lxml.html example Пример использования lxml.html

# -*- coding: utf-8 -*-
from lxml import html

#~ response = requests.get('https://www.yahoo.com/news/') 
#~ parsed_body = html.fromstring(response.text)

responsetext='<ul><li><span>Model No.:</span><em>CN-374181929</em></li><li><span>Material:</span><em>ABS</em></li><li><span>Product Size:</span><em>4.5cm</em></li><li><span>Product Weight:</span><em>0.053kg</em></li><li><span>Features:</span><em>Phthalates Free</em></li><li></li><li><span>Package Size:</span><em>13*7.5*4.9cm</em></li><li><span>Package Weight:</span><em>0.072kg</em></li><li><span>Package Type:</span><em>colorbox</em></li><li></li><li><span>QTY/CTN:</span><em>160PCS</em></li><li><span>Case Size:</span><em>58.5*43*40cm</em></li><li><span>N.W:</span><em>8.5kg</em></li><li><span>G.W:</span><em>10.5kg</em></li><li><span>Volume:</span><em>0.1CBM</em></li></ul>'
parsed_body = html.fromstring(responsetext)
data = parsed_body.xpath(".//li")
print len(data)

for i in range(len(data)):
    print(data[i])
    datasub=data[i]
    for node in datasub: # Перебираем элементы
        print('text =',[node.text])    #text = ['Sign In']
        print(node.values())           #['/accounts/signin/']
        print(node.keys())             #['href']
        print(node.tag)                #a
        #~ print(node.content())           #['/accounts/signin/']
        print node.get("data-current")
        #~ print('-------------------------');