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 = html.xpath('//li[1]/a/text()')
print(result)#输出第一个超链接里面的内容
result = html.xpath('//li[last()]/a/text()')
print(result)#输出最后一个超链接的内容
result = html.xpath('//li[position()<3]/a/text()')
print(result)#输出位置小于3的a标签里面的内容
result = html.xpath('//li[last()-2]/a/text()')
print(result)#输出最后一个链接向前移动两个位置的a标签内容
'''
输出结果：
['first item']
['fifth item']
['first item', 'second item']
['third item']
'''
