scrapy+selenium爬取淘宝

------------------taobao.py---------------------

# -*- coding: utf-8 -*-
import scrapy
from scrapy import Request
from urllib.parse import quote
from ..items import ScrapyseleniumtestItem


class TaobaoSpider(scrapy.Spider):


    name = 'tao_bao'
    allowed_domains = ['www.taobao.com']
    base_url = 'https://s.taobao.com/search?q='

    def start_requests(self):
        # 通过self.settings.get（）的方式获取setting里面的参数
        for keyword in self.settings.get('KEYWORDS'):
            for page in range(1, self.settings.get('MAX_PAGE') + 1):
                url = self.base_url + quote(keyword)
                # 通过meta={'键':"值"},传递你接下来需要的数据
                yield Request(url=url,
                              callback=self.parse,
                              meta={
  'page':page},
                              dont_filter=True)

    def parse(self, response):
        # xpath中class中有空格(class="J_ItemPic img") 可以使用contains(@class,'img')
        products = response.xpath(
            '//div[@id="mainsrp-itemlist"]//div[@class="items"]//div[contains(@class, "item")]')
        for product in products:
            item = ScrapyseleniumtestItem()
            item['price'] = ''.join(product.xpath(
                './/div[contains(@class, "price")]//text()').extract()).strip()
            item['title'] = ''.join(product.xpath(
                './/div[contains(@class, "title")]//text()').extract()).strip()
            item['shop'] = ''.join