4000 爬虫 取得站内最大页数

<li class="l_pager pager_theme_4 pb_list_pager"><span class="tP">1</span>
<a href="/p/4245039489?pn=2">2</a>
<a href="/p/4245039489?pn=3">3</a>
<a href="/p/4245039489?pn=4">4</a>
<a href="/p/4245039489?pn=5">5</a>
<a href="/p/4245039489?pn=6">6</a>
<a href="/p/4245039489?pn=7">7</a>
<a href="/p/4245039489?pn=8">8</a>
<a href="/p/4245039489?pn=9">9</a>
<a href="/p/4245039489?pn=10">10</a>
<a href="/p/4245039489?pn=2">下一页</a>
<a href="/p/4245039489?pn=19">尾页</a>

</li>

import re

last_page_num = re.findall(r'<a href="/p/.*?pn=(\d+)">',first_html,re.S)
print last_page_num[-1]

from lxml import etree
#html指的是上述的xml代码
selector = etree.HTML(html)
print selector.xpath('//li[@class="l_pager pager_theme_4 pb_list_pager"]/a[last()]/@href')[0][-2:]

from lxml import etree
#html指的是上述的xml代码
selector = etree.HTML(html)
print selector.xpath(u'//li[@class="l_pager pager_theme_4 pb_list_pager"]/a[text()="尾页"]/@href')[0][-2:]