# !/usr/bin/env python
# -*- coding: utf-8 -*-
from lxml import etree
# 获取文件元素
htmlEmt = etree.parse('test03.html')
# 获取所有的 <li> 标签
result = htmlEmt.xpath('//li/@class')
print result
print type(result)
<html><body><div>
<ul>
<li class="item-0">a01<a href="link1.html">first item</a></li>
<li class="item-1">b02<a href="link2.html">second item</a></li>
<li class="item-inactive">c03<a href="link3.html">third item</a></li>
<li class="item-1">d04<a href="link4.html">fourth item</a></li>
<li class="item-0">e05<a href="link5.html">fifth item</a></li>
<a class='aaaa'>ddd</a>
</ul>
<div>
<li class="item-6"></li>
</div>
<li class="4444">aaaa</li>
<li class="55555">bbbbb</li>
<span>
<a><li>cc</li></a>
</span>
</div></body></html>
C:Python27python.exe C:/Users/TLCB/PycharmProjects/untitled/xpath/l2.py
['item-0', 'item-1', 'item-inactive', 'item-1', 'item-0', 'item-6', '4444', '55555']
<type 'list'>
# !/usr/bin/env python
# -*- coding: utf-8 -*-
from lxml import etree
# 获取文件元素
htmlEmt = etree.parse('test03.html')
# 获取所有的 <li> 标签
result = htmlEmt.xpath('//@class')
print result
print type(result)
C:Python27python.exe C:/Users/TLCB/PycharmProjects/untitled/xpath/l2.py
['item-0', 'item-1', 'item-inactive', 'item-1', 'item-0', 'aaaa', 'item-6', '4444', '55555']
<type 'list'>
Process finished with exit code 0