lxml的使用

from urllib import request
from lxml import etree
# url = '''http://bangumi.tv/anime/browser?sort=rank'''
# response = request.urlopen(url)
# html = response.read()
html = '''
 id="item_1728" class="item even clearit">
    <a href="/subject/1728" class="subjectCover cover ll">
            <span class="image">
            <img src="//lain.bgm.tv/pic/cover/s/71/37/1728_HLsCr.jpg" class="cover">
        </span>
        <span class="overlay"></span>
        </a>
    <div class="inner">
                                <h3>

                    <a href="/subject/1728" class="l">浪客剑心 追忆篇</a> <small class="grey">るろうに剣心 -明治剣客浪漫譚- 追憶編</small>
                </h3>

        <span class="rank"><small>Rank </small>12</span>
        <p class="info tip">
                         4话 /  1999年2月20日                    </p>
                <p class="rateInfo">
                        <span class="sstars9 starsinfo"></span> <small class="fade">8.8</small> <span class="tip_j">(2165人评分)</span>
                    </p>

    </div>
</li>
'''

html = etree.HTML(html)
result = etree.tostring(html)
print(result)
li_all = html.xpath('//a')
print(li_all)#[<Element a at 0x2ebe198>, <Element a at 0x2ebe170>]
# li_all = html.xpath('//a/@href')['/subject/1728', '/subject/1728']
# print(li_all)
li_all = html.xpath('//a/@class')#['subjectCover cover ll', 'l']
print(li_all)
li_all = html.xpath('//a[@href="/subject/1728"]')#获取所有href等于这个的标签
print(li_all)
li_all = html.xpath('//div/a')#获取a标签下所有的子span标签
print(li_all)
li_all = html.xpath('//div//a')#获取a标签下所有的子孙span标签
print(li_all)
li_all = html.xpath('//div//a//@class')#获取a标签下所有的子孙span标签
print(li_all)
li_all = html.xpath('//div//p[last()]/span')#获取最后一个p元素的所有span标签
print(li_all)
li_all = html.xpath('//div//p[last()-1]')#获取倒数第二个个p元素的所有span标签
print(li_all[0].text)
li_all = html.xpath('string()')#过滤标签，返回所有文本
print(li_all)
li_all = html.xpath('//text()')#过滤标签，将每个文本存放于列表中
print(li_all)
li_all = html.xpath('//text()')
print(li_all[0].getparent().tag)#根据文本返回它的标签名
print(li_all[1].is_tail)
print(li_all[1].is_tail)#判断是普通文本还是tail文本