用xPath解析和提取属性值

<bookstore>
  <book category="children">
    <title lang="en">Harry Potter</title>
    <author>J.K. Rowling</author>
    <year>2005</year>
    <price>29.99</price>
  </book>
  <book category="web">
    <title lang="en">Learning XML</title>
    <author>Erik T. Ray</author>
    <year>2003</year>
    <price>39.95</price>
  </作者>
</bookstore>

from lxml import etree

xml_data = '''
<bookstore>
  <book category="children">
    <title lang="en">Harry Potter</title>
    <author>J.K. Rowling</author>
    <year>2005</year>
    <price>29.99</price>
  </book>
  <book category="web">
    <title lang="en">Learning XML</title>
    <author>Erik T. Ray</author>
    <year>2003</year>
    <price>39.95</price>
  </book>
</bookstore>
'''

tree = etree.fromstring(xml_data)
books = tree.xpath('//book/@category')

print(books)  # 输出: ['children', 'web']

namespaces = {'ns': 'http://example.com/namespace'}
books = tree.xpath('//ns:book/@category', namespaces=namespaces)