Extract CSS from url

getcss.py

# headless browser
from selenium import webdriver
from webdriver_manager.chrome import ChromeDriverManager
from selenium.webdriver.chrome.options import Options
import re


url = 'myurl.com'
querySelect = 'section'

chrome_options = Options()
chrome_options.add_argument("--headless")
driver = webdriver.Chrome(ChromeDriverManager().install(), options=chrome_options)


js = '''
// this is a js function 

const isSameDomain = (styleSheet) => {
  if (!styleSheet.href) {
    return true;
  }

  return styleSheet.href.indexOf(window.location.origin) === 0;
};

const isStyleRule = (rule) => rule.type === 1;

const getCSSCustomPropIndex = () =>
  [...document.styleSheets]
    .filter(isSameDomain)
    .reduce(
      (finalArr, sheet) =>
        finalArr.concat([...sheet.cssRules].filter(isStyleRule)),
      []
    );

var css  = {}

var stylesheet = getCSSCustomPropIndex();

stylesheet.forEach(d=>
    css[d.selectorText] = css[d.selectorText]||'' + d.style.cssText)

return css

'''




driver.get(url)
stylesheets = driver.execute_script(js)




ekind = re.compile(r'\<(\w+)')
relevant = [querySelect]

# starting with our selected elements
for match in driver.find_elements_by_css_selector(querySelect):
    # lets look at each child
    for child in match.find_elements_by_css_selector('*'):
        relevant.append('.'+child.get_attribute('class'))
        relevant.append('#'+child.get_attribute('id'))
        relevant.append(ekind.search(child.get_attribute('outerHTML'))[1])

relevant = list(set(relevant)-set(['','.','#']))

# print(relevant)



cleancss = re.compile('\>|\<|:[^\s]+|\[.+\]')
cssmatch = re.compile(re.sub('[\. #]','','|'.join(relevant)))


def matched (x):
    x = cleancss.sub('',x)
    passed = False
    # for each grouped selection
    for groups in re.split(' *, *',x):
        singlepass = True
        # for each chain
        for chain in re.split('[\s \.#<>]+',groups):
            singlepass *= bool(cssmatch.fullmatch(chain))
            # print(chain,bool(cssmatch.fullmatch(chain)))

        passed += bool(singlepass)
        # print(passed,re.split('[\s \.#<>]+',groups),'---',x)

    return passed



csskeys = list(filter(matched,stylesheets.keys()))
csskeys.sort()

# print(csskeys,cssmatch)



with open(querySelect+'.css','w') as f:
    for i in csskeys:
        f.write('%s{%s}\n\n'%(i,stylesheets[i]))