根据a标签 查找属性为href的值
# !/usr/bin/env python
# -*- coding: utf-8 -*-
from lxml import etree
# 获取文件元素
from lxml import etree
# 获取文件元素
htmlEmt = etree.parse('test02.html')
# 获取所有的 <li> 标签
result = htmlEmt.xpath('//a/@href')
print(result)
print type(result)
for x in result:
# print x
# print type(x)
# print '-------------------------'
print x
<html>
<div class="daohang-kuai">
<div class="daohang-org"><span>风险管理部</span></div>
<a href="aaa" ></a>
<a href="bbb" ></a>
</div>
</html>