# -*- coding: utf-8 -*-
import scrapy
from qiubai.items import QiubaiItem


class QiushibaiSpider(scrapy.Spider):
    name = 'qiushibai'
    # allowed_domains = ['www.qiushibaike.com/text/']
    start_urls = ['http://www.qiushibaike.com/text/']
    url = "https://www.qiushibaike.com/text/page/%d/"
    page = 1
    def
 
 parse(self, response):
        #    建議大家使用xpath進行指定內容的解析（框架集成了xpath解析的介面）
        #    段子的內容和作者
        div_list = response.xpath('//div[@id="content-left"]/div')

        # data_list = []
        for div in div_list:

            # xpath解析到的指定內容被儲存到了Selector物件
            # extract()該方法可以將Selector物件中儲存的資料值拿到
 

            # author = div.xpath("./div/a[2]/h2/text()").extract()[0]
            # extract_first() == extract()[0]
            author = div.xpath("./div/a[2]/h2/text()").extract_first()
            content = div.xpath('.//div[@class="content"]/span/text()').extract_first()


            # 將解析到數值的資料儲存到item物件
            item = QiubaiItem()
            item[
 
"author"] = author
            item["content"] = content
            # 將item物件提交給管道
            yield item
        if self.page <= 13:
            print("正在爬取第%d頁" % self.page)
            self.page += 1
            new_url = format(self.url % self.page)
            yield scrapy.Request(url=new_url, callback=self.parse)

        #     data_list.append(data)
        # return data_list

用yield    callback