爬取苏宁图书

# -*- coding: utf-8 -*-
import scrapy
from copy import deepcopy


class SuSpider(scrapy.Spider):
    name = 'su'
    allowed_domains = ['suning.com']
    start_urls = ['http://book.suning.com/']

    def parse(self, response):
        div_list=response.xpath('//div[@class="menu-list"]/div[@class="menu-item"]')
        a_list = response.xpath('//div[@class="menu-sub"]/div[@class="submenu-left"]')
        for d,div in enumerate(div_list):
            item={}
            item['b_case']=div.xpath('./dl//a/text()').extract_first()
            for i,a in enumerate(a_list):
                if d==i:
                    m_title_list=a.xpath('./p/a')
                    for m in m_title_list:
                        item['m_case']=m.xpath('./text()').extract_first()
                        item['m_url']=m.xpath('./@href').extract_first()
                        yield scrapy.Request(url=item['m_url'],
                                       callback=self.parse_m_case,
                                       meta={'item':deepcopy(item)})


    def parse_m_case(self,response):
        item=response.meta.get('item')
        li_list=response.xpath('//ul[@class="clearfix"]/li')
        for li in li_list:
            sale=li.xpath('.//div[@class=" "]//em/text()').extract_first()
            print(sale)
            if sale=='满125用100':
                item['s_title']=li.xpath('.//p[@class="com-cnt"]/a/@title').extract_first()
                item['s_url'] = li.xpath('.//p[@class="com-cnt"]/a/@href').extract_first()
                item['s_money'] = li.xpath('.//p[@class="prive-tag"]/em//text()').extract_first()
                
                print(item)