class MySpider(CrawlSpider):
    name = "scraper"
    allowed_domains = ["amazon.com"]
    start_urls = ["http://www.amazon.com/s/ref=sr_pg_3?rh=n%3A133140011%2Cn%3A%21133141011%2Cn%3A154606011%2Cn%3A668010011%2Cn%3A158591011%2Cn%3A158592011&page=3&bbn=158591011&ie=UTF8&qid=1403264902"]

    rules = [Rule(SgmlLinkExtractor(allow=('\/dp\/B00.*digital-text')),callback='parse_items')]

    def parse_items(self, response):

        sel=Selector(response)
        items = []
        url=response.url
        item = AmazonItem()
        print 'inside'
        print sel.css('#btAsinTitle::text').extract()
        item ["title"] = ''.join(sel.css('#btAsinTitle::text').extract())
        print '-----',item["title"]
        print response.url
        item["digitalprice"] = ''.join(sel.css('.digitalListPrice>.listprice::text').extract())
        item["digitalprice"]=re.sub('\s+','',item["digitalprice"])
        item["listprice"] = ''.join(sel.css('.listPrice::text').extract())
        item["listprice"]=re.sub('\s+','',item["listprice"])
        item["kindleprice"] = ''.join(sel.css('.priceLarge::text').extract())
        item["kindleprice"]=re.sub('\s+','',item["kindleprice"])
        item["author"]=''.join(sel.css('span.contributorNameTrigger a::text').extract())
        item["author"]=re.sub('\s+','',item["author"])
        item["reviews"]=''.join(sel.css('#divsinglecolumnminwidth > div:nth-child(34) > span > span > a::text').extract())
        item["reviews"]=re.sub('\s+','',item["reviews"])
        item["reviews"] = ''.join([i for i in item["reviews"] if i.isdigit()])


        #if item["digitalprice"] != None and item["listprice"] != None and item["kindleprice"] != None and item["author"] != None and item["reviews"] !=None:
        items.append(item)
        print items
        return items