plants_loader.py 文件源码

def parse(self, response):
        l = ItemLoader(item=PlantItem(), response=response)

        l.add_xpath('name', "//div[@id='bodycontent']/div[@class='post']/div[@class='pagebanner']/h2/text()")
        l.add_xpath('species', "//div[@id='bodycontent']/div[@class='post']/div[@class='pagebanner']/div[@class='clear resultSpecies']/text()")
        l.add_xpath('key', "//div[@id='bodycontent']/div[@class='post']/div[@class='contents']/div[@id='tabbedinfo']/div[@class='tabscontain']/div[@class='tabs']/div[@class='post-meta']/div[@class='post-meta-key']/text()")
        l.add_xpath('value', "//div[@id='bodycontent']/div[@class='post']/div[@class='contents']/div[@id='tabbedinfo']/div[@class='tabscontain']/div[@class='tabs']/div[@class='post-meta']/div[@class='post-meta-value']/child::node()")
        # l.add_xpath('value', "//div[@id='bodycontent']/div[@class='post']/div[@class='contents']/div[@id='tabbedinfo']/div[@class='tabscontain']/div[@class='tabs']/div[@class='post-meta']/div[@class='post-meta-value']/a/text()")

        return l.load_item()