Scrapy第六章改寫後的parse程式

parse_completed_scrapy6.py

def parse(self, response):
        for block in response.xpath('//ul[@id="newslistul"]//li'):
            href = block.xpath('.//a[contains(@class, "tit")]/@href').extract_first()
            # 爬取新聞正文內容
            yield response.follow(url=href, callback=self.parse_content)
        a_next = response.xpath('//a[contains(@class, "p_next")]/@href').extract_first()
        if a_next:
            # 爬下一頁
            yield response.follow(a_next, callback=self.parse)