crawlerBlog.py 文件源码

def parse_blog(self, response):
        print 'link parseado %s' %response.url
        hxs = HtmlXPathSelector(response)
        item = HackerWayItem()
        item['title'] = hxs.select('//title/text()').extract() # Selector XPath para el titulo
        item['author'] = hxs.select("//span[@class='author']/a/text()").extract() # Selector XPath para el author
        item['tag'] = hxs.select("//meta[@property='og:title']/text()").extract() # Selector XPath para el tag
        item['date'] = hxs.select("//span[@class='date']/text()").extract() # Selector XPath para la fecha
        return item # Retornando el Item.