cssselect_lxml_css_to_xpath_html_element_finder.py

1from lxml.html import fromstring
2from cssselect import GenericTranslator, SelectorError
3
4# Create a sample HTML document
5html = """
6<div id="main">
7    <article class="post">
8        <h2>First Post</h2>
9        <p>This is a paragraph.</p>
10    </article>
11    <article class="post">
12        <h2>Second Post</h2>
13    </article>
14</div>
15"""
16
17# Parse the HTML into an lxml tree
18tree = fromstring(html)
19
20# Use cssselect to find elements
21# Note: In practice, lxml provides a .cssselect() shortcut, 
22# but the official documentation demonstrates the underlying translation:
23try:
24    expression = GenericTranslator().css_to_xpath('div#main article.post h2')
25    elements = tree.xpath(expression)
26    
27    for element in elements:
28        print(f"Found: {element.text}")
29except SelectorError as e:
30    print(f"Invalid selector: {e}")