【Python】xml遍历练习

 

<?xml version="1.0" encoding="utf-8" ?>
<!--this is a test about xml.-->
<collection shelf="New Arrivals">
    <movie title="Enemy Behind">
        <type>War, Thriller</type>
        <format>DVD</format>
        <year>2003</year>
        <rating>PG</rating>
        <stars>10</stars>
        <description>Talk about a US-Japan war</description>
    </movie>
    <movie title="Transformers">
        <type>Anime, Science Fiction</type>
        <format>DVD</format>
        <year>1989</year>
        <rating>R</rating>
        <stars>8</stars>
        <description>A schientific fiction</description>
    </movie>
    <movie title="Trigun">
        <type>Anime, Action</type>
        <format>DVD</format>
        <episodes>4</episodes>
        <rating>PG</rating>
        <stars>10</stars>
        <description>Vash the Stampede!</description>
    </movie>
    <movie title="Ishtar">
        <type>Comedy</type>
        <format>VHS</format>
        <rating>PG</rating>
        <stars>2</stars>
        <description>Viewable boredom</description>
    </movie>
</collection>

 

#练习：计算movie文件中有多少个名字叫War, Thriller的电影

import sys

try:

    import xml.etree.cElementTree as ET

except ImportError:

    import xml.etree.ElementTree as ET

 

tree = ET.parse("e:\movie.xml")

 

count = 0

for elem in tree.iter(tag='movie'): #遍历树中的movie节点

    print elem.tag

    if elem[0].text == 'War, Thriller':

        count += 1

print count

 

#以下代码实现了边读文件边解析的作用，节省了内存

count = 0

for event, elem in ET.iterparse("e:\movie.xml"):  #遍历所有xml文件中的标签

    #print elem.tag

    if event == 'end':  #检测“闭合的”(end)事件，标签关闭

        if elem.tag == 'type' and elem.text == 'War, Thriller':  #标签为type，且文本内容为War, Thriller ,则count+1

            count += 1

    elem.clear() #清除元素内容,不清除则整个儿树也会在内存中，没有起到节省内存的作用。

 

print count