.//p

Aug. 9, 2020

.//p

python/lxml example: current node selection

page="""

<!DOCTYPE html>  
    <body>       
	<!-- this is a comment -->
        <div name="div_a">
            <h1 name="head1">First Heading</h1>
            <p name="p1">My first paragraph.</p>
	    <div name="div_a1">
		<div name="div_a2">
		    <p name="p2">Description1</p>
		    <p name="p3">Description2</p>
		</div>	
	    </div>
	    <div name="div_a3" class="description">Description3</div>
        </div>

        <div name="div_b"> 
            <h1 name="head1">First Heading</h1>   
            <p name="p1">My first paragraph.</p>  
            <div name="div_b1">
                <div name="div_b2">                   
                    <p name="p2">Description1</p>
                    <p name="p3">Description2</p> 
                </div>  
            </div>
	    <div name="div_b3" class="description">Description3</div>
        </div>

        <div name="div_c">
            <h1 name="head1">First Heading</h1>
            <p name="p1">My first paragraph.</p>
            <div name="div_c1">
                <div name="div_c2">
                    <p name="p2">Description1</p>
                    <p name="p3">Description2</p>
                </div>
            </div>
	    <div name="div_c3" class="description">Description3</div>
        </div>  

	<img width = "5"></img>
 	<img width = "15"></img>
   
    </body>   
</html>
"""

doc = html.fromstring(page)
elements = doc.xpath('//div[@name="div_b"]')
paragraphs = elements[0].xpath('.//p')

for e in paragraphs:
    print "[%s %s]" % (e, e.attrib)


Rezults are:

[ {'name': 'p1'}]
[ {'name': 'p2'}]
[ {'name': 'p3'}]
Return to home