class MovieSpider(scrapy.Spider):
name = 'movie'
allowed_domains = ['www.id97.com']
start_urls = ['http://www.id97.com/']
def parse(self, response):
div_list = response.xpath('//div[@class="col-xs-1-5 movie-item"]')
for div in div_list:
item = MovieproItem()
item['name'] = div.xpath('.//h1/a/text()').extract_first()
item['score'] = div.xpath('.//h1/em/text()').extract_first()
#xpath(string(.))表示提取当前节点下所有子节点中的数据值(.)表示当前节点
item['kind'] = div.xpath('.//div[@class="otherinfo"]').xpath('string(.)').extract_first()
item['detail_url'] = div.xpath('./div/a/@href').extract_first()
#请求二级详情页面,解析二级页面中的相应内容,通过meta参数进行Request的数据传递
yield scrapy.Request(url=item['detail_url'],callback=self.parse_detail,meta={'item':item})
def parse_detail(self,response):
#通过response获取item
item = response.meta['item']
item['actor'] = response.xpath('//div[@class="row"]//table/tr[1]/a/text()').extract_first()
item['time'] = response.xpath('//div[@class="row"]//table/tr[7]/td[2]/text()').extract_first()
item['long'] = response.xpath('//div[@class="row"]//table/tr[8]/td[2]/text()').extract_first()
#提交item到管道
yield item