python的lxml模块解析xml

xml内容如下：

<?xml version="1.0" encoding="utf8"?>
<dblp>
    <article mdate="2002-01-03" key="中国">
        <author>E. F. Codd</author>
        <title>: A cloud data storage system for supporting both OLTP and OLAP.</title>
        <journal>IBM Research Report, San Jose, California</journal>
        <volume>RJ909</volume>
        <month>August</month>
        <year>1971</year>
    </article>
    <article mdate="2002-01-03" key="美国">
        <author>E. F. Codd</author>
        <title><i>Entropy</i> Best Paper Award 2013.</title>
        <journal>IBM Research Report, San Jose, California</journal>
        <volume>RJ909</volume>
        <month>August</month>
        <year>1971</year>
        <cdrom>ibmTR/rj909.pdf</cdrom>
        <ee>db/labs/ibm/RJ909.html</ee>
    </article>
</dblp>

 

解析程序如下：

from lxml import etree

def getxml_content():

    tree = etree.parse("xml.txt")  #获取树结构
    root = tree.getroot() # 获取根节点
    for elments in root: #遍历根节点获取子节点
        #######################
        # 方法1、获取节点下所有属性遍历获取，是一个字典
        #######################
        for key in elments.attrib.keys():
              print(key,":",elments.get(key))
        #######################
        # 方法2、根据已知的名称获取属性值
        #######################
        print("mdate:",elments.get("mdate"))  #.get获取标签里面的属性内容
        for e in elments:
            print(e.tag,':',e.text) #.tag获取节点（标签）名称，.text获取两个标签中间夹着的内容


    print(root)  #

xml内容如下：

<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
<template type="授权委托书" version="1.0">
    <root>
        <element allowTimes="" code="00" controlName="一般情况" dataFormat="" dataType="" displayName="一般情况" id="2" nodeSource="1" showType="ElementTable" sortNo="14242" sourceId="00">
            <text>住院号：0000385632。病区名称：221W介入2。科室名称：介入与血管外科二。病床号：51。患者姓名：李XXX。性别：女。年龄：84岁。受委托人身份证号：XXXX</text>
        </element>
    </root>
</template>

def xml_parse_two(VISITSQNO,LOCALID,DOCNAME,FILENAME,XML_TWO):
    strs=bytes(bytearray(XML_TWO, encoding='utf-8')) #最好是byte，不然报错
    t=etree.XML(strs) #获取根template
    tree = etree.ElementTree(t)
    root=tree.getroot()  #获取第一层template根标签
    list = []
    for elments in root: #获取第二层标签
        for elment in elments:  #获取第三层标签
            for e in elment: #获取第四层标签
                attr_list=[]
                attr_list.append(VISITSQNO)
                attr_list.append(LOCALID)
                attr_list.append(DOCNAME)
                attr_list.append(FILENAME)
                for key in e.attrib.keys(): #获取第四层属性值
                    if 'controlName' in key or 'displayName' in key:
                        atrribut_value=e.get(key) #获取第四层属性及属性值
                        attr_list.append(atrribut_value)
                if len(e)>0:
                    attr_list.append(e[0].text) #第四层content的内容
                    list.append(tuple(attr_list))
    return list