python只获取xml文件_如何用python获取xml文件中的特定节点

您可以使用pulldom API来处理对大文件的解析，而不必一次将其全部加载到内存中。与使用SAX相比，这提供了一个更方便的接口，而且性能损失很小。

它基本上允许您流式处理xml文件，直到找到您感兴趣的位为止，然后在这之后开始使用regular DOM operations。from xml.dom import pulldom

# http://mail.python.org/pipermail/xml-sig/2005-March/011022.html

def getInnerText(oNode):

rc = ""

nodelist = oNode.childNodes

for node in nodelist:

if node.nodeType == node.TEXT_NODE:

rc = rc + node.data

elif node.nodeType==node.ELEMENT_NODE:

rc = rc + getInnerText(node) # recursive !!!

elif node.nodeType==node.CDATA_SECTION_NODE:

rc = rc + node.data

else:

# node.nodeType: PROCESSING_INSTRUCTION_NODE, COMMENT_NODE, DOCUMENT_NODE, NOTATION_NODE and so on

pass

return rc

# xml_file is either a filename or a file

stream = pulldom.parse(xml_file)

for event, node in stream:

if event == "START_ELEMENT" and node.nodeName == "AssetType":

if node.getAttribute("longname") == "characters":

stream.expandNode(node) # node now contains a mini-dom tree

type_nodes = node.getElementsByTagName('type')

for type_node in type_nodes:

# type_text will have the value of what's inside the type text

type_text = getInnerText(type_node)