getAttribute(attrname) if node else ''def get_nodevalue(node, index = 0): return node.childNodes[index].nodeValue if node else ''def get_xmlnode(node, name): return node.getElementsByTagName(name) if node else []def get_xml_data(filename = 'user.xml'): doc = minidom.parse(filename) root = doc.documentElement user_nodes = get_xmlnode(root, 'user') print "user_nodes:", user_nodes user_list=[] for node in user_nodes: user_id = get_attrvalue(node, 'id') node_name = get_xmlnode(node, 'username') node_email = get_xmlnode(node, 'email') node_age = get_xmlnode(node, 'age') node_sex = get_xmlnode(node, 'sex') user_name =get_nodevalue(node_name[0]) user_email = get_nodevalue(node_email[0]) user_age = int(get_nodevalue(node_age[0])) user_sex = get_nodevalue(node_sex[0]) user = {} user['id'] , user['username'] , user['email'] , user['age'] , user['sex'] = ( int(user_id), user_name , user_email , user_age , user_sex ) user_list.append(user) return user_listdef test_load_xml(): user_list = get_xml_data() for user in user_list : print '-----------------------------------------------------' if user: user_str='No.:\t%d\nname:\t%s\nsex:\t%s\nage:\t%s\nEmail:\t%s' % (int(user['id']) , user['username'], user['sex'] , user['age'] , user['email']) print user_strif __name__ == "__main__": test_load_xml()
结果
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 | C:\Users\wzh94434\Desktop\xml>python user.pyuser_nodes: [<DOM Element: user at 0x2758c48>, <DOM Element: user at 0x2756288>, <DOM Element: user at 0x2756888>, <DOM Element: user at 0x2756e88>, <DOM Element: user at 0x275e4c8>, <DOM Element: user at 0x275eac8>]-----------------------------------------------------No.: 1000001name: Adminsex: boyage: 23Email: admin@live.cn-----------------------------------------------------No.: 1000002name: Admin2sex: boyage: 22Email: admin2@live.cn-----------------------------------------------------No.: 1000003name: Admin3sex: boyage: 27Email: admin3@live.cn-----------------------------------------------------No.: 1000004name: Admin4sex: grilage: 25Email: admin4@live.cn-----------------------------------------------------No.: 1000005name: Admin5sex: boyage: 20Email: admin5@live.cn-----------------------------------------------------No.: 1000006name: Admin6sex: grilage: 23Email: admin6@live.cn |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 | minidom.parse(filename)加载读取XML文件doc.documentElement获取XML文档对象node.getAttribute(AttributeName)获取XML节点属性值node.getElementsByTagName(TagName)获取XML节点对象集合node.childNodes #返回子节点列表。node.childNodes[index].nodeValue获取XML节点值node.firstChild#访问第一个节点。等价于pagexml.childNodes[0]doc = minidom.parse(filename)doc.toxml('UTF-8')返回Node节点的xml表示的文本Node.attributes["id"]a.name #就是上面的 "id"a.value #属性的值 访问元素属性 |
联系客服
