Python scrapy爬取起点中文网小说榜单

import scrapy

class QidianHotItem(scrapy.Item):
    name = scrapy.Field() #名称
    author = scrapy.Field() #作者
    type = scrapy.Field() #类型
    form= scrapy.Field() #是否完载

#coding:utf-8

from scrapy import Request
from scrapy.spiders import Spider
from ..items import QidianHotItem
#导入下需要的库

class HotSalesSpider(Spider):#设置spider的类
    name = "hot" #爬虫的名称
    qidian_header={"user-agent":"Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/90.0.4430.93 Safari/537.36"} #设置header
    current_page = 1 #爬虫起始页
    def start_requests(self): #重写第一次请求
        url="https://www.qidian.com/rank/hotsales?style=1&page=1"
        yield Request(url,headers=self.qidian_header,callback=self.hot_parse)
		#Request发起链接请求
		#url：目标url
		#header:设置头部（模拟浏览器）
		#callback:设置页面抓起方式（空默认为parse）
    def hot_parse(self, response):#数据解析
        #xpath定位
        list_selector=response.xpath("//div[@class='book-mid-info']")
        #获取所有小说
        for one_selector in list_selector:
            #获取小说信息
            name=one_selector.xpath("h4/a/text()").extract()[0]
            #获取作者
            author=one_selector.xpath("p[1]/a[1]/text()").extract()[0]
            #获取类型
            type=one_selector.xpath("p[1]/a[2]/text()").extract()[0]
            # 获取形式
            form=one_selector.xpath("p[1]/span/text()").extract()[0]

            item = QidianHotItem()
            #生产存储器，进行信息存储
            item['name'] = name
            item['author'] = author
            item['type'] = type
            item['form'] = form

            yield item #送出信息

            # 获取下一页URL，并生成一个request请求
            self.current_page += 1
            if self.current_page <= 10:#爬取前10页
                next_url = "https://www.qidian.com/rank/hotsales?style=1&page="+str(self.current_page)
                yield Request(url=next_url,headers=self.qidian_header,callback=self.hot_parse)


    def css_parse(self,response):
        #css定位
        list_selector = response.css("[class='book-mid-info']")
        for one_selector in list_selector:
            # 获取小说信息
            name = one_selector.css("h4>a::text").extract()[0]
            # 获取作者
            author = one_selector.css(".author a::text").extract()[0]
            # 获取类型
            type = one_selector.css(".author a::text").extract()[1]
            # 获取形式
            form = one_selector.css(".author span::text").extract()[0]
            # 定义字典

            item=QidianHotItem()
            item['name']=name
            item['author'] = author
            item['type'] = type
            item['form'] = form
            yield  item

from scrapy import cmdline
#导入cmd命令窗口
cmdline.execute("scrapy crawl hot -o hot.csv" .split())
#运行爬虫并生产csv文件