python的xml.dom学习笔记

首先说一下，由于这篇文章主要是自己随性学习写的，所以读者看起来可能很乱，呵呵。可以给大家稍微推荐一篇：http://www.cnblogs.com/xuxm2007/archive/2011/01/16/1936610.html 稍微清晰一点

#coding=utf-8

#解析xml文件中的所有的link标签
from xml.dom import minidom
from xml.dom.minidom import getDOMImplementation
doc=minidom.parse("d:\\hello.html")

nodes=doc.getElementsByTagName("link")

for node in nodes:
    print "<",node.tagName,
    print "type=\"",node.getAttribute("type"),"\"",
    print "rel=\"",node.getAttribute("rel"),"\"",
    print "href=\"",node.getAttribute("href"),"\"",
    print "/>"
    
print "通过另外一种方式获得link标签"
linknodes=doc.getElementsByTagName("link")
for i in range(len(linknodes)):
    print linknodes[i].getAttribute("type"),
    print linknodes[i].getAttribute("rel"),
    print linknodes[i].getAttribute("href")
    

#操作节点
node=linknodes[0]
print dir(node)
print node.parentNode
print node.prefix
print node.nodeType,node.nodeValue,node.nodeName
print node.localName
print node.childNodes
print node.firstChild,node.lastChild
print node.attributes
print node.namespaceURI
print node.nextSibling
print "--"*10
print node.tagName

print "==="*20
impl=getDOMImplementation()
newdoc=impl.createDocument(None , "some_tag", None)
top_element=newdoc.documentElement
node1=newdoc.createTextNode("node1")
node2=newdoc.createTextNode("node2")
node3=newdoc.createTextNode("node3")

top_element.appendChild(node1)
top_element.appendChild(node2)
top_element.appendChild(node3)

top_element.removeChild(node3)
top_element.insertBefore(node3,node2)

print top_element.childNodes

　　运行结果：

< link type=" text/css " rel=" stylesheet " href=" http://www.cnblogs.com/css/common.css " />
< link type=" text/css " rel=" stylesheet " href=" http://www.cnblogs.com/Skins/kubrick/style.css " />
< link type=" text/css " rel=" stylesheet " href=" http://www.cnblogs.com/css/common2.css " />
< link type=" text/css " rel=" stylesheet " href=" http://common.cnblogs.com/css/shCore.css " />
< link type=" text/css " rel=" stylesheet " href=" http://common.cnblogs.com/css/shThemeDefault.css " />
< link type=" application/rss+xml " rel=" alternate " href=" http://www.cnblogs.com/rollenholt/rss " />
< link type=" application/rsd+xml " rel=" EditURI " href=" http://www.cnblogs.com/rollenholt/rsd.xml " />
< link type=" application/wlwmanifest+xml " rel=" wlwmanifest " href=" http://www.cnblogs.com/rollenholt/wlwmanifest.xml " />
通过另外一种方式获得link标签
text/css stylesheet http://www.cnblogs.com/css/common.css
text/css stylesheet http://www.cnblogs.com/Skins/kubrick/style.css
text/css stylesheet http://www.cnblogs.com/css/common2.css
text/css stylesheet http://common.cnblogs.com/css/shCore.css
text/css stylesheet http://common.cnblogs.com/css/shThemeDefault.css
application/rss+xml alternate http://www.cnblogs.com/rollenholt/rss
application/rsd+xml EditURI http://www.cnblogs.com/rollenholt/rsd.xml
application/wlwmanifest+xml wlwmanifest http://www.cnblogs.com/rollenholt/wlwmanifest.xml
['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', '__doc__', '__init__', '__module__', '__nonzero__', '__repr__', '_attrs', '_attrsNS', '_call_user_data_handler', '_child_node_types', '_get_attributes', '_get_childNodes', '_get_firstChild', '_get_lastChild', '_get_localName', '_get_tagName', '_magic_id_nodes', 'appendChild', 'attributes', 'childNodes', 'cloneNode', 'firstChild', 'getAttribute', 'getAttributeNS', 'getAttributeNode', 'getAttributeNodeNS', 'getElementsByTagName', 'getElementsByTagNameNS', 'getInterface', 'getUserData', 'hasAttribute', 'hasAttributeNS', 'hasAttributes', 'hasChildNodes', 'insertBefore', 'isSameNode', 'isSupported', 'lastChild', 'localName', 'namespaceURI', 'nextSibling', 'nodeName', 'nodeType', 'nodeValue', 'normalize', 'ownerDocument', 'parentNode', 'prefix', 'previousSibling', 'removeAttribute', 'removeAttributeNS', 'removeAttributeNode', 'removeAttributeNodeNS', 'removeChild', 'replaceChild', 'schemaType', 'setAttribute', 'setAttributeNS', 'setAttributeNode', 'setAttributeNodeNS', 'setIdAttribute', 'setIdAttributeNS', 'setIdAttributeNode', 'setUserData', 'tagName', 'toprettyxml', 'toxml', 'unlink', 'writexml']
<DOM Element: head at 0x1b3e968>
None
1 None link
link
[]
None None
<xml.dom.minidom.NamedNodeMap object at 0x01B4D648>
http://www.w3.org/1999/xhtml
<DOM Text node "u'\n'">
--------------------
link
============================================================
[<DOM Text node "'node1'">, <DOM Text node "'node3'">, <DOM Text node "'node2'">]