import scrapy class LianjiaSpider(scrapy.Spider): name = "lianjia" allowed_domains = ["lianjia.com"] start_urls = [f"https://bj.lianjia.com/zufang/pg{i}/#contentList" for i in range(1,3)] def parse(self, response): full_url = ['https://bj.lianjia.com' + url for url in response.xpath('//div[@class="content__list--item--main"]/p[1]/a/@href').extract()] print(full_url) all_url = [] for i in range(len(full_url)): if i % 2 == 0: all_url.append(full_url[i]) print(all_url) # # 把获得的url再次发送请求 for item in all_url: # self.parse_info是一个解析响应的方法 ''' 回调函数，Scrapy能够在接收到响应后自动调用该函数，并将响应传递给它进行处理。 这使得可以在请求不同页面时使用不同的解析方法来提取数据，实现爬虫的多页面爬取和数据处理功能 ''' yield scrapy.Request(url=item,callback=self.parse_info) # # 处理响应结果 def parse_info(self,response): # .replace(' ','').replace('\n ','') title = response.xpath("//div[@class='content clear w1150']/p/text()").get().replace(' ','').replace('\n ','') #房源标题 total_price = response.xpath('//div[@class="content__aside--title"]/span/text()|//div[@class="content__aside--title"]/text()').getall() price = ''.join(total_price).replace('\n ', '').replace(' \n ', '').replace('\n ','') print(title,price) 要跳过title为Nonetype的内容，怎样设置

要跳过 `title` 为 `NoneType` 的内容，你可以在获取 `title` 的代码段中添加条件判断来过滤掉空值。以下是修改后的代码示例：

import scrapy

class LianjiaSpider(scrapy.Spider):
    name = "lianjia"
    allowed_domains = ["lianjia.com"]
    start_urls = [f"https://bj.lianjia.com/zufang/pg{i}/#contentList" for i in range(1, 3)]

    def parse(self, response):
        full_url = ['https://bj.lianjia.com' + url for url in response.xpath('//div[@class="content__list--item--main"]/p[1]/a/@href').extract()]
        print(full_url)
        all_url = []
        for i in range(len(full_url)):
            if i % 2 == 0:
                all_url.append(full_url[i])
                print(all_url)

        # 发送请求
        for url in all_url:
            yield scrapy.Request(url=url, callback=self.parse_info)

    def parse_info(self, response):
        title = response.xpath("//div[@class='content clear w1150']/p/text()")
        if title:
            title = title.get().replace('                 ', '').replace('\n         ', '')  # 房源标题
            total_price = response.xpath('//div[@class="content__aside--title"]/span/text()|//div[@class="content__aside--title"]/text()').getall()
            price = ''.join(total_price).replace('\n           ', '').replace('            \n          ', '').replace('\n           ', '')
            print(title, price)

在这个示例中，我添加了一个条件判断 `if title:` 来过滤掉空值。只有当 `title` 不为空时，才会执行后续的代码。

希望这样能解决你的问题。如果还有其他问题，请随时提问。