python的lxml模块，

第三方模块安装：pip instll lxml

获取文本内容用：text()

取后代的标签用：//

通配符，代表任意标签：/*

from lxml import etree

xml = '''
<book>
    <id>1</id>
    <name>中秋节月饼</name>
    <price>9.8元</price>
    <nick>博饼</nick>
    <author>
        <nick id="1">嫦娥</nick>
        <nick id="2">月兔</nick>
        <nick id="3">广寒宫</nick>
        <dv>
            <nick id="4">天蓬元帅</nick>
        </dv>
        <span>
            <nick id="5">王刚</nick>
        </span>
    </author>

    <parent>
        <nick id="5">后裔</nick>
    </parent>
</book>
'''

tree = etree.XML(xml)  # 先创建一个etree对象
result1 = tree.xpath('/book/nick/text()')  # text():作用是拿文本
print (result1)  # 输出：['博饼']

result2 = tree.xpath('/book/author/nick/text()') # 取同一层级下的所有nick标签的文本
print(result2) # 输出：['嫦娥', '月兔', '广寒宫']

result3 = tree.xpath('/book/author//nick/text()')  # :"//“取author下所有的nick标签的文本
print(result3)

result4 = tree.xpath('/book/author/*/nick/text()')  #  "*"通配符，代表任意结点，因为有2个nick分别在div,span下面
print(result4)

result5 = tree.xpath('/book//nick/text()')  # 获取book下所有nick的文本
print(result5)