Question

我正在使用Scrapy在python中创建一个Web搜寻器，并且我开发了以下代码：

import scrapy
from scrapy.selector import Selector

class SapoSpider(scrapy.Spider):
   name = "imo"
   allowed_domains = ["imovirtual.com"]
   start_urls = ["https://www.imovirtual.com/arrendar/apartamento/lisboa/"]
   custom_setting = {
   'FEED_URI': './output.json'
}

def parse(self,response):
    subpage_links = []

    for i in response.css('div.offer-item-details'):
        youritem = {
        'Titulo':i.css('span.offer-item-title::text').extract(),
        #'Titulo':i.css
        'Preço':i.css('li.offer-item-price::text').re('[^\t\n]+'),
        }

        subpage_link = i.css('header[class=offer-item-header] 
a::attr(href)').extract()
        subpage_links.extend(subpage_link)

        for subpage_link in subpage_links:
            yield scrapy.Request(subpage_link, callback=self.parse_subpage, meta={'item':youritem})

def parse_subpage(self,response):
    #for j in response.css('div.article-offer'):
        #respo = Selector(response) # a HTML selector
        youritem = response.meta.get('item')
        youritem['Tipologia'] = response.xpath('//ul[@class="main-list"]//li[3]//span').extract()
        youritem['Condição'] = response.xpath('//ul[@class="sub-list"]/li[3]/text()').extract()
        youritem['Caracteristicas'] = response.css('ul.dotted-list li::text').extract()
        yield youritem

当我打开json文件时，我发现与变量“ Tipologia”有关的数据采用以下格式：“ Tipologia”：[span strong T2 / strong / span]。我如何获得这些子弹（跨度高）？有什么建议吗？

我如何获得这些子弹？

0 个答案: