Xpath素材

from lxml import etree
text = """
<div>
    <ul>
        <li class="item-0"><a href="link1.html">first item</a></li>
        <li class="item-1"><a href="link2.html">second item</a></li>
        <li class="item-inactive"><a href="link3.html">third item</a></li>
        <li class="item-1"><a href="link4.html">fourth item</a></li>
        <li class="item-0"><a href="link5.html">fifth item</a>
    </ul>
</div>
"""
html = etree.HTML(text)
result = etree.tostring(html,pretty_print=True).decode('utf-8')
print(result)

from lxml import etree
text = """
<div>
    <ul>
        <li class="item-0"><a href="link1.html">first item</a></li>
        <li class="item-1"><a href="link2.html">second item</a></li>
        <li class="item-inactive"><a href="link3.html"><span class="bold">third item</span>></a></li>
        <li class="item-1"><a href="link4.html">fourth item</a></li>
        <li class="item-0"><a href="link5.html">fifth item</a></li>
    </ul>
</div>
"""
# 初始化一个Xpath解析对象
html = etree.HTML(text)
# 解析对象输出代码 是一个bytes类型
result = etree.tostring(html,encoding='utf-8')
print(type(html))  # <class 'lxml.etree._Element'>
print(type(result))  # <class 'bytes'>
print(result.decode('utf-8'))