1 # -*- coding: utf-8 -*-
2
3 # Define here the models for your scraped items
4 #
5 # See documentation in:
6 # http://doc.scrapy.org/en/latest/topics/items.html
7
8 import scrapy
9
10
11 class AmazonItem(scrapy.Item):
12 # define the fields for your item here like:
13 # name = scrapy.Field()
14 description=scrapy.Field()
15 price=scrapy.Field()
16 url=scrapy.Field()
17 value=scrapy.Field()
1 #!/usr/bin/python
2
3 import scrapy
4 class AmazonSpider(scrapy.Spider):
5 name='amazon'
6 allowd_domains=['amazon.cn']
7 start_urls=['http://www.amazon.cn/s/ref=sv_cps_0?ie=UTF8&node=665002051&page=1']
8 def parse(self,response):
9 try:
10 page=response.xpath("//span[@class='pagnDisabled']/text()").extract()[0]
11 except:
12 pass
13 for item in response.xpath("//li[@class='s-result-item']"):
14 title=item.xpath("./div/div[2]/div/a/h2/text()").extract()[0]
15 price=item.xpath("./div/div[3]/div[1]/a/span[1]/text()").extract()[0]
16 url=item.xpath("./div/div[1]/div/div/a[1]/@href").extract()[0]
17 print title
18 print price
19 print url
20 for i in range(int(page)):
21 request=scrapy.Request('http://www.amazon.cn/s/ref=sv_cps_0?ie=UTF8&node=665002051&page='+str(i),callback=self.parse)
22 yield request
23
