bs4和xpath比较

xpath速度确实快....
bs_info = bs(restext, 'lxml')
selector = lxml.etree.HTML(restext)
s1 = time.time()
rank=selector.xpath('//*[@class="pic"]//em/text()')
e1 = time.time()

s2 = time.time()
rank = [
    x.find("em").text for x in bs_info.find_all(
        'div', {
            'class': 'pic'})]
e2 = time.time()

print(e1-s1)
print(e2-s2)
print(rank)
exit()