import scrapy
from tutorial.items import DmozItem
from scrapy.contrib.loader import ItemLoader
class DmozSpider(scrapy.Spider):
    name="dmoz"
    allowed_domains=["dmoz.org"]
    start_urls=[
        "http://www.dmoz.org/Computers/Programming/Languages/Python/Books/",
        "http://www.dmoz.org/Computers/Programming/Languages/Python/Resources/"
    ]   

    def parse(self,response):
        """Some contracts are used here
                @url http://www.dmoz.org/Computers/Programming/Languages/Python/Books/
                @returns items 1 100
                @returns requests 0 0
                @scrapes title link 
        """
#       CODE 1
#       for sel in response.xpath('//ul/li'):
#               item = DmozItem()
#               item['title'] = sel.xpath('a/text()').extract()
#               item['link'] = sel.xpath('a/@href').extract()
#               item['desc'] = sel.xpath('text()').extract()
#               yield item


#       CODE 2
        for sel in response.xpath("//ul/li"):   
                l = ItemLoader(item=DmozItem(),selector=sel)
                l.add_xpath('title','a/text()')
                l.add_xpath('link','a/@href')
                l.add_xpath('desc','text()')
                it= l.load_item()
                yield it