PydataSpiderDetails.py 文件源码

def parse_details(self, response):
        print 'link parseado %s' %response.url      
        hxs = scrapy.Selector(response)
        item = PydatascheduleItem()
        item['speaker'] = hxs.select('//div[@class="col-md-8"]/h4/a/text()').extract()[0].strip()
        item['url'] = response.url
        item['talk'] = hxs.select('//div[@class="col-md-8"]/h2/text()').extract()[0].strip()
        item['time'] = hxs.select('//div[@class="col-md-8"]/h4/text()').extract()[0].replace("\n","").strip()
        item['description'] = hxs.select('//div[@class="description"]/p/text()').extract()[0]
        return item