python xml包使用记录

<?xml version="1.0" encoding="utf-8" ?> 
<request>
    <functionID>subPackageInfo</functionID>
    <time>2014-02-10 15:10:50</time>
    <packageList>
        <packageInfo>    
            <orderId>22088315090</orderId>
            <expressName>EMS</expressName>    
            <expressTel>01</expressTel>    
            <expressNo>0001</expressNo>
            <productId>1001173023</productId>
            <allotQuatity>5</allotQuatity>
            <outOfStockQuatity>0</outOfStockQuatity>
            <promotionID></promotionID>
        </packageInfo>

        <packageInfo>
            <orderId>22088315090</orderId>
            <expressName>EMS</expressName>    
            <expressTel>010-55675233</expressTel>    
            <expressNo>0001</expressNo>
            <productId>1001173123</productId>
            <allotQuatity>5</allotQuatity>
            <outOfStockQuatity>0</outOfStockQuatity>
            <promotionID>-1</promotionID>
        </packageInfo>

        <packageInfo>
            <orderId>22088315090</orderId>
            <expressName>EMS</expressName>    
            <expressTel>010-55675233</expressTel>    
            <expressNo>0001</expressNo>
            <productId>1001173223</productId>
            <allotQuatity>0</allotQuatity>
            <outOfStockQuatity>1</outOfStockQuatity>
            <promotionID>-1</promotionID>
        </packageInfo>


    </packageList>
</request>

首先把以上xml文件保存到本地

导入xml模块，使用dom.minidom导入xml文件

#coding:utf-8
from xml.dom import minidom
dom=minidom.parse('22088315090.xml')

>>> packs=dom.getElementsByTagName('packageInfo')

　　查找xml下面的所有packageInfo节点

>>> pack_childnotes=packs[0].childNodes

　　查找第一个packageInfo的所有子节点

>>> for i in pack_childnotes:print '###',i.toxml()

###     
    
### <orderId>22088315090</orderId>
###
    
### <expressName>EMS</expressName>
###     
    
### <expressTel>01</expressTel>
###     
    
### <expressNo>0001</expressNo>
###
    
### <productId>1001173023</productId>
###
    
### <allotQuatity>5</allotQuatity>
###
    
### <outOfStockQuatity>0</outOfStockQuatity>
###
    
### <promotionID/>
### 

以上打印出所有类型的xml信息，包括元素类型和文本类型

>>> for i in pack_childnotes:
    if i.nodeType==i.TEXT_NODE:
        pass
    else:
        print 'name',i.nodeName
        tagname=i.nodeName
        if i.childNodes:
            print 'type',i.childNodes[0].data
            value=i.childNodes[0].data
        else:
            value=''
        orders_info[tagname]=value
    print orders_info

        
{u'orderId': u'22088315090', u'promotionID': '', u'outOfStockQuatity': u'0', u'expressNo': u'0001', u'expressTel': u'01', u'productId': u'1001173023', u'expressName': u'EMS', u'allotQuatity': u'5'}

把第一个packageInfo的子节点数据拿到保存在字典中

完整的代码如下：

#coding:utf-8
from xml.dom import minidom
dom=minidom.parse('22088315090.xml')
packs=dom.getElementsByTagName('packageInfo')
orders=[]
#pack_childnotes=packs[0].childNodes

def control(pack):
    pack_childnotes=pack.childNodes
    orders_info={}
    for i in pack_childnotes:
        if i.nodeType==i.TEXT_NODE:
            pass
        else:
            #print 'name',i.nodeName
            tagname=i.nodeName
            if i.childNodes:
                #print 'type',i.childNodes[0].data
                value=i.childNodes[0].data
            else:
                value=''
            orders_info[tagname]=value
    return orders_info


for pack in packs:
    #print pack
    
    orders.append(control(pack))
print orders