网络爬虫——xpath使用

from lxml import etree

wb_data = """
        <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>
        """
#解析字符串为html对象，自动补全html。body
html=etree.HTML(wb_data)

#解析数据，a标签的文本
#写法一：text属性
data1 = html.xpath('/html/body/div/ul/li/a')
for i in data1:
    print(i.text)

#写法二