获取所有的<li>标签
<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>
</ul>
<li>aaaa</li>
<li>bbbbb</li>
<span>
<a><li>cc</li></a>
</span>
</div></body></html>
# !/usr/bin/env python
# -*- coding: utf-8 -*-
from lxml import etree
# 获取文件元素
htmlEmt = etree.parse('text.xml')
# 获取所有的 <li> 标签
result = htmlEmt.xpath('//li')
print(result)
# 获取标签数量
print(len(result))
# 取出第一个 li 标签
print type(result)
for x in result:
print x.text
C:Python27python.exe C:/Users/TLCB/PycharmProjects/untitled/xpath/l2.py
[<Element li at 0x26da9e0>, <Element li at 0x26da198>, <Element li at 0x26da030>, <Element li at 0x26da0d0>, <Element li at 0x26da238>, <Element li at 0x26da440>, <Element li at 0x26da4e0>, <Element li at 0x26da5a8>]
8
<type 'list'>
a01
b02
c03
d04
e05
aaaa
bbbbb
cc
Process finished with exit code 0