def parse(self, response):
sel = Selector(response)
sites = sel.xpath('//ol[@class="grid_view"]/li/div/div[@class="pic"]')
items = []
for site in sites:
item = top100Item()
item["movie_rank"] = site.xpath("em/text()").extract()
item["movie_name"] = site.xpath("a/img/@alt").extract()
item["movie_url"] = site.xpath("a/@href").extract()
items.append(item)
yield item
# 获得下一篇top250的url
urls = sel.xpath('//div[@class="paginator"]/a/@href').extract()
urls[:-1]
urls.reverse()
for url in urls:
if url != "?start=0&filter=":
# print url
url = "http://movie.douban.com/top250" + url
# print url
yield Request(url, callback=self.parse)
"""i=0
def parse(self, response):
sel = Selector(response)
sites=sel.xpath('//ol[@class="grid_view"]/li/div/div[@class="pic"]')
items = []
for site in sites:
item=top100Item()
item['movie_rank']=site.xpath('em/text()').extract()
item['movie_name']=site.xpath('a/img/@alt').extract()
item['movie_url']=site.xpath('a/@href').extract()
items.append(item)
return items
