python DOM解析XML

 

#conding:utf-8
# -*- coding:utf-8 -*-
__author__ = 'hdfs'
"""
XML 解析 ：DOM解析珍整个文档作为一个可遍历的对象 提交给应用程序，dom解析会将文档全部load进内存，这样对于大型的xml可能性能不多好。
"""

import pprint
import xml.dom.minidom
from xml.dom.minidom import Node

doc=xml.dom.minidom.parse('books.xml')

mapping={}
#遍历DOM对象
for node in doc.getElementsByTagName("book"):
    #获取属性
    isbn=node.getAttribute('isbn')
    #子节点
    L=node.getElementsByTagName('title')
    for node2 in L:
        title=""
        for node3 in node2.childNodes:
            #Node.Text_NODE:文字节点,
            if node3.nodeType == Node.TEXT_NODE:
                title+=node3.data
        mapping[isbn]=title
pprint.pprint(mapping)

 

books.xml:

<catalog>
    <book isbn="0-596-00128-2">
        <title>Python &amp; XML</title>
        <title>Python &amp; HTML</title>
        <date>December 2001</date>
        <author>Jones, Drake</author>
    </book>
    <book isbn="0-596-15810-6">
        <title>Programming Python, 4th Edition</title>
        <date>October 2010</date>
        <author>Lutz</author>
    </book>
    <book isbn="0-596-15806-8">
        <title>Learning Python, 4th Edition</title>
        <date>September 2009</date>
        <author>Lutz</author>
    </book>
    <book isbn="0-596-15808-4">
        <title>Python Pocket Reference, 4th Edition</title>
        <date>October 2009</date>
        <author>Lutz</author>
    </book>
    <book isbn="0-596-00797-3">
        <title>Python Cookbook, 2nd Edition</title>
        <date>March 2005</date>
        <author>Martelli, Ravenscroft, Ascher</author>
    </book>
    <book isbn="0-596-10046-9">
        <title>Python in a Nutshell, 2nd Edition</title>
        <date>July 2006</date>
        <author>Martelli</author>
    </book>
    <!-- plus many more Python books that should appear here -->
</catalog>