lxml cssselect example

lxml-cssselect

import lxml

root = lxml.html.parse(filename).getroot()

# in case the file contains unicode characters
parser = lxml.html.HTMLParser(encoding='utf-8')
root = lxml.html.parse(filename, parser=parser).getroot()

# get matched elements using css selector
els = root.cssselect('div.shop-info div.info-name h2 a')
el_text = els[0].text
el_href = els[0].attrib['href']