notebook.community

Edit and run



In [2]:

    
from lxml import etree



In [3]:

    
sample = """
<html>
    <head>
        <title>My page title</title>
    </head>
    <body>
        <h2>Hello <a href="#">World</a>
        <p>a paragraph</p>
        <input type="hidden" name="_xsrf" value="sdakjflkajdfskl" />
        <!-- comments -->
    </body>
</html>
"""



In [5]:

    
s1 = etree.HTML(sample)



In [6]:

    
s1.xpath('/html/head/title/text()')









    Out[6]:





['My page title']



In [7]:

    
s1.xpath('//p/text()')









    Out[7]:





['a paragraph']



In [11]:

    
s1.xpath('//h2/a/@href')









    Out[11]:





['#']



In [13]:

    
s1.xpath('//input[@name="_xsrf"]/@value')









    Out[13]:





['sdakjflkajdfskl']



In [14]:

    
s1.xpath('//comment()')









    Out[14]:





[<!-- comments -->]