python xpath基础 01 

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)#构造了一个XPath解析对象并对HTML文本进行自动修正
result = etree.tostring(html)#输出修正后的结果，类型是bytes
print(result.decode('utf-8'))#以utf8的编码的方式打印修正后的内容
# 修正后的内容
test_data='''<html><body><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>
     </li></ul>
 </div>
</body></html>'''

　　

posted @ 2018-12-25 18:12  青春叛逆者  阅读(120)  评论(0)    收藏  举报