spider 

from lxml import etree
import  requests
def getHtml(html):
    novelcontent = requests.get(html).content
    return etree.HTML(novelcontent)

source = getHtml("http://www.cabintu.com")

listclassify = source.xpath('//ul[@class="sg_menu"]/li/a')
listtype = source.xpath('//div[@class="mainleft"]/ul[@class="sg_menu"]/li[@class="section"]//ul[@class="subnav_a"]/li[@class="airline"]/a')

for i in range(0,len(listclassify)-1):
    fname = source.xpath('//div[@class="mainleft"]/ul[@class="sg_menu"]/li[@class="section"]/a/text()')[i]
    print fname



for n in range(0,len(listtype)-1):
    typelist = source.xpath('//div[@class="mainleft"]/ul[@class="sg_menu"]/li[@class="section"]//ul[@class="subnav_a"]/li[@class="airline"]/a/text()')[n]
    print typelist



#    for n in range(0,)


#      ftypelist = source.xpath('//div[@class="mainleft"]/ul[@class="sg_menu"]/li[@class="section"]/ul[@class="subnav_a"]/li[@class="airline"]/a/text()')[i]

posted on 2016-11-25 19:53  chinxfin  阅读(132)  评论(0)  编辑  收藏  举报

导航