import scrapy
from scrapy.contrib.loader import ItemLoader
from scrapy.contrib.spiders import CrawlSpider,Rule
from scrapy.selector import XmlXPathSelector
from scrapy.contrib.linkextractors.sgml import SgmlLinkExtractor
from cancerstories.items import CancerstoriesItem

class LungcancerSpider(CrawlSpider):
    name = "lungcancer"
    allowed_domains = ["coloncancercoalition.org"]
    start_urls = (
        'http://www.coloncancercoalition.org/community/stories/survivor-stories/',
    )
    rules = (
             Rule(SgmlLinkExtractor(allow=[r'http://www.coloncancercoalition.org/d+/d+/d+/w+']),callback='parse_page',follow=True),
             )

def parse_page(self, response):
    Li = ItemLoader(item=CancerstoriesItem(),response=response)
    Li.add_xpath('name', '/html/body/div[4]/div[1]/div[1]/div/h1/text()')
    Li.add_xpath('story','//../div/div/p/text()')

    yield Li.load_item()
    pass