python+scrapy爬取亚马逊手机商品

# -*- coding: utf-8 -*-

# Define here the models for your scraped items
#
# See documentation in:
# http://doc.scrapy.org/en/latest/topics/items.html

import scrapy


class AmazonItem(scrapy.Item):
    # define the fields for your item here like:
    # name = scrapy.Field()
    description=scrapy.Field()
    price=scrapy.Field()
    url=scrapy.Field()
    value=scrapy.Field()

#!/usr/bin/python

import scrapy
class AmazonSpider(scrapy.Spider):
    name='amazon'
    allowd_domains=['amazon.cn']
    start_urls=['http://www.amazon.cn/s/ref=sv_cps_0?ie=UTF8&node=665002051&page=1']
    def parse(self,response):
        try:
            page=response.xpath("//span[@class='pagnDisabled']/text()").extract()[0]
        except:
            pass
        for item in response.xpath("//li[@class='s-result-item']"):
            title=item.xpath("./div/div[2]/div/a/h2/text()").extract()[0]
            price=item.xpath("./div/div[3]/div[1]/a/span[1]/text()").extract()[0]
            url=item.xpath("./div/div[1]/div/div/a[1]/@href").extract()[0]
            print title
            print price
            print url
        for i in range(int(page)):
            request=scrapy.Request('http://www.amazon.cn/s/ref=sv_cps_0?ie=UTF8&node=665002051&page='+str(i),callback=self.parse)
            yield request