python之scrapy(二)

extract_first("") = extract()[0]

 

  def parse(self, response):
        re_selector = response.xpath('//*[@class="entry-header"]/h1/text()').extract_first("")

        zan = response.xpath('//*[@id="112376votetotal"]/text()')
        shoucang = response.xpath('//span[contains(@class,"bookmark-btn")]/text()').extract()[0]
        shoucang = re.match(".*(\d+).*",shoucang).group(1)
        pinglun = response.xpath('//a[@href="#article-comment"]/span/text()').extract()[0]
        pinglun = re.match(".*(\d+).*", pinglun).group(1)

        zhengwen = response.xpath('//div[@class="entry"]').extract()[0]
        print(re_selector.extract()[0].strip())
        print(zan)
        print(shoucang)
        print(pinglun)
        print(zhengwen)
        pass