rushter/selectolax

pip install selectolax

pip install selectolax[cython]

git clone --recursive  https://github.com/rushter/selectolax
cd selectolax
pip install -r requirements_dev.txt
python setup.py install

make clean
make dev

from selectolax.lexbor import LexborHTMLParser

html = """
<h1 id="title" data-updated="20201101">Hi there</h1>
<div class="post">Lorem Ipsum is simply dummy text of the printing and typesetting industry. </div>
<div class="post">Lorem ipsum dolor sit amet, consectetur adipiscing elit.</div>
"""
tree = LexborHTMLParser(html)

print(tree.css_first('h1#title').text())
# 'Hi there'

print(tree.css_first('h1#title').attributes)
# {'id': 'title', 'data-updated': '20201101'}

print([node.text() for node in tree.css('.post')])
# ['Lorem Ipsum is simply dummy text of the printing and typesetting industry. ',
#  'Lorem ipsum dolor sit amet, consectetur adipiscing elit.']

from selectolax.lexbor import LexborHTMLParser

html = "<div><p id=p1><p id=p2><p id=p3><a>link</a><p id=p4><p id=p5>text<p id=p6></div>"
selector = "div > :nth-child(2n+1):not(:has(a))"

for node in LexborHTMLParser(html).css(selector):
    print(node.attributes, node.text(), node.tag)
    print(node.parent.tag)
    print(node.html)
# {'id': 'p1'}  p
# div
# <p id="p1"></p>
# {'id': 'p5'} text p
# div
# <p id="p5">text</p>

from selectolax.lexbor import LexborHTMLParser
html = "<div><p>hello </p><p id='main'>lexbor is AwesOme</p></div>"
parser = LexborHTMLParser(html)
# Case-insensitive search
results = parser.css('p:lexbor-contains("awesome" i)')
# Case-sensitive search
results = parser.css('p:lexbor-contains("AwesOme")')
assert len(results) == 1
assert results[0].text() == "lexbor is AwesOme"